Target recognition device

Abstract

To effectively improve recognition accuracy of a target.SOLUTION: A target recognition device includes: a camera 42 configured to capture a front of a vehicle VH; and a target recognition part 110 configured to calculate a reliability index of a target recognition of a target in an image captured by the camera 42, while recognizing the target as a truly existing target when the reliability index thus calculated exceeds a prescribed reliability threshold value. The target recognition device further includes: a light distribution control part 100 configured to shield or dim part of irradiation light emitted from a head lamp 60 according to the target existing in front of the vehicle VH, so as to control light distribution of the head lamp 60 by a light distribution pattern including an irradiation region and a light control region; and reliability threshold change part 120 configured to change, if the target in the image does not exist within the irradiation region, the reliability threshold value to a smaller value than a value when the target exists in the irradiation region.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to an object recognition device, and particularly to a technology suitable for recognizing an object in front of a vehicle.

Background Art

[0002] For example, Patent Document 1 discloses a technology for enabling appropriate object recognition even in the low-beam state by changing a correction threshold value of a pixel value used for image recognition processing depending on whether the headlight is in the low-beam state or the high-beam state in an in-vehicle image processing device.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0004] For example, in a vehicle equipped with a system that switches between a high-beam state and a low-beam state partially, such as an Adaptive High-beam System (AHS), the irradiation area of the headlight is always variable in each of the high-beam state and the low-beam state. Therefore, simply changing the correction threshold value of the pixel value based on whether the headlight is in the low-beam state or the high-beam state as in the device described in Patent Document 1 does not appropriately perform the correction process, and there is a possibility of false detection or non-detection of an object.

[0005] The technology of the present disclosure has been made in view of the above circumstances, and an object thereof is to effectively improve the recognition accuracy of an object.

[0006] The object recognition device of the present disclosure is imaging means for imaging a predetermined range in front of the vehicle, Calculating a reliability index for target recognition of a target in an image captured by the imaging means, and when the calculated reliability index is equal to or greater than a predetermined reliability threshold, recognizing the target as an actually existing target; a target recognition device comprising: Based on the presence information of a target existing in front of the vehicle, by blocking or reducing the intensity of a part of the irradiation light emitted from the headlamp provided in the vehicle, a light distribution pattern including an irradiation area for irradiating the irradiation light and a dimming area for blocking or reducing the intensity of the irradiation light is used to control the light distribution of the headlamp; a light distribution control means When the target in the image does not exist in the irradiation area, a reliability threshold changing means for changing the reliability threshold to a smaller value compared to the case where the target exists in the irradiation area; characterized by the above.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Embodiments for Carrying Out the Invention

[0008] Hereinafter, a target recognition device according to the present embodiment will be described with reference to the drawings.

[0009] [Hardware Configuration] FIG. 1 is a schematic diagram showing the hardware configuration of a vehicle VH according to the present embodiment. Hereinafter, when it is necessary to distinguish the vehicle VH from other vehicles or the like, it may be referred to as the host vehicle.

[0010] The vehicle VH has an ECU (Electronic Control Unit) 10. The ECU 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, an interface device 14, etc. The CPU 11 is a processor that executes various programs stored in the ROM 12. The ROM 12 is a non-volatile memory that stores data and the like necessary for the CPU 11 to execute various programs. The RAM 13 is a volatile memory that provides a working area where various programs are expanded when executed by the CPU 11. The interface device 14 is a communication device for communicating with external devices.

[0011] The ECU 10 is a central device that performs driving assistance control such as collision avoidance control (Pre-Crash Safety Control: hereinafter, PCS control). The driving assistance control is a concept that includes automatic driving control. Connected to the ECU 10 in a communicable manner are a driving device 20, a steering device 21, a braking device 22, an in-vehicle sensor device 30, an external sensor device 40, a cornering light sensor 50, a left headlight 60L, a right headlight 60R, an HMI (Human Machine Interface) 70, etc.

[0012] The driving device 20 generates a driving force to be transmitted to the drive wheels of the vehicle VH. Examples of the driving device 20 include an electric motor and an engine. In the present implementation device, the vehicle VH may be any of a hybrid vehicle (HEV), a plug-in hybrid vehicle (PHEV), a fuel cell vehicle (FCEV), a battery electric vehicle (BEV), and an engine vehicle. The steering device 21 applies a steering force to the wheels of the vehicle VH. The braking device 22 applies a braking force to the wheels of the vehicle VH.

