Dazzle warning device, dazzle warning system, and dazzle warning method

Abstract

To warn a driver in advance that the driver of a vehicle may be dazzled by reflected rays of sunlight.SOLUTION: A first vehicle information estimation unit 1 estimates first vehicle information including a driving route and driving state information of a target vehicle. An line-of-sight information estimation unit 2 estimates the transition of line-of-sight information including a driver's line-of-sight starting point area and reference vision. A sunlight ray calculation unit 3 calculates an irradiation direction of sunlight. A second vehicle information estimation unit 4 estimates second vehicle information including the driving route and driving state information of a vehicle of interest based on an image of the vehicle of interest, and identifies the type of the vehicle of interest. A reflective member identification unit 5 identifies an installation position and an angle of a reflective member of the vehicle of interest. A reflective ray estimation unit 6 estimates the reflective rays of light based on the direction of sunlight and other factors. A determination unit 7 determines whether the reflected rays of light enter the line-of-sight starting point area or not. A warning unit 8 issues a warning to the driver if the reflective rays enter the line-of-sight starting point area.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present disclosure relates to a glare warning device, a glare warning system, and a glare warning method. [Background technology]

[0002] Generally, a driver of a vehicle drives while viewing the outside of the vehicle through the windshield, door glass, etc. In this case, if the direction of the sun's rays and the line of sight are parallel or nearly parallel, the sun's rays may enter the driver's eyes and cause dazzle. Since dazzle caused by the sun's rays may cause improper driving operations, it is desirable to prevent the occurrence of dazzle.

[0003] Various methods for preventing dazzling of the driver of a vehicle have been proposed. For example, Patent Document 1 proposes a navigation device that can contribute to preventing accidents in the evening hours. This navigation device determines whether the vehicle is traveling in a westward direction when the vehicle is traveling before sunset. If the vehicle is traveling in a westward direction, the navigation device is set to a warning operation mode because there is a risk that the setting sun will be in the driver's eyes. In this way, the navigation device contributes to providing appropriate driving assistance to the driver in the evening hours. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2002-181554 A Summary of the Invention [Problem to be solved by the invention]

[0005] A driver of a vehicle can easily grasp the general position of the sun by observing the sunlight shining outside the vehicle. Even when it is difficult to grasp the position of the sun, the driver can know the incidence of the sunlight by, for example, the above-mentioned navigation device. In this case, the driver can take appropriate anti-glare measures, such as moving the line of sight away from the sunlight or using a shielding plate installed inside the vehicle.

[0006] On the other hand, it is also assumed that sunlight may be reflected by structures outside the vehicle or other vehicles and then indirectly enter the vehicle. However, while the vehicle is traveling, the positional relationship between the vehicle and the object that reflects the sunlight changes from moment to moment. Therefore, it is difficult for the driver to predict in advance that the driver may be dazzled by the sunlight that indirectly enters the vehicle. In particular, when the object that reflects the sunlight is another vehicle, it is even more difficult to predict in advance because the other vehicle may have various shapes and moves while traveling.

[0007] The present disclosure has been made in consideration of the above circumstances, and aims to warn a vehicle driver in advance that the driver may be dazzled by reflected sunlight. [Means for solving the problem]

[0008] A glare warning device according to the present disclosure includes a first vehicle information estimation unit that estimates first vehicle information including a first driving route of a first vehicle during an estimation target period between a first time and a second time in the future of the first time and information on the driving state of the first vehicle on the first driving route, a gaze information estimation unit that estimates a transition of gaze information during the estimation target period, the gaze information including a gaze origin area that is an area indicating an origin of the gaze of a driver driving the first vehicle and a reference field of view of the driver, a sunlight ray calculation unit that calculates a direction of sunlight from the sun during the estimation target period, and a second driving route of the second vehicle during the estimation target period and information on the driving state of the second vehicle on the second driving route based on an image captured of a second vehicle. a second vehicle information estimation unit that estimates second vehicle information including a direction of incidence of the sunlight and identifies a type of the second vehicle based on the image; a reflective member identification unit that identifies a reflective member of the second vehicle that reflects the sunlight in accordance with the identified type of the second vehicle and identifies an attachment position and angle of the reflective member on the second vehicle; a reflected light ray estimation unit that estimates a reflected light ray generated when the sunlight is reflected by the reflective member from the irradiation direction of the sunlight, the second vehicle information, and the attachment position and angle of the reflective member; a determination unit that determines whether the estimated reflected light ray will enter the gaze origin area through the reference field of view within the estimation target period; and a warning unit that issues a warning to the driver when the reflected light ray is entered into the gaze origin area.

[0009] A glare warning system according to the present disclosure includes an imaging device attached to a first vehicle and configured to capture an image of the outside of the first vehicle; a first vehicle information estimation unit configured to estimate first vehicle information including a first driving route of the first vehicle during an estimation target period between a first time and a second time in the future of the first time and information on a driving state of the first vehicle on the first driving route; a gaze information estimation unit configured to estimate a transition of gaze information during the estimation target period, the gaze information including a gaze origin area that is an area indicating an origin of the gaze of a driver driving the first vehicle and a reference field of view of the driver; a sunlight ray calculation unit configured to calculate an irradiation direction of sunlight rays from the sun during the estimation target period; and a second vehicle information estimation unit configured to estimate a second driving route of the second vehicle during the estimation target period and information on a driving state of the first vehicle on the first driving route based on an image of a second vehicle captured by the imaging device. a second vehicle information estimation unit that estimates second vehicle information including information on the driving state of the second vehicle on a driving route of the second vehicle and identifies a type of the second vehicle based on the image; a reflective member identification unit that identifies a reflective member of the second vehicle that reflects the sunlight in accordance with the identified type of the second vehicle and identifies an attachment position and angle of the reflective member on the second vehicle; a reflected light ray estimation unit that estimates a reflected light ray generated when the sunlight is reflected by the reflective member from the irradiation direction of the sunlight, the second vehicle information, and the attachment position and angle of the reflective member; a determination unit that determines whether the estimated reflected light ray will enter the gaze origin area through the reference field of view within the estimation target period; and a warning unit that issues a warning to the driver when the reflected light ray is entered into the gaze origin area.

[0010] A glare warning method according to the present disclosure estimates first vehicle information including a first driving route of a first vehicle during an estimation target period between a first time and a second time in the future of the first time, and information on a driving state of the first vehicle on the first driving route; estimates a transition of gaze information during the estimation target period, the gaze information including a gaze origin area that is an area indicating an origin of the gaze of a driver driving the first vehicle, and a reference field of view of the driver; calculates an irradiation direction of sunlight from the sun during the estimation target period; and calculates a second driving route of the second vehicle during the estimation target period and the driving state of the second vehicle on the second driving route based on an image captured of a second vehicle. and information on the state of the line of sight, identify a type of the second vehicle based on the image, identify a reflective member of the second vehicle that reflects the sunlight in accordance with the identified type of the second vehicle, identify an attachment position and angle of the reflective member on the second vehicle, estimate a reflected light ray generated when the sunlight is reflected by the reflective member from the irradiation direction of the sunlight, the second vehicle information, and the attachment position and angle of the reflective member, determine whether the estimated reflected light ray will enter the line of sight origin area through the reference field of view within the estimation target period, and if the reflected light ray is entered into the line of sight origin area, issue a warning to the driver. Effect of the Invention

[0011] According to the present disclosure, it is possible to warn a vehicle driver in advance that the driver may be dazzled by reflected sunlight. [Brief description of the drawings]

[0012] [Figure 1] 1 is a diagram illustrating a schematic configuration of a glare warning system according to a first embodiment. [Diagram 2] 1 is a diagram illustrating an example of a hardware configuration for realizing a glare warning device according to a first embodiment. [Diagram 3] 1 is an overhead view showing an overview of the incidence of reflected light from a target vehicle on a target vehicle. [Figure 4]1 is a side view showing an overview of the incidence of reflected light from a target vehicle on a target vehicle. [Diagram 5] 1 is a diagram illustrating a functional configuration of a glare warning device according to a first embodiment. FIG. [Figure 6] 4 is a flowchart of a dazzle warning operation of the dazzle warning device according to the first embodiment. [Figure 7] FIG. 2 is a diagram illustrating a schematic configuration of a first vehicle information estimation unit. [Figure 8] 6 is a flowchart of the operation of a first vehicle information estimation unit. [Figure 9] 11 is a diagram showing the relationship between the travel routes of a target vehicle and a vehicle of interest and travel state information. FIG. [Figure 10] 4 is a diagram illustrating a schematic configuration of a second vehicle information estimation unit. FIG. [Figure 11] 10 is a flowchart of the operation of a second vehicle information estimation unit. [Figure 12] FIG. 2 is a diagram showing an example of the appearance of a vehicle of interest. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the drawings, the same elements are given the same reference numerals, and duplicated explanations will be omitted as necessary.

[0014] First embodiment In this embodiment, a glare warning system 110 mounted on a vehicle to prevent a driver of the vehicle from being dazzled by reflected sunlight from outside the vehicle will be described. Fig. 1 shows a schematic configuration of the glare warning system 110 according to the first embodiment. The glare warning system 110 includes an imaging device such as a camera 101 capable of capturing an image of the surrounding environment outside the vehicle, and a glare warning device 100.

[0015] The camera 101 and the glare warning device 100 are communicatively connected by any communication means such as wired, wireless, or a combination of wired and wireless. Fig. 1 shows an example in which the camera 101 and the glare warning device 100 are communicatively connected via a cable 102.

[0016] Camera 101 captures images of the terrain, structures, other vehicles, pedestrians, etc., around the vehicle. The images captured by camera 101 include various images or video information of objects, such as moving images, still images, and frame-by-frame moving images consisting of a plurality of still images captured continuously at a predetermined time interval. Camera 101 is configured to be able to output the captured images to glare warning device 100 via cable 102.

[0017] The glare warning device 100 is configured to warn the driver in advance when there is a risk that sunlight reflected by another vehicle may indirectly enter the driver's eyes, and to encourage the driver to avoid glare. In the following, the vehicle on which the glare warning device 100 is mounted is referred to as the target vehicle V1, and the vehicle that reflects sunlight and produces reflected light rays is referred to as the target vehicle V2. The target vehicle is also referred to as the first vehicle, and the target vehicle is also referred to as the second vehicle.

[0018] FIG. 2 shows an example of a hardware configuration for implementing a glare warning device. The glare warning device can be implemented by a computer 1000, such as a dedicated computer or a personal computer (PC). However, the computer does not need to be physically single, and may be multiple when performing distributed processing. As shown in FIG. 2, the computer 1000 has a CPU (Central Processing Unit) 1001, a ROM (Read Only Memory) 1002, and a RAM (Random Access Memory) 1003, which are interconnected via a bus 1004. Note that an OS software for operating the computer will not be described, but it is assumed that the computer that constructs this network analysis system also has such software.

[0019] An input / output interface 1005 is also connected to the bus 1004. To the input / output interface 1005, for example, an input unit 1006 including a keyboard, a mouse, a sensor, etc., a display including a CRT, an LCD, etc., an output unit 1007 including a headphone, a speaker, etc., a storage unit 1008 including a hard disk, etc., and a communication unit 1009 including a modem, a terminal adapter, etc. are connected.

[0020] The CPU 1001 executes various processes in accordance with various programs stored in the ROM 1002 or various programs loaded from the storage unit 1008 to the RAM 1003, for example, in this embodiment, the processes of each part of the glare warning device described later. A GPU (Graphics Processing Unit) may be provided to execute various processes in accordance with various programs stored in the ROM 1002 or various programs loaded from the storage unit 1008 to the RAM 1003, similarly to the CPU 1001, for example, the processes of each part of the glare warning device in this embodiment. The GPU is suitable for performing typical processes in parallel, and can improve the processing speed compared to the CPU 1001 by applying it to processing in a neural network, for example. The RAM 1003 also stores data necessary for the CPU 1001 and the GPU to execute various processes as appropriate.

[0021] The communication unit 1009 performs communication processing, for example, via the Internet (not shown), transmits data provided by the CPU 1001, and outputs data received from a communication partner to the CPU 1001, RAM 1003, and storage unit 1008. The storage unit 1008 exchanges information with the CPU 1001 and stores and erases information. The communication unit 1009 also performs communication processing of analog or digital signals with other devices.

[0022] The input / output interface 1005 is also connected to a drive 1010 as necessary, and, for example, a magnetic disk 1011, an optical disk 1012, a flexible disk 1013, or a semiconductor memory 1014 is appropriately attached, and computer programs read from them are installed in the memory unit 1008 as necessary.

[0023] Next, the incidence of reflected light from the target vehicle V2 on the target vehicle V1 will be considered. FIG. 3 shows an overhead view illustrating an overview of the incidence of reflected light from the target vehicle V2 on the target vehicle V1. FIG. 4 shows a side view illustrating an overview of the incidence of reflected light from the target vehicle V2 on the target vehicle V1. FIG. 3 and FIG. 4 show an example in which the target vehicle V1 and the target vehicle V2 are traveling opposite each other on a one-lane road. An example is assumed in which sunlight ray SL is irradiated from diagonally above the target vehicle V2, the sunlight ray SL is reflected by a highly reflective member on the front of the target vehicle V2, and the reflected light ray RL travels toward the target vehicle V1.

[0024] In this case, if the reflected light ray RL enters the driver's eyes, the driver may be dazzled. To prevent this, the glare warning system 110 estimates the path of the reflected light ray RL and estimates whether the reflected light ray RL will enter the driver's eyes.

[0025] Next, the position of the driver's eyes will be considered. When the driver sits in the driver's seat of the target vehicle V1 and drives, the position of the driver's eyes is expected to fall within a predetermined range, even taking into account individual differences such as physique. Therefore, the gaze origin area A, which indicates the variation in the eye position when the driver looks forward outside the vehicle through the windshield, in other words the variation in the origin of the gaze, also falls within a predetermined range. The gaze origin area A can be determined in advance as a predetermined range by, for example, conducting a survey. Hereinafter, the gaze origin area A is set within a plane perpendicular to the gaze direction when the driver faces forward horizontally to the bottom surface of the vehicle body.

[0026] In addition, when the driver faces forward while driving the target vehicle V1, the driver's field of view centered on the line of sight can be predicted. Although the driver's field of view is limited by being blocked by the vehicle body, it is expected that it will not vary significantly even if the driver is different. Therefore, in this embodiment, a constant field of view that is independent of the driver is assumed. At this time, when the variation in eye position due to the difference in the driver is taken into consideration, the variation in eye position can be added to the assumed constant field of view to set the driver's reference field of view ES.

[0027] The reference visual field ES can be defined as a range of any shape within a predetermined angle range from the driver's line of sight origin area A. For example, the reference visual field ES is defined as a region of a shape such as a rectangle or a circle, which is expressed by the range of elevation / depression angles and azimuth angles in three-dimensional polar coordinates. However, the method of defining the visual field is not limited to this, and various definition methods may be applied.

[0028] Here, an example in which the gaze origin area A is determined in advance has been described, but for example, if the target vehicle V1 is equipped with a camera or the like that is installed so that the driver's state can be observed, the gaze origin area A may be determined based on an image capturing the driver's eyes. Also, the movement of the driver's eyes may be detected based on an image capturing the driver, and the reference visual field ES may be determined based on the detection result.

[0029] Next, a description will be given of the glare warning device 100. Fig. 5 shows a schematic functional configuration of the glare warning device 100 according to the first embodiment. The glare warning device 100 has a first vehicle information estimation unit 1, a line of sight information estimation unit 2, a sunlight ray calculation unit 3, a second vehicle information estimation unit 4, a reflective member identification unit 5, a reflected light ray estimation unit 6, a determination unit 7, and a warning unit 8.

[0030] Each component of the dazzle warning device 100 will be described together with the flow of the dazzle warning operation of the dazzle warning device 100. In order to predict in advance a situation in which the driver will be dazzled, the dazzle warning device 100 estimates whether or not the driver is likely to be dazzled in an estimated target period ΔT, which is a period from the present time to a predetermined time in the future. In the following, the position of the target vehicle V1 at the present time, which is the start time of the warning issuing operation performed by the dazzle warning device 100, is defined as P1, and the position of the noted vehicle V2 is defined as P2. Fig. 6 shows a flowchart of the dazzle warning operation of the dazzle warning device 100. The dazzle warning operation of the dazzle warning device 100 includes steps ST1 to ST8, which will be described below.

[0031] Step ST1 The first vehicle information estimation unit 1 estimates vehicle information INF1 including a travel route R1 of the target vehicle V1 in an estimation target period ΔT and travel state information WS1 indicating the travel state of the target vehicle V1 on the travel route R1. Hereinafter, the travel route R1 is also referred to as a first travel route. The travel state information WS1 is also referred to as information on the travel state of the first vehicle. The vehicle information INF1 is also referred to as first vehicle information. Hereinafter, step ST1 will be specifically described.

[0032] Fig. 7 shows a schematic configuration of the first vehicle information estimation unit 1. The first vehicle information estimation unit 1 has a position identification unit 11, a traveling state acquisition unit 12, and an estimation unit 13. Below, each unit of the first vehicle information estimation unit 1 will be described together with the operation flow of the first vehicle information estimation unit 1. Fig. 8 shows a flowchart of the operation of the first vehicle information estimation unit 1. Step ST1 includes the following steps ST11 to ST13.

[0033] Step ST11 The position identification unit 11 identifies the current position P1 of the target vehicle V1. The position identification unit 11 can identify the current position P1 of the target vehicle V1 by using, for example, a car navigation system or a global positioning system (GPS). However, the method by which the position identification unit 11 identifies the current position P1 of the target vehicle V1 is not limited to these, and various position identification methods may be used.

[0034] Step ST12 The driving state acquisition unit 12 acquires current driving state information of the target vehicle V1 at the specified current position P1 of the target vehicle V1. Here, the driving state information may include an azimuth angle indicating the direction of the target vehicle V1, a driving speed, an acceleration, a pitch angle which is a tilt angle in the up-down direction, and a roll angle which is a tilt angle in the left-right direction.

[0035] Step ST13 The estimation unit 13 estimates a travel route R1 of the target vehicle V1 during the estimation target period ΔT from the current position P1 of the target vehicle V1 and the travel state information. Fig. 9 shows the relationship between the travel routes of the target vehicle V1 and the attention vehicle V2 and the travel state information.

[0036] For example, the estimation unit 13 may estimate the travel route R1 of the target vehicle V1 by extrapolating the position of the target vehicle V1 on the time axis of the estimation target period ΔT from the current position P1 of the target vehicle V1 and the travel state information. Also, for example, the estimation unit 13 may identify the road on which the target vehicle V1 is traveling from map information included in a car navigation system, and estimate the travel route R1 along the path of the identified road. Furthermore, for example, when the estimation unit 3 can detect the steering or operation of the turn signal of the target vehicle V1, it may change the road applied to the estimation of the travel route R1 according to the detection result.

[0037] In addition, the estimation unit 13 estimates driving state information WS1 of the target vehicle V1 along the driving route R1 during the estimation target period ΔT from the driving route R1 and the driving state information. For example, the estimation unit 13 may obtain information such as the extension direction of the road and the inclination angle of the ground from map information included in a car navigation system, and estimate the driving state information WS1 using the obtained information.

[0038] Step ST2 The gaze information estimation unit 2 analyzes the shift in the driver's gaze when the target vehicle V1 travels along the travel route R1. Since the gaze origin area A and the reference visual field ES are fixed in position and range with respect to the target vehicle V1, the gaze information estimation unit 2 can estimate gaze information indicating the shift in the gaze origin area A and the reference visual field ES along the travel route R1 during the estimation target period ΔT. The gaze origin area A and the reference visual field ES may be held in advance by the gaze information estimation unit 2. In addition, the gaze origin area A and the reference visual field ES may be stored in a storage device (not shown) inside or outside the glare warning device 100, and the gaze information estimation unit 2 may read them as necessary.

[0039] Step ST3 The solar ray calculation unit 3 calculates the azimuth angle and solar altitude of the sun from the date and time and the current position P1 of the target vehicle V1. The solar ray estimation unit 3 then calculates the irradiation direction of the sun's rays during the estimation target period ΔT based on the azimuth angle and solar altitude of the sun. The astronomical information used to calculate the azimuth angle and solar altitude of the sun can be data and calculation methods provided by various organizations such as the National Astronomical Observatory, as appropriate.

[0040] Step ST4 The second vehicle information estimation unit 4 estimates vehicle information INF2 including a travel route R2 of the target vehicle V2 during the estimation target period ΔT and travel state information WS2 of the target vehicle V2 on the travel route R2. Hereinafter, the travel route R2 is also referred to as the second travel route. The travel state information WS2 is also referred to as information on the travel state of the second vehicle. The vehicle information INF2 is also referred to as the second vehicle information. Step ST4 will be specifically described below.

[0041] Fig. 10 shows a schematic configuration of the second vehicle information estimation unit 4. The second vehicle information estimation unit 4 has a vehicle detection unit 41, a position identification unit 42, a traveling state acquisition unit 43, an estimation unit 44, and a vehicle identification unit 45. Each unit of the second vehicle information estimation unit 4 will be described below together with the operation flow of the first vehicle information estimation unit 4. Fig. 11 shows a flowchart of the operation of the second vehicle information estimation unit 4. Step ST4 includes the following steps ST41 to ST45.

[0042] Step ST41 The vehicle detection unit 41 detects a target vehicle V2 that is within the driver's reference field of view ES from an image captured by the camera 101 provided on the target vehicle V1. When the image includes multiple vehicles, the vehicle detection unit 41 detects each of the multiple vehicles as the target vehicle V2. When multiple target vehicles are detected, the glare warning device 100 performs the same process for each target vehicle.

[0043] Step ST42 The position identifying unit 42 identifies the current position P2 of the attention vehicle V2 from the image captured by the camera 101. The position identifying unit 42 may identify the current position P2 of the attention vehicle V2, for example, by identifying the distance and direction of the attention vehicle V2 relative to the target vehicle V1 and comparing the identified distance and direction with map information included in a car navigation system. However, the method by which the position identifying unit 42 identifies the position of the attention vehicle V2 is not limited to these, and various position identifying methods may be used.

[0044] Step ST43 The running state acquisition unit 43 acquires the current running state information of the attention vehicle V2 from the moving image captured by the camera 101. The information included in the running state information of the attention vehicle V2 is similar to the information included in the running state information of the target vehicle V1, so a duplicated description will be omitted.

[0045] Step ST44 The estimation unit 44 estimates a travel route R2 of the target vehicle V2 during the estimation target period ΔT from the current position P2 of the target vehicle V2 and the travel state information. The estimation of the travel route R2 is similar to the estimation of the travel route R1, so a duplicated explanation will be omitted. In addition, the estimation unit 44 estimates travel state information WS2 of the target vehicle V2 along the travel route R2 from the travel route R2 and the travel state information.

[0046] Step ST45 The vehicle identification unit 45 identifies the type of the attention vehicle V2 from the image captured by the camera 101. The vehicle identification unit 45 may, for example, hold in advance vehicle identification information indicating the correspondence between vehicle features and types. The vehicle identification unit 45 compares the features extracted from the attention vehicle V2 with the vehicle features included in the vehicle identification information, and determines which type of vehicle has the same or similar features included in the vehicle identification information, thereby identifying the type of the attention vehicle V2. The vehicle identification information may be stored in a storage device (not shown) inside or outside the glare warning device 100, and may be read by the vehicle identification unit 45 as necessary.

[0047] The vehicle identification information may store, for example, information on vehicle models for each automobile manufacturer. Also, representative vehicle form models may be stored for each type, such as compact cars, sedans, minivans, and large vehicles. In this case, when the vehicle identification unit 45 cannot determine the specific vehicle model of the attention vehicle V2, it may determine whether the vehicle matches any of these form models to identify the type of the attention vehicle V2.

[0048] The vehicle identification unit 45 may identify the type of the target vehicle V2 based on, for example, machine learning. In this case, a trained model can be constructed by performing supervised learning using an image of the target vehicle V2 as input data and the type of the vehicle as teacher data. The vehicle identification unit 45 may then input an image of the target vehicle V2 or features of the target vehicle V2 to this trained model, thereby identifying the target vehicle V2 from the type estimation result of the vehicle identification unit 45.

[0049] Step ST5 Based on the identification result of the target vehicle V2, the reflective member identification unit 5 refers to the reflective member information indicating the correspondence between the type of the vehicle and the reflective member appearing on the exterior, and identifies the reflective member that reflects the sunlight in the target vehicle V2. The reflective member information includes information indicating the mounting position and angle of the reflective member that reflects the sunlight on the windshield, window glass, each part of the vehicle body, etc., for each type of vehicle. In this way, the reflective member identification unit 5 obtains information indicating the mounting position and angle of each reflective member of the target vehicle V2. The reflective member identification unit 5 can identify one or more reflective members from one target vehicle V2, but for the sake of simplicity of explanation, the following description focuses on one reflective member. The reflective member information may be held in advance by the reflective member identification unit 5. The reflective member information may be stored in a storage device (not shown) inside or outside the glare warning device 100, and the reflective member identification unit 5 may read it as necessary.

[0050] Step ST6 The reflected light ray estimation unit 6 estimates the progression of the reflected light ray RL generated by the sunlight ray SL being reflected by the identified reflective member during the estimation target period ΔT based on the irradiation direction of the sunlight's rays, the driving route R2 of the target vehicle V2, the driving state information WS2, and the attachment position and angle of the reflective member.

[0051] Step ST7 The determination unit 7 determines whether the estimated reflected light ray RL is incident on the gaze origin area A through the driver's reference visual field ES during the estimation target period ΔT. The determination unit 7 may perform a determination process for each of a plurality of times set at any interval within the estimation target period ΔT, and determine whether the reflected light ray RL is incident on the gaze origin area A at one or more timings.

[0052] Step ST8 If the reflected light RL enters the gaze origin area A during the estimation target period ΔT, the reflected light RL may enter the driver's eyes and dazzle the driver. Therefore, in this case, the warning unit 8 issues a warning by voice or the like to notify the driver that the reflected light RL may dazzle the driver.

[0053] At this time, the warning unit 8 may not only notify the driver of the presence of the reflected light RL, but also notify the driver of other information. For example, the warning unit 8 may notify the driver of the incident direction of the reflected light RL, or may recommend the driver to avert his / her gaze from the reflected light RL. The warning unit 8 may notify the driver of the timing when the reflected light RL enters the driver's eyes. In this case, the driver can easily avoid dazzle by following the warning.

[0054] According to the present configuration, when there is a risk that the reflected light generated by the sunlight shining on another vehicle may enter the driver's eyes, a warning can be issued to the driver in advance. This allows the driver to avoid being dazzled by the reflected light in advance in response to the warning.

[0055] Embodiment 2 In the first embodiment, the reflective member identification unit 5 identifies the reflective member by reading information on the reflective member from the reflective member information according to the type of the noted vehicle V2. However, depending on the noted vehicle V2, in addition to the standard accessories, it is assumed that retrofit members such as optional items are attached to the vehicle body according to necessity or user preference.

[0056] Fig. 12 shows an example of the appearance of a target vehicle V2. In Fig. 12, a reflective member OP is attached to the rear surface of a large vehicle having a box-shaped cargo bed. In this way, when a retrofit member OP is attached to the vehicle body, the reflective member identification unit 5 cannot identify the member OP as a reflective member by simply comparing the target vehicle V2 with the vehicle appearance information included in the reflective member information.

[0057] In such a case, the reflective member identification unit 5 may detect a reflective member not included in the reflective member information based on an image of the noted vehicle V2. For example, the reflective member identification unit 5 may have a trained model that has previously learned reflective members that may be attached to a vehicle body by machine learning, and may input an image of the noted vehicle V2 to be estimated to the trained model to identify the member of the noted vehicle V2 that is not included in the reflective member information as a reflective member.

[0058] Furthermore, candidate component information may be prepared in advance, in which information indicating the size, position, and mounting angle of a component that is a candidate for a component to be added later is stored, separate from the reflective component information. The reflective component identification unit 5 may identify a component of the noted vehicle V2 that is not included in the reflective component information as a reflective component by comparing an image of the noted vehicle V2 or features of the noted vehicle V2 with the candidate component information.

[0059] According to this configuration, the components of the target vehicle V2 that are not included in the reflective member information can be suitably identified as reflective members, and a warning can be issued in response to the reflected light from a wider variety of reflective members attached to the target vehicle V2.

[0060] Other embodiments The present invention is not limited to the above embodiment, and can be modified as appropriate without departing from the spirit of the present invention. For example, the reflected light estimating unit may use map information to detect whether the sunlight is blocked by the surrounding topography or buildings, and use this information to estimate the reflected light. This can prevent unnecessary warnings from being issued and improve the accuracy of warning issuance.

[0061] In addition, if the target vehicle is equipped with a sensor that detects the brightness of the surrounding environment, a warning may be issued according to the brightness of the surrounding environment. For example, a stronger warning may be issued when the target vehicle is located in a dark place, such as hidden in the shadow of a building, and there is a risk of reflected light entering the target vehicle. For example, a stronger warning may be issued when the target vehicle is estimated to leave the shadow of a building and come out into a bright place, and there is a risk of reflected light entering the target vehicle.

[0062] The processes executed by the glare warning device according to the above-described embodiments may be realized by using a semiconductor processing device including an ASIC (Application Specific Integrated Circuit). These processes may also be realized by having a computer system including at least one processor (e.g., a microprocessor, a CPU, a GPU, an MPU, a DSP (Digital Signal Processor)) execute a program. Specifically, one or more programs including a set of instructions for causing a computer system to execute algorithms related to these transmission signal processing or reception signal processing may be created, and the program may be supplied to a computer.

[0063] These programs can be stored and provided to a computer using various types of non-transitory computer readable media. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROM (Read Only Memory), CD-R, CD-R / W, and semiconductor memory (e.g., mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (random access memory)). The programs may also be provided to a computer by various types of transitory computer readable media. Examples of transitory computer readable media include electric signals, optical signals, and electromagnetic waves. The transitory computer readable media can provide the programs to a computer via a wired communication path such as an electric wire and an optical fiber, or via a wireless communication path. [Explanation of symbols]

[0064] 1. First vehicle information estimation unit 2 Gaze information estimation section 3. Solar radiation calculation section 4. Second vehicle information estimation unit 5 Reflective material identification section 6 Reflected ray estimation part 7 Judgment section 8 Warning part 11, 42 Position identification part 12, 43 Driving condition acquisition unit 13, 44 Estimation part 41 Vehicle detection unit 44 Estimation part 45 Vehicle Identification Department 100 Dazzle warning device 101 Camera 102 Cable 110 Dazzle Warning System 1000 Computers 1000 Dazzle Warning System 1004 Bus 1005 Input / Output Interface 1006 Input section 1007 Output section 1008 Storage section 1009 Communications Department 1010 Drive 1011 Magnetic disk 1012 Optical disc 1013 Flexible Disk 1014 Semiconductor memory A Gaze starting area ES standard field of view INF1, INF2 vehicle information OP parts R1, R2 driving route RL reflected ray SL Sunbeam V1 Target vehicle V2 Featured Vehicles WS1, WS2 driving status information

Claims

1. a first vehicle information estimation unit that estimates first vehicle information including a first travel route of a first vehicle in an estimation target period between a first time point and a second time point that is future than the first time point and information on a travel state of the first vehicle on the first travel route; a gaze information estimation unit that estimates a transition of gaze information including a gaze origin area, which is an area indicating an origin of a gaze of a driver who drives the first vehicle, and a reference visual field of the driver, during the estimation target period; a sunbeam calculation unit for calculating a direction of irradiation of a sunbeam from the sun during the estimation target period; a second vehicle information estimation unit that estimates second vehicle information including a second driving route of the second vehicle during the estimation target period and information on a driving state of the second vehicle on the second driving route based on an image captured of a second vehicle, and identifies a type of the second vehicle based on the image; a reflecting member identification unit that identifies a reflecting member of the second vehicle that reflects the sunlight according to the identified type of the second vehicle, and identifies an attachment position and an attachment angle of the reflecting member on the second vehicle; a reflected light ray estimation unit that estimates a reflected light ray generated when the sunlight is reflected by the reflecting member based on the irradiation direction of the sunlight, the second vehicle information, and the attachment position and angle of the reflecting member; a determination unit that determines whether or not the estimated reflected light ray is incident on the gaze origin area through the reference visual field within the estimation target period; A warning unit that issues a warning to the driver when the reflected light beam is incident on the line of sight origin area. Dazzle warning device.

2. The gaze origin area is determined based on the variation in eye position due to the difference in the driver, or is determined based on an image capturing the driver's eyes, The reference field of view is determined based on the eye movement of the driver detected based on the image of the driver. The glare warning device of claim 1.

3. The reflective member specifying unit is identifying the reflective member by comparing the second vehicle in the captured image with reflective member information indicating a correspondence between a vehicle type and a reflective member appearing on an exterior of the vehicle; When the second vehicle in the image captured of the second vehicle has a member that is not included in the vehicle appearance information of the reflective member information, By comparing the second vehicle in the image captured of the second vehicle with candidate member information including information indicating a candidate member of the reflective member that is not included in the reflective member information, or An image of the second vehicle or a feature of the second vehicle is input to a trained model that has previously trained a reflective member attached to a vehicle, Identifying the reflective member; A glare warning device according to claim 1 or 2.

4. an imaging device attached to a first vehicle and configured to capture an image of an area outside the first vehicle; a first vehicle information estimation unit that estimates first vehicle information including a first travel route of the first vehicle in an estimation target period between a first time point and a second time point that is future than the first time point and information on a travel state of the first vehicle on the first travel route; a gaze information estimation unit that estimates a transition of gaze information including a gaze origin area, which is an area indicating an origin of a gaze of a driver who drives the first vehicle, and a reference visual field of the driver, during the estimation target period; a sunbeam calculation unit for calculating a direction of irradiation of a sunbeam from the sun during the estimation target period; a second vehicle information estimation unit that estimates second vehicle information including a second travel route of the second vehicle during the estimation target period and information on a travel state of the second vehicle on the second travel route based on an image of the second vehicle captured by the imaging device, and identifies a type of the second vehicle based on the image; a reflecting member identification unit that identifies a reflecting member of the second vehicle that reflects the sunlight according to the identified type of the second vehicle, and identifies an attachment position and an attachment angle of the reflecting member on the second vehicle; a reflected light ray estimation unit that estimates a reflected light ray generated when the sunlight is reflected by the reflecting member based on the irradiation direction of the sunlight, the second vehicle information, and the attachment position and angle of the reflecting member; a determination unit that determines whether or not the estimated reflected light ray is incident on the gaze origin area through the reference visual field within the estimation target period; A warning unit that issues a warning to the driver when the reflected light beam is incident on the line of sight origin area. Dazzle warning system.

5. Estimating first vehicle information including a first travel route of a first vehicle in an estimation target period between a first time and a second time in the future of the first time, and information on a travel state of the first vehicle on the first travel route; Estimating a transition of gaze information including a gaze origin area, which is an area indicating a gaze origin of a driver who drives the first vehicle, and a reference visual field of the driver, during the estimation target period; Calculating the direction of sunlight from the sun during the estimation target period; estimating second vehicle information including a second travel route of the second vehicle during the estimation target period and information on a travel state of the second vehicle on the second travel route based on an image of a second vehicle, and identifying a type of the second vehicle based on the image; Identifying a reflective member of the second vehicle that reflects the sunlight according to the identified type of the second vehicle, and identifying an attachment position and an attachment angle of the reflective member on the second vehicle; estimating a reflected light beam generated when the sunlight is reflected by the reflecting member from the irradiation direction of the sunlight, the second vehicle information, and the mounting position and angle of the reflecting member; determining whether or not the estimated reflected light ray is incident on the gaze origin area through the reference visual field within the estimation target period; When the reflected light is incident on the gaze origin area, a warning is issued to the driver. Dazzle warning method.

Images