Headlight control device and headlight control method
The headlight control device adjusts headlight irradiation based on the driver's orientation and driving conditions to ensure proper illumination, addressing the limitations of conventional systems and enhancing visibility and safety.
Patent Information
- Application Number
- JP2024543676
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2022-08-31
- Publication Date
- 2025-01-10
- Estimated Expiration
- 2042-08-31
AI Technical Summary
Conventional headlight control systems fail to consider the actual direction the driver is facing, leading to potential gaps in illuminating the area the driver intends to see, which can result in delayed detection of objects or reduced visibility.
A headlight control device that utilizes a direction detection unit to determine the driver's orientation based on captured images, combined with driving-related information, to estimate a depth distance and adjust the headlight irradiation range accordingly, ensuring appropriate illumination of the intended viewing area.
The system effectively illuminates the driver's intended viewing area, enhancing visibility and reducing glare to other vehicles, thereby improving driving safety and support.
Smart Images

Figure 0007612117000001 
Figure 0007612117000002 
Figure 0007612117000003
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a headlight control device and a headlight control method. [Background technology]
[0002] Conventionally, in controlling the lighting of headlights in a vehicle, a technique is known in which the headlight illumination range is changed based on the direction in which the driver is facing so that the headlight light is directed in the direction in which the driver is facing in order to improve the driver's visibility (for example, Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2009-120148 A Summary of the Invention [Problem to be solved by the invention]
[0004] The conventional technology disclosed in Patent Document 1 had a problem in that it was not possible to control the headlights taking into consideration how far ahead the driver is actually trying to see in the direction he or she is facing. As a result, there was a possibility that a situation occurred in which the headlights were not able to illuminate the area the driver was actually trying to see.
[0005] The present disclosure has been made to solve the above-mentioned problems, and aims to provide a headlight control device that enables headlight lighting control in a vehicle based on the direction the driver is facing, taking into account how far ahead in the direction the driver is actually attempting to see. [Means for solving the problem]
[0006] The headlight control device according to the present disclosure includes an orientation detection unit that detects the orientation of the driver based on an image of the driver of the vehicle; a driving-related information acquisition unit that acquires driving-related information related to the driving of the vehicle; a depth distance estimation unit that estimates a depth distance, which is the distance from an installation position of the headlights provided on the vehicle to an estimated viewing position that is estimated to be the driver's viewing position in the direction the driver is facing, based on the orientation information regarding the driver's orientation detected by the orientation detection unit and the driving-related information acquired by the driving-related information acquisition unit; an illumination determination unit that determines the illumination range of light by the headlights based on the depth distance estimated by the depth distance estimation unit; and a headlight control unit that causes the headlights to illuminate the light in the illumination range determined by the illumination determination unit. Effect of the Invention
[0007] According to the present disclosure, in a vehicle, headlight illumination control based on the direction in which the driver is facing can be performed taking into account how far ahead in the direction in which the driver is actually facing. [Brief description of the drawings]
[0008] [Figure 1] 1 is a diagram illustrating an example of the configuration of a headlight control device according to a first embodiment. [Diagram 2] 4 is a diagram showing an example of contents of depth distance estimation information used by a depth distance estimation unit to estimate a depth distance in the first embodiment. FIG. [Diagram 3] This figure shows the depth distances corresponding to the input information under conditions No. 1 to No. 6 set in the depth distance estimation information shown in Figure 2, in correspondence with an example of the vehicle's driving state estimated from the driver's behavior and vehicle information, which are the basis for deriving the depth distance, and an example of an estimated visible object of the driver. [Figure 4] FIG. 4 is a diagram for explaining an example of a state in which a headlight control unit causes a headlight to irradiate light onto an illumination range determined by an illumination determination unit in the first embodiment. [Diagram 5]4 is a flowchart for explaining the operation of the headlight control device according to the first embodiment. [Figure 6] 6A and 6B are diagrams illustrating an example of a hardware configuration of the headlight control device according to the first embodiment. [Figure 7] FIG. 11 is a diagram illustrating an example of the configuration of a headlight control device according to a second embodiment. [Figure 8] FIG. 11 is a diagram showing an example of the contents of depth distance estimation information used by a depth distance estimation unit to estimate a depth distance in the second embodiment. [Figure 9] This figure shows the depth distances corresponding to the input information under conditions No. 1 to No. 6 set in the depth distance estimation information shown in Figure 8, in correspondence with an example of the vehicle's driving state estimated from the driver's behavior, vehicle information, and map information, which are the basis for deriving the depth distance, and an example of an object visible to the driver. [Figure 10] FIG. 10A is a diagram for explaining an example of a depth distance estimated by a depth distance estimation unit in embodiment 2, and FIG. 10B is a diagram for explaining an example of a state in which a headlight control unit in embodiment 2 irradiates light to a headlight in an irradiation range determined by an irradiation determination unit based on the depth distance estimated by the depth distance estimation unit as shown in FIG. 10A. [Figure 11] 11A and 11B are diagrams illustrating an example of a method by which the depth distance estimation unit calculates a specific range of meters for a depth distance range with a margin of 5 meters that includes a sidewalk near an intersection and a crosswalk at the intersection in embodiment 1. [Figure 12] FIG. 12A is a diagram for explaining another example of the depth distance estimated by the depth distance estimation unit in embodiment 2, and FIG. 12B is a diagram for explaining an example of the manner in which the headlight control unit in embodiment 2 causes the headlight to irradiate light to an irradiation range determined by the irradiation determination unit based on the depth distance estimated by the depth distance estimation unit as shown in FIG. 12A. [Figure 13]10 is a flowchart for explaining the operation of the headlight control device according to the second embodiment. [Figure 14] FIG. 11 is a diagram illustrating an example of the configuration of a headlight control device according to a third embodiment. [Figure 15] FIG. 11 is a diagram showing an example of the contents of depth distance estimation information used by a depth distance estimation unit to estimate a depth distance in the third embodiment. [Figure 16] This figure shows the depth distances corresponding to the input information under conditions No. 1 to No. 8 set in the depth distance estimation information shown in Figure 15, in correspondence with examples of the vehicle driving state estimated from the driver's behavior and outside vehicle information and an example of an object viewed by the driver, which are the basis for deriving the depth distance. [Figure 17] FIG. 11 is a diagram for explaining an example of a state in which an illumination determination unit determines an illumination range based on a depth distance estimated by a depth distance estimation unit, and a headlight control unit causes a headlight to illuminate the illumination range determined by the illumination determination unit in embodiment 3. [Figure 18] FIG. 11 is a diagram for explaining another example of a state in which the illumination determination unit determines the illumination range based on the depth distance estimated by the depth distance estimation unit, and the headlight control unit causes the headlight to illuminate the illumination range determined by the illumination determination unit, in embodiment 3. [Figure 19] FIG. 11 is a diagram for explaining another example of a state in which the illumination determination unit determines the illumination range based on the depth distance estimated by the depth distance estimation unit, and the headlight control unit causes the headlight to illuminate the illumination range determined by the illumination determination unit, in embodiment 3. [Figure 20] 10 is a flowchart for explaining the operation of the headlight control device according to the third embodiment. [Figure 21] FIG. 13 is a diagram illustrating an example of the configuration of a headlight control device according to a fourth embodiment. [Figure 22] FIG. 13 is a diagram showing an example of the contents of depth distance estimation information used by a depth distance estimation unit to estimate a depth distance in the fourth embodiment. [Diagram 23]This figure shows the depth distances corresponding to the input information under conditions No. 1 to No. 7 set in the depth distance estimation information shown in Figure 22, in correspondence with examples of the vehicle's driving state and the driver's visible objects estimated from the driver's behavior, vehicle information, map information, and outside vehicle information, which are the basis for deriving the depth distances. [Figure 24] FIG. 24A is a diagram for explaining an example of a depth distance estimated by a depth distance estimation unit in embodiment 4, and FIG. 24B is a diagram for explaining an example of a state in which a headlight control unit in embodiment 4 irradiates light to a headlight in an irradiation range determined by an irradiation determination unit based on the depth distance estimated by the depth distance estimation unit as shown in FIG. 24A. [Diagram 25] 10 is a flowchart for explaining the operation of a headlight control device according to a fourth embodiment. [Figure 26] FIG. 13 is a diagram illustrating a configuration example of a headlight control device according to a fifth embodiment. [Figure 27] FIG. 13 is a diagram for explaining an example of a situation in which the reliability determination unit determines that the reliability of the direction of the driver detected by the direction detection unit is low in the fifth embodiment. [Figure 28] 13 is a flowchart for explaining the operation of the headlight control device according to the fifth embodiment. [Figure 29] FIG. 13 is a diagram illustrating an example of the configuration of a headlight control device according to a sixth embodiment. [Diagram 30] 30A is a diagram illustrating an example of a state in which the headlight control unit causes the headlight to irradiate light onto the first illumination range and the second illumination range determined by the illumination determination unit in embodiment 6, where FIG. 30A is a diagram illustrating the state in which light is irradiated onto the first illumination range and the second illumination range as viewed from the side, and FIG. 30B is a diagram illustrating the state in which light is irradiated onto the first illumination range and the second illumination range as viewed from the vehicle side. [Diagram 31] 13 is a flowchart for explaining the operation of the headlight control device according to the sixth embodiment. [Diagram 32]FIG. 13 is a diagram illustrating a configuration example of a headlight control device according to a seventh embodiment. [Diagram 33] FIG. 23 is a diagram for explaining an example of the contents of a surrounding confirmation determination condition used by a surrounding confirmation determination unit to determine whether or not a driver is checking the surroundings in the seventh embodiment. [Diagram 34] FIG. 23 is a diagram for explaining an example of a state in which the surrounding confirmation determination unit irradiates light onto the illumination range after widening the second illumination range set by the illumination determination unit in the seventh embodiment. [Diagram 35] FIG. 23 is a diagram for explaining an example of an illumination range of light that the headlight control device causes the headlight to irradiate in the seventh embodiment, and is a bird's-eye view of the surroundings of the vehicle as seen from above. [Diagram 36] FIG. 36B is a diagram illustrating an example of the irradiation range of light that the headlight control device causes the headlight to be irradiated with the headlight in the surrounding conditions of the vehicle as shown in FIG. 35, and FIG. 36A is a diagram illustrating an example of the irradiation range of light that the headlight control device of embodiment 6 causes the headlight to be irradiated with the headlight in the surrounding conditions of the vehicle as shown in FIG. 35. [Figure 37] 13 is a flowchart for explaining the operation of the headlight control device according to the seventh embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. Embodiment 1 FIG. 1 is a diagram showing an example of the configuration of a headlight control device 1 according to the first embodiment. In the first embodiment, it is assumed that the headlight control device 1 is mounted on a vehicle 100. The headlight control device 1 controls the illumination of the headlights 2 provided on the vehicle 100 based on the orientation of the driver of the vehicle 100. In the first embodiment, the "direction of the driver" is represented by the direction of the driver's face or the direction of the driver's line of sight. In the first embodiment, the "direction of the driver" may include the direction of the driver's body, in other words, the driver's posture, in addition to the direction of the driver's face or the direction of the driver's line of sight. In the following first embodiment, as an example, the "direction of the driver" is assumed to include the driver's posture. In the first embodiment, the headlight control device 1 performs the illumination control of the headlights 2 based on the driver's direction, which is assumed to be performed when the driver turns on the headlights 2 in a dark place around the vehicle 100, such as a parking lot at night or an urban area at night, or when the headlight control device 1 determines that the headlights 2 should be automatically turned on based on the brightness of the surroundings.
[0010] The headlight control device 1 is connected to a headlight 2, an in-vehicle image capturing device 3, and a driving-related information acquisition device 4. The headlight 2, the in-vehicle image capturing device 3, and the driving-related information acquisition device 4 are provided in a vehicle 100.
[0011] The headlight 2 is a lighting fixture that illuminates the area ahead of the vehicle 100. The headlight 2 is, for example, a general headlight that can emit a high beam, a low beam, and an auxiliary light, and therefore a detailed configuration example will not be described. The headlight 2 includes a left light (not shown) mounted on the left side of the vehicle 100 in the traveling direction of the vehicle 100, and a right light (not shown) mounted on the right side of the vehicle 100 in the traveling direction of the vehicle 100. The left light and the right light are each composed of a high beam unit (not shown) that illuminates a distant area, a low beam unit (not shown) that illuminates a nearby area, and an auxiliary light unit (not shown). The high beam unit, the low beam unit, and the auxiliary light unit are each composed of a plurality of light sources (not shown), such as LED light sources, arranged in an array, and each light source can be turned on individually. In the first embodiment, "arranged in an array" means that the light sources are arranged in a line in the width direction of the vehicle 100. When each light source is turned on, a high beam, a low beam, or an auxiliary light is irradiated to an area in front of the vehicle 100. The high beam unit, the low beam unit, and the auxiliary light unit may each use, for example, a Micro Electro Mechanical System (MEMS). The high beam unit, the low beam unit, and the auxiliary light unit can control the light distribution range by reflecting light with a MEMS mirror.
[0012] In the first embodiment, the area in front of the vehicle 100 where the high beam unit can irradiate a high beam is called a "high beam irradiable area". The extent of the high beam irradiable area is determined in advance according to the specifications of the high beam unit. In the first embodiment, the area in front of the vehicle 100 where the low beam unit can irradiate a low beam is called a "low beam irradiable area". The extent of the low beam irradiable area is determined in advance according to the specifications of the low beam unit. In the first embodiment, the area in front of the vehicle 100 where the auxiliary light unit can irradiate auxiliary light is called an "auxiliary light irradiable area". The extent of the auxiliary light irradiable area is determined in advance according to the specifications of the auxiliary light unit.
[0013] The headlight control device 1 according to the first embodiment controls the illumination range of the headlight 2 by, for example, turning on or off each light source to illuminate or block high beam, low beam, or auxiliary light. The headlight control device 1 can not only turn on and off each light source, but also control the amount of light when it is turned on. For example, the headlight control device 1 can control the amount of light of the headlight 2 by controlling the current value of each light source of the headlight 2.
[0014] The in-vehicle imaging device 3 is a camera or the like installed in the vehicle 100 for the purpose of monitoring the inside of the vehicle 100, and is installed so as to be able to capture an image of at least the face of the driver. The in-vehicle imaging device 3 is an infrared camera, a visible light camera, or the like. The in-vehicle image capturing device 3 outputs the captured image (hereinafter referred to as an “in-vehicle image”) to the headlight control device 1. The in-vehicle image capturing device 3 may be, for example, a shared image capturing device included in a so-called “Driver Monitoring System (DMS)” that is mounted on the vehicle 100 to monitor the state of the driver inside the vehicle 100.
[0015] The driving-related information acquisition device 4 acquires information related to the driving of the vehicle 100 (hereinafter referred to as "driving-related information"). In the first embodiment, the traveling-related information acquisition device 4 is assumed to be, for example, a vehicle speed sensor (not shown) or a steering wheel angle sensor (not shown). The vehicle speed sensor or steering wheel angle sensor acquires information related to the vehicle 100, such as the vehicle speed or the steering wheel angle, as traveling-related information (hereinafter referred to as "vehicle information"). The driving-related information acquisition device 4, here a device such as a vehicle speed sensor or a steering wheel angle sensor, outputs the acquired driving-related information, here vehicle information, to the headlight control device 1.
[0016] The headlight control device 1 includes a direction detection unit 11, a driving-related information acquisition unit 12, a depth distance estimation unit 13, an illumination determination unit 14, a headlight control unit 15, and a memory unit 16. The driving-related information acquisition unit 12 includes a vehicle information acquisition unit 121.
[0017] The orientation detection unit 11 acquires an in-vehicle captured image from the in-vehicle image capture device 3. Then, the orientation detection unit 11 detects the orientation of the driver based on the in-vehicle captured image acquired from the in-vehicle image capture device 3.
[0018] The orientation detection unit 11 detects the driver's facial parts (e.g., eyes, nose, mouth, etc.) from the in-vehicle image acquired from the in-vehicle imaging device 3, and detects the driver's facial orientation or gaze direction using a known image recognition technology that detects a person's facial orientation from an image in which a person's face is captured, or a known image recognition technology that detects a person's gaze direction from an image in which a person's face is captured. For example, when the in-vehicle image capture device 3 is an infrared camera, the direction detection unit 11 can detect the driver's line of sight direction from the positional relationship between the Purkinje image reflected by the cornea and the pupil by irradiating a near-infrared point light source. For example, the direction detection unit 11 can detect the driver's face direction by finding the face direction angle with the highest similarity by pattern matching between the in-vehicle captured image and standard patterns of face images for each face direction angle that are prepared in advance and stored in the direction detection unit 11.
[0019] Furthermore, the orientation detection unit 11 detects the driver's posture using a known image recognition technique for detecting the posture of a person from a captured image of the person.
[0020] The direction detection unit 11 only needs to detect at least one of the driver's facial direction and line of sight. For example, the direction detection unit 11 may detect both the driver's face direction and line of sight direction and adopt the more reliable one. For example, when the driver is wearing sunglasses or glasses, the direction detection unit 11 determines that the driver's face direction is more reliable than the driver's line of sight direction. For example, the orientation detection unit 11 may detect both the driver's facial direction and gaze direction, and then assign a priority to either one of them and adopt it as the driver's orientation. For example, when the difference between the detected driver's facial direction and gaze direction is large, the orientation detection unit 11 adopts the driver's gaze direction as the driver's orientation, and when the difference between the detected driver's facial direction and gaze direction is small, the orientation detection unit 11 adopts the driver's facial direction as the driver's orientation.
[0021] In the first embodiment, the orientation detection unit 11 detects, for example, the driver's facial orientation or line of sight direction of the driver, based on the center of the driver's head. Since the installation position and angle of view of the in-vehicle image capture device 3 are known in advance, the orientation detection unit 11 can calculate the position of the center of the driver's head. The position of the center of the driver's head is a point in real space, and is represented by, for example, coordinate values that can be mapped on a map. In the first embodiment, the driver's orientation, the driver's face direction or line of sight direction, is represented, for example, by the horizontal angle and vertical angle with respect to a line passing through the center of the driver's head and a point in front of the center of the head. In the first embodiment, "horizontal" is not limited to being strictly horizontal, but includes being approximately horizontal. In the first embodiment, "vertical" is not limited to being strictly vertical, but includes being approximately vertical. In detail, the driver's facial direction or line of sight is expressed, for example, as an angle that takes as a reference (0 degrees) when the driver faces directly ahead in the traveling direction of the vehicle 100, and the value increases as the driver faces to the right or up from the state where the driver faces directly ahead in the traveling direction of the vehicle 100. The driver's facial direction or line of sight is expressed, for example, as an angle that takes as a reference (0 degrees) when the driver faces a document in the traveling direction of the vehicle 100, and the value decreases as the driver faces to the left or down from the state where the driver faces directly ahead in the traveling direction of the vehicle 100. In the first embodiment, the word "front" is not limited to being strictly directly ahead, and includes an angle that is approximately directly ahead.
[0022] In the following first embodiment, when the term "the driver's facial direction" is used simply, the term "the driver's facial direction" refers to "the driver's facial direction or line of sight" which also includes the driver's line of sight.
[0023] Orientation detection unit 11 outputs information relating to the detected orientation of the driver (hereinafter referred to as "orientation information") to depth distance estimation unit 13 and stores it in storage unit 16. The orientation information includes information indicating the facial orientation and posture of the driver, specifically, information indicating the horizontal and vertical angles of the driver's facial orientation and information indicating the horizontal and vertical angles of the driver's posture. When storing the orientation information in the storage unit 16, the orientation detection unit 11, for example, adds a detection time to the orientation information and stores the orientation information. For example, a plurality of storage units 16 (for example, 50 storage units) may be provided, and the orientation detection unit 11 may store the latest 50 pieces of orientation information in each of the storage units 16. In this case, when storing the orientation information in the storage unit 16, the orientation detection unit 11 may not need to add the detection time to the orientation information.
[0024] In the first embodiment, when the orientation detection unit 11 does not detect the orientation of the driver, it stores the orientation information as an invalid value in the storage unit 16, for example, and determines whether a preset time (hereinafter referred to as the "orientation detection determination time") has elapsed since the orientation of the driver was no longer detected. When the orientation information is stored in the storage unit 16 without being assigned a detection time, the orientation detection unit 11 may determine whether the orientation detection determination time has elapsed based on how many consecutive invalid values are stored in the storage unit 16. When the orientation detection determination time has not elapsed, the orientation detection unit 11 refers to the storage unit 16 and outputs orientation information indicating the most recently detected orientation of the driver to the depth distance estimation unit 13. When it is determined that the direction detection determination time has elapsed since the direction of the driver was no longer detected, the direction detection unit 11 outputs direction information in which an invalid value is set for the direction of the driver (hereinafter referred to as "invalid direction information") to the headlight control unit 15. The direction detection unit 11 may output the invalid direction information to the headlight control unit 15 via the depth distance estimation unit 13 and the irradiation determination unit 14, or may output it directly to the headlight control unit 15. Note that an arrow from the direction detection unit 11 to the headlight control unit 15 is omitted in FIG. 1.
[0025] The driving-related information acquisition unit 12 acquires driving-related information from the driving-related information acquisition device 4 . In detail, the vehicle information acquisition unit 121 acquires the vehicle information from the driving-related information acquisition device 4. The vehicle information acquisition unit 121 outputs the acquired vehicle information to the depth distance estimation unit 13 as driving-related information.
[0026] The depth distance estimation unit 13 estimates a depth distance based on the direction information regarding the direction of the driver detected by the direction detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12. In detail, the depth distance estimation unit 13 estimates the depth distance by comparing the orientation information, driving-related information (here, vehicle information), and depth distance estimation information in which information regarding the driver's behavior and the driving-related information are associated with each other. In the first embodiment, the depth distance is the distance from the installation position of the headlight 2 provided on the vehicle 100 to a position that is estimated to be viewed by the driver in the direction the driver is facing (hereinafter referred to as the "estimated viewing position"). In other words, the depth distance is the distance from a point indicating the installation position of the headlight 2 to a point indicating the estimated viewing position on a virtual line indicating the direction the driver is facing. Note that the depth distance may be the distance from the installation position of the right light to the estimated viewing position, or may be the distance from the installation position of the left light to the estimated viewing position. The depth distance estimation information is information for estimating the depth distance, and is set in advance by an administrator or the like and stored in a location that the depth distance estimation unit 13 can refer to.
[0027] FIG. 2 is a diagram showing an example of the contents of depth distance estimation information used by depth distance estimation unit 13 to estimate the depth distance in the first embodiment. As shown in Fig. 2, the depth distance estimation information is information in a table format in which input information and estimated information are defined and associated with each other. In the first embodiment, as shown in Fig. 2, for example, the driver's behavior and vehicle information are defined as the input information, and the depth distance is defined as the estimated information. In the depth distance estimation information, the driver's behavior includes, for example, the up-down direction of the driver's face, the left-right direction of the driver's face, and the driver's state. In the depth distance estimation information, the vehicle information includes, for example, the vehicle speed and the steering angle. The up-down direction of the driver's face is expressed as "front" if the driver's face is facing forward, "up" if the driver's face is facing upward, or "down" if the driver's face is facing downward. The left-right direction of the driver's face is expressed as "front" if the driver's face is facing forward, "right" if the driver's face is facing right, or "left" if the driver's face is facing left. The state of the driver includes, for example, a state in which the driver is leaning forward, a state in which the amount of change in the driver's face direction is equal to or less than a preset threshold, and the like.
[0028] The depth distance estimation unit 13 determines the driver's behavior based on the orientation information output from the orientation detection unit 11, and estimates the depth distance by comparing the determined behavior and information indicating the vehicle speed and steering angle included in the vehicle information acquired by the vehicle information acquisition unit 121 with the driver's behavior and vehicle information as input information set in the depth distance estimation information as shown in Figure 2 to obtain depth distance information as estimated information.
[0029] For example, the depth distance estimation unit 13 determines whether the up-down direction of the driver's face direction is "front", "up", or "down" from information indicating the driver's face direction in the vertical direction included in the orientation information. For example, information (hereinafter referred to as "up-down angle range information") that defines an angle range in which the driver's face direction is "front", an angle range in which the driver's face direction is "up", and an angle range in which the driver's face direction is "down" is set in advance and stored in a location that the depth distance estimation unit 13 can refer to. Based on the driver's face direction in the vertical direction detected by the orientation detection unit 11, the depth distance estimation unit 13 determines whether the up-down direction of the driver's face direction is "front", "up", or "down" by referring to the up-down angle range information.
[0030] Also, for example, the depth distance estimation unit 13 determines whether the left-right direction of the driver's face direction is "front", "right", or "left" from information indicating the horizontal face direction of the driver included in the orientation information. For example, information (hereinafter referred to as "left-right angle range information") that defines an angle range in which the driver's face direction is "front", an angle range in which the driver's face direction is "right", and an angle range in which the driver's face direction is "left" is set in advance and stored in a location that the depth distance estimation unit 13 can refer to. Based on the driver's vertical face direction detected by the orientation detection unit 11, the depth distance estimation unit 13 determines whether the left-right direction of the driver's face direction is "front", "right", or "left" by referring to the left-right angle range information.
[0031] Also, for example, the depth distance estimation unit 13 judges whether the driver's posture is a preset "leaning-in state" based on the information indicating the driver's posture included in the orientation information. The condition for judging the driver's posture as "leaning-in state" at how much the driver's posture must be tilted is set in advance by an administrator or the like and stored in a location that the depth distance estimation unit 13 can refer to. Also, for example, the depth distance estimation unit 13 calculates the amount of change in the driver's face direction from the time-series direction information stored in the storage unit 16, and determines whether the amount of change is equal to or less than a threshold. Note that the threshold used to determine the amount of change is set in advance by an administrator or the like, and is stored in a location that the depth distance estimation unit 13 can refer to.
[0032] For example, suppose that the driver's face is facing in the "upward" direction. The vehicle 100 is traveling at a speed of 90 km / h. The steering angle of the vehicle 100 is 3 degrees to the right. The depth distance estimation information is as shown in FIG. 2. In this case, the depth distance estimation unit 13 estimates the depth distance to be "80 to 100 m" using the orientation information, driving-related information (here, vehicle information), and information for depth distance estimation (see No. 6 of information for depth distance estimation in Figure 2).
[0033] For example, when the driver's face is facing "upward," the vehicle speed is "80 km / h" or more, and the steering wheel angle is "5 degrees or less to the right or left," the vehicle 100 is traveling on a highway, and an object that is likely to be in the direction of the driver's face, that is, an object that is in the estimated viewing position (hereinafter referred to as "estimated visual object") that the driver is trying to view is estimated to be a sign. Therefore, in the depth distance estimation information, the depth distance is set to "80 to 100 m," which is assumed to be at a depth distance of about this range when the driver tries to check a sign while the vehicle 100 is traveling on a highway at "80 km / h" or more and the steering wheel angle is "5 degrees or less to the right or left" (No. 6 in the depth distance estimation information in FIG. 2).
[0034] Similarly, for conditions No. 1 to No. 5 of the depth distance estimation information in Figure 2, the depth distance is set based on the driver's behavior, the driving state of the vehicle 100 estimated from the vehicle information, and the estimated object viewed by the driver. Figure 3 is a diagram showing an example of the driving state of the vehicle 100 estimated from the driver's behavior and vehicle information, which is the basis for deriving the depth distance corresponding to the input information under conditions No. 1 to No. 6 set in the depth distance estimation information shown in Figure 2, and an example of an estimated visual object of the driver. The manager or the like generates depth distance estimation information based on a correspondence relationship between the running state of the vehicle 100 estimated from the driver's behavior and vehicle information and an example of an object estimated to be viewed by the driver, as shown in Fig. 3. The manager or the like may generate depth distance estimation information by verifying the correspondence relationship from information obtained by test driving the vehicle 100, for example.
[0035] In the depth distance estimation information shown in Fig. 2, six patterns of conditions No. 1 to No. 6 are set, but these are merely examples. Also, the contents of the depth distance estimation information as shown in Fig. 2 are merely examples. The depth distance estimation information may be information that allows depth distance information to be obtained from direction information and traveling-related information (here, vehicle information).
[0036] Also, as in the above example, a range of values can be set for the depth distance. For example, if the depth distance estimation unit 13 estimates that the depth distance is "80 to 100 m," in detail, the depth distance estimation unit 13 estimates that the depth distance is in the range of 80 m to 100 m from the installation position of the headlight 2 to the estimated viewing position.
[0037] The depth distance estimation unit 13 outputs information relating to the estimated depth distance (hereinafter referred to as “depth distance information”) to the irradiation determination unit 14. The depth distance information is information in which the depth distance and the estimated viewing position are associated with each other. Since the installation position of the headlight 2 and the position of the center of the driver's head are known, the depth distance estimation unit 13 can estimate the estimated viewing position based on the positional relationship between the installation position of the headlight 2 and the center of the driver's head, the estimated depth distance, and the driver's direction. The estimated viewing position is a point in real space, and is represented, for example, by coordinate values with the right or left lamp as the origin, or by coordinate values that can be mapped on a map.
[0038] If the driver's behavior and vehicle information determined based on the direction information regarding the driver's direction detected by the direction detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12 (here, the vehicle information acquired by the vehicle information acquisition unit 121) do not correspond to the driver's behavior and vehicle information as input information set in the depth distance estimation information, the depth distance estimation unit 13 determines that the depth distance could not be estimated from the depth distance estimation information and sets the depth distance to an initial value. The initial value of the depth distance is, for example, set in advance by an administrator or the like and stored in a location that the depth distance estimation unit 13 can refer to. The depth distance estimation unit 13 outputs depth distance information regarding the depth distance for which the initial value is set to the irradiation determination unit 14.
[0039] The illumination determination unit 14 determines the illumination range of the light from the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13. In detail, the illumination determination unit 14 determines the range of illumination by the headlight 2, that is, the range within the irradiable area of the headlight 2, in other words, the high beam irradiable area, the low beam irradiable area, and the auxiliary light irradiable area, to which light is to be irradiated. In the following description, the range illuminated by the light from the headlights 2 will also be simply referred to as the "illumination range."
[0040] An example of a method for determining the irradiation range by the irradiation determination unit 14 will be described. The illumination determination unit 14 determines the up-down and left-right directions of the illumination range in the direction in which the driver is facing. In detail, the illumination determination unit 14 determines the vertical range from how many degrees to how many degrees in the up-down direction of the illumination range and the horizontal range from how many degrees to how many degrees in the left-right direction of the illumination range, with the installation position of the headlight 2 as the reference position in the direction in which the driver is facing, and the illumination angle of the light emitted from the installation position to the front as the reference (0 degrees).
[0041] For example, for the up-down direction of the illumination range, the illumination determination unit 14 first calculates the vertical direction between a virtual line segment from the installation position of the headlight 2 to an estimated viewing position that is away from the installation position of the headlight 2 by the depth distance, and a virtual straight line drawn from the installation position of the headlight 2 in the traveling direction of the vehicle 100 (hereinafter referred to as "depth distance vertical angle"). The illumination determination unit 14 can calculate the depth distance vertical angle in the same manner as the depth distance horizontal angle. Then, the illumination determination unit 14 determines, for example, an angle range expanded by a preset angle in the vertical direction from the depth distance vertical angle as the up-down direction of the illumination range.
[0042] Also, for example, the illumination determination unit 14 first calculates, for the left-right direction of the illumination range, the horizontal direction formed by a virtual line segment from the installation position of the headlight 2 to an estimated viewing position away from the installation position of the headlight 2 by the depth distance, and a virtual straight line drawn from the installation position of the headlight 2 in the traveling direction of the vehicle 100 (hereinafter referred to as "depth distance horizontal angle"). The illumination determination unit 14 can know the depth distance and the estimated viewing position based on the depth distance information. Also, the installation position of the headlight 2 is known in advance. The illumination determination unit 14 can calculate the depth distance horizontal angle based on the depth distance, the estimated viewing position, and the installation position of the headlight 2. Then, the illumination determination unit 14 determines, for example, an angle range expanded from the depth distance horizontal angle by a preset angle in the horizontal direction as the up-down direction of the illumination range.
[0043] As described above, the depth distance may be estimated by the depth distance estimation unit 13 as a value having a range. In this case, for the up-down direction of the irradiation range, the irradiation determination unit 14 first calculates a depth distance vertical angle (defined as a first depth distance vertical angle) based on the smallest distance (for example, "80 m" in the example described above with reference to FIG. 2) in the range of depth distance. The irradiation determination unit 14 also calculates a depth distance vertical angle (defined as a first depth distance vertical angle) based on the largest distance (for example, "100 m" in the example described above with reference to FIG. 2) in the range of depth distance. Then, the illumination determination unit 14 determines, for example, the range from the smaller one of the first depth distance vertical angle and the second depth distance vertical angle to the larger one as the up-down direction of the illumination range. The depth distance estimation unit 13 calculates the first depth distance horizontal angle and the second depth distance horizontal angle in a similar manner for the left and right directions of the irradiation range, and determines, for example, the range from the smaller to the larger of the first depth distance horizontal angle and the second depth distance horizontal angle to be the left and right direction of the irradiation range.
[0044] For example, the illumination determination unit 14 may determine the up-down direction of the illumination range based on the center of the range of the depth distance. For example, when the depth distance is estimated to be "80m to 100m", the illumination determination unit 14 calculates the depth distance vertical angle from the center depth distance of "90m". The illumination determination unit 14 may set the calculated depth distance vertical angle as the center, and set the range of angles expanded by a preset angle in the vertical direction from the depth distance vertical angle as the up-down direction of the illumination range. Also, for example, the illumination determination unit 14 may determine the horizontal direction of the illumination range based on the center of the range of the depth distance in a similar manner.
[0045] When the depth distance estimation unit 13 sets an initial value of the depth distance to the depth distance, the illumination determination unit 14 determines the illumination range based on the initial value. In detail, when depth distance information regarding the depth distance for which an initial value is set is output from the depth distance estimation unit 13, the illumination determination unit 14 determines the up-down and left-right directions of the illumination range corresponding to the initial value of the depth distance.
[0046] The illumination determination unit 14 outputs information on the determined illumination range (hereinafter referred to as “illumination information”) to the headlight control unit 15. The illumination information includes information indicating the vertical angular range and the horizontal angular range of the illumination range with the installation position of the headlight 2 as the reference position.
[0047] The headlight control unit 15 causes the headlights 2 to irradiate the illumination range determined by the illumination determination unit 14 with light.
[0048] For example, it is assumed that the illumination determination unit 14 outputs illumination information to the headlight control unit 15 indicating that θ1 degree to θ2 degrees is the up-down direction and φ1 degree to φ2 degrees is the left-right direction. In this case, the headlight control unit 15 controls, for example, the light sources of the low beam unit, high beam unit, or auxiliary light unit of the headlight 2 to irradiate light in a range of φ1 degree to φ2 degrees in the left-right direction and a range of θ1 degree to θ2 degrees in the up-down direction. The headlight control unit 15 may control, for example, the multiple light sources of the low beam unit, high beam unit, or auxiliary light unit to irradiate light in the above ranges by changing the optical axis of each of them, or may control the light sources to be turned on among the multiple light sources of the low beam unit, high beam unit, or auxiliary light unit to irradiate light in the above ranges.
[0049] As a result, the light emitted by the headlight 2 is irradiated to the irradiation range as described with reference to FIG. FIG. 4 is a diagram for explaining an example of a state in which headlight control unit 15 causes headlight 2 to irradiate light onto the illumination range determined by illumination determination unit 14 in the first embodiment. In Fig. 4, the driver is indicated by "D" and the range of light irradiation by the headlight 2 is indicated by "LA". Fig. 4 is a side view of the road on which the vehicle 100 is traveling. In Fig. 4, as an example, the headlight control unit 15 causes the headlight 2 to irradiate light to the irradiation range determined by the irradiation determination unit 14 when the driver's face is facing within the "upward" range, the vehicle 100 is traveling at a speed of 90 km / h, and the steering angle of the vehicle 100 is 3 degrees to the right. In the example shown in FIG. 4, the depth distance estimation unit 13 estimates the depth distance to be "80 to 100 m" based on the depth distance estimation information having the content as shown in FIG. 2, assuming that the driver's direction and driving-related information (here, vehicle information) correspond to No. 6 of the depth distance estimation information, and the illumination determination unit 14 determines the illumination range to be a range of φ1 degree to φ2 degrees in the left-right direction and a range of θ1 degree to θ2 degrees in the up-down direction (the left-right illumination range is omitted in FIG. 4). The illumination determination unit 14 calculates a first depth distance vertical angle based on a depth distance of "80 m" for the up-down direction of the illumination range, and calculates a second depth distance vertical angle based on a depth distance of "100 m," thereby determining the up-down direction of the illumination range.
[0050] The headlight control unit 15 causes the headlights 2 to emit light in the direction in which the driver is facing, to an illumination range determined by the illumination determination unit 14 based on the depth distance estimated by the depth distance estimation unit 13 taking into account the driver's orientation and driving-related information (here, vehicle information). As a result, the headlight control unit 15 can control the headlights 2 so that light is irradiated onto the estimated viewed object estimated to be present at the estimated viewing position. The driver can view the estimated viewed object. In the situation shown in Fig. 4, the presumed visual object is presumed to be a sign (see Fig. 3). That is, the headlight control unit 15 can cause light to be irradiated onto the sign, which is the presumed visual object of the driver. Note that, although Fig. 4 illustrates the sign for ease of understanding, the sign is an object presumed to exist and does not necessarily exist in reality.
[0051] Furthermore, when direction invalid information is output from the direction detection unit 11, the headlight control unit 15 causes the headlights 2 to irradiate light in an irradiation direction for when the driver's direction cannot be acquired. The irradiation direction for when the driver's direction cannot be acquired is, for example, the forward direction. Information on the extent of the forward direction is generated in advance by an administrator or the like and stored in a location that the headlight control unit 15 can refer to.
[0052] The storage unit 16 stores various types of information. 1, the storage unit 16 is provided in the headlight control device 1, but this is merely an example. The storage unit 16 may be provided in a location outside the headlight control device 1 that can be referenced by the headlight control device 1.
[0053] The operation of the headlight control device 1 according to the first embodiment will be described. FIG. 5 is a flowchart for explaining the operation of the headlight control device 1 according to the first embodiment. For example, when the headlight 2 or the headlight control device 1 is turned on, the headlight control device 1 determines to perform lighting control of the headlight 2 based on the driver's direction, and starts the operation shown in the flowchart of Fig. 5. The headlight control device 1 repeats the operation shown in the flowchart of Fig. 5 until, for example, the headlight 2 is turned off, the headlight control device 1 is turned off, or the power of the vehicle 100 is turned off. For example, a control unit (not shown) of the headlight control device 1 acquires information indicating the state of the headlights 2 from a headlight switch mounted on the vehicle 100, and determines whether or not the headlights 2 are on. Alternatively, if there is a driver's direction tracking function switch, the control unit of the headlight control device 1 determines whether or not the headlight control device 1 is on. When the control unit determines that the headlights 2 are on, it determines to start lighting control of the headlights 2 based on the driver's direction, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, and the headlight control unit 15 to instruct them to start lighting control of the headlights 2. In addition, when the control unit determines that the headlights 2 are off, the headlight control device 1 is off, or the vehicle 100 has been turned off, it determines to end the control of the headlights 2 lighting based on the driver's direction, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, and the headlight control unit 15 instructing them to end the control of the headlights 2 lighting.
[0054] The orientation detection unit 11 acquires an in-vehicle captured image from the in-vehicle image capture device 3, and detects the orientation of the driver based on the acquired in-vehicle captured image (step ST1-1). The direction detection unit 11 outputs the direction information to the depth distance estimation unit 13 and stores it in the storage unit 16 . In step ST1-1, if the orientation detection unit 11 does not detect the driver's orientation, then until the orientation detection determination time has elapsed since the orientation detection unit 11 stopped detecting the driver's orientation, the orientation detection unit 11 refers to the memory unit 16 and outputs orientation information indicating the driver's orientation detected most recently to the depth distance estimation unit 13. If the direction detection determination time has elapsed since the direction of the driver was no longer detected, the direction detection unit 11 outputs direction invalid information to the headlight control unit 15. If the direction detection unit 11 outputs direction invalid information to the headlight control unit 15, the operation of the headlight control device 1 skips the processing of steps ST2 to ST3 described below and proceeds to the processing of step ST4.
[0055] The driving-related information acquisition unit 12 acquires driving-related information from the driving-related information acquisition device 4 . In detail, the vehicle information acquisition unit 121 acquires vehicle information from the driving-related information acquisition device 4 (step ST1-2). The vehicle information acquisition unit 121 outputs the acquired vehicle information to the depth distance estimation unit 13.
[0056] The depth distance estimation unit 13 estimates the depth distance using orientation information regarding the driver's orientation detected by the orientation detection unit 11 in step ST1-1, the driving-related information acquired by the driving-related information acquisition unit 12 in step ST1-2, and information for depth distance estimation (step ST2). The depth distance estimation unit 13 outputs the depth distance information to the irradiation determination unit 14.
[0057] The illumination determination unit 14 determines the illumination range of the light from the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13 in step ST2 (step ST3). The illumination determination unit 14 outputs the illumination information to the headlight control unit 15.
[0058] The headlight control unit 15 causes the headlights 2 to irradiate the illumination range determined by the illumination determination unit 14 in step ST3 with light (step ST4). If, in step ST1-1, the orientation detection unit 11 outputs invalid orientation information to the headlight control unit 15, in step ST4, the headlight control unit 15 causes the headlight 2 to emit light in an illumination direction for when the orientation of the driver cannot be obtained.
[0059] It should be noted that, for example, in step ST2, when the depth distance estimation unit 13 is unable to estimate the depth distance, it sets the depth distance to, for example, an initial value of the depth distance. For example, suppose that the contents of the depth distance estimation information are as shown in Fig. 2, and the driver's face is facing within the range of "forward" in the up-down direction and "right" in the left-right direction. Also, suppose that the traveling speed of the vehicle 100 is 30 km / h. Also, suppose that the steering wheel angle is 5 degrees. In this case, the driver's face direction and the vehicle speed correspond to the depth distance estimation information No. 2, but the steering wheel angle does not correspond. Therefore, the depth distance estimation unit 13 sets an initial value to the depth distance. In this case, in step ST3, the illumination determination unit 14 determines the illumination range based on the depth distance for which an initial value is set, and in step ST4, the headlight control unit 15 causes the headlight 2 to illuminate the illumination range determined based on the depth distance for which an initial value is set. For example, thereafter, if the depth distance estimation unit 13 can estimate the depth distance using the depth distance estimation information, the depth distance estimation unit 13 estimates the depth distance using the depth distance estimation information. For example, in the above example, it is assumed that the driver's face direction and vehicle speed remain the same and the steering wheel angle becomes 20 degrees. It is assumed that the driver turns the steering wheel to the right in an attempt to make a right turn. In this case, the depth distance estimation unit 13 estimates the depth distance to be "15 to 20 m" assuming that the driver's face direction, vehicle speed, and steering wheel angle correspond to No. 2 of the depth distance estimation information. Then, the illumination determination unit 14 determines the illumination range based on the depth distance estimated by the depth distance estimation unit 13 based on the depth distance estimation information, and the headlight control unit 15 causes the headlight 2 to illuminate the illumination range determined by the illumination determination unit 14. In other words, the headlight control device 1 switches from lighting control of the headlights 2 with the depth distance set as an initial value to lighting control of the headlights 2 according to the depth distance estimated by the depth distance estimation unit 13, in other words, lighting control such that light is irradiated onto the estimated visual object estimated to be present at the driver's estimated visual position.
[0060] The distance between the installation position of the headlight 2 and the position where it is estimated that the driver is actually looking (estimated viewing position), that is, the depth distance, cannot be determined only from the driver's direction. If the distance at which the headlight 2 is to emit light is fixedly determined, it would be difficult for the headlight 2 to emit light at the place where it is estimated that the driver is actually looking or at an object present at that place. In addition, the position of the driver's head is different from the installation position of headlight 2. Therefore, if headlight 2 is irradiated with light to cover the entire range in the direction in which the driver is facing, the irradiation range will be too wide, causing glare to pedestrians and drivers of other vehicles. The conventional techniques described above do not take the above into consideration, and a situation may occur in which the light from the headlights 2 is not irradiated onto the estimated viewing position of the driver.
[0061] For example, a situation may occur in which the driver's estimated viewing position is closer than the fixed illumination range of light from the headlights 2, and the light from the headlights 2 cannot be illuminated at the driver's estimated viewing position. To give a specific example, suppose that a driver is checking whether a pedestrian will jump out from behind a parked vehicle in front of him in an underground parking lot. In this case, the driver is actually checking several meters ahead where there is a parked vehicle, but if the distance from the headlights 2 to the headlights 2 to irradiate light is fixed to several tens of meters ahead, which is assumed to be the driver's field of vision during normal driving such as driving in an area where there are no parked vehicles around, the light of the headlights 2 may not be irradiated onto the upper body of the pedestrian behind the parked vehicle. This is because the light of the headlights 2 may not be within the range of light irradiation by the headlights 2 several meters ahead. In this way, even if light is irradiated to a range that is a fixed distance ahead from the headlights 2 without considering the depth distance, there is a possibility that the light will not be irradiated to the pedestrian who jumps out. This will delay the driver's discovery of the pedestrian. Conversely, a situation may occur in which the driver's estimated viewing position is farther away than the fixed illumination range of light from the headlights 2, and the light from the headlights 2 cannot illuminate the driver's estimated viewing position. To give a specific example, suppose a driver is driving on a highway and wants to check a sign ahead. In this case, the sign that the driver is trying to check is farther away than the fixed range of light from the headlights 2 and may not be within that range. Even if light is emitted to a range the fixed distance ahead from the headlights 2, without taking the depth distance into consideration, there is a possibility that the light will not be able to be emitted onto the sign. This will result in the driver being late in checking the sign.
[0062] In contrast, the headlight control device 1 according to the first embodiment detects the direction of the driver based on an in-vehicle captured image and acquires driving-related information (here, vehicle information) as described above. The headlight control device 1 estimates a depth distance based on the detected direction information on the driver's direction and the acquired driving-related information, and determines an illumination range of light by the headlight 2 based on the estimated depth distance. Then, the headlight control device 1 causes the headlight 2 to illuminate the determined illumination range with light. Therefore, the headlight control device 1 can appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0063] In the above-described first embodiment, in the headlight control device 1, the depth distance estimation unit 13 estimates the depth distance using the direction information regarding the direction of the driver detected by the direction detection unit 11, the driving-related information acquired by the driving-related information acquisition unit 12, more specifically, the vehicle information acquired by the vehicle information acquisition unit 121, and the information for depth distance estimation. Without being limited to this, for example, the depth distance estimation unit 13 may estimate the depth distance and the width of the irradiation range (hereinafter referred to as the "ideal width of the irradiation range"). For example, the administrator or the like sets the depth distance in the information for depth distance estimation, and sets the upper limit of the irradiation range in the vertical direction and the upper limit of the irradiation range in the horizontal direction as the ideal width of the irradiation range. The depth distance estimation unit 13 estimates the depth distance and the ideal width of the irradiation range based on the direction information, the vehicle information, and the information for depth distance estimation. In this case, the depth distance estimation unit 13 outputs the depth distance information and information on the ideal width of the irradiation range to the irradiation determination unit 14. The illumination determination unit 14 determines the illumination range based on the depth distance and the ideal width of the illumination range estimated by the depth distance estimation unit 13. In detail, when the illumination range calculated based on the depth distance estimated by the depth distance estimation unit 13 exceeds the ideal width of the illumination range, for example, the illumination determination unit 14 determines the range up to the ideal width of the illumination range as the illumination range. For example, if the depth distance estimated by the depth distance estimation unit 13 is a value with a range, the illumination range determined by the illumination determination unit 14 based on the depth distance may be too wide, and the light from the headlight 2 may cause glare to oncoming vehicles, etc. The depth distance estimation unit 13 estimates the ideal width of the illumination range, and the illumination determination unit 14 determines the illumination range with the ideal width of the illumination range as the upper limit, so that the headlight control device 1 can reduce the glare given to oncoming vehicles, etc.
[0064] In the above-described first embodiment, the depth distance estimation unit 13 may estimate the depth distance and also estimate the amount of light irradiated by the headlights 2 (hereinafter referred to as the "ideal light amount"). For example, the administrator or the like sets the depth distance in the depth distance estimation information and sets the ideal amount of light irradiated according to the depth distance as the ideal light amount. For example, the administrator or the like sets a larger value for the ideal light amount as the depth distance is larger. The depth distance estimation unit 13 estimates the depth distance and the ideal light amount based on the orientation information, the vehicle information, and the depth distance estimation information. In this case, the depth distance estimation unit 13 outputs the depth distance information to the illumination determination unit 14 and also outputs information on the estimated ideal light amount to the headlight control unit 15. The headlight control unit 15 causes the headlights 2 to emit light in the illumination range determined by the illumination determination unit 14 with the ideal light amount estimated by the depth distance estimation unit 13. The depth distance estimation unit 13 estimates the ideal light amount, and the headlight control unit 15 causes the headlight 2 to emit light at the ideal light amount, so that the headlight control device 1 can emit light in the direction the driver is facing, with the amount of light assumed to be necessary for the driver to see the estimated visual object, depending on the distance from the vehicle 100 to which the light is being emitted.
[0065] In the above-described first embodiment, the depth distance estimation unit 13 may estimate the depth distance as well as the ideal width and ideal light amount of the irradiation range.
[0066] In the above-described first embodiment, the headlight control device 1 is an in-vehicle device mounted on the vehicle 100, and the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) are provided in the in-vehicle device. However, some of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, and the headlight control unit 15 may be provided in the in-vehicle device of the vehicle 100, and the rest may be provided in a server connected to the in-vehicle device via a network. In addition, all of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) may be provided in the server.
[0067] 6A and 6B are diagrams showing an example of a hardware configuration of the headlight control device 1 according to the first embodiment. In the first embodiment, the functions of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) are realized by the processing circuit 1001. That is, the headlight control device 1 includes the processing circuit 1001 for estimating a depth distance based on direction information relating to the direction of the driver detected based on an in-vehicle captured image acquired from the in-vehicle image capture device 3 and driving-related information, and for controlling the lighting of the headlights 2 based on the estimated depth distance. The processing circuit 1001 may be dedicated hardware as shown in FIG. 6A, or may be a processor 1004 executing a program stored in a memory 1005 as shown in FIG. 6B.
[0068] When the processing circuit 1001 is dedicated hardware, the processing circuit 1001 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof.
[0069] When the processing circuit is the processor 1004, the functions of the orientation detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14, the headlight control unit 15, and the control unit (not shown) are realized by software, firmware, or a combination of software and firmware. The software or firmware is described as a program and stored in the memory 1005. The processor 1004 reads and executes the program stored in the memory 1005 to execute the functions of the orientation detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14, the headlight control unit 15, and the control unit (not shown). That is, the headlight control device 1 includes a memory 1005 for storing a program that, when executed by the processor 1004, results in the execution of steps ST1-1 and ST1-2 to ST4 in FIG. 5 described above. The programs stored in the memory 1005 can also be said to cause the computer to execute the procedures or methods of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14, the headlight control unit 15, and the control unit (not shown). Here, the memory 1005 corresponds to, for example, a non-volatile or volatile semiconductor memory such as a RAM, a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, a DVD (Digital Versatile Disc), and the like.
[0070] The functions of the orientation detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown) may be partially realized by dedicated hardware and partially realized by software or firmware. For example, the functions of the orientation detection unit 11 and the driving-related information acquisition unit 12 may be realized by a processing circuit 1001 as dedicated hardware, and the functions of the depth distance estimation unit 13, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown) may be realized by a processor 1004 reading and executing a program stored in a memory 1005. The storage unit 16 is configured with a memory 1005, for example. The headlight control device 1 also includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with devices such as the headlight 2, the in-vehicle image capture device 3, or the driving-related information acquisition device 4.
[0071] As described above, the headlight control device 1 of embodiment 1 is configured to include an orientation detection unit 11 that detects the direction of the driver based on an image (in-vehicle image) of the driver of the vehicle 100, a driving-related information acquisition unit 12 that acquires driving-related information related to the driving of the vehicle 100, a depth distance estimation unit 13 that estimates a depth distance, which is the distance from the installation position of the headlight 2 provided on the vehicle 100 to an estimated viewing position that is estimated to be the driver's viewing position in the direction the driver is facing, based on the orientation information related to the direction of the driver detected by the orientation detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12, an illumination determination unit 14 that determines the illumination range of light by the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13, and a headlight control unit 15 that causes the headlight 2 to illuminate with light in the illumination range determined by the illumination determination unit 14. Therefore, the headlight control device 1 can control the lighting of the headlights 2 in the vehicle 100 based on the direction in which the driver is facing, taking into consideration how far ahead in the direction in which the driver is actually facing he or she is trying to see. The headlight control device 1 can appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0072] In detail, in the headlight control device 1, the driving-related information acquisition unit 12 has a vehicle information acquisition unit 121 that acquires vehicle information regarding the vehicle 100 as driving-related information, and the depth distance estimation unit 13 estimates the depth distance based on the orientation information and the vehicle information. Therefore, the headlight control device 1 can control the lighting of the headlights 2 in the vehicle 100 based on the direction in which the driver is facing, taking into consideration how far ahead in the direction in which the driver is actually facing he or she is trying to see. The headlight control device 1 can appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0073] Embodiment 2 In the first embodiment, the headlight control device estimates the depth distance based on the direction information and the vehicle information. In the second embodiment, an embodiment in which the depth distance is estimated using map information will be described.
[0074] FIG. 7 is a diagram showing an example of the configuration of a headlight control device 1a according to the second embodiment. In the second embodiment, it is assumed that the headlight control device 1a is mounted on a vehicle 100. The headlight control device 1a controls the lighting of the headlights 2 provided on the vehicle 100 based on the direction of the driver of the vehicle 100. In the second embodiment, the "direction of the driver" is represented by the direction of the driver's face or the direction of the driver's line of sight. In the second embodiment, the "direction of the driver" may include the direction of the driver's body, in other words, the driver's posture, in addition to the direction of the driver's face or the direction of the driver's line of sight. In the second embodiment, the headlight control device 1a performs light control of the headlights 2 based on the driver's direction, and it is assumed that the light control is performed when the headlights 2 are turned on in a dark place around the vehicle 100, such as a parking lot at night or an urban area at night. In the following second embodiment as well, when simply referring to "the driver's facial direction", the "driver's facial direction" refers to "the driver's facial direction or line of sight", which also includes the driver's line of sight.
[0075] 7, the same components as those in the headlight control device 1 described in the first embodiment with reference to FIG. 1 are denoted by the same reference numerals, and duplicated description will be omitted. The headlight control device 1a according to the second embodiment differs from the headlight control device 1 according to the first embodiment in that the driving-related information acquisition unit 12a includes a map information acquisition unit 122 in addition to the vehicle information acquisition unit 121. Furthermore, the specific operation of the depth distance estimation unit 13a in the headlight control device 1a according to the second embodiment is different from the specific operation of the depth distance estimation unit 13 in the headlight control device 1 according to the first embodiment.
[0076] In the second embodiment, the driving-related information acquisition device 4 includes a vehicle speed sensor (not shown) or a steering wheel angle sensor (not shown), as well as a positioning device such as a car navigation device, a Global Positioning System (GPS), or a high-precision locator. The positioning device such as a car navigation device holds map information. The map information includes the current position of the vehicle 100, route information regarding the route the vehicle 100 is traveling, and information regarding the lane the vehicle 100 is traveling on (the lane here is a so-called lane). For example, a high-precision locator can obtain information regarding the current position of the vehicle 100 to an accuracy of several tens of centimeters, and therefore can obtain information regarding the lane the vehicle 100 is traveling on. The driving-related information acquisition device 4 outputs the vehicle information and the map information to the headlight control device 1a as driving-related information.
[0077] The map information acquisition unit 122 acquires map information from the driving-related information acquisition device 4 . The map information acquisition unit 122 outputs the acquired map information to the depth distance estimation unit 13a as driving-related information.
[0078] The depth distance estimation unit 13a estimates the depth distance based on the driver's direction detected by the direction detection unit 11 and the driving-related information acquisition unit 12a (more specifically, the vehicle information acquired by the vehicle information acquisition unit 121 and the map information acquired by the map information acquisition unit 122). In detail, the depth distance estimation unit 13a estimates the depth distance by comparing the direction information, the driving-related information (here, vehicle information and map information), and the depth distance estimation information.
[0079] FIG. 8 is a diagram showing an example of the contents of depth distance estimation information used by depth distance estimation unit 13a to estimate the depth distance in the second embodiment. As shown in FIG. 8, in the second embodiment, the depth distance estimation information is, for example, a table in which the driver's behavior, vehicle information, map information, and depth distance are associated with each other. In the depth distance estimation information, the driver's behavior includes, for example, the up-down direction of the driver's face and the left-right direction of the driver's face. The up-down direction of the driver's face is expressed as "front," "upward," or "downward." The left-right direction of the driver's face is expressed as "front," "right," or "left." In the depth distance estimation information, the vehicle information includes, for example, the vehicle speed. In the depth distance estimation information, the map information includes, for example, information on the traveling position of the vehicle 100, route information, and lane position information.
[0080] The depth distance estimation unit 13a determines the driver's behavior based on the driver's direction detected by the direction detection unit 11, and estimates the depth distance by comparing the determined behavior, information indicating the vehicle speed and steering angle contained in the vehicle information acquired by the vehicle information acquisition unit 121, and information indicating the traveling position of the vehicle 100, route information, and information indicating the lane position contained in the map information acquired by the map information acquisition unit 122, with the driver's behavior, vehicle information, and map information set in the depth distance estimation information as shown in Figure 8 to obtain depth distance information.
[0081] For example, the depth distance estimation unit 13a determines whether the up-down direction of the driver's face is "forward," "upward," or "downward" from information indicating the driver's vertical face direction included in the orientation information. Also, for example, the depth distance estimation unit 13a determines whether the left-right direction of the driver's facial direction is “front,” “right,” or “left” from information indicating the horizontal facial direction of the driver included in the orientation information. The method by which depth distance estimation unit 13a determines whether the up-down and left-right directions of the driver's face are "forward", "up", "down", "right" or "left" is similar to the method by depth distance estimation unit 13 for determining whether the up-down and left-right directions of the driver's face are "forward", "up", "down", "right" or "left" already described in embodiment 1, so duplicated explanations will be omitted.
[0082] For example, assume that the driver's face is facing "forward" in the vertical direction and facing "right" in the horizontal direction. Also assume that the vehicle 100 is traveling at a speed of 30 km / h. Also assume that the vehicle 100 is traveling 15 m before an intersection. Also assume that the route of the vehicle 100 is to "turn right at the next intersection." It is assumed that the depth distance estimation information has contents as shown in FIG. In this case, the depth distance estimation unit 13a uses the orientation information, driving-related information (here, vehicle information and map information), and information for depth distance estimation to estimate that the depth distance is "a range with a margin of 5 m including the sidewalk and crosswalk at the intersection" (see information for depth distance estimation No. 2 in Figure 8).
[0083] For example, if the driver's face is facing "front to upward" in the vertical direction and "right or left" in the horizontal direction, the vehicle speed is "15 to 35 km / h", and the vehicle 100 is about to "turn right or left at the next intersection" within "20 m of the intersection", the vehicle 100 is about to turn right or left at the intersection, and the presumed visual object of the driver is presumed to be a pedestrian. Therefore, in the depth distance estimation information, the depth distance is set to "a range with a margin of 5 m including the sidewalk and crosswalk at the intersection" which is assumed to be located at a depth distance of about this range when the driver tries to check for a pedestrian while the vehicle 100 is traveling "within 20 m of the intersection" to turn right or left at the intersection (No. 2 of the depth distance estimation information in FIG. 8). Similarly, for conditions No. 1, and No. 3 to No. 6 of the depth distance estimation information in Figure 8, the depth distance is set based on the driving state of the vehicle 100 estimated from the driver's behavior, vehicle information, and map information, and the estimated visible object of the driver. FIG. 9 is a diagram showing an example of the driving state of the vehicle 100 estimated from the driver's behavior, vehicle information, and map information, which are the basis for deriving the depth distance corresponding to the input information under conditions No. 1 to No. 6 set in the depth distance estimation information shown in FIG. 8, and an example of an estimated visual object of the driver.
[0084] In the depth distance estimation information shown in Fig. 8, six patterns of conditions No. 1 to No. 6 are set, but these are merely examples. Also, the contents of the depth distance estimation information as shown in Fig. 8 are merely examples. In the depth distance estimation information shown in Figure 8, the driving position, route information, and lane position are set as map information, but this is merely an example, and in the depth distance estimation information, for example, information indicating the distance from a certain position (for example, within 20 m to an intersection, within 50 m to a highway interchange, etc.) may be set as map information. The information for estimating depth distance needs only to be information that can obtain depth distance information from orientation information and driving-related information (here, vehicle information and map information), and in the information for estimating depth distance, at least the driver's facial direction, vehicle speed, and driving position information need only be associated with the depth distance.
[0085] The depth distance estimation unit 13a outputs the depth distance information to the irradiation determination unit .
[0086] In addition, when the orientation information regarding the driver's orientation detected by the orientation detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12a (here, the vehicle information acquired by the vehicle information acquisition unit 121 and the map information acquired by the map information acquisition unit 122) do not correspond to the input information set in the depth distance estimation information, the depth distance estimation unit 13a determines that the depth distance cannot be estimated from the depth distance estimation information, and sets the depth distance to an initial value of the depth distance. The depth distance estimation unit 13a outputs to the irradiation determination unit 14 depth distance information regarding the depth distance for which the initial value has been set.
[0087] The illumination determination unit 14 determines the illumination range of the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13a, and outputs illumination information to the headlight control unit 15. The headlight control unit 15 causes the headlight 2 to illuminate the illumination range determined by the illumination determination unit 14.
[0088] FIG. 10A is a diagram for explaining an example of the depth distance estimated by the depth distance estimation unit 13a in the second embodiment. FIG. 10B is a diagram illustrating an example of a state in which headlight control unit 15 causes headlight 2 to irradiate light to an illumination range determined by illumination determination unit 14 based on the depth distance estimated by depth distance estimation unit 13a as shown in FIG. 10A in embodiment 2. FIG. 10A is a bird's-eye view of the road on which the vehicle 100 is traveling. Fig. 10B is a side view of the road on which the vehicle 100 is traveling. In Fig. 10B, the driver is indicated by "D" and the illumination range of the light from the headlights 2 is indicated by "LA". In Fig. 10A, the depth distance is the distance from the right light to the driver's estimated viewing position. In Fig. 10B, for convenience, the vehicle 100 is shown as seen from the left, but the illumination range shown in Fig. 10B is the illumination range by the right light. 10A and 10B, as an example, when the driver's face is facing "forward" in the up-down direction and "right" in the left-right direction, and the vehicle 100 is traveling at a speed of 30 km / h to turn right at the next intersection 15 m before the intersection, the depth distance estimation unit 13a estimates the depth distance using the depth distance estimation information, and the headlight control unit 15 causes the headlight 2 to irradiate light to the irradiation range determined by the irradiation determination unit 14. It is assumed that the depth distance estimation information has contents as shown in FIG.
[0089] Based on the depth distance estimation information shown in FIG. 8, the depth distance estimation unit 13a estimates the depth distance as "a range with a margin of 5 m including the sidewalk and the crosswalk at the intersection" assuming that the driver's behavior determined from the orientation information and the driving-related information (here, vehicle information and map information) correspond to No. 2 of the depth distance estimation information. As a result, the depth distance range with a margin of 5 m including the sidewalk near the intersection and the crosswalk at the intersection is estimated in the driver's orientation (see FIG. 10A). At this time, the depth distance estimation unit 13a calculates the range of the depth distance with a margin of 5 m including the sidewalk near the intersection and the crosswalk at the intersection based on the map information, for example, by a method to be described using FIG. 11A and FIG. 11B below. Note that the method described below using Figures 11A and 11B is just one example, and the depth distance estimation unit 13a may calculate the depth distance range with a margin of 5 m, including the sidewalk near the intersection and the crosswalk at the intersection, using other methods. Moreover, Figures 11A and 11B are convenient diagrams for explaining an example of a method in embodiment 1 by depth distance estimation unit 13a to calculate the specific range of meters for the depth distance range with a margin of 5 meters, including the sidewalk near the intersection and the crosswalk at the intersection, and the road shown in Figures 11A and 11B does not match the road shown in Figure 10A.
[0090] 11A and 11B are bird's-eye views of a road on which a vehicle 100 is traveling. In Fig. 11A and 11B, the vehicle 100 is not shown for the sake of simplicity, but the vehicle 100 is traveling on a general road and is about to turn right at the next intersection, with the driver facing right. The driver's orientation at this time is assumed to be θd degrees.
[0091] Acquisition of various information First, the depth distance estimation unit 13a acquires information indicating the number of lanes of a road including the own lane and the lane of the right turn destination and the distance to the intersection from the map information. Here, for example, the depth distance estimation unit 13a acquires information that the road including the own lane and the lane of the right turn destination is a two-lane road on one side and the distance to the intersection is 15 m. In the example shown in Fig. 11A and Fig. 11B, the driver is facing right. In this case, the depth distance estimation unit 13a estimates from the direction information and the map information that the driver is trying to look at the sidewalk in front of the vehicle 100. Furthermore, since the road shown in Fig. 11A and Fig. 11B is a general road, the depth distance estimation unit 13a assumes that the lane width is 3.5 m. Note that the assumed lane width is determined in advance depending on the road type. When a high-precision locator is used as the driving-related information acquisition device 4, the depth distance estimation unit 13a may use the lane width information acquired from the high-precision locator.
[0092] <Calculating the distance from the installation position of headlight 2 to the front of the sidewalk> The depth distance estimation unit 13a calculates the distance from the installation position of the headlight 2 to the front of the sidewalk. In detail, the depth distance estimation unit 13a calculates the distance (indicated by "D11" in Fig. 11A) of a virtual straight line indicating the direction in which the driver is facing from the center of the driver's head to the front of the sidewalk, and calculates the distance from the installation position of the headlight 2 to the front of the sidewalk based on this. Because the vehicle 100 is about to turn right, the depth distance estimation unit 13a estimates that the vehicle 100 is currently traveling in the right lane of a two-lane road. When a high-precision locator is used as the traveling-related information acquisition device 4, the depth distance estimation unit 13a may estimate the lane in which the vehicle 100 is traveling by using information on the actual traveling lane. The depth distance estimation unit 13a calculates the distance from the center of the driver's head to the sidewalk on a virtual straight line indicating the direction the driver is facing, based on the position of the center of the driver's head, the direction of the driver, the assumed lane width, and the number of lanes of the road acquired from the map information. It is assumed that the lane in which the vehicle 100 is traveling is the right lane of a two-lane road, and the lane width is 3.5 m. The direction of the driver is θd degrees. For example, if the position of the center of the driver's head is the center in the width direction of the lane in which the vehicle 100 is traveling, the depth distance estimation unit 13a calculates (3.5×2.5) / sinθd(m) as the distance from the center of the driver's head to the sidewalk on a virtual straight line indicating the direction the driver is facing. Then, the depth distance estimation unit 13a calculates the distance from the installation position of the headlight 2 to the sidewalk on the basis of the calculated distance from the center of the driver's head to the sidewalk on a virtual straight line indicating the direction the driver is facing. Since the positional relationship between the center of the driver's head and the installation position of the headlight 2 is known, the depth distance estimation unit 13a can calculate the distance from the installation position of the headlight 2 to the front of the sidewalk based on the distance from the center of the driver's head to the front of the sidewalk of a virtual straight line indicating the direction the driver is facing.
[0093] <Calculating the distance from the installation position of headlight 2 to the back of the sidewalk> The depth distance estimation unit 13a calculates the distance from the installation position of the headlight 2 to the back of the sidewalk in a manner similar to that used to calculate the distance from the installation position of the headlight 2 to the front of the sidewalk. In detail, the depth distance estimation unit 13a calculates the distance (indicated by "D12" in Fig. 11B) of a virtual straight line indicating the direction in which the driver is facing from the center of the driver's head to the back of the sidewalk, and calculates the distance from the installation position of the headlight 2 to the back of the sidewalk based on this. Here, the depth distance estimation unit 13a calculates {15-(3.5×2)} / sinθd(m) as the distance from a virtual straight line indicating the direction the driver is facing to the back of the sidewalk, and calculates the distance from the installation position of the headlight 2 to the back of the sidewalk based on this distance.
[0094] <Calculating the range of depth distance> The depth distance estimation unit 13a calculates the range of the depth distance based on the calculated distance from the installation position of the headlight 2 to the front of the sidewalk and the calculated distance from the installation position of the headlight 2 to the back of the sidewalk. Now, the depth distance estimation unit 13a calculates a depth distance range with a margin of 5 m, including the sidewalk near the intersection and the crosswalk at the intersection. For example, if the distance from the installation position of the headlight 2 to the front of the sidewalk calculated by the depth distance estimation unit 13a is "Am" and the distance from the installation position of the headlight 2 to the back of the sidewalk is "Bm", the depth distance estimation unit 13a adds a margin of 5 m to these distances and calculates a range from "Am-5m" to "Bm+5m" as the depth distance range with a margin of 5 m, including the sidewalk near the intersection and the crosswalk at the intersection.
[0095] Returning to the explanation using FIG. 10A. Here, the depth distance estimation unit 13a estimates the depth distance to be "10m to 30m" by, for example, the method described above with reference to Fig. 11A and Fig. 11B. Specifically, after calculating that the distance from the installation position of the headlight 2 to the front of the sidewalk is 15m and the distance from the installation position of the headlight 2 to the back of the sidewalk is 25m, a margin of 5m is added to each, and the range of the depth distance is set to be "15m-5m=10m" to "25m+5m=30m." Furthermore, for example, based on the depth distance "10m to 30m" estimated by the depth distance estimation unit 13a, the illumination determination unit 14 determines the illumination range to be a range of φ3 degrees to φ4 degrees in the left-right direction and a range of θ3 degrees to θ4 degrees in the up-down direction (see Figure 10B. The illumination range in the left-right direction is omitted in Figure 10B). In this case, the illumination determination unit 14 calculates a first depth distance vertical angle based on a depth distance of "10 m" for the up-down direction of the illumination range, and calculates a second depth distance vertical angle based on a depth distance of "30 m" to determine the up-down direction of the illumination range.
[0096] The headlight control unit 15 causes the headlights 2 to emit light in the direction in which the driver is facing, to an illumination range determined by the illumination determination unit 14 based on the depth distance estimated by the depth distance estimation unit 13a taking into account the driver's orientation and driving-related information (here, vehicle information and map information). As a result, the headlight control unit 15 can control the headlights 2 so that light is irradiated onto the estimated viewed object estimated to be present at the estimated viewing position. The driver can view the estimated viewed object.
[0097] In the situation shown in Fig. 10A and Fig. 10B, the presumed visual object is presumed to be a pedestrian (see Fig. 9). That is, the headlight control unit 15 can irradiate light to a pedestrian A (indicated by W1 in Fig. 10A and Fig. 10B) who is presumed to be present in the direction in which the driver is facing, and who is the presumed visual object of the driver. The direction in which the driver faces now includes the sidewalk in front of the intersection and the road in the traveling direction. Therefore, the pedestrian who is the presumed visual object of the driver is presumed to be a pedestrian A crossing the sidewalk in front of the intersection or the crosswalk on the road in the traveling direction. For example, on the route of the vehicle 100, there may be a pedestrian B (indicated as W2 in FIG. 10A) on the sidewalk on the other side of the intersection. However, the pedestrian B is not in the direction the driver is facing. Therefore, the pedestrian B is not estimated as an estimated visual target of the driver. In other words, the light is not irradiated onto the pedestrian B. The headlight control unit 15 controls the headlights 2 so that light is irradiated onto an object estimated to be viewed by the driver, which is estimated to be located at a position (estimated viewing position) the estimated depth distance away in the direction in which the driver is facing. In addition, in Figures 10A and 10B, pedestrians A and B are also shown for ease of understanding, but pedestrians A and B are assumed to exist and may not actually exist.
[0098] FIG. 12A is a diagram for explaining another example of the depth distance estimated by the depth distance estimation unit 13a in the second embodiment. FIG. 12B is a diagram illustrating an example of a state in which, in embodiment 2, headlight control unit 15 causes headlight 2 to irradiate light to an illumination range determined by illumination determination unit 14 based on the depth distance estimated by depth distance estimation unit 13a as shown in FIG. 12A. FIG. 12A is a bird's-eye view of the road on which the vehicle 100 is traveling. Fig. 12B is a side view of the road on which the vehicle 100 is traveling. In Fig. 12B, the driver is indicated by "D" and the illumination range of the light from the headlights 2 is indicated by "LA". In Fig. 12A, the depth distance is the distance from the right light to the driver's estimated viewing position. In Fig. 12B, for convenience, the vehicle 100 is shown as seen from the left side relative to the traveling direction, but the illumination range shown in Fig. 12B is the illumination range by the right light. 12A and 12B, as in Fig. 10A and 10B, as an example, when the driver's face is facing "forward" in the up-down direction and "right" in the left-right direction, and the vehicle 100 is traveling at a speed of 30 km / h to turn right at the next intersection 15 m before the intersection, the depth distance estimation unit 13a estimates the depth distance using the depth distance estimation information, and the headlight control unit 15 causes the headlight 2 to irradiate light to the irradiation range determined by the irradiation determination unit 14. The depth distance estimation information is assumed to have the content as shown in Fig. 8. The driver's face direction is different between FIG. 10 and FIG.
[0099] In this case, the depth distance estimation unit 13a estimates the depth distance as "a range with a margin of 5 m including the sidewalk and the crosswalk at the intersection" based on the depth distance estimation information of the content shown in Fig. 8, assuming that the behavior of the driver determined from the direction information and the driving-related information (here, the vehicle information and the map information) correspond to No. 2 of the depth distance estimation information. As a result, the depth distance with a margin of 5 m including the sidewalk near the intersection and the crosswalk at the intersection in the direction in which the driver is facing is estimated (see Fig. 12B). Here, the depth distance estimation unit 13a estimates the depth distance to be, for example, "20m to 37m" based on the map information. Specifically, after calculating that the distance from the installation position of the headlight 2 to the front of the sidewalk is 25m and the distance from the installation position of the headlight 2 to the back of the sidewalk is 32m, a margin of 5m is added to each, and the range of the depth distance is set to be "25m-5m=20m" to "32m+5m=37m." Furthermore, for example, based on the depth distance "20 m to 37 m" estimated by the depth distance estimation unit 13a, the illumination determination unit 14 determines the illumination range to be a range of φ5 degrees to φ6 degrees in the left-right direction and a range of θ5 degrees to θ6 degrees in the up-down direction (see FIG. 12B. The left-right illumination range is omitted in FIG. 12B). In this case, the illumination determination unit 14 calculates the first depth distance vertical angle based on the depth distance of "20 m" for the up-down direction of the illumination range, and calculates the second depth distance vertical angle based on the depth distance of "37 m" to determine the up-down direction of the illumination range.
[0100] The headlight control unit 15 causes the headlights 2 to emit light in the direction in which the driver is facing, to an illumination range determined by the illumination determination unit 14 based on the depth distance estimated by the depth distance estimation unit 13 taking into account the driver's orientation and driving-related information (here, vehicle information and map information). In the situation shown in Figures 12A and 12B, the presumed visual object is presumed to be a pedestrian (see Figure 9), but now, as shown in Figures 12A and 12B, the direction in which the driver is facing is a direction including the road in the traveling direction of the vehicle 100 and the sidewalk on the other side of the intersection. In this case, the presumed visual object of the driver is presumed to be pedestrian B (indicated by W2 in Figures 12A and 12B) crossing the sidewalk on the other side of the intersection or the crosswalk on the road in the traveling direction. The headlight control unit 15 can cause light to be irradiated onto a pedestrian B who is an estimated visual target of the driver and is estimated to be present in the direction in which the driver is facing. Even if there is a pedestrian A (indicated as W1 in FIG. 12A) on the sidewalk just before an intersection on the route of the vehicle 100, the pedestrian A is not in the direction the driver is facing. Therefore, the pedestrian A is not estimated to be an estimated visual target of the driver. In other words, the light is not irradiated onto the pedestrian A.
[0101] In this way, the headlight control device 1a can appropriately control the lighting of the headlights 2 so that light is irradiated onto the object estimated to be viewed by the driver based on the depth distance estimated using orientation information, vehicle information, map information, and information for estimating depth distance.
[0102] In the headlight control device 1 according to the first embodiment, the depth distance estimation unit 13 estimates the depth distance from the direction information and the vehicle information by using the depth distance estimation information. The depth distance estimation unit 13 does not take the map information into consideration when estimating the depth distance. Therefore, for example, in the headlight control device 1 of embodiment 1, the depth distance estimation unit 13 estimates the depth distance using depth distance estimation information such as that shown in Figure 2. If the driver's face is facing "forward" in the up-down direction and "right" in the left-right direction, and the vehicle 100 is traveling at a speed of 30 km / h and intends to turn right at the next intersection 15 m before the intersection, the depth distance estimation unit 13 cannot estimate the depth distance unless the driver turns the steering wheel a certain amount (for example, more than 20 degrees) to make the right turn. In such a situation, the depth distance estimation unit 13 can estimate the depth distance to be, for example, "15 to 20 m" only after the driver turns the steering wheel to a certain extent in the traveling direction, here to the right (see No. 2 in FIG. 2). This is because it is difficult to estimate the traveling state of the vehicle 100 and the estimated visual object of the driver until the driver turns the steering wheel to a certain extent in the right direction.
[0103] In contrast, in the headlight control device 1a according to the second embodiment, the depth distance estimation information used by the depth distance estimation unit 13a to estimate the depth distance includes map information. Note that when generating the depth distance estimation information, the administrator or the like can estimate the estimated visually recognized object based on the route of the vehicle 100, for example, and set the depth distance. The depth distance estimation unit 13a estimates a depth distance using the direction information, the vehicle information, the map information, and the depth distance estimation information. As a result, in the above example, the depth distance estimation unit 13a can estimate the depth distance at a timing earlier than the driver turns the steering wheel to a certain extent to make a right turn. That is, the headlight control device 1a according to the second embodiment can perform lighting control of the headlights 2 according to the depth distance at an earlier timing than the headlight control device 1 according to the first embodiment. For example, the headlight control device 1a according to the second embodiment can switch, at an earlier timing than the headlight control device 1 according to the first embodiment, from lighting control of the headlights 2 using the depth distance as an initial value to lighting control of the headlights 2 according to the depth distance estimated by the depth distance estimation unit 13a, in other words, lighting control that irradiates light onto an estimated visual object estimated to be present at the estimated visual position of the driver.
[0104] The operation of the headlight control device 1a according to the second embodiment will be described. FIG. 13 is a flowchart for explaining the operation of the headlight control device 1a according to the second embodiment. For example, when the headlights 2 are turned on, the headlight control device 1a determines to perform lighting control of the headlights 2 based on the driver's direction, and starts the operation shown in the flowchart of Fig. 13. The headlight control device 1a repeats the operation shown in the flowchart of Fig. 13 until, for example, the headlights 2 are turned off or the power of the vehicle 100 is turned off. For example, a control unit (not shown) of the headlight control device 1a acquires information indicating the state of the headlights 2 from a headlight switch mounted on the vehicle 100, and determines whether the headlights 2 are on or not. When the control unit determines that the headlights 2 are on, it determines to start control of the headlights 2 based on the driver's direction, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12a, the depth distance estimation unit 13a, the illumination determination unit 14, and the headlight control unit 15 to instruct them to start control of the headlights 2. In addition, when the control unit determines that the headlights 2 are off or that the vehicle 100 has been turned off, it determines to end the lighting control of the headlights 2 based on the driver's direction, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12a, the depth distance estimation unit 13a, the illumination determination unit 14, and the headlight control unit 15 instructing them to end the lighting control of the headlights 2.
[0105] Regarding the operation shown in the flowchart of FIG. 13, the processing contents of steps ST1-1, ST1-2, and ST3 to ST4 are respectively similar to the processing contents of steps ST1-1, ST1-2, and ST3 to ST4 of the operation of the headlight control device 1 shown in the flowchart of FIG. 5, which have already been explained in embodiment 1, and therefore duplicate explanations will be omitted.
[0106] The map information acquisition unit 122 acquires map information from the travel-related information acquisition device 4 (step ST1-3). The map information acquisition unit 122 outputs the acquired map information to the depth distance estimation unit 13a as driving-related information.
[0107] The depth distance estimation unit 13a estimates the depth distance using orientation information regarding the driver's orientation detected by the orientation detection unit 11 in step ST1-1, vehicle information acquired by the vehicle information acquisition unit 121 in step ST1-2, map information acquired by the map information acquisition unit 122 in step ST1-3, and information for depth distance estimation (step ST2a).
[0108] In step ST3, the illumination determination unit 14 determines the illumination range of the light from the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13 in step ST2a (step ST3).
[0109] In this way, the headlight control device 1a detects the driver's direction based on the in-vehicle captured image and acquires driving-related information (here, vehicle information and map information). The headlight control device 1a estimates the depth distance based on the detected direction information on the driver's direction and the acquired driving-related information, and determines the illumination range of the light by the headlight 2 based on the estimated depth distance. Then, the headlight control device 1a causes the headlight 2 to illuminate the determined illumination range. Therefore, the headlight control device 1a can appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like. By using map information to estimate the depth distance, the headlight control device 1a is able to estimate the depth distance even in situations where it is difficult to estimate the depth distance based on the driver's direction and vehicle information alone, and can provide driving assistance when the vehicle 100 is traveling at night, etc.
[0110] In the above-described second embodiment, for example, the depth distance estimation unit 13a may estimate the depth distance and also estimate the ideal width of the irradiation range. In this case, the depth distance estimation unit 13a outputs the depth distance information and the information on the ideal width of the irradiation range to the irradiation determination unit 14. The illumination determination unit 14 determines the illumination range based on the depth distance estimated by the depth distance estimation unit 13a and the ideal width of the illumination range. In detail, when the illumination range calculated based on the depth distance estimated by the depth distance estimation unit 13a exceeds the ideal width of the illumination range, the illumination determination unit 14 determines the range up to the ideal width of the illumination range as the illumination range. The depth distance estimation unit 13a estimates the ideal width of the illumination range, and the illumination determination unit 14 determines the illumination range with the ideal width of the illumination range as the upper limit, so that the headlight control device 1a can reduce the glare given to oncoming vehicles, etc.
[0111] In the above-described second embodiment, the depth distance estimation unit 13a may estimate the depth distance and also estimate the ideal light amount of the headlight 2. In this case, the depth distance estimation unit 13a outputs the depth distance information to the illumination determination unit 14 and also outputs information on the estimated ideal light amount to the headlight control unit 15. The headlight control unit 15 causes the headlights 2 to emit light in the illumination range determined by the illumination determination unit 14 with the ideal light amount estimated by the depth distance estimation unit 13a. The depth distance estimation unit 13a estimates the ideal light amount, and the headlight control unit 15 causes the headlight 2 to emit light at the ideal light amount, so that the headlight control device 1a can emit light in the direction the driver is facing, with the amount of light assumed to be necessary for the driver to see the estimated visual object, depending on the distance from the vehicle 100 to which the light is being emitted.
[0112] In the above-described second embodiment, the depth distance estimating unit 13a may estimate the depth distance as well as the ideal width and ideal light amount of the irradiation range.
[0113] In the above-described second embodiment, the headlight control device 1a is an in-vehicle device mounted on the vehicle 100, and the direction detection unit 11, the driving-related information acquisition unit 12a, the depth distance estimation unit 13a, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown) are provided in the in-vehicle device. However, some of the direction detection unit 11, the driving-related information acquisition unit 12a, the depth distance estimation unit 13a, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown) may be provided in the in-vehicle device of the vehicle 100, and the rest may be provided in a server connected to the in-vehicle device via a network. In addition, all of the direction detection unit 11, the driving-related information acquisition unit 12a, the depth distance estimation unit 13a, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown) may be provided in the server.
[0114] The hardware configuration of the headlight control device 1a according to the second embodiment is similar to the hardware configuration of the headlight control device 1 described in the first embodiment with reference to Figs. 6A and 6B, and therefore is not illustrated. In the second embodiment, the functions of the direction detection unit 11, the driving-related information acquisition unit 12a, the depth distance estimation unit 13a, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) are realized by a processing circuit 1001. That is, the headlight control device 1a includes the processing circuit 1001 for estimating a depth distance based on direction information relating to the direction of the driver detected based on an in-vehicle captured image acquired from the in-vehicle image capture device 3 and driving-related information, and for controlling the lighting of the headlights 2 based on the estimated depth distance. The processing circuit 1001 may be dedicated hardware as shown in FIG. 6A, or may be a processor 1004 executing a program stored in a memory 1005 as shown in FIG. 6B.
[0115] The processing circuit 1001 reads out and executes the programs stored in the memory 1005, thereby executing the functions of the direction detection unit 11, the driving-related information acquisition unit 12a, the depth distance estimation unit 13a, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown). That is, the headlight control device 1a includes a memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of steps ST1-1, ST1-2, and ST1-3 to ST4 in FIG. 13 described above. The program stored in the memory 1005 can also be said to cause a computer to execute the procedures or methods of the processing of the direction detection unit 11, the driving-related information acquisition unit 12a, the depth distance estimation unit 13a, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown). The storage unit 16 is configured with a memory 1005, for example. The headlight control device 1a includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with devices such as the headlight 2, the in-vehicle image capture device 3, or the driving-related information acquisition device 4.
[0116] As described above, the headlight control device 1a according to embodiment 2 is configured to include an orientation detection unit 11 that detects the direction of the driver based on an image (in-vehicle image) of the driver of the vehicle 100, a driving-related information acquisition unit 12a that acquires driving-related information related to the driving of the vehicle 100, a depth distance estimation unit 13a that estimates a depth distance based on the orientation information regarding the direction of the driver detected by the orientation detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12a, an illumination determination unit 14 that determines the illumination range of light by the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13a, and a headlight control unit 15 that causes the headlight 2 to illuminate the illumination range determined by the illumination determination unit 14. Therefore, the headlight control device 1a can control the lighting of the headlights 2 in the vehicle 100 based on the direction in which the driver is facing, taking into consideration how far ahead in the direction in which the driver is actually facing he or she is trying to see. The headlight control device 1a can appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0117] In detail, in the headlight control device 1a, the driving-related information acquisition unit 12a has a vehicle information acquisition unit 121 that acquires vehicle information regarding the vehicle 100 as the driving-related information, and a map information acquisition unit 122 that acquires map information as the driving-related information, and the depth distance estimation unit 13a estimates the depth distance based on the orientation information, the vehicle information, and the map information. Therefore, the headlight control device 1a can control the lighting of the headlights 2 in the vehicle 100 based on the direction in which the driver is facing, taking into consideration how far ahead in the direction in which the driver is actually facing he or she is trying to see. The headlight control device 1a can appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0118] Embodiment 3 In the first embodiment, the headlight control device estimates the depth distance based on the direction information and the vehicle information. In the third embodiment, an embodiment in which the depth distance is estimated based on the direction information and the information on the periphery of the vehicle will be described.
[0119] FIG. 14 is a diagram showing an example of the configuration of a headlight control device 1b according to the third embodiment. In the third embodiment, it is assumed that the headlight control device 1b is mounted on a vehicle 100. The headlight control device 1b controls the lighting of the headlights 2 provided on the vehicle 100 based on the direction of the driver of the vehicle 100. In the third embodiment, the "direction of the driver" is represented by the direction of the driver's face or the direction of the driver's line of sight. In the third embodiment, the "direction of the driver" may include the direction of the driver's body, in other words, the driver's posture, in addition to the direction of the driver's face or the direction of the driver's line of sight. In the third embodiment, the headlight control device 1b performs the light control of the headlights 2 based on the driver's direction, and it is assumed that the light control is performed when the headlights 2 are turned on in a dark place around the vehicle 100, such as a parking lot at night or an urban area at night. In the following third embodiment as well, when simply referring to "the driver's facial direction", the "driver's facial direction" refers to "the driver's facial direction or line of sight", which also includes the driver's line of sight.
[0120] In FIG. 14, the same components as those in the headlight control device 1 described in the first embodiment with reference to FIG. 1 are denoted by the same reference numerals, and duplicated description will be omitted. The headlight control device 1b according to the third embodiment is different from the headlight control device 1 according to the first embodiment in that the driving-related information acquisition unit 12b includes an outside-vehicle information acquisition unit 123 instead of the vehicle information acquisition unit 121. Furthermore, the specific operation of the depth distance estimation unit 13b in the headlight control device 1b according to the third embodiment is different from the specific operation of the depth distance estimation unit 13 in the headlight control device 1 according to the first embodiment.
[0121] In the third embodiment, the driving-related information acquisition device 4 is assumed to be a device such as an outside-vehicle image capture device (not shown) or a radar (not shown). The driving-related information acquisition device 4 such as an outside-vehicle image capture device or a radar acquires information on objects around the vehicle 100 (hereinafter referred to as "outside-vehicle information") as driving-related information. The outside-vehicle information includes, for example, a captured image of the periphery of the vehicle 100 (hereinafter referred to as "outside-vehicle captured image") and information on the distance to objects existing around the vehicle 100 (hereinafter referred to as "distance information").
[0122] The exterior image capturing device captures at least an image in front of the vehicle 100. The exterior image capturing device may capture an image of the side or rear of the vehicle 100, in addition to the image in front of the vehicle 100. The outside-of-vehicle image capturing device outputs the captured outside-of-vehicle image to the headlight control device 1b as driving-related information. In this example, it is assumed that one outside-vehicle image capturing device is connected to the headlight control device 1b, but this is merely an example. For example, a plurality of outside-vehicle image capturing devices may be mounted on the vehicle 100, and the plurality of outside-vehicle image capturing devices may be connected to the headlight control device 1b.
[0123] The radar acquires the distance to an object present at least in front of the vehicle 100. The radar may acquire the distance to an object present not only in front of the vehicle 100 but also to the side or rear of the vehicle 100. The radar outputs the obtained distance information on the distance to the object to the headlight control device 1b as driving-related information. The distance information includes, for example, information indicating the presence of the object, the position of the object, the distance to the object, etc. It is assumed here that one radar is connected to the headlight control device 1b, but this is merely an example. For example, a plurality of radars may be mounted on the vehicle 100 and connected to the headlight control device 1b. For example, a plurality of radars of different types, such as a radar that acquires the distance to a nearby object and a radar that acquires the distance to a distant object, may be connected to the headlight control device 1b.
[0124] The outside-vehicle information acquisition unit 123 acquires outside-vehicle information from the driving-related information acquisition device 4. In detail, the vehicle outside information acquisition unit 123 acquires a vehicle outside captured image from an outside vehicle imaging device, and acquires distance information from a radar. The vehicle outside information acquisition unit 123 outputs the acquired vehicle outside information to the depth distance estimation unit 13b as driving-related information.
[0125] The depth distance estimation unit 13b estimates a depth distance based on the direction information regarding the direction of the driver detected by the direction detection unit 11 and the vehicle outside information acquired by the vehicle outside information acquisition unit 123. In detail, the depth distance estimation unit 13b estimates the depth distance by comparing the direction information, the driving-related information (here, the vehicle exterior information), and the depth distance estimation information.
[0126] FIG. 15 is a diagram showing an example of the contents of depth distance estimation information used by depth distance estimation unit 13b to estimate the depth distance in the third embodiment. As shown in FIG. 15, in the third embodiment, the depth distance estimation information is, for example, a table in which the driver's behavior, the vehicle exterior information, and the depth distance are associated with each other. In the depth distance estimation information, the driver's behavior includes, for example, the up-down direction of the driver's face and the left-right direction of the driver's face. The up-down direction of the driver's face is expressed as "front," "upward," or "downward." The left-right direction of the driver's face is expressed as "front," "right," or "left." In the depth distance estimation information, the outside-of-vehicle information includes, for example, information about an object present in front of the vehicle 100.
[0127] In the third embodiment, the depth distance estimation unit 13b estimates the depth distance using the depth distance estimation information, and then adjusts the estimated depth distance based on the vehicle exterior information and with reference to a depth distance adjustment condition (described in detail later). The depth distance estimation unit 13b confirms the adjusted depth distance as the estimated depth distance. Hereinafter, a detailed description will be given of a flow in which the depth distance estimation unit 13b estimates the depth distance, adjusts the estimated depth distance, and confirms the estimated depth distance.
[0128] Depth distance estimation First, the depth distance estimation unit 13b judges the behavior of the driver based on the orientation information. For example, the depth distance estimation unit 13b judges whether the up-down direction of the driver's face is "front", "up", or "down" from the information indicating the driver's vertical face direction included in the orientation information. Also, for example, the depth distance estimation unit 13b judges whether the left-right direction of the driver's face direction is "front", "right", or "left" from the information indicating the driver's horizontal face direction included in the orientation information. The method by which depth distance estimation unit 13b determines whether the up-down and left-right directions of the driver's face are "forward", "up", "down", "right" or "left" is similar to the method by depth distance estimation unit 13 for determining whether the up-down and left-right directions of the driver's face are "forward", "up", "down", "right" or "left" already described in embodiment 1, so duplicated explanations will be omitted.
[0129] Further, the depth distance estimation unit 13b determines objects (e.g., signs, pedestrians, white lines, vehicles, etc.) present around the vehicle 100 based on the vehicle exterior information acquired by the vehicle exterior information acquisition unit 123. For example, the depth distance estimation unit 13b can determine objects present around the vehicle 100 by performing image recognition processing using a known image recognition technology on the vehicle exterior captured image. Furthermore, since the installation position and angle of view of the vehicle exterior image capture device and the installation position and detection range of the radar are known in advance, the depth distance estimation unit 13b can associate the object on the vehicle exterior captured image with the object indicated by the distance information. That is, based on the vehicle exterior captured image and the distance information, the depth distance estimation unit 13b can associate the object captured in the vehicle exterior captured image with the distance position from the vehicle 100. The depth distance estimation unit 13b may associate the object in the outside-of-vehicle captured image with the object indicated by the distance information using various known methods, such as a method of regarding objects located close to each other as the same object based on the coordinates indicating the position of the object in the outside-of-vehicle captured image and the coordinates indicating the position of the object in the distance information. Since the relationship between the installation position of the radar and the position of the vehicle 100 is known in advance, the depth distance estimation unit 13b can determine, based on the distance information, how far the object detected by the radar is from the vehicle 100.
[0130] The depth distance estimation unit 13b may store the outside-vehicle information output from the outside-vehicle information acquisition unit 123 in the storage unit 16 with the acquisition date and time, calculate the acceleration of the detected object from the past outside-vehicle information, and determine that the object is an erroneously detected object if it is determined that the calculated acceleration has changed significantly, in other words, that the object has moved suddenly. The depth distance estimation unit 13b does not use the outside-vehicle information related to the object determined to be an erroneously detected object in estimating the depth distance.
[0131] Furthermore, the association between the object on the vehicle outside captured image and the object indicated by the distance information may be performed by the vehicle outside information acquisition unit 123. In this case, for example, the vehicle outside information acquisition unit 123 outputs the vehicle outside information to the depth distance estimation unit 13b in a form in which the corresponding object can be identified. Furthermore, the vehicle outside information acquisition unit 123 may determine whether or not an object has been erroneously detected based on past vehicle outside information. The vehicle outside information acquisition unit 123 is configured not to output vehicle outside information relating to an object that has been determined to be an erroneously detected object to the depth distance estimation unit 13b.
[0132] Then, the depth distance estimation unit 13b estimates the depth distance by comparing the determined behavior and information indicating objects present around the vehicle 100 with the driver's behavior and outside vehicle information set in the depth distance estimation information as shown in Figure 15 to obtain depth distance information.
[0133] For example, assume that the driver's face is facing "forward," that there are multiple "sideways stopped vehicles" in front of the vehicle 100, and that there is a "pedestrian." It is assumed that the depth distance estimation information has contents as shown in FIG. In this case, the depth distance estimation unit 13b estimates the depth distance to be "5 to 15 m" using orientation information regarding the driver's orientation, driving-related information (here, information outside the vehicle), and information for depth distance estimation (see No. 1 of information for depth distance estimation in Figure 15).
[0134] For example, if the driver's face is facing "front to upward" in the vertical direction, there are multiple "sideways stopped vehicles" in front of the vehicle 100, and there is a "pedestrian," the vehicle 100 is about to park and the driver's presumed visual object is presumed to be a pedestrian (or a place where a pedestrian is likely to be). Therefore, in the depth distance estimation information, the depth distance is set to "5 to 15 m," which is assumed to be the depth distance at which the driver is likely to be when the vehicle 100 is about to park and stop and tries to check for a pedestrian (or a place where a pedestrian is likely to be) (No. 1 in the depth distance estimation information in FIG. 15). Similarly, for conditions No. 2 to No. 8 of the depth distance estimation information in Figure 15, the depth distance is set based on the driver's behavior and the driving state of the vehicle 100 estimated from outside the vehicle information, and the estimated object viewed by the driver. Figure 16 is a diagram showing the depth distances corresponding to the input information under conditions No. 1 to No. 8 set in the depth distance estimation information shown in Figure 15, in correspondence with examples of the driving state of the vehicle 100 estimated from the driver's behavior and outside vehicle information, which are the basis for deriving the depth distances, and examples of objects visible to the driver.
[0135] In addition, in the depth distance estimation information shown in Fig. 15, eight patterns of conditions No. 1 to No. 8 are set, but this is only an example. Also, the contents of the depth distance estimation information as shown in Fig. 15 are only an example. For example, in the depth distance estimation information, information indicating an object present behind the vehicle and information indicating the type of adjacent lane (overtaking lane or oncoming lane) may be set as the outside vehicle information. For example, when the object present behind the vehicle is a vehicle and the type of adjacent lane is an overtaking lane, the depth distance is set to a value assuming that the vehicle 100 is traveling on a highway and the estimated visual object of the driver is a sign. For example, in the depth distance estimation information, information indicating an object present on the side of the vehicle and information indicating the height of the object may be set as the outside-vehicle information. For example, when the object present on the side of the vehicle is a stationary object such as a building wall, and the height of the stationary object is equal to or greater than a predetermined threshold, the depth distance is set assuming that the vehicle 100 is traveling through an intersection with poor visibility and that the estimated visual object of the driver is a pedestrian. The depth distance estimation information may be information that allows depth distance information to be obtained from orientation information and driving-related information (here, vehicle exterior information).
[0136] In addition, when the orientation information regarding the driver's orientation detected by the orientation detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12b (here, the outside-vehicle information acquired by the outside-vehicle information acquisition unit 123) do not correspond to the input information set in the depth distance estimation information, the depth distance estimation unit 13b determines that the depth distance cannot be estimated from the depth distance estimation information, and sets the depth distance to an initial value of the depth distance.
[0137] Adjusting the estimated depth distance When the depth distance is estimated, the depth distance estimation unit 13b adjusts the estimated depth distance based on the estimated depth distance and the vehicle exterior information, and finalizes the estimated depth distance. Note that the depth distance estimation unit 13b does not perform this adjustment when the depth distance estimated based on the depth distance estimation information does not have a range. In detail, the depth distance estimation unit 13b adjusts the depth distance based on the estimated depth distance and the vehicle exterior information, with reference to a depth distance adjustment condition for adjusting the depth distance. The depth distance adjustment conditions are generated in advance by an administrator or the like, and are stored in a location that can be referenced by the depth distance estimation unit 13b.
[0138] As the depth distance adjustment conditions, for example, the following conditions (Condition 1) to (Condition 4) are set.
[0139] (Condition 1) When a moving object is present in front of the vehicle in the direction in which the driver is facing, and the distance from the headlight to the moving object is within the range of the depth distance, the estimated depth distance is regarded as the distance from the headlight to the moving object.
[0140] (Condition 2) When a moving object is present in front of the vehicle in the direction the driver is facing and the distance from the headlights to the moving object is outside the range of the depth distance, the depth distance based on the depth distance estimation information is used as the depth distance as is.
[0141] (Condition 3) When there is no moving object in the direction the driver is facing ahead of the vehicle, but there is an object other than a moving object, in other words a stationary object, around the vehicle, and the distance from the headlight to the stationary object is shorter than the depth distance estimated based on the depth distance estimation information, the estimated depth distance is set to (the distance from the headlight to the stationary object + a predetermined additional distance).
[0142] (Condition 4) When there is no moving object in front of the vehicle in the direction the driver is facing and there is no stationary object around the vehicle, the depth distance estimated based on the depth distance estimation information is used as the depth distance as is. In addition, when there is no moving object in front of the vehicle in the direction the driver is facing and there is a stationary object around the vehicle but the distance from the headlights to the stationary object is outside the range of the depth distance estimated based on the information for depth distance estimation, the depth distance estimated based on the information for depth distance estimation is used as the depth distance as is.
[0143] In the depth distance adjustment conditions, the moving object includes a person. In the depth distance adjustment conditions, the distance to be added is set in advance by an administrator or the like and stored in a location that can be referenced by the depth distance estimation unit 13b. For example, a distance between 2 and 5 m is set as the distance to be added. Here, as an example, it is assumed that "3 m" is set as the distance to be added. A value with a certain range may be set as the distance to be added.
[0144] Based on the outside-vehicle information acquired by the outside-vehicle information acquisition unit 123, the depth distance estimation unit 13b can determine whether or not there is an object in front of the vehicle 100 in the direction in which the driver is facing, and if there is an object, the type of object, in this case, whether it is a moving object or a stationary object. Since the installation position and detection range of the radar are known in advance, the depth distance estimation unit 13b can determine whether or not there is an object in the direction in which the driver is facing. The depth distance estimation unit 13b can determine the direction in which the driver is facing from the direction information. As described above, the depth distance estimation unit 13b can associate an object on the outside-of-vehicle captured image with an object indicated by the distance information. Therefore, when the depth distance estimation unit 13b determines that there is an object in the direction in which the driver is facing, it can perform, for example, image recognition processing using a known image recognition technique on the outside-of-vehicle captured image to determine the type of the object, in other words, whether the object is a moving object or a stationary object. The depth distance estimation unit 13b may determine the type of object by using, for example, distance information. The distance information includes, for example, information regarding the speed of the object. In addition, since the relationship between the installation position of the radar, the position of the vehicle 100, and the installation position of the headlight 2 is known in advance, the depth distance estimation unit 13b can determine, based on the positional relationship and distance information, how far an object detected by the radar is from the headlight 2. Note that the depth distance estimation unit 13b may determine, for example, a range expanded vertically and horizontally by a preset angle centered on the direction of the driver's face as the "direction in which the driver is facing" for determining whether or not an object is present.
[0145] It should be noted that the above-described depth distance adjustment conditions are merely examples, and the depth distance adjustment conditions can be set as appropriate. In addition, the conditions for adjusting the depth distance may be information in a table format in which, for example, the type of detected object, information indicating the difference between the distance from the headlight 2 to the object and the depth distance estimated based on the depth distance estimation information, and information indicating the adjusted depth distance are associated with each other.
[0146] After adjusting the depth distance, the depth distance estimation unit 13b sets the adjusted depth distance as the estimated depth distance, and outputs the depth distance information to the irradiation determination unit .
[0147] In addition, when the driver's behavior and vehicle exterior information determined based on the orientation information regarding the driver's orientation detected by the orientation detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12b (here, the vehicle exterior information acquired by the vehicle exterior information acquisition unit 123) do not correspond to the driver's behavior and vehicle exterior information as input information set in the depth distance estimation information, the depth distance estimation unit 13b determines that the depth distance cannot be estimated from the depth distance estimation information, and sets the depth distance to an initial value of the depth distance. The depth distance estimation unit 13b outputs to the irradiation determination unit 14 depth distance information regarding the depth distance for which the initial value has been set.
[0148] The illumination determination unit 14 determines the illumination range of the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13b, and outputs illumination information to the headlight control unit 15. The headlight control unit 15 causes the headlight 2 to illuminate the illumination range determined by the illumination determination unit 14.
[0149] 17, 18, and 19 are diagrams for explaining an example of a state in which the illumination determination unit 14 determines an illumination range based on the depth distance estimated by the depth distance estimation unit 13b, and the headlight control unit 15 causes the headlight 2 to illuminate the illumination range determined by the illumination determination unit 14 in the third embodiment. It is assumed that the depth distance estimation information used by the depth distance estimation unit 13b to estimate the depth distance has contents as shown in FIG. 15. It is assumed that the depth distance estimation unit 13b adjusts the depth distance according to the depth distance adjustment conditions of the above-mentioned (Condition 1) to (Condition 4). 17, 18, and 19 are each views of a road viewed from the side on which the vehicle 100 is traveling. In Fig. 17, 18, and 19, the driver is indicated by "D" and the illumination range of the light from the headlights 2 is indicated by "LA."
[0150] In the example shown in Fig. 17, the driver's face is facing within the range of "forward" in the vertical direction, there are multiple stopped vehicles (indicated by "C" in Fig. 17; for simplicity of explanation, only one stopped vehicle is shown in Fig. 17) ahead of the vehicle 100, and the vehicle 100 is traveling in a situation where there is a pedestrian (indicated by "W" in Fig. 17). The pedestrian is located 12 m away from the headlight 2 in the direction the driver is facing. In this case, the depth distance estimation unit 13b estimates the depth distance to be "5 to 15 m" based on the depth distance estimation information, assuming that the driver's face direction and the driving-related information (here, vehicle exterior information) correspond to No. 1 of the depth distance estimation information. Thereafter, the depth distance estimation unit 13b adjusts the depth distance estimated to be "5 to 15". In the example shown in FIG. 17, since a pedestrian is present within a range of "5 to 15 m" in the direction in which the driver is facing, the depth distance estimation unit 13b adjusts the depth distance to set the estimated depth distance to "12 m". The illumination determination unit 14 determines the illumination range based on the depth distance "12 m" estimated by the depth distance estimation unit 13b. Here, the illumination determination unit 14 determines the illumination range to be a range of φ7 degrees to φ8 degrees in the left-right direction and a range of θ7 degrees to θ7 degrees in the up-down direction (illustration of the illumination range in the left-right direction is omitted in FIG. 17). In this case, the illumination determination unit 14 calculates the depth distance vertical angle for the up and down directions of the illumination range based on the depth distance of "12 m", and determines the angle range for the up and down directions of the illumination range to be the angle range expanded vertically from the depth distance vertical angle by a preset angle.
[0151] The headlight control unit 15 causes the headlights 2 to emit light in the direction in which the driver is facing, to an illumination range determined by the illumination determination unit 14 based on the depth distance estimated by the depth distance estimation unit 13b taking into account the driver's orientation and driving-related information (here, information outside the vehicle). As a result, the headlight control unit 15 can control the headlights 2 so that light is irradiated onto a pedestrian who is in the direction in which the driver is facing. The driver can see the pedestrian. The depth distance estimated using the depth distance estimation information is not estimated taking into consideration an object that actually exists in the direction in which the driver is facing. On the other hand, if a moving object actually exists within the range of the depth distance estimated using the depth distance estimation information in the direction in which the driver is facing, it can be said that there is a high probability that the driver is trying to visually recognize the moving object. By adjusting the depth distance based on a moving object that actually exists in the direction in which the driver is facing, the depth distance estimation unit 13b illuminates light onto a moving object (here, a pedestrian) that actually exists and has a high probability of being an estimated visually recognized object.
[0152] In the example shown in Fig. 18, as in the example shown in Fig. 17, the driver's face is facing within the range of "forward" in the vertical direction, there are multiple stopped vehicles (indicated by "C" in Fig. 18; for simplicity of explanation, only one stopped vehicle is shown in Fig. 18) ahead of the vehicle 100, and there is a pedestrian (indicated by "W" in Fig. 18) while the vehicle 100 is traveling. However, the pedestrian is assumed to be present at a distance of 20 m from the headlight 2 in the direction the driver is facing. In this case, since there are no pedestrians within the range of "5 to 15 m" in the direction in which the driver is facing, the depth distance estimation unit 13b uses the depth distance estimated as "5 to 15 m" based on the depth distance estimation information as the estimated depth distance. The illumination determination unit 14 determines the illumination range based on the depth distance "5 to 15 m" estimated by the depth distance estimation unit 13b. Here, the illumination determination unit 14 determines the illumination range based on the depth distance "5 to 15 m" estimated by the depth distance estimation unit 13b. 10 degrees, and in the vertical direction, θ9 degrees to θ 10 The range of illumination is determined to be within a range of 100 degrees (illumination range in the left and right directions is omitted in FIG. 18). In this case, the illumination determination unit 14 calculates a first depth distance vertical angle based on a depth distance of "5 m" for the up-down direction of the illumination range, and calculates a second depth distance vertical angle based on a depth distance of "15 m" to determine the up-down direction of the illumination range.
[0153] The headlight control unit 15 causes the headlights 2 to emit light in the direction in which the driver is facing, to an illumination range determined by the illumination determination unit 14 based on the depth distance estimated by the depth distance estimation unit 13b taking into account the driver's orientation and driving-related information (here, information outside the vehicle). As a result, the headlight control unit 15 controls the headlights 2 so that light is irradiated onto the estimated visual object of the driver. Here, the position where the pedestrian actually exists is not included in the irradiation range of the light of the headlights 2. In other words, the light of the headlights 2 is not irradiated onto the pedestrian. A pedestrian who is located farther away from the headlights 2 than the depth distance estimated using the depth distance estimation information is not an estimated visual object, and it is estimated that an estimated visual object exists at a closer distance than the pedestrian. When the depth distance estimation unit 13b adjusts the depth distance, even if a pedestrian actually exists in the direction in which the driver is facing, if the pedestrian is located farther away than the depth distance estimated using the depth distance estimation information, the depth distance is not increased, and the depth distance estimated using the depth distance estimation information is left as it is. As a result, the headlight control device 1b can control the headlights 2 so that light is not emitted to pedestrians who are unlikely to be the presumed visual object even if they are actually present, and light is emitted to an area where it is estimated that the presumed visual object is more likely to exist.
[0154] In the example shown in FIG. 19, the driver's face is facing within the range of "forward" in the vertical direction, and vehicle 100 is traveling in a situation where there are multiple stopped vehicles (indicated by "C" in FIG. 19; for simplicity of explanation, only one stopped vehicle is shown in FIG. 19) ahead of vehicle 100. There are no moving objects such as pedestrians around vehicle 100. The distance to the stopped vehicles is assumed to be "4 m." In this case, there is no moving object in the direction the driver is facing, but there is a stopped vehicle, and the distance from the headlight 2 to the stopped vehicle is within the range of "5 to 15 m" estimated based on the depth distance estimation information, so the depth distance estimation unit 13b adjusts the depth distance and sets "7 m" as the estimated depth distance. The illumination determination unit 14 determines the illumination range based on the depth distance "7 m" estimated by the depth distance estimation unit 13b. Here, the illumination determination unit 14 determines the illumination range based on the depth distance "7 m" estimated by the depth distance estimation unit 13b. 11 degree~φ 12 degree range and θ in the vertical direction 11 degree~θ 12 The range of illumination is determined to be within a range of 100 degrees (illumination range in the left and right directions is omitted in FIG. 19). In this case, the irradiation determination unit 14 calculates the depth distance vertical angle for the up and down directions of the irradiation range based on the depth distance of "7 m", and determines the angle range for the up and down directions of the irradiation range to be the angle range expanded vertically from the depth distance vertical angle by a preset angle.
[0155] The headlight control unit 15 causes the headlights 2 to emit light in the direction in which the driver is facing, to an illumination range determined by the illumination determination unit 14 based on the depth distance estimated by the depth distance estimation unit 13b taking into account the driver's orientation and driving-related information (here, information outside the vehicle). As a result, the headlight control unit 15 controls the headlights 2 so that light is irradiated onto the object estimated to be viewed by the driver. Here, the light of the headlights 2 is irradiated onto a range behind the stopped vehicle as seen from the vehicle 100. For example, if there is a stationary object in the direction in which the driver is facing, there is a possibility that a moving object such as a pedestrian may jump out from behind the stationary object, and it is estimated that the driver is trying to visually check whether or not such a pedestrian is jumping out. By adjusting the depth distance by the depth distance estimation unit 13b, if the direction in which the driver is facing is a situation in which a pedestrian is likely to jump out, the depth distance is adjusted to a depth distance in which the place where the pedestrian is likely to jump out is set as the estimated viewing position. This allows the headlight control device 1b to control the headlights 2 so that light is irradiated onto a range where the presumed visually recognized object is more likely to exist.
[0156] For example, the headlight control device 1 according to the first embodiment does not estimate the depth distance taking into consideration objects that actually exist around the vehicle 100. In contrast, as described above, the headlight control device 1b according to the third embodiment estimates the depth distance based on the vehicle exterior information, more specifically, estimates the depth distance by adjusting the depth distance estimated based on the depth distance estimation information based on the vehicle exterior information, and thereby estimates the depth distance to confirm the depth distance, thereby estimating the depth distance taking into consideration objects that actually exist around the vehicle 100. The headlight control device 1b estimates the depth distance that is more suited to the actual situation, based on whether or not there is an object that actually exists in the direction in which the driver is facing. This allows the headlight control device 1b to more appropriately illuminate the estimated viewing position of the driver, and to provide driving assistance when the vehicle 100 is traveling at night or the like.
[0157] The operation of the headlight control device 1b according to the third embodiment will be described. FIG. 20 is a flowchart for explaining the operation of the headlight control device 1b according to the third embodiment. For example, when the headlight 2 is turned on, the headlight control device 1b determines to perform lighting control of the headlight 2 based on the driver's direction, and starts the operation shown in the flowchart of Fig. 20. The headlight control device 1b repeats the operation shown in the flowchart of Fig. 20 until, for example, the headlight 2 is turned off or the power of the vehicle 100 is turned off. For example, a control unit (not shown) of the headlight control device 1b acquires information indicating the state of the headlights 2 from a headlight switch mounted on the vehicle 100, and determines whether the headlights 2 are on or not. When the control unit determines that the headlights 2 are on, it determines to start control of the lighting of the headlights 2 based on the direction of the driver, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12b, the depth distance estimation unit 13b, the illumination determination unit 14, and the headlight control unit 15 to instruct them to start control of the lighting of the headlights 2. In addition, when the control unit determines that the headlights 2 are off or that the vehicle 100 has been turned off, it determines to end the lighting control of the headlights 2 based on the driver's direction, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12b, the depth distance estimation unit 13b, the illumination determination unit 14, and the headlight control unit 15 instructing them to end the lighting control of the headlights 2.
[0158] Regarding the operation shown in the flowchart of FIG. 20, the processing contents of step ST1-1 and step ST3 to step ST4 are respectively similar to the processing contents of step ST1-1 and step ST3 to step ST4 of the operation of the headlight control device 1 shown in the flowchart of FIG. 5, which have already been explained in embodiment 1, and therefore duplicate explanations will be omitted.
[0159] The outside-vehicle information acquisition unit 123 acquires outside-vehicle information from the driving-related information acquisition device 4 (step ST1-4). In detail, the vehicle outside information acquisition unit 123 acquires a vehicle outside captured image from an outside vehicle imaging device, and acquires distance information from a radar. The vehicle outside information acquisition unit 123 outputs the acquired vehicle outside information to the depth distance estimation unit 13b as driving-related information.
[0160] The depth distance estimation unit 13b estimates the depth distance using orientation information regarding the driver's orientation detected by the orientation detection unit 11 in step ST1-1, the outside vehicle information acquired by the outside vehicle information acquisition unit 123 in step ST1-4, and information for depth distance estimation (step ST2b). In detail, when the depth distance estimation unit 13b estimates the depth distance using the depth distance estimation information, the depth distance estimation unit 13b adjusts the estimated depth distance based on the outside vehicle information and by referring to the depth distance adjustment conditions, and confirms the estimated depth distance. The depth distance estimation unit 13b outputs the depth distance information to the irradiation determination unit .
[0161] In step ST3, the illumination determination unit 14 determines the illumination range of the light from the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13b in step ST2b (step ST3).
[0162] In this way, the headlight control device 1b detects the driver's direction based on the in-vehicle captured image and acquires driving-related information (here, vehicle exterior information). The headlight control device 1b estimates the depth distance based on the detected direction information on the driver's direction and the acquired driving-related information. At that time, the headlight control device 1b adjusts the depth distance estimated using the depth distance estimation information based on the vehicle exterior information and the depth distance adjustment condition, and sets the adjusted depth distance information as the estimated depth information. Then, the headlight control device 1b determines the irradiation range of the light by the headlight 2 based on the estimated depth distance, and causes the headlight 2 to irradiate the light to the determined irradiation range. Therefore, the headlight control device 1b can more appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0163] In the above-described third embodiment, for example, the depth distance estimation unit 13b may estimate the depth distance and also estimate the ideal width of the irradiation range. In this case, the depth distance estimation unit 13b outputs the depth distance information and the information on the ideal width of the irradiation range to the irradiation determination unit 14. The illumination determination unit 14 determines the illumination range based on the depth distance estimated by the depth distance estimation unit 13b and the ideal width of the illumination range. In detail, when the illumination range calculated based on the depth distance estimated by the depth distance estimation unit 13b exceeds the ideal width of the illumination range, the illumination determination unit 14 determines the range up to the ideal width of the illumination range as the illumination range. The depth distance estimation unit 13b estimates the ideal width of the illumination range, and the illumination determination unit 14 determines the illumination range with the ideal width of the illumination range as the upper limit, so that the headlight control device 1b can reduce the glare given to oncoming vehicles and the like.
[0164] In the above-described third embodiment, the depth distance estimation unit 13b may estimate the depth distance and also estimate the ideal light amount of the headlight 2. In this case, the depth distance estimation unit 13b outputs the depth distance information to the illumination determination unit 14 and also outputs information on the estimated ideal light amount to the headlight control unit 15. The headlight control unit 15 causes the headlights 2 to emit light in the illumination range determined by the illumination determination unit 14 with the ideal light amount estimated by the depth distance estimation unit 13b. The depth distance estimation unit 13b estimates the ideal light amount, and the headlight control unit 15 causes the headlight 2 to emit light at the ideal light amount, so that the headlight control device 1b can emit light in the amount of light assumed to be necessary for the driver to see the estimated visual object, in the direction the driver is facing, depending on the distance from the vehicle 100 to which the light is being emitted.
[0165] In the above third embodiment, the depth distance estimating unit 13b may estimate the depth distance as well as the ideal width and ideal light amount of the irradiation range.
[0166] In the above-described third embodiment, the headlight control device 1b is an in-vehicle device mounted on the vehicle 100, and the direction detection unit 11, the driving-related information acquisition unit 12b, the depth distance estimation unit 13b, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) are provided in the in-vehicle device. However, some of the direction detection unit 11, the driving-related information acquisition unit 12b, the depth distance estimation unit 13b, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) may be provided in the in-vehicle device of the vehicle 100, and the rest may be provided in a server connected to the in-vehicle device via a network. In addition, all of the direction detection unit 11, the driving-related information acquisition unit 12b, the depth distance estimation unit 13b, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) may be provided in the server.
[0167] The hardware configuration of the headlight control device 1b according to the third embodiment is similar to the hardware configuration of the headlight control device 1 described in the first embodiment with reference to Figs. 6A and 6B, and therefore is not illustrated. In the third embodiment, the functions of the direction detection unit 11, the driving-related information acquisition unit 12b, the depth distance estimation unit 13b, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) are realized by a processing circuit 1001. That is, the headlight control device 1b includes the processing circuit 1001 for estimating a depth distance based on direction information regarding the driver's direction detected based on an in-vehicle captured image acquired from the in-vehicle image capture device 3 and driving-related information, and for controlling the lighting of the headlights 2 based on the estimated depth distance. The processing circuit 1001 may be dedicated hardware as shown in FIG. 6A, or may be a processor 1004 executing a program stored in a memory 1005 as shown in FIG. 6B.
[0168] The processing circuit 1001 reads out and executes the programs stored in the memory 1005, thereby executing the functions of the direction detection unit 11, the driving-related information acquisition unit 12b, the depth distance estimation unit 13b, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown). That is, the headlight control device 1b includes a memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of steps ST1-1 and ST1-4 to ST4 in FIG. 20 described above. The program stored in the memory 1005 can also be said to cause a computer to execute the procedures or methods of the processing of the direction detection unit 11, the driving-related information acquisition unit 12b, the depth distance estimation unit 13b, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown). The storage unit 16 is configured with a memory 1005, for example. The headlight control device 1b includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with devices such as the headlight 2, the in-vehicle image capture device 3, or the driving-related information acquisition device 4.
[0169] As described above, the headlight control device 1b according to embodiment 3 is configured to include an orientation detection unit 11 that detects the direction of the driver based on an image (in-vehicle image) of the driver of the vehicle 100, a driving-related information acquisition unit 12b that acquires driving-related information related to the driving of the vehicle 100, a depth distance estimation unit 13b that estimates a depth distance based on the orientation information regarding the direction of the driver detected by the orientation detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12b, an illumination determination unit 14 that determines the illumination range of light by the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13b, and a headlight control unit 15 that causes the headlight 2 to illuminate the illumination range determined by the illumination determination unit 14. Therefore, the headlight control device 1b can control the lighting of the headlights 2 in the vehicle 100 based on the direction in which the driver is facing, taking into consideration how far ahead in the direction in which the driver is actually facing he or she is trying to see. The headlight control device 1b can more appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0170] In detail, in the headlight control device 1b, the driving-related information acquisition unit 12b has an outside information acquisition unit 123 that acquires outside information related to the front of the vehicle 100 as driving-related information, and the depth distance estimation unit 13b estimates the depth distance based on the orientation information and the outside information. Therefore, the headlight control device 1b can control the lighting of the headlights 2 in the vehicle 100 based on the direction in which the driver is facing, taking into consideration how far ahead in the direction in which the driver is actually facing he or she is trying to see. The headlight control device 1b can more appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0171] Embodiment 4 In the second embodiment, the headlight control device in the first embodiment acquires map information in addition to vehicle information, and estimates the depth distance based on the direction information, vehicle information, and map information. In the third embodiment, in the headlight control device in the first embodiment, vehicle exterior information is acquired instead of vehicle information, and the depth distance is estimated based on the direction information and the vehicle exterior information. In the fourth embodiment, an embodiment in which the second and third embodiments are combined will be described.
[0172] FIG. 21 is a diagram showing an example of the configuration of a headlight control device 1c according to the fourth embodiment. In the fourth embodiment, it is assumed that the headlight control device 1c is mounted on a vehicle 100. In Figure 21, configurations similar to those of the headlight control devices 1, 1a, and 1b described in embodiment 1, embodiment 2, and embodiment 3 using Figures 1, 7, and 14, respectively, are given the same symbols and duplicate explanations are omitted.
[0173] In the headlight control device 1c, the driving-related information acquisition unit 12c includes a vehicle information acquisition unit 121, a map information acquisition unit 122, and an outside-vehicle information acquisition unit 123.
[0174] The depth distance estimation unit 13c estimates the depth distance based on orientation information regarding the driver's orientation detected by the orientation detection unit 11, vehicle information acquired by the vehicle information acquisition unit 121, map information acquired by the map information acquisition unit 122, and outside vehicle information acquired by the outside vehicle information acquisition unit 123. In detail, the depth distance estimation unit 13b estimates the depth distance by comparing the direction information, the driving-related information (here, the vehicle information, the map information, and the vehicle exterior information), and the depth distance estimation information.
[0175] FIG. 22 is a diagram showing an example of the contents of depth distance estimation information used by the depth distance estimation unit 13c to estimate the depth distance in the fourth embodiment. As shown in FIG. 22, in the fourth embodiment, the depth distance estimation information is a table in which, for example, the driver's behavior, the vehicle information, the map information, the vehicle exterior information, and the depth distance are associated with each other. In the fourth embodiment, the depth distance estimation unit 13c estimates the depth distance using the depth distance estimation information, and adjusts the estimated depth distance by referring to the depth distance adjustment condition based on the vehicle exterior information. The depth distance estimation unit 13c determines the adjusted depth distance as the estimated depth distance. The depth distance estimation unit 13c outputs the depth distance information to the irradiation determination unit .
[0176] Figure 23 is a diagram showing the depth distances corresponding to the input information under conditions No. 1 to No. 7 set in the depth distance estimation information shown in Figure 22, in correspondence with examples of the driving state of the vehicle 100 and the object visible to the driver, which are estimated from the driver's behavior, vehicle information, map information, and outside vehicle information and are the basis for deriving the depth distance.
[0177] In addition, when the driver's behavior, vehicle information, map information, and outside vehicle information determined based on the orientation information regarding the driver's orientation detected by the orientation detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12c (here, the vehicle information acquired by the vehicle information acquisition unit 121, the map information acquired by the map information acquisition unit 122, and the outside vehicle information acquired by the outside vehicle information acquisition unit 123) do not correspond to the driver's behavior, vehicle information, map information, and outside vehicle information as input information set in the depth distance estimation information, the depth distance estimation unit 13c determines that the depth distance cannot be estimated from the depth distance estimation information, and sets the initial value of the depth distance to the depth distance. The depth distance estimation unit 13c outputs to the irradiation determination unit 14 depth distance information regarding the depth distance for which the initial value has been set.
[0178] The illumination determination unit 14 determines the illumination range of the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13c, and outputs illumination information to the headlight control unit 15. The headlight control unit 15 causes the headlight 2 to illuminate the illumination range determined by the illumination determination unit 14.
[0179] FIG. 24A is a diagram for explaining an example of the depth distance estimated by the depth distance estimation unit 13c in the fourth embodiment. FIG. 24B is a diagram illustrating an example of a state in which the headlight control unit 15 causes the headlight 2 to irradiate light to an illumination range determined by the illumination determination unit 14 based on the depth distance estimated by the depth distance estimation unit 13c as shown in FIG. 24A in embodiment 4. FIG. 24A is a bird's-eye view of the road on which the vehicle 100 is traveling. Fig. 24B is a side view of the road on which the vehicle 100 is traveling. In Fig. 24B, the driver is indicated by "D" and the illumination range of the light from the headlights 2 is indicated by "LA". In Fig. 24A, the depth distance is the distance from the right light to the driver's estimated viewing position. In Fig. 24B, for convenience, the vehicle 100 is shown as seen from the left side relative to the traveling direction, but the illumination range shown in Fig. 24B is the illumination range by the right light.
[0180] 24A and 24B, as an example, it is assumed that the driver's face is facing within the range of "forward" in the vertical direction, and that there are two pedestrians (pedestrian C and pedestrian D, shown as "W3" and "W4" in Figs. 24A and 24B, respectively) around vehicle 100 in the direction in which the driver is facing. The distance between pedestrian C and headlight 2 is "6 m," and the distance between pedestrian D and headlight 2 is "22 m." It is also assumed that there is a sign (not shown in Figs. 24A and 24B) ahead of vehicle 100, and the white lines are broken in the lane in which vehicle 100 is traveling (the lane here is what is known as a lane). In this case, the depth distance estimation unit 13c estimates the depth distance as "a range with a margin of 5 m including the sidewalk and crosswalk at the intersection" based on the depth distance estimation information of the contents shown in Fig. 22, assuming that the behavior of the driver determined from the direction information and the driving-related information (here, vehicle information, map information, and vehicle exterior information) correspond to No. 3 of the depth distance estimation information. The depth distance estimation unit 13c calculates the "range with a margin of 5 m including the sidewalk and crosswalk at the intersection" as "5 m to 20 m" based on the map information (see Fig. 24A). Since the distance from the headlight 2 to the pedestrian C is within the depth distance range, the depth distance estimation unit 13c adjusts the depth distance to "6 m" and sets "6 m" as the estimated depth distance.
[0181] The illumination determination unit 14 determines the illumination range based on the depth distance "6 m" estimated by the depth distance estimation unit 13c. 13 degree~φ 14 degree range and θ in the vertical direction 13 degree~θ 14 It is assumed that the range of illumination in the left and right directions is determined as the illumination range (see FIG. 24B. In FIG. 24B, the illumination range in the left and right directions is omitted). In this case, the irradiation determination unit 14 calculates the depth distance vertical angle for the up and down directions of the irradiation range based on the depth distance of "6 m", and determines the angle range for the up and down directions of the irradiation range to be the angle range expanded vertically from the depth distance vertical angle by a preset angle.
[0182] As a result, the headlight control unit 15 can control the headlights 2 so that light is irradiated onto the pedestrian C who is present in the direction in which the driver is facing. The driver can visually recognize the pedestrian C. The light from headlight 2 is not directed at pedestrian D.
[0183] Assume that pedestrian D is located at a distance of "12 m" from the headlight 2. Both pedestrian C and pedestrian D are located within the range of the depth distance estimated by the depth distance estimation unit 13c based on the depth distance estimation information. In this case, the depth distance estimation unit 13c may estimate, for example, a range including the distance from the headlight 2 to pedestrian C and the distance from the headlight 2 to pedestrian D as the depth distance. In this case, the depth distance adjustment condition is set to, for example, "when there are multiple moving objects whose distances from the headlight are within the range of the depth distance estimated based on the depth distance estimation information, the range including the distances from the headlight to the multiple moving objects is adjusted to be within the range of the depth distance estimated based on the depth distance estimation information." The headlight control unit 15 controls the headlights 2 so that both pedestrians C and D are irradiated with light.
[0184] In this way, the headlight control device 1c of embodiment 4 is a headlight control device that combines the headlight control device 1a of embodiment 2 and the headlight control device 1b of embodiment 3, and is thereby able to control the headlights 2 in a wider range of situations, and estimates a depth distance that is more suited to the actual situation based on whether or not there is an object actually present in the direction the driver is facing. This allows the headlight control device 1b to more appropriately illuminate the estimated viewing position of the driver, and to provide driving assistance when the vehicle 100 is traveling at night or the like.
[0185] The operation of the headlight control device 1c according to the fourth embodiment will be described. FIG. 25 is a flowchart for explaining the operation of the headlight control device 1c according to the fourth embodiment. For example, when the headlights 2 are turned on, the headlight control device 1c determines to perform lighting control of the headlights 2 based on the driver's direction, and starts the operation shown in the flowchart of Fig. 25. The headlight control device 1c repeats the operation shown in the flowchart of Fig. 25 until, for example, the headlights 2 are turned off or the power of the vehicle 100 is turned off. For example, a control unit (not shown) of the headlight control device 1c acquires information indicating the state of the headlights 2 from a headlight switch mounted on the vehicle 100, and determines whether the headlights 2 are on or not. When the control unit determines that the headlights 2 are on, it determines to start control of the headlights 2 based on the driver's direction, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12c, the depth distance estimation unit 13c, the illumination determination unit 14, and the headlight control unit 15 to instruct them to start control of the headlights 2. In addition, when the control unit determines that the headlights 2 are off or that the vehicle 100 has been turned off, it determines to end the control of the headlights 2 lighting based on the driver's direction, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12c, the depth distance estimation unit 13c, the illumination determination unit 14, and the headlight control unit 15 instructing them to end the control of the headlights 2 lighting.
[0186] Regarding the operation shown in the flowchart of Fig. 25, the processing contents of steps ST1-1, ST1-2, ST1-3, and ST3 to 4 are respectively similar to the processing contents of steps ST1-1, ST1-2, ST1-3, and ST3 to 4 of the operation of the headlight control device 1a shown in the flowchart of Fig. 13, which have been explained in embodiment 2, so duplicated explanations will be omitted. Also, regarding the operation shown in the flowchart of Fig. 25, the processing contents of step ST1-4 are similar to the processing contents of step ST1-4 of the operation of the headlight control device 1b shown in the flowchart of Fig. 20, which have been explained in embodiment 3, so duplicated explanations will be omitted.
[0187] The depth distance estimation unit 13c estimates the depth distance using orientation information regarding the driver's orientation detected by the orientation detection unit 11 in step ST1-1, vehicle information acquired by the vehicle information acquisition unit 121 in step ST1-2, map information acquired by the map information acquisition unit 122 in step ST1-3, outside vehicle information acquired by the outside vehicle information acquisition unit 123 in step ST1-4, and information for depth distance estimation (step ST2c). In detail, when the depth distance estimation unit 13c estimates the depth distance using the depth distance estimation information, the depth distance estimation unit 13c adjusts the estimated depth distance based on the outside vehicle information and by referring to the depth distance adjustment conditions, and confirms the estimated depth distance. The depth distance estimation unit 13c outputs the depth distance information to the irradiation determination unit .
[0188] In step ST3, the illumination determination unit 14 determines the illumination range of the light from the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13c in step ST2c (step ST3).
[0189] In this way, the headlight control device 1c detects the driver's direction based on the in-vehicle captured image, and acquires driving-related information (here, vehicle information, map information, and vehicle exterior information). The headlight control device 1c estimates the depth distance based on the detected direction information on the driver's direction and the acquired driving-related information. At that time, the headlight control device 1c adjusts the depth distance estimated using the depth distance estimation information based on the vehicle exterior information and the depth distance adjustment condition, and sets the adjusted depth distance information as the estimated depth information. Then, the headlight control device 1c determines the illumination range of the headlight 2 based on the estimated depth distance, and causes the headlight 2 to illuminate the determined illumination range. Therefore, the headlight control device 1c can more appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0190] In the above-described fourth embodiment, for example, the depth distance estimation unit 13c may estimate the depth distance and also estimate the ideal width of the irradiation range. In this case, the depth distance estimation unit 13c outputs the depth distance information and the information on the ideal width of the irradiation range to the irradiation determination unit 14. The illumination determination unit 14 determines the illumination range based on the depth distance estimated by the depth distance estimation unit 13c and the ideal width of the illumination range.
[0191] In the above-described fourth embodiment, the depth distance estimation unit 13c may estimate the depth distance and also estimate the ideal light amount of the headlight 2. In this case, the depth distance estimation unit 13c outputs the depth distance information to the illumination determination unit 14 and also outputs information on the estimated ideal light amount to the headlight control unit 15. The headlight control unit 15 causes the headlights 2 to emit light in the illumination range determined by the illumination determination unit 14 with the ideal light amount estimated by the depth distance estimation unit 13c.
[0192] In the above fourth embodiment, the depth distance estimating unit 13c may estimate the depth distance as well as the ideal width and ideal light amount of the irradiation range.
[0193] In the above-described fourth embodiment, the headlight control device 1c is an in-vehicle device mounted on the vehicle 100, and the direction detection unit 11, the driving-related information acquisition unit 12c, the depth distance estimation unit 13c, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown) are provided in the in-vehicle device. However, some of the direction detection unit 11, the driving-related information acquisition unit 12c, the depth distance estimation unit 13c, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown) may be provided in the in-vehicle device of the vehicle 100, and the rest may be provided in a server connected to the in-vehicle device via a network. In addition, all of the direction detection unit 11, the driving-related information acquisition unit 12c, the depth distance estimation unit 13c, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown) may be provided in the server.
[0194] Moreover, the above-mentioned embodiment 4 is an embodiment in which the embodiment 2 and the embodiment 3 are combined, but the embodiment is not limited to this, and the embodiment may be an embodiment in which the embodiment 1 and the embodiment 3 are combined. In this case, in the configuration example of the headlight control device 1b shown in FIG. 14, the driving-related information acquisition unit 12b of the headlight control device 1b includes a vehicle information acquisition unit 121 and a vehicle outside information acquisition unit 123. The depth distance estimation unit 13b estimates the depth distance based on the direction information, the vehicle information, and the vehicle outside information. In detail, the depth distance estimation unit 13b estimates the depth distance based on the direction information, the vehicle information, and the vehicle outside information, for example, by comparing the contents of the depth distance estimation information as shown in FIG. 22 with the depth distance estimation information in which map information is not set in the input information.
[0195] The hardware configuration of the headlight control device 1c according to the fourth embodiment is similar to the hardware configuration of the headlight control device 1 described in the first embodiment with reference to Figs. 6A and 6B, and therefore is not illustrated. In the fourth embodiment, the functions of the direction detection unit 11, the driving-related information acquisition unit 12c, the depth distance estimation unit 13c, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) are realized by the processing circuit 1001. That is, the headlight control device 1c includes the processing circuit 1001 for estimating a depth distance based on direction information relating to the direction of the driver detected based on an in-vehicle captured image acquired from the in-vehicle image capture device 3 and driving-related information, and for controlling the lighting of the headlights 2 based on the estimated depth distance. The processing circuit 1001 may be dedicated hardware as shown in FIG. 6A, or may be a processor 1004 executing a program stored in a memory 1005 as shown in FIG. 6B.
[0196] The processing circuit 1001 reads out and executes the programs stored in the memory 1005, thereby executing the functions of the direction detection unit 11, the driving-related information acquisition unit 12c, the depth distance estimation unit 13c, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown). That is, the headlight control device 1c includes a memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of steps ST1-1, ST1-2, ST1-3, and ST1-4 to ST4 in FIG. 25 described above. The program stored in the memory 1005 can also be said to cause a computer to execute the procedures or methods of the processing of the direction detection unit 11, the driving-related information acquisition unit 12c, the depth distance estimation unit 13c, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown). The storage unit 16 is configured with a memory 1005, for example. The headlight control device 1c includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with devices such as the headlight 2, the in-vehicle image capture device 3, or the driving-related information acquisition device 4.
[0197] As described above, the headlight control device 1c according to embodiment 4 is configured to include an orientation detection unit 11 that detects the orientation of the driver based on an image (in-vehicle image) of the driver of the vehicle 100, a driving-related information acquisition unit 12c that acquires driving-related information related to the driving of the vehicle 100, a depth distance estimation unit 13c that estimates a depth distance based on the orientation of the driver detected by the orientation detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12c, an illumination determination unit 14 that determines the illumination range of light by the headlight 2 based on the depth distance estimated by the depth distance estimation unit 13c, and a headlight control unit 15 that causes the headlight 2 to illuminate the illumination range determined by the illumination determination unit 14. Therefore, the headlight control device 1c can control the lighting of the headlights 2 in the vehicle 100 based on the direction in which the driver is facing, taking into consideration how far ahead in the direction in which the driver is actually facing he or she is trying to see. The headlight control device 1c can more appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0198] In detail, in the headlight control device 1c, the driving-related information acquisition unit 12c has an outside-vehicle information acquisition unit 123 that acquires outside-vehicle information related to the area ahead of the vehicle 100 as driving-related information, and the depth distance estimation unit 13c estimates the depth distance based on the orientation information, vehicle information, map information, and outside-vehicle information. Therefore, the headlight control device 1c can control the lighting of the headlights 2 in the vehicle 100 based on the direction in which the driver is facing, taking into consideration how far ahead in the direction in which the driver is actually facing he or she is trying to see. The headlight control device 1c can more appropriately illuminate the estimated viewing position of the driver, and can provide driving assistance when the vehicle 100 is traveling at night or the like.
[0199] Embodiment 5. For example, the driver may turn without trying to see something, such as nodding, looking away for a moment so that the headlight 2 light does not need to follow, or squinting, etc. In this case, the driver's direction should not be used to estimate the depth distance. In embodiment 5, an embodiment is described in which control is performed to illuminate the light of the headlight 2 in the direction the driver is facing, based on a reliability indicating whether the driver's direction can be estimated to be the direction in which the driver is trying to see something.
[0200] FIG. 26 is a diagram showing an example of the configuration of a headlight control device 1d according to the fifth embodiment. In the fifth embodiment, it is assumed that the headlight control device 1d is mounted on a vehicle 100. The headlight control device 1d controls the lighting of the headlights 2 provided on the vehicle 100 based on the direction of the driver of the vehicle 100. In the fifth embodiment, the "direction of the driver" is represented by the direction of the driver's face or the direction of the driver's line of sight. In the fifth embodiment, the "direction of the driver" may include the direction of the driver's body, in other words, the driver's posture, in addition to the direction of the driver's face or the direction of the driver's line of sight. In the fifth embodiment, the headlight control device 1d performs the light control of the headlights 2 based on the driver's direction, assuming that the light control device 1d performs the light control when the headlights 2 are turned on in a dark place around the vehicle 100, such as a parking lot at night or an urban area at night.
[0201] In FIG. 26, the same components as those in the headlight control device 1 described in the first embodiment with reference to FIG. 1 are denoted by the same reference numerals, and duplicated description will be omitted. A headlight control device 1d according to the fifth embodiment differs from the headlight control device 1 according to the first embodiment in that a reliability determination unit 17 is provided.
[0202] The reliability determination unit 17 determines the reliability of the driver's direction detected by the direction detection unit 11. In the fifth embodiment, the "reliability" of the driver's direction indicates the degree to which it can be estimated that the direction is the direction when trying to visually confirm something, and a case where the reliability is low includes both a case where the accuracy of the detected driver's direction may be low and a case where the detected driver's direction is a direction that does not need to be illuminated by the headlights 2. An example of a case where the accuracy of the detected driver's direction may be low is, for example, a case where the driver is squinting his / her eyes. An example of a direction that does not need to be illuminated by the headlights 2 is, for example, a direction of the driver when the driver is nodding, or a direction of the driver when the driver is looking away. In the fifth embodiment, as an example, it is assumed that the reliability determination unit 17 determines whether the reliability of the driver's direction is "high" or "low". The reliability determination unit 17 determines the reliability of the driver's orientation based on the orientation of the driver detected by the orientation detection unit 11 going back a preset period (hereinafter referred to as the "reliability determination period"), for example. The reliability determination unit 17 may determine the orientation of the driver detected by the orientation detection unit 11 going back a reliability determination period from the orientation information stored in the storage unit 16.
[0203] For example, if the driver's orientation changes by a certain amount or more during the reliability determination period, the reliability determination unit 17 determines that the reliability of the driver's orientation detected by the orientation detection unit 11 is "low." Examples of scenes in which the driver's orientation changes by a certain amount or more during the reliability determination period include a scene in which the driver nods, a scene in which the driver looks away for an instant, and the like. In addition, for example, the reliability of the driver's direction detected in a scene where the driver is squinting is also considered to be "low". In this case, the reliability can be determined at any time from the detected driver's direction, regardless of whether the driver's direction has changed by a certain amount or more during the reliability determination period. Therefore, for example, the reliability determination unit 17 may always determine the reliability in a scene where the driver is squinting, based on the driver's direction detected by the direction detection unit 11, regardless of the reliability determination period.
[0204] When the reliability determination unit 17 determines that the reliability of the driver's orientation detected by the orientation detection unit 11 is “low”, the reliability determination unit 17 does not output the orientation information indicating the orientation to the depth distance estimation unit 13. For example, the reliability determination unit 17 rewrites the orientation information output from the orientation detection unit 11 to orientation information most recently determined to have a “high” reliability, and outputs the rewritten orientation information to the depth distance estimation unit 13. The depth distance estimation unit 13 does not use the driver's direction, for which the reliability determination unit 17 has determined that the reliability is low, in estimating the depth distance. In addition, if the reliability determination unit 17 determines that the reliability of the driver's direction detected by the direction detection unit 11 is “high”, it outputs the direction information output from the direction detection unit 11 to the depth distance estimation unit 13.
[0205] Fig. 27 is a diagram for explaining an example of a situation in which the reliability determination unit 17 determines that the reliability of the driver's direction detected by the direction detection unit 11 is low in the fifth embodiment. In Fig. 27, the illumination range of the light of the headlight 2 is indicated by "LA". For example, when the driver nods, the direction of the driver's face changes momentarily downward. In this case, the reliability determination unit 17 determines that the reliability of the driver's direction is “low”, and outputs to the depth distance estimation unit 13 the direction information most recently determined to have “high” reliability, in this case the direction information before the driver nodded. The depth distance estimation unit 13 estimates the depth distance using the direction information before the driver nods, the vehicle information, and the depth distance estimation information. As a result, the headlights 2 are controlled by the headlight control unit 15 to irradiate light onto the presumed viewed object in the direction in which the driver was facing before the driver nodded.
[0206] The headlight control device 1d can prevent unnecessary leveling and reduce the annoyance caused to the driver by the light of the headlights 2 following a direction that is not the direction in which the driver is trying to see something, by excluding the driver's direction with low reliability from the target of estimating the depth distance among the detected driver directions. In the first embodiment, the unnecessary leveling is, for example, the headlights 2 illuminating downward following the driver's direction at the moment the driver nods, or the headlights 2 illuminating in a direction that the driver is not looking at due to a decrease in gaze detection accuracy when the driver narrows his / her eyes.
[0207] The operation of the headlight control device 1d according to the fifth embodiment will be described. FIG. 28 is a flowchart for explaining the operation of the headlight control device 1d according to the fifth embodiment. For example, when the headlight 2 is turned on, the headlight control device 1d determines to perform lighting control of the headlight 2 based on the driver's direction, and starts the operation shown in the flowchart of Fig. 28. The headlight control device 1d repeats the operation shown in the flowchart of Fig. 28 until, for example, the headlight 2 is turned off or the power of the vehicle 100 is turned off. For example, a control unit (not shown) of the headlight control device 1d acquires information indicating the state of the headlights 2 from a headlight switch mounted on the vehicle 100, and judges whether the headlights 2 are on or not. When the control unit judges that the headlights 2 are on, the control unit judges to start lighting control of the headlights 2 based on the direction of the driver, and outputs information instructing the direction detection unit 11, the reliability judgment unit 17, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, and the headlight control unit 15 to start lighting control of the headlights 2. In addition, when the control unit determines that the headlights 2 are off or that the vehicle 100 has been turned off, it determines to end the control of the headlights 2 lighting based on the driver's direction, and outputs information to the direction detection unit 11, the reliability determination unit 17, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, and the headlight control unit 15 instructing them to end the control of the headlights 2 lighting.
[0208] Regarding the operation shown in the flowchart of FIG. 28, the processing contents of steps ST1-11, ST1-2, and ST2 to 4 are respectively similar to the processing contents of steps ST1-1, ST1-2, and ST2 to 4 of the operation of the headlight control device 1 shown in the flowchart of FIG. 5, which have already been explained in embodiment 1, and therefore duplicate explanations will be omitted.
[0209] The reliability determination unit 17 determines the reliability of the driver's direction detected by the direction detection unit 11 in step ST1-11 (step ST1-12). The reliability determination unit 17 determines the reliability of the driver's orientation based on the driver's orientation detected by the orientation detection unit 11 going back over a reliability determination period, for example. When the reliability determination unit 17 determines that the reliability of the driver's orientation detected by the orientation detection unit 11 is “low”, the reliability determination unit 17 prevents the orientation information output from the orientation detection unit 11 from being output to the depth distance estimation unit 13. For example, the reliability determination unit 17 rewrites the orientation information output from the orientation detection unit 11 to orientation information most recently determined to have a “high” reliability, and outputs the rewritten orientation information to the depth distance estimation unit 13. When the reliability determination unit 17 determines that the reliability of the driver's direction detected by the direction detection unit 11 is “high”, it outputs the direction information output from the direction detection unit 11 to the depth distance estimation unit 13.
[0210] In this way, the headlight control device 1d determines the reliability of the detected driver's direction, and does not use the driver's direction determined to have low reliability in estimating the depth distance using the depth distance estimation information. By excluding the detected driver's direction with low reliability from the target for estimating the depth distance, the headlight control device 1d can prevent unnecessary leveling and reduce the annoyance felt by the driver due to the light of the headlight 2 following a direction other than the one in which the driver is attempting to see something.
[0211] In the above-described fifth embodiment, the reliability determination unit 17 determines the reliability of the driver's orientation detected by the orientation detection unit 11, but this is merely an example, and the reliability determination unit 17 may determine the reliability of the driver's facial features detected by the orientation detection unit 11. In this case, for example, the orientation detection unit 11 outputs information on the driver's facial features used to detect the driver's orientation to the reliability determination unit 17 together with the orientation information. When the reliability determination unit 17 determines that the reliability of the detected driver's facial features is "low", for example, the reliability determination unit 17 causes the driver's orientation to be redetected based on the driver's facial features that were most recently determined to have a "high" reliability. The reliability determination unit 17 may redetect the driver's orientation. Note that the reliability determination unit 17 may perform this redetection in the case where, for example, some of the detected driver's facial features cannot be acquired.
[0212] In the above-described fifth embodiment, the headlight control device 1d is an in-vehicle device mounted on the vehicle 100, and the orientation detection unit 11, the reliability determination unit 17, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) are provided in the in-vehicle device. However, some of the orientation detection unit 11, the reliability determination unit 17, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) may be provided in the in-vehicle device of the vehicle 100, and the rest may be provided in a server connected to the in-vehicle device via a network. In addition, all of the orientation detection unit 11, the reliability determination unit 17, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14, the headlight control unit 15, and a control unit (not shown) may be provided in the server.
[0213] In the above-described embodiment 5, the headlight control device 1 according to embodiment 1 is provided with the reliability determination unit 17, but this is merely an example. For example, the headlight control device 1a according to embodiment 2, the headlight control device 1b according to embodiment 3, or the headlight control device 1c according to embodiment 4 may be configured to include the reliability determination unit 17.
[0214] The hardware configuration of a headlight control device 1d according to the fifth embodiment is similar to the hardware configuration of the headlight control device 1 described in the first embodiment with reference to Figs. 6A and 6B, and therefore is not illustrated. In the fifth embodiment, the functions of the direction detection unit 11, the reliability determination unit 17, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown) are realized by a processing circuit 1001. That is, the headlight control device 1d includes the processing circuit 1001 for estimating a depth distance based on direction information relating to the direction of the driver detected based on an in-vehicle captured image acquired from the in-vehicle image capture device 3 and driving-related information, and for controlling the lighting of the headlights 2 based on the estimated depth distance. The processing circuit 1001 may be dedicated hardware as shown in FIG. 6A, or may be a processor 1004 executing a program stored in a memory 1005 as shown in FIG. 6B.
[0215] The processing circuit 1001 reads out and executes the programs stored in the memory 1005, thereby executing the functions of the orientation detection unit 11, the reliability determination unit 17, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown). That is, the headlight control device 1d includes a memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of steps ST1-11 to ST1-12, ST1-2, and ST2 to ST4 in FIG. 28 described above. It can also be said that the program stored in the memory 1005 causes a computer to execute the procedures or methods of the processing of the orientation detection unit 11, the reliability determination unit 17, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14, the headlight control unit 15, and a control unit (not shown). The storage unit 16 is configured with a memory 1005, for example. The headlight control device 1d includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with devices such as the headlight 2, the in-vehicle image capture device 3, or the driving-related information acquisition device 4.
[0216] As described above, the headlight control device 1d according to embodiment 5 includes a reliability determination unit 17 that determines the reliability of the driver's direction detected by the direction detection unit 11 based on the driver's direction detected by the direction detection unit 11 going back through the reliability determination period, and the depth distance estimation unit 13 is configured not to use the driver's direction that the reliability determination unit 17 has determined to be low in estimating the depth distance. Therefore, the headlight control device 1d can prevent unnecessary leveling and reduce the annoyance felt by the driver due to the light of the headlight 2 following a direction other than the direction in which the driver is intending to see something.
[0217] Embodiment 6 In the sixth embodiment, an embodiment in which a headlight control device sets a plurality of illumination ranges with different light intensities will be described.
[0218] FIG. 29 is a diagram showing an example of the configuration of a headlight control device 1e according to the sixth embodiment. In the sixth embodiment, it is assumed that the headlight control device 1e is mounted on a vehicle 100. The headlight control device 1e controls the illumination of the headlights 2 provided on the vehicle 100 based on the orientation of the driver of the vehicle 100. In the sixth embodiment, the "orientation of the driver" is represented by the orientation of the driver's face or the direction of the driver's line of sight. In the sixth embodiment, the "orientation of the driver" may include the orientation of the driver's body, in other words, the driver's posture, in addition to the orientation of the driver's face or the direction of the driver's line of sight. In the sixth embodiment, it is assumed that the headlight control device 1e performs the light control of the headlights 2 based on the driver's direction when the headlights 2 are turned on in a dark place around the vehicle 100, such as a parking lot at night or an urban area at night.
[0219] In FIG. 29, the same components as those in the headlight control device 1 described in the first embodiment with reference to FIG. 1 are denoted by the same reference numerals, and duplicated description will be omitted. In the headlight control device 1e according to the sixth embodiment, the specific operations of the illumination decision unit 14a and the headlight control unit 15a are different from the specific operations of the illumination decision unit 14 and the headlight control unit 15 in the headlight control device 1 according to the first embodiment.
[0220] The illumination determination unit 14a sets a plurality of illumination ranges with different intensities of light to be illuminated by the headlight 2. In the sixth embodiment, the light illuminated by the headlight 2 is strong means that the amount of light illuminated by the headlight 2 is large. In the sixth embodiment, as an example, the illumination determination unit 14a sets two illumination ranges in which the amount of light irradiated by the headlight 2 is different: an illumination range (referred to as a first illumination range) in which the amount of light irradiated by the headlight 2 is increased, and an illumination range (referred to as a second illumination range) in which the amount of light irradiated by the headlight 2 is decreased. The amount of light irradiated in the first irradiation range can be set appropriately, but should be sufficient to allow the driver to adequately see the presumed visible object that may be present in the first irradiation range. The amount of light irradiated in the second irradiation range should be smaller than the amount of light irradiated in the first irradiation range and should be small enough not to cause glare to pedestrians or other vehicles that may be present in the second irradiation range.
[0221] The illumination determination unit 14a determines, for example, the upper limit angle of the first illumination range in the up-down direction, which is set in advance, among the up-down direction of the illumination range calculated based on the depth distance estimated by the depth distance estimation unit 13. The illumination determination unit 14a determines, for example, the range expanded vertically from the center of the up-down direction of the illumination range calculated based on the depth distance to the upper limit angle as the up-down direction of the first illumination range. The illumination determination unit 14a determines, for example, the range other than the first illumination range in the up-down direction of the illumination range calculated based on the depth distance as the left-right direction of the second illumination range. Furthermore, the illumination determination unit 14a determines the left-right direction of the first illumination range to be, for example, up to a preset upper limit angle of the left-right direction of the first illumination range among the horizontal directions of the illumination range calculated based on the depth distance estimated by the depth distance estimation unit 13. For example, the illumination determination unit 14a determines the left-right direction of the first illumination range to be a range expanded horizontally from the center of the left-right direction of the illumination range calculated based on the depth distance to the upper limit angle. The illumination determination unit 14a determines the left-right direction of the second illumination range to be a range other than the first illumination range among the left-right directions of the illumination range calculated based on the depth distance. The upper limit angle in the up-down direction and the upper limit angle in the left-right direction of the first irradiation range are set, for example, by an administrator or the like, and are stored in a location that can be referenced by the irradiation determination unit 14a.
[0222] For example, the upper limit angle of the first irradiation range in the vertical direction is "5 degrees" and the upper limit angle of the left-right direction is "8 degrees". For example, the vertical direction and the left-right direction of the irradiation range calculated based on the depth distance estimated by the depth distance estimation unit 13 are respectively in the ranges of "3 degrees to 13 degrees" and "0.5 degrees to 12.5 degrees" with the installation position of the headlight 2 as the reference (0 degrees). In this case, the irradiation determination unit 14a determines the range of "5.5 degrees to 10.5 degrees" which is expanded vertically from the center "8 degrees" of the vertical direction of the irradiation range to 5 degrees, as the first irradiation range in the vertical direction, and determines the range of "2.5 degrees to 8.5 degrees" which is expanded horizontally from the center "6.5 degrees" of the horizontal direction of the irradiation range to 8 degrees, as the first irradiation range in the left-right direction. The depth distance estimation unit 13 determines the second illumination range in the up and down direction to be a range of "3 degrees to 5.5 degrees" and a range of "10.5 degrees to 13 degrees" in the vertical direction based on the installation position of the headlight 2, and determines the second illumination range in the horizontal direction to be a range of "0.5 degrees to 5.5 degrees" and a range of "10.5 degrees to 12.5 degrees" in the horizontal direction based on the installation position of the headlight 2.
[0223] The illumination determination unit 14a outputs illumination information relating to the determined illumination range to the headlight control unit 15a. The illumination information output by the illumination determination unit 14a includes information indicating the vertical and horizontal angular ranges of the first illumination range and information indicating the vertical and horizontal angular ranges of the second illumination range.
[0224] The headlight control unit 15a causes the headlights 2 to irradiate the illumination range determined by the illumination determination unit 14a with light. In detail, the headlight control unit 15a controls the headlight 2 to irradiate the second illumination range, which is set by the illumination determination unit 14a, with a smaller amount of light than the light irradiated to the first illumination range, which is set by the illumination determination unit 14a.
[0225] FIG. 30 is a diagram illustrating an example of a state in which the headlight control unit 15a causes the headlight 2 to irradiate light onto the first illumination range and the second illumination range determined by the illumination determination unit 14a in the sixth embodiment. FIG. 30A is a view from the side of the road along which the vehicle 100 is traveling, showing the first illumination range and the second illumination range being illuminated with light, and FIG. 30B is a view from the side of the vehicle 100, showing the first illumination range and the second illumination range being illuminated with light. In Fig. 30, the driver is indicated by "D", and among the ranges of light irradiation by the headlight 2, a first irradiation range is indicated by "LA1", and a second irradiation range is indicated by "LA2". Note that in Fig. 30B, the vehicle 100 and the like are omitted from the illustration.
[0226] For example, if the depth distance estimated by the depth distance estimation unit 13 is a distance with a range, such as "5 to 15 m" or "80 to 100 m," if the illumination determination unit 14a determines the illumination range so that light is illuminated within the range of the depth distance, the width of the illumination range of the light that the headlight control unit 15a causes the headlight 2 to illuminate becomes large. In that case, the headlight control device 1d may give glare to pedestrians or drivers of other vehicles. Therefore, the headlight control device 1d according to the sixth embodiment sets a first illumination range in which the amount of light irradiated by the headlight 2 is increased, and a second illumination range in which the amount of light irradiated by the headlight 2 is decreased, and causes the headlight 2 to irradiate the second illumination range set by the illumination determination unit 14a with light of an amount smaller than the light irradiated to the first illumination range set by the illumination determination unit 14a. This allows the headlight control device 1d to emit light so that the driver of the vehicle 100 can see the estimated visible object in the direction the driver is facing, while reducing the glare that may be caused to pedestrians or drivers of other vehicles.
[0227] The above-described method of determining the first and second illumination ranges by the illumination determination unit 14a is merely an example. The illumination determination unit 14a may determine the first and second illumination ranges by other methods. For example, among the irradiation range calculated based on the depth distance estimated by the depth distance estimation unit 13, a proportion that is the up-down direction of the first irradiation range and a proportion that is the left-right direction of the first irradiation range are respectively set, and the irradiation determination unit 14a may set the up-down direction and the left-right direction of the first irradiation range based on the preset proportions.
[0228] Also, for example, the illumination determination unit 14a may set the range of the illumination range calculated based on the depth distance estimated by the depth distance estimation unit 13 to be the vertical and horizontal directions of the first illumination range based on the driving state of the vehicle 100 estimated from the driver's behavior and driving-related information, which are the basis for deriving the depth distance. For example, the depth distance estimation unit 13 may set the vertical and horizontal directions of the first illumination range to "10 degrees" when the driving state of the vehicle 100 is parked and stopped, and set the vertical and horizontal directions of the first illumination range to "5 degrees" when the driving state of the vehicle 100 is running. Note that the vertical and horizontal directions of the first illumination range are determined in advance depending on the driving state of the vehicle 100. In this case, for example, as described in the first embodiment with reference to Fig. 3, information in which the traveling state of the vehicle 100 and the estimated visual object of the driver are associated with each other is generated in advance by an administrator or the like and stored in a location that can be referenced by the illumination determination unit 14a. In addition, the depth distance estimation unit 13 outputs the direction information and the traveling-related information together with the depth distance information to the illumination determination unit 14a.
[0229] Also, for example, when the depth distance estimation unit 13 estimates the depth distance and also estimates the ideal width of the irradiation range, the irradiation determination unit 14a may determine an irradiation range according to the ideal width of the irradiation range as a first irradiation range, and a range other than the first irradiation range among the irradiation ranges based on the depth distance as a second irradiation range.
[0230] The operation of the headlight control device 1e according to the sixth embodiment will be described. FIG. 31 is a flowchart for explaining the operation of the headlight control device 1e according to the sixth embodiment. For example, when the headlights 2 are turned on, the headlight control device 1e determines to perform lighting control of the headlights 2 based on the driver's direction, and starts the operation shown in the flowchart of Fig. 31. The headlight control device 1e repeats the operation shown in the flowchart of Fig. 31 until, for example, the headlights 2 are turned off or the power of the vehicle 100 is turned off. For example, a control unit (not shown) of the headlight control device 1e acquires information indicating the state of the headlights 2 from a headlight switch mounted on the vehicle 100, and determines whether the headlights 2 are on or not. When the control unit determines that the headlights 2 are on, it determines to start lighting control of the headlights 2 based on the driver's direction, and outputs information instructing the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14a, and the headlight control unit 15a to start lighting control of the headlights 2. In addition, when the control unit determines that the headlights 2 are off or that the vehicle 100 has been turned off, it determines to end the lighting control of the headlights 2 based on the driver's direction, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14a, and the headlight control unit 15a instructing them to end the lighting control of the headlights 2.
[0231] Regarding the operation shown in the flowchart of FIG. 31, the processing contents of steps ST1-1, ST1-2, and ST2 are respectively similar to the processing contents of steps ST1-1, ST1-2, and ST2 of the operation of the headlight control device 1 shown in the flowchart of FIG. 5, which have already been explained in embodiment 1, and therefore duplicate explanations will be omitted.
[0232] The illumination determination unit 14a sets a first illumination range in which the amount of light irradiated by the headlight 2 is increased and a second illumination range in which the amount of light irradiated by the headlight 2 is decreased based on the depth distance estimated by the depth distance estimation unit 13 in step ST2 (step ST3a). The illumination determination unit 14a outputs illumination information relating to the determined illumination range to the headlight control unit 15a.
[0233] The headlight control unit 15a causes the headlight 2 to irradiate the illumination range determined by the illumination determination unit 14a in step ST3a with light (step ST4a). In detail, the headlight control unit 15a controls the headlight 2 to irradiate the second illumination range, which is set by the illumination determination unit 14a, with a smaller amount of light than the light irradiated to the first illumination range, which is set by the illumination determination unit 14a.
[0234] In this way, the headlight control device 1e sets a first illumination range and a second illumination range in which the amount of light irradiated by the headlight 2 is smaller than that of the first illumination range, within the illumination range determined based on the depth distance, and causes the headlight 2 to irradiate the second illumination range with a smaller amount of light than that irradiated to the first illumination range. Therefore, the headlight control device 1e can emit light so that the driver of the vehicle 100 can see the estimated visible object in the direction in which the driver is facing, while reducing the glare that may be caused to pedestrians or drivers of other vehicles.
[0235] In the sixth embodiment, the position of the illumination range is changed in accordance with the change in the driver's direction, but the headlight control device 1e may make the moving speed of the first illumination range, which is changed in accordance with the change in the driver's direction, different from the moving speed of the second illumination range, which is changed in accordance with the change in the driver's direction. For example, in the headlight control device 1e, the illumination determination unit 14a may control the moving speed of the first illumination range, which is changed in accordance with the change in the driver's direction, based on a short-term average of the driver's direction, and control the moving speed of the second illumination range, which is changed in accordance with the change in the driver's direction, based on a long-term average of the driver's direction. Thereby, the headlight control device 1e can keep the direction in which the driver is no longer facing within the second illumination range for a while, and can illuminate the light of the headlight 2. As a result, for example, when a pedestrian suddenly appears in the direction in which the driver is no longer facing, the headlight control device 1e can illuminate the pedestrian with the light of the headlight 2, allowing the driver to discover the pedestrian early.
[0236] In the above-described sixth embodiment, the illumination determination unit 14a sets two illumination ranges having different amounts of light irradiated by the headlights 2. However, this is merely an example, and the illumination determination unit 14a may set three or more illumination ranges having stepwise different amounts of light irradiated by the headlights 2.
[0237] In the sixth embodiment, the irradiation determination unit 14a sets two irradiation ranges (first and second irradiation ranges) with different amounts of irradiation light in the vertical and horizontal directions of the irradiation range, but this is merely an example. For example, the irradiation determination unit 14a may set an irradiation range with different amounts of irradiation light only in the vertical direction of the irradiation range, or may set an irradiation range with different amounts of irradiation light only in the horizontal direction of the irradiation range.
[0238] In the above-described sixth embodiment, the headlight control device 1e is an in-vehicle device mounted on the vehicle 100, and the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14a, the headlight control unit 15a, and a control unit (not shown) are provided in the in-vehicle device. However, some of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14a, the headlight control unit 15a, and a control unit (not shown) may be provided in the in-vehicle device of the vehicle 100, and the rest may be provided in a server connected to the in-vehicle device via a network. In addition, the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14a, the headlight control unit 15a, and a control unit (not shown) may all be provided in the server.
[0239] In the above-described sixth embodiment, the first and second illumination ranges are set in the headlight control device 1 according to the first embodiment, but this is merely an example. For example, the first and second illumination ranges may be set in the headlight control device 1a according to the second embodiment, the headlight control device 1b according to the third embodiment, the headlight control device 1c according to the fourth embodiment, or the headlight control device 1d according to the fifth embodiment. The headlight control device 1b according to the third embodiment and the headlight control device 1c according to the fourth embodiment adjust the depth distance in consideration of an object that is actually present in the direction of the driver. For example, if the distance between the headlight 2 and a moving object present in the direction of the driver is estimated as the depth distance, the depth distance is likely to be a distance that does not have a width. In this case, it is assumed that the width of the irradiation range of the light that the headlight control devices 1b and 1c irradiate to the headlight 2 will not be large. However, for example, the position of an object measured by an outside-vehicle image capture device or a radar may include a measurement error. Therefore, for example, the headlight control devices 1b and 1c may set the range of the measurement error as the second irradiation range.
[0240] The hardware configuration of a headlight control device 1e according to the sixth embodiment is similar to the hardware configuration of the headlight control device 1 described in the first embodiment with reference to FIGS. 6A and 6B, and therefore is not illustrated. In the sixth embodiment, the functions of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14a, the headlight control unit 15a, and a control unit (not shown) are realized by the processing circuit 1001. That is, the headlight control device 1e includes the processing circuit 1001 for estimating a depth distance based on direction information relating to the direction of the driver detected based on an in-vehicle captured image acquired from the in-vehicle image capture device 3 and driving-related information, and for controlling the lighting of the headlights 2 based on the estimated depth distance. The processing circuit 1001 may be dedicated hardware as shown in FIG. 6A, or may be a processor 1004 executing a program stored in a memory 1005 as shown in FIG. 6B.
[0241] The processing circuit 1001 reads out and executes the programs stored in the memory 1005, thereby executing the functions of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14a, the headlight control unit 15a, and a control unit (not shown). That is, the headlight control device 1e includes a memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of steps ST1-1, ST1-2, and ST2 to ST4a in FIG. 31 described above. It can also be said that the program stored in the memory 1005 causes a computer to execute the procedures or methods of the processing of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14a, the headlight control unit 15a, and a control unit (not shown). The storage unit 16 is configured with a memory 1005, for example. The headlight control device 1e includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with devices such as the headlight 2, the in-vehicle image capture device 3, or the driving-related information acquisition device 4.
[0242] As described above, the headlight control device 1e according to the sixth embodiment is configured such that the illumination determination unit 14a sets, within the illumination range, a first illumination range and a second illumination range in which the amount of light irradiated by the headlight 2 is made smaller than that of the first illumination range, and the headlight control unit 15a causes the headlight 2 to irradiate the second illumination range set by the illumination determination unit 14a with a smaller amount of light than the light irradiated to the first illumination range set by the illumination determination unit 14a. Therefore, the headlight control device 1e can emit light so that the driver of the vehicle 100 can see the estimated visible object in the direction in which the driver is facing, while reducing the glare that may be caused to pedestrians or drivers of other vehicles.
[0243] Embodiment 7 In the seventh embodiment, an embodiment will be described in which, when the headlight control device sets multiple illumination ranges with different light intensities, the illumination range with weak light is made wider than the range set in the sixth embodiment.
[0244] FIG. 32 is a diagram showing an example of the configuration of a headlight control device 1f according to the seventh embodiment. In the configuration example of the headlight control device 1f according to the seventh embodiment, the same components as those in the configuration example of the headlight control device 1e according to the sixth embodiment described using FIG. 29 are denoted by the same reference symbols and redundant explanations are omitted. The configuration example of the headlight control device 1f according to the seventh embodiment differs from the headlight control device 1e according to the sixth embodiment described using FIG. 29 in that the illumination decision unit 14b is equipped with a surrounding confirmation judgment unit 141.
[0245] The surrounding confirmation determination unit 141 determines whether or not the driver is checking the surroundings based on information regarding the driver's direction detected by the direction detection unit 11 and driving-related information acquired by the driving-related information acquisition unit 12 (here, vehicle-related information acquired by the vehicle information acquisition unit 121), and when it is determined that the driver is checking the surroundings, it widens the second illumination range set by the illumination determination unit 14b. In detail, for example, the surrounding confirmation determination unit 141 determines whether or not the driver is checking the surroundings by comparing the orientation information, the driving-related information (here, the vehicle information), and the surrounding confirmation determination conditions for determining whether or not the driver is checking the surroundings.
[0246] Here, FIG. 33 is a diagram for explaining an example of the contents of the surrounding confirmation determination condition used by the surrounding confirmation determination unit 141 in the seventh embodiment to determine whether or not the driver is checking the surroundings. The surrounding confirmation determination conditions are, for example, a table in which the driver's behavior and vehicle information are associated with each other. The surrounding confirmation determination conditions are generated in advance by an administrator or the like, and are stored in a location that can be referenced by the surrounding confirmation determination unit 141. The surrounding confirmation judgment unit 141 judges the driver's behavior, vehicle speed, etc. from the orientation information and vehicle information, and if the judged driver's behavior, vehicle speed, etc. match the conditions for surrounding confirmation judgment, it judges that the driver is checking the surroundings. When the determined behavior of the driver, the vehicle speed, and the like do not match the conditions for determining surrounding confirmation, the surrounding confirmation determination unit 141 determines that the driver is not checking the surroundings.
[0247] Then, when it is determined that the driver is checking the surroundings, the surroundings confirmation determination unit 141 widens the second illumination range set by the illumination determination unit 14b. The illumination determination unit 14b may set the first illumination range and the second illumination range in a similar manner to that of the illumination determination unit 14a included in the headlight control device 1e according to the sixth embodiment, and therefore a duplicated description will be omitted. Here, for example, when the surrounding confirmation judgment unit 141 judges that the driver is checking the surroundings, it expands the left and right directions of the second illumination range to the limits of the area where the headlight 2 can emit light, in other words, the high beam illumination area, the low beam illumination area, and the auxiliary light illumination area.
[0248] The illumination decision unit 14b outputs illumination information including information indicating the first illumination range set by the illumination decision unit 14b and, if the surrounding confirmation judgment unit 141 expands the second illumination range, information indicating the expanded second illumination range to the headlight control unit 15a. If the surrounding confirmation determination unit 141 does not expand the second illumination range, the illumination decision unit 14b outputs illumination information including information indicating the first illumination range and the second illumination range set by the illumination decision unit 14b to the headlight control unit 15a.
[0249] FIG. 34 is a diagram for explaining an example of a state in which the surrounding confirmation determination unit 141 irradiates light onto the illumination range after widening the second illumination range set by the illumination determination unit 14b in the seventh embodiment. FIG. 34 is a diagram showing the first illumination range and the second illumination range being illuminated with light, as viewed from the vehicle 100 side. In FIG. 34, the first irradiation area is indicated by "LA1" and the second irradiation area is indicated by "LA2." In addition, if the surrounding confirmation determination unit 141 does not expand the second illumination range, the first illumination range and the second illumination range set by the illumination determination unit 14b into which light is irradiated are the ranges as shown in FIG. 30B in the sixth embodiment.
[0250] By the surrounding confirmation judgment unit 141 widening the second illumination range, as shown in FIG. 34, the headlight control device 1f can illuminate not only the estimated visible object in the direction the driver is looking, but also areas where there may be objects that the driver is unlikely to see. The headlight control device 1f widens the second illumination range, in other words, the range smaller than the first illumination range, where the amount of illumination light is irradiated so as not to cause glare to pedestrians, drivers of other vehicles, etc. Therefore, the headlight control device 1f can brighten a place where an object that is likely not seen by the driver may exist, and can prevent glare from being caused to pedestrians, drivers of other vehicles, etc. in a direction that the driver is not looking.
[0251] 35 and 36 are diagrams for explaining an example of an illumination range of light that the headlight control device 1f causes the headlight 2 to illuminate in the seventh embodiment. FIG. 35 is a bird's-eye view of the surroundings 100 of the vehicle 100 as seen from above. Figure 36B is a diagram showing an example of the irradiation range of light that the headlight control device 1f causes the headlight 2 to irradiate in the surrounding conditions of the vehicle 100 as shown in Figure 35, and Figure 36A is a diagram showing an example of the irradiation range of light that the headlight control device 1e of embodiment 6 causes the headlight 2 to irradiate in the surrounding conditions of the vehicle 100 as shown in Figure 35.
[0252] For example, suppose that vehicle 100 is now traveling in an underground parking lot, and a first stopped vehicle (indicated by "C1" in FIG. 35) and a second stopped vehicle (indicated by "C2" in FIG. 35) are stopped on the left and right sides of the road on which vehicle 100 is traveling in front of vehicle 100 with respect to the traveling direction of vehicle 100. In addition, a pedestrian (indicated by "W" in FIG. 35) is about to come out from behind the first stopped vehicle on the right front as viewed from vehicle 100. The driver is facing forward and to the left as viewed from the vehicle 100.
[0253] In this case, for example, in the headlight control device 1e according to the sixth embodiment, as shown in Fig. 36A, in the illumination range determined based on the estimated depth distance, the second illumination range of the illumination range is set in the direction in which the driver is facing, that is, the left front of the vehicle 100. In this case, the right front of the vehicle 100 where the pedestrian (indicated by "W" in Fig. 36A) is about to emerge is opposite to the direction in which the driver is facing, and no illumination range is set. As a result, the area around the pedestrian becomes dark, and the driver is delayed in finding the pedestrian.
[0254] In contrast, the headlight control device 1f according to the seventh embodiment expands the second illumination range, which is set to the left front of the vehicle 100 in the illumination range determined based on the estimated depth distance, in the left and right directions to the limit of the illumination possible area, as shown in Fig. 36B. As a result, the right front of the vehicle 100 where the pedestrian (indicated by "W" in Fig. 36B) is about to emerge is set as the illumination range, more specifically, the second illumination range. As a result, the light from the headlights 2 is also irradiated near the pedestrian, enabling the driver to find the pedestrian early.
[0255] It should be noted that the extent to which the surrounding confirmation determination unit 141 expands the second irradiation range can be set appropriately. In the seventh embodiment described above, the surrounding confirmation determination unit 141 widens the second illumination range in the left-right direction to the limit of the area where the headlight 2 can illuminate, but this is merely an example, and the surrounding confirmation determination unit 141 may widen the second illumination range in the left-right direction by a preset range. It is sufficient that the illumination determination unit 14b widens the second illumination range beyond the second illumination range determined based on the depth distance estimated by the depth distance estimation unit 13.
[0256] The surrounding confirmation determination unit 141 may set how much to widen the second illumination range based on the traveling state of the vehicle 100 (for example, while parking or stopping, or while turning right or left at an intersection) or the vehicle speed of the vehicle 100, which is estimated from the driver's behavior and the traveling-related information, which are the basis for deriving the depth distance. In this case, for example, information in which the traveling state of the vehicle 100 and the estimated visually recognized object of the driver are associated with each other, as described in the first embodiment using FIG. 3, is generated in advance by an administrator or the like, and stored in a location that can be referenced by the surrounding confirmation determination unit 141. The depth distance estimation unit 13 outputs the direction information and the traveling-related information together with the depth distance information to the illumination determination unit 14b.
[0257] In addition, in the above-described seventh embodiment, the surrounding confirmation determination unit 141 is configured to expand the second illumination range only in the left-right direction of the second illumination range, but this is merely an example, and the surrounding confirmation determination unit 141 may expand the second illumination range in the up-down direction of the second illumination range.
[0258] The operation of the headlight control device 1f according to the seventh embodiment will be described. FIG. 37 is a flowchart for explaining the operation of the headlight control device 1f according to the seventh embodiment. For example, when the headlights 2 are turned on, the headlight control device 1f determines to control the lighting of the headlights 2 based on the driver's direction, and starts the operation shown in the flowchart of Fig. 37. The headlight control device 1f repeats the operation shown in the flowchart of Fig. 37 until, for example, the headlights 2 are turned off or the power of the vehicle 100 is turned off. For example, a control unit (not shown) of the headlight control device 1f acquires information indicating the state of the headlights 2 from a headlight switch mounted on the vehicle 100, and determines whether the headlights 2 are on or not. When the control unit determines that the headlights 2 are on, it determines to start control of the headlights 2 based on the driver's direction, and outputs information instructing the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14b, and the headlight control unit 15a to start control of the headlights 2. In addition, when the control unit determines that the headlights 2 are off or that the vehicle 100 has been turned off, it determines to end the lighting control of the headlights 2 based on the driver's direction, and outputs information to the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14b, and the headlight control unit 15a instructing them to end the lighting control of the headlights 2.
[0259] Regarding the operation shown in the flowchart of FIG. 37, the processing contents of step ST1-1, step ST1-2, step ST2 to step ST3a, and step ST4a are similar to the processing contents of step ST1-1, step ST1-2, step ST2 to step ST3a, and step ST4a of the operation of the headlight control device 1e shown in the flowchart of FIG. 31, which have already been explained in embodiment 6, and therefore duplicate explanations will be omitted. The operation of the headlight control device 1f according to the seventh embodiment is different from the operation of the headlight control device 1e according to the sixth embodiment described using the flowchart of FIG. 31 in that steps ST3a-1 to ST3a-2 are added.
[0260] In step ST3a, the illumination determination unit 14a sets the first illumination range and the second illumination range based on the depth distance estimated by the depth distance estimation unit 13 in step ST2.The surrounding confirmation judgment unit 141 judges whether the driver is checking the surroundings based on the orientation information regarding the driver's orientation detected by the orientation detection unit 11 in step ST1-1 and the vehicle-related information acquired by the vehicle information acquisition unit 121 in step ST1-2 (step ST3a-1).
[0261] If it is determined in step ST3a-1 that the driver is checking the surroundings (if "YES" in step ST3a-1), the surrounding confirmation determination unit 141 widens the second illumination range set by the illumination determination unit 14b in step ST3a (step ST3a-2). The illumination decision unit 14b outputs illumination information including information indicating the first illumination range set in step ST3a and information indicating the second illumination range after being expanded by the surrounding confirmation judgment unit 141 in step ST3a-2 to the headlight control unit 15a.
[0262] When it is determined in step ST3a-1 that the driver has not checked the surroundings (in the case of "NO" in step ST3a-1), the illumination determination unit 14b outputs illumination information including information indicating the first illumination range and the second illumination range set in step ST3a to the headlight control unit 15a. Then, the operation of the headlight control device 1b skips the process of step ST3a-2 and proceeds to the process of step ST4a.
[0263] In this way, the headlight control device 1f determines whether the driver is checking the surroundings based on directional information regarding the driver's orientation and driving-related information (here, vehicle information), and if it determines that the driver is checking the surroundings, it widens the second illumination range. Therefore, the headlight control device 1f can illuminate not only the presumed visual object in the direction the driver is looking, but also the place where an object that the driver is likely not looking at may exist. The headlight control device 1f can illuminate the place where an object that the driver is likely not looking at may exist, and can prevent glare from being given to pedestrians or drivers of other vehicles in the direction the driver is not looking.
[0264] In the above seventh embodiment, the headlight control device 1f is an in-vehicle device mounted on the vehicle 100, and the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14b, the headlight control unit 15a, and a control unit (not shown) are provided in the in-vehicle device. However, some of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14b, the headlight control unit 15a, and a control unit (not shown) may be provided in the in-vehicle device of the vehicle 100, and the rest may be provided in a server connected to the in-vehicle device via a network. In addition, all of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14b, the headlight control unit 15a, and a control unit (not shown) may be provided in the server.
[0265] The hardware configuration of the headlight control device 1f according to the seventh embodiment is similar to the hardware configuration of the headlight control device 1 described in the first embodiment with reference to Figs. 6A and 6B, and therefore is not illustrated. In the seventh embodiment, the functions of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the illumination determination unit 14b, the headlight control unit 15a, and a control unit (not shown) are realized by the processing circuit 1001. That is, the headlight control device 1f includes the processing circuit 1001 for estimating a depth distance based on direction information relating to the direction of the driver detected based on an in-vehicle captured image acquired from the in-vehicle image capture device 3 and driving-related information, and for controlling the lighting of the headlights 2 based on the estimated depth distance. The processing circuit 1001 may be dedicated hardware as shown in FIG. 6A, or may be a processor 1004 executing a program stored in a memory 1005 as shown in FIG. 6B.
[0266] The processing circuit 1001 reads out and executes the programs stored in the memory 1005, thereby executing the functions of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14b, the headlight control unit 15a, and a control unit (not shown). That is, the headlight control device 1f includes a memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of steps ST1-1, ST1-2, and ST2 to ST4a in FIG. 37 described above. The program stored in the memory 1005 can also be said to cause a computer to execute the procedures or methods of the processing of the direction detection unit 11, the driving-related information acquisition unit 12, the depth distance estimation unit 13, the irradiation determination unit 14b, the headlight control unit 15a, and a control unit (not shown). The storage unit 16 is configured with a memory 1005, for example. The headlight control device 1f includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with devices such as the headlight 2, the in-vehicle image capture device 3, or the driving-related information acquisition device 4.
[0267] As described above, the headlight control device 1f of embodiment 7 is configured such that the illumination decision unit 14b determines whether or not the driver is checking the surroundings based on information relating to the driver's direction detected by the direction detection unit 11 and the driving-related information acquired by the driving-related information acquisition unit 12, and has a surrounding confirmation determination unit 141 that expands the second illumination range when it is determined that the driver is checking the surroundings. Therefore, the headlight control device 1f can illuminate not only the presumed visual object in the direction the driver is looking, but also the place where an object that the driver is likely not looking at may exist. The headlight control device 1f can illuminate the place where an object that the driver is likely not looking at may exist, and can prevent glare from being given to pedestrians or drivers of other vehicles in the direction the driver is not looking.
[0268] In the above first to seventh embodiments, the depth distance estimation units 13, 13a, 13b, and 13c estimate the depth distance using the depth distance estimation information, but this is merely an example. For example, the depth distance estimation units 13, 13a, 13b, and 13c may estimate the depth distance using a trained model (hereinafter referred to as a "machine learning model") that receives orientation information as input and outputs the depth distance. The machine learning model may be a model that takes orientation information as input and outputs a depth distance and an ideal width of the irradiation range, or a model that takes orientation information as input and outputs a depth distance and an ideal light amount, or a model that takes orientation information as input and outputs a depth distance, an ideal width of the irradiation range, and an ideal light amount. For example, the manager or the like performs a test run of the vehicle 100 to collect orientation information and information on the depth distance to an object that the driver is trying to see during the test run, and causes the learning device to generate a machine learning model using the collected orientation information and depth distance information as learning data. The generated machine learning model is stored in a location that can be referenced by the headlight control devices 1, 1a, 1b, 1c, 1d, 1e, and 1f. In addition, the machine learning model may be a model that inputs not only orientation information but also map information, vehicle information, or outside vehicle information, and outputs the depth distance and the ideal width of the illumination range. The headlight control devices 1, 1a, 1b, 1c, 1d, 1e, and 1f are configured to estimate the depth distance using a machine learning model, so that they can estimate the depth distance that corresponds to the variation in the direction information.
[0269] Furthermore, the embodiments may be freely combined, or any of the components in each embodiment may be modified, or any of the components in each embodiment may be omitted. [Industrial Applicability]
[0270] The headlight control device of the present disclosure can control the lighting of headlights in a vehicle based on the direction the driver is facing, taking into account how far ahead the driver is actually attempting to see in the direction of his or her face or line of sight. [Explanation of symbols]
[0271] 1, 1a, 1b, 1c, 1d, 1e, 1f headlight control device, 11 orientation detection unit, 12, 12a, 12b, 12c driving-related information acquisition unit, 121 vehicle information acquisition unit, 122 map information acquisition unit, 123 outside vehicle information acquisition unit, 13, 13a, 13b, 13c depth distance estimation unit, 14, 14a, 14b illumination determination unit, 141 surrounding confirmation determination unit, 15, 15a headlight control unit, 16 memory unit, 17 reliability determination unit, 2 headlight, 3 in-vehicle imaging device, 4 driving-related information acquisition device, 100 vehicle, 1001 processing circuit, 1002 input interface device, 1003 output interface device, 1004 processor, 1005 memory.
Claims
1. A direction detection unit that detects a direction of a driver of a vehicle based on a captured image of the driver; a driving-related information acquisition unit that acquires driving-related information related to the driving of the vehicle; a depth distance estimation unit that estimates a depth distance, which is a distance from an installation position of a headlight provided on the vehicle to an estimated viewing position that is estimated to be the viewing position of the driver in a direction in which the driver is facing, based on orientation information regarding the orientation of the driver detected by the orientation detection unit and the driving-related information acquired by the driving-related information acquisition unit; and an illumination determination unit that determines an illumination range of the headlight based on the depth distance estimated by the depth distance estimation unit; a headlight control unit that causes the headlight to irradiate the light to the illumination range determined by the illumination determination unit; A headlight control device comprising:
2. The depth distance estimation unit is The depth distance is estimated by comparing the orientation information, the driving-related information, and depth distance estimation information in which information related to the driver's behavior and the driving-related information are associated with each other.
2. The headlight control device according to claim 1.
3. The depth distance estimation unit is The depth distance is estimated based on the orientation information, the driving-related information, and a machine learning model that receives the orientation information and the driving-related information as input and outputs information regarding the depth distance.
2. The headlight control device according to claim 1.
4. The traveling-related information acquisition unit includes a vehicle information acquisition unit that acquires vehicle information related to the vehicle as the traveling-related information, The depth distance estimation unit estimates the depth distance based on the orientation information and the vehicle information.
4. The headlight control device according to claim 1, wherein the headlight control device is a control unit for controlling a headlight.
5. the driving-related information acquisition unit includes a vehicle information acquisition unit that acquires vehicle information related to the vehicle as the driving-related information, and a map information acquisition unit that acquires map information as the driving-related information, The depth distance estimation unit estimates the depth distance based on the orientation information, the vehicle information, and the map information.
4. The headlight control device according to claim 1, wherein the headlight control device is a control unit for controlling a headlight.
6. The driving-related information acquisition unit includes an outside-vehicle information acquisition unit that acquires outside-vehicle information related to a periphery of the vehicle as the driving-related information, The depth distance estimation unit estimates the depth distance based on the orientation information and the vehicle exterior information.
2. The headlight control device according to claim 1.
7. the driving-related information acquisition unit includes a vehicle information acquisition unit that acquires vehicle information related to the vehicle as the driving-related information, and an outside-vehicle information acquisition unit that acquires outside-vehicle information related to a periphery of the vehicle as the driving-related information, The depth distance estimation unit estimates the depth distance based on the orientation information, the vehicle information, and the vehicle exterior information.
2. The headlight control device according to claim 1.
8. the driving-related information acquisition unit includes a vehicle information acquisition unit that acquires vehicle information related to the vehicle as the driving-related information, a map information acquisition unit that acquires map information as the driving-related information, and an outside-vehicle information acquisition unit that acquires outside-vehicle information related to a location ahead of the vehicle as the driving-related information, The depth distance estimation unit estimates the depth distance based on the orientation information, the vehicle information, the map information, and the vehicle exterior information.
2. The headlight control device according to claim 1.
9. The vehicle outside information acquired by the vehicle outside information acquisition unit includes information regarding a distance to an object existing around the vehicle, The depth distance estimation unit adjusts the depth distance based on a distance to the object present in front of the vehicle, and regards the adjusted depth distance as the estimated depth distance.
9. The headlight control device according to claim 6, wherein the headlight control device is a control unit for controlling a headlight.
10. A reliability determination unit that determines the reliability of the driver's orientation detected by the orientation detection unit, The depth distance estimation unit does not use the driver's orientation, for which the reliability determination unit has determined that the reliability is low, in estimating the depth distance.
2. The headlight control device according to claim 1.
11. The illumination determination unit sets a first illumination range and a second illumination range in which an amount of light illuminated by the headlight is smaller than that of the first illumination range, in the illumination range, The headlight control unit controls the headlight to irradiate the second irradiation range set by the irradiation determination unit with the light having an amount of irradiation light smaller than the amount of light to be irradiated to the first irradiation range set by the irradiation determination unit.
2. The headlight control device according to claim 1.
12. The illumination determination unit has a surroundings confirmation determination unit that determines whether the driver is checking the surroundings based on the direction information and the driving-related information, and expands the second illumination range when it is determined that the driver is checking the surroundings.
12. The headlight control device according to claim 11.
13. the depth distance estimation unit estimates the depth distance and an ideal width of the illumination range; The illumination determination unit determines the illumination range based on the depth distance estimated by the depth distance estimation unit and the ideal width of the illumination range.
2. The headlight control device according to claim 1.
14. the depth distance estimation unit estimates the depth distance and also estimates an ideal light amount of the light from the headlight; The headlight control unit causes the headlight to irradiate the light in the illumination range determined by the illumination determination unit with the ideal light amount estimated by the depth distance estimation unit.
2. The headlight control device according to claim 1.
15. A direction detection unit detects a direction of a driver of the vehicle based on a captured image of the driver; A driving-related information acquisition unit acquires driving-related information related to driving of the vehicle; a depth distance estimation unit estimating a depth distance, which is a distance from an installation position of a headlight provided on the vehicle to an estimated viewing position that is estimated to be the viewing position of the driver in a direction in which the driver is facing, based on orientation information regarding the orientation of the driver detected by the orientation detection unit and the driving-related information acquired by the driving-related information acquisition unit; an illumination determination unit determining an illumination range of the light from the headlight based on the depth distance estimated by the depth distance estimation unit; A step in which a headlight control unit causes the headlight to irradiate the light onto the illumination range determined by the illumination determination unit. A headlight control method comprising:
Citation Information
Patent Citations
Vehicle lamp control method and device
CN108773317A
Driver'S face direction detector
JP2001347881A
Vehicular lamp control system
JP2009120148A