[0013] The in-vehicle sensor device 30 is sensors that acquire the state of the vehicle VH. The in-vehicle sensor device 30 includes a vehicle speed sensor 31, an accelerator sensor 32, a brake sensor 33, a steering angle sensor 34, a steering torque sensor 35, a yaw rate sensor 36, etc.

[0014] The vehicle speed sensor 31 detects the traveling speed (vehicle speed V) of the vehicle VH. The accelerator sensor 32 detects the operation amount of an accelerator pedal (not shown) by the driver. The brake sensor 33 detects the operation amount of a brake pedal (not shown) by the driver. The steering angle sensor 34 detects the rotation angle (steering angle) of a steering wheel or a steering shaft (not shown). The steering torque sensor 35 detects the rotational torque (steering torque) of a steering wheel or a steering shaft (not shown). The yaw rate sensor 36 detects the yaw rate of the vehicle VH. The in-vehicle sensor device 30 transmits the state of the vehicle VH detected by each of the sensors 31 to 36 to the ECU 10 at a predetermined cycle.

[0015] The external sensor device 40 is sensors that recognize target information regarding targets around the vehicle VH. Specifically, the external sensor device 40 includes a radar sensor 41, a camera 42, and the like. Here, examples of the target information include surrounding vehicles, pedestrians, traffic lights, white lines on the road, signs, and the like.

[0016] The radar sensor 41 detects targets existing around the vehicle VH. The radar sensor 41 includes a millimeter-wave radar and / or a lidar. The millimeter-wave radar emits radio waves (millimeter waves) in the millimeter-wave band and receives the millimeter waves (reflected waves) reflected by the targets existing within the emission range. The millimeter-wave radar obtains the relative distance between the vehicle VH and the target, the relative speed between the vehicle VH and the target, etc. based on the phase difference between the transmitted millimeter waves and the received reflected waves, the attenuation level of the reflected waves, the time from transmitting the millimeter waves to receiving the reflected waves, etc. The lidar sequentially scans pulsed laser light with a shorter wavelength than millimeter waves in a plurality of directions, and receives the reflected light reflected by the target, thereby obtaining the shape of the target detected in front of the vehicle VH, the relative distance between the vehicle VH and the target, the relative speed between the vehicle VH and the target, etc. The camera 42 is the imaging means of the present disclosure, and obtains target information in front of the vehicle VH by imaging the front of the vehicle VH. As the camera 42, for example, a digital camera having an imaging element such as a CMOS or a CCD can be used. The external sensor device 40 repeatedly transmits the target information obtained by the radar sensor 41 and the camera 42 to the ECU 10 every time a predetermined time elapses.

[0017] The conlite sensor (illuminance sensor) 50 is a sensor that detects the illuminance of light. The conlite sensor 50 is mounted on the vehicle VH so as to be able to detect the illuminance around the vehicle VH. The conlite sensor 50 transmits the detected illuminance information to the ECU 10 at a predetermined period.

[0018] The left front headlight 60L and the right front headlight 60R irradiate irradiation light toward the front of the vehicle VH. Here, the front of the vehicle VH is a concept that includes not only the front direction but also the left front diagonal direction and the right front diagonal direction. The left front headlight 60L is provided on the left side of the front part of the vehicle VH. The right front headlight 60R is provided on the right side of the front part of the vehicle VH. Note that the left front headlight 60L and the right front headlight 60R are basically configured substantially the same and are mirror images of each other. Therefore, hereinafter, when there is no need to distinguish between the left front headlight 60L and the right front headlight 60R, they are simply referred to as "headlight 60".

[0019] The headlamp 60 includes a low beam headlamp and a high beam headlamp. The low beam headlamp irradiates low beam illumination light onto the front area of the vehicle VH. The high beam headlamp irradiates high beam illumination light onto a wider area in front of the vehicle VH than the low beam illumination light. The headlamp 60 turns on or off in response to an instruction signal transmitted from the ECU 10 according to an operation of an operation device (not shown) by the driver. Also, when the operation device (not shown) is operated to the automatic position, the headlamp 60 turns on or off in response to an instruction signal transmitted from the ECU 10 based on the illuminance information acquired by the ambient light sensor 50.

[0020] The headlamp 60 is an AHS-compatible headlamp and has a function of blocking a part of the irradiation area by high beam irradiation according to the position of a dimming target object (for example, a preceding vehicle, an oncoming vehicle, a pedestrian, a sign, etc.) acquired by the external sensor device 40. In the present disclosure, blocking includes the concept of reducing light. Examples of the headlamp having such a function include those provided with a plurality of LEDs (Light Emitting Diodes) arranged in a matrix, or those provided with a DMD (Digital Mirror Device) composed of a plurality of micro mirror elements arranged in a matrix, or those provided with a MEMS (Micro Electro Mechanical Systems) mirror. Since the configurations of these headlamps are well-known, detailed descriptions thereof are omitted.

[0021] The HMI 70 is an interface for inputting and outputting information between the ECU 10 and the driver, and includes an input device and an output device. Examples of the input device include a touch panel, a switch, a voice pickup microphone, etc. Examples of the output device include a display device 71, a speaker 72, etc. The display device 71 is, for example, a center display, a multi-information display, a head-up display, etc. The speaker 72 is, for example, a speaker of an audio system or a navigation system.

[0022] [Software Configuration] FIG. 2 is a schematic diagram showing the software configuration of the ECU 10 according to the present embodiment. As shown in FIG. 2, the ECU 10 includes, as functional elements, a light distribution control unit 100, a target recognition unit 110, a reliability threshold correction unit 120, a PCS control unit 130, and the like. Each of these functional elements 100 to 130 is realized by the CPU 11 of the ECU 10 reading out a program stored in the ROM 12 and executing it in the RAM 13. Note that all or part of each of the functional elements 100 to 130 can also be provided in another ECU separate from the ECU 10 or an information processing device of a facility (such as a management center) capable of communicating with the vehicle VH.

[0023] The light distribution control unit 100 is the light distribution control means of the present disclosure. It acquires the position of the dimming target object based on the detection result of the external sensor device 40, and performs light distribution control to shield or dim a part of the irradiation area by high beam irradiation according to the position of the acquired dimming target object. Examples of the dimming target object include a preceding vehicle, an oncoming vehicle, the face of a pedestrian, a road sign, and the like. By shielding or dimming the position of the preceding vehicle or oncoming vehicle or the face of the pedestrian, it becomes possible to prevent the driver of the preceding vehicle or oncoming vehicle or the pedestrian from being dazzled by glare. Also, by shielding or dimming the position of a retroreflective object such as a road sign, it becomes possible to prevent the driver of the own vehicle VH from being dazzled by the reflected light from the retroreflective object.

[0024] FIG. 3 shows an example of the light distribution pattern of the high beam irradiation light emitted from the headlamp 60. Note that the light distribution pattern shown in FIG. 3 is the combined irradiation light of the left headlamp 60L and the right headlamp 60R. The area surrounded by the dashed line X in the figure indicates the irradiation area by the high beam irradiation of the headlamp 60. In addition, the area surrounded by the dashed line Y in the figure is an example of the imaging range of the camera 42. Based on the detection result of the external sensor device 40, when the headlamp control unit 100 acquires, for example, the oncoming vehicle VH2 as the dimming target object, the headlamp 60 irradiates the high beam with a light distribution pattern in which the area corresponding to the position of the oncoming vehicle VH2 is shielded or dimmed. Hereinafter, the area irradiated with the high beam by the headlamp 60 is referred to as the "headlamp irradiation area A". In addition, the area where the high beam of the headlamp 60 is not irradiated (including the shielded or dimmed area) is referred to as the "headlamp non-irradiation area B".

[0025] The object recognition unit 110 is the object recognition means of the present disclosure, and recognizes an object existing in front of the vehicle VH based on the image data transmitted from the camera 42 of the external sensor device 40. Specifically, the object recognition unit 110 calculates the reliability DR of the object based on the sharpness of the contour of the object included in the image data captured by the camera 42, the degree of coincidence with the feature points of the registered image pattern, and the like. The reliability DR is an index indicating the probability that the object actually exists. When the reliability DR is small, the possibility that the object actually exists is low, and when the reliability DR is large, the possibility that the object actually exists is high. When the calculated reliability DR is equal to or higher than a predetermined reliability threshold DRv (DR≧DRv), the object recognition unit 110 recognizes the object included in the image data as an object actually existing.

[0026] By the way, the object (reference numerals VH2 and H in FIG. 3) existing in the headlamp non-irradiation area B tends to have a lower tendency to increase the reliability DR compared to the object existing in the headlamp irradiation area A. For this reason, if the reliability threshold DRv is set to a uniform fixed value, there is a possibility that the object recognition unit 110 may cause false detection or non-detection of not recognizing an object actually existing in the headlamp non-irradiation area B.

[0027] The reliability threshold correction unit 120 performs threshold correction to correct the reliability threshold DRv in order to prevent misdetection or non-detection of a target existing in the headlamp non-irradiation area B. The reliability threshold correction unit 120 is a reliability threshold changing means of the present disclosure. The reliability threshold correction unit 120 identifies the headlamp irradiation area A by the headlamp 60 from the image data of the camera 42 based on the information of the light distribution control by the light distribution control unit 100. When the reliability threshold correction unit 120 identifies the headlamp irradiation area A, it determines whether or not the target in the image data exists within the headlamp irradiation area A. When the reliability threshold correction unit 120 determines that the target exists in the headlamp irradiation area A, it does not perform threshold correction.

[0028] On the other hand, when the reliability threshold correction unit 120 determines that the target does not exist in the headlamp irradiation area A, that is, when the target in the image data exists in the headlamp non-irradiation area B, it performs threshold correction. The reliability threshold correction unit 120 performs threshold correction by multiplying the reliability threshold DRv by a predetermined gain coefficient k. Hereinafter, the corrected reliability threshold (= DRv × k) is referred to as "corrected reliability threshold DRv'". The gain coefficient k is a numerical value of 0 or more and less than 1 (0 ≦ k < 1). That is, the corrected reliability threshold DRv' is a value smaller than the reliability threshold DRv. Thus, when the target in the image data exists in the headlamp non-irradiation area B, by correcting the threshold used by the target recognition unit 110 for target recognition determination to the corrected reliability threshold DRv' smaller than the reliability threshold DRv, it becomes possible to effectively prevent non-detection or misdetection of a target existing in the headlamp non-irradiation area B. The gain coefficient k may be a fixed value or may be a variable value according to the illuminance detected by the ambient light sensor 50.

[0029] The PCS control unit 130 is the collision avoidance control means of the present disclosure, and executes PCS control to avoid a collision between the host vehicle VH and a forward target or reduce the damage caused by the collision. The PCS control unit 130 determines whether there is a target (hereinafter referred to as a target object) to be subjected to PCS control in front of the host vehicle VH based on the information of the target recognized by the target recognition unit 110. When the PCS control unit 130 determines that a target object exists, it acquires the coordinate information of the target object based on the detection result of the external sensor device 40. Further, the PCS control unit 130 calculates the turning radius of the host vehicle VH based on the detection results of the vehicle speed sensor 31, the steering angle sensor 34, and the yaw rate sensor 36, and calculates the trajectory of the host vehicle VH based on this turning radius. The PCS control unit 130 determines whether the target object in front of the host vehicle VH is an obstacle that may collide with the host vehicle VH. When the target object is a moving object, the PCS control unit 130 calculates the trajectory of the target object based on the coordinate information of the target object, and determines the target object as an obstacle when the trajectory of the target object intersects with the trajectory of the host vehicle VH. Further, when the target object is a stationary object, the PCS control unit 130 determines the target object as an obstacle when the trajectory of the host vehicle VH intersects with the current position of the target object.

[0030] When the PCS control unit 130 determines that the target object is an obstacle, it calculates the time to collision (hereinafter referred to as TTC) until the host vehicle VH collides with the obstacle based on the distance L from the host vehicle VH to the obstacle and the relative speed Vr of the host vehicle VH with respect to the obstacle. TTC is an index value indicating the possibility that the host vehicle VH collides with the obstacle. TTC can be obtained by dividing the distance L from the host vehicle VH to the obstacle by the relative speed Vr (TTC = L / Vr). When TTC is equal to or less than a predetermined collision determination threshold value Tv, the PCS control unit 130 determines that the possibility that the host vehicle VH collides with the obstacle is high. In the present embodiment, when the target object exists in the non-illumination area B of the headlamp, the object recognition unit 110 recognizes the existence of the object based on the corrected reliability threshold value DRv' that is smaller than the reliability threshold value DRv. That is, even when the obstacle that is the target of the PCS control exists in the non-illumination area B of the headlamp, it is configured to effectively prevent the non-detection or mis-detection of the obstacle. Thereby, it becomes possible to surely improve the accuracy of the collision determination of the PCS control.

[0031] When the PCS control unit 130 determines that the possibility that the host vehicle VH collides with the obstacle is high, it executes an alarm by the speaker 72 and / or the display device 71 and executes automatic brake control. The automatic brake control is control for decelerating the host vehicle VH so that the deceleration of the host vehicle VH matches a predetermined target deceleration by controlling the operation of the braking device 22 and / or the driving device 20. Thereby, the host vehicle VH can be forcibly decelerated without requiring the driver to operate the brake pedal.

[0032] Next, based on FIG. 4, a routine of the object recognition process and the PCS control process by the CPU 11 of the ECU 10 will be described. This routine starts when the vehicle VH is running.

[0033] In step S100, the ECU 10 determines whether or not there is an object target for PCS control in front of the host vehicle VH based on the detection result of the external sensor device 40. If there is an object target (Yes), the ECU 10 proceeds to the process of step S110. On the other hand, if there is no object target (No), the ECU 10 returns to this routine.

[0034] In step S110, the ECU 10 determines whether or not the illuminance around the host vehicle VH is equal to or less than a predetermined illuminance based on the illuminance information acquired by the contrast sensor 50. If the illuminance around the vehicle VH is equal to or less than the predetermined illuminance (Yes), that is, in a dark place, the ECU 10 proceeds to the process of step S120. On the other hand, if the illuminance around the vehicle VH is not equal to or less than the predetermined illuminance (No), that is, in a bright place, the ECU 10 proceeds to the process of step S160.

[0035] In step S120, the ECU 10 determines whether or not the light distribution control of the headlamp 60 is being executed. If the light distribution control is being executed (Yes), the ECU 10 proceeds to the process of step S130. On the other hand, if the light distribution control is not being executed (No), the ECU 10 proceeds to the process of step S160.

[0036] In step S130, the ECU 10 specifies the headlamp irradiation area A by the headlamp 60. Next, in step S140, the ECU 10 determines whether or not the object target exists in the headlamp irradiation area A. If the object target exists in the headlamp irradiation area A (Yes), the ECU 10 proceeds to the process of step S160. On the other hand, if the object target does not exist in the headlamp irradiation area A (No), that is, if the object target exists in the headlamp non-irradiation area B, the ECU 10 proceeds to the process of step S150.

[0037] In step S150, the ECU 10 corrects the reliability threshold DRv to set the threshold used for the determination of target recognition to the corrected reliability threshold DRv'. Next, in step S155, the ECU 10 recognizes a target whose reliability DR is equal to or higher than the corrected reliability threshold DRv' as an object target for PCS control.

[0038] When proceeding from step S110, or step S120, or step S140 to the process of step S160, the ECU 10 sets the threshold value used for the determination of object recognition to the normal reliability threshold value DRv. Next, in step S165, an object with a reliability DR greater than or equal to the reliability threshold value DRv is recognized as an object target for PCS control.

[0039] In step S170, the ECU 10 determines whether the object target recognized in the processes of step S155 and / or step S165 is an obstacle. When the object target is a moving object, the ECU 10 determines the object target as an obstacle when the trajectory of the object target intersects with the trajectory of the host vehicle VH. Also, when the object target is a stationary object, the ECU 10 determines the object target as an obstacle when the trajectory of the host vehicle VH intersects with the current position of the object target. When the ECU 10 determines that the object target is an obstacle (Yes), it proceeds to the process of step S180. On the other hand, when the ECU 10 determines that the object target in front of the host vehicle VH is not an obstacle (No), it returns from this routine.

[0040] In step S180, the ECU 10 calculates TTC (= L / vr) by dividing the distance L from the host vehicle VH to the object target by the relative speed Vr. Next, in step S185, the ECU 10 determines whether TTC is less than or equal to the collision determination threshold value Tv. When TTC is less than or equal to the collision determination threshold value Tv (Yes), the ECU 10 proceeds to the process of step S190. On the other hand, when TTC is greater than the collision determination threshold value Tv (No), the ECU 10 returns from this routine.

[0041] In step S190, the ECU 10 executes an alarm and executes automatic brake control to decelerate the host vehicle VH based on a predetermined target deceleration. Thereafter, the ECU 10 returns from this routine.

[0042] As described above, the object recognition device according to the present embodiment has been described. However, the present disclosure is not limited to the above embodiment, and various modifications are possible without departing from the object of the present disclosure.

[0043] For example, in the above-described embodiment, the target recognized by the target recognition unit 110 has been described as being applied to PCS control, but it can also be applied to other driving support controls such as Adaptive Cruise Control (ACC) and Lane Trace Asist (LTA). Further, the technology of the present disclosure can also be applied to an autonomous vehicle that automatically performs part or all of the driving operations.

Claims

1. Imaging means for imaging a predetermined range in front of the vehicle, a target recognition means for calculating a reliability index of target recognition of a target in an image captured by the imaging means and recognizing the target as an actually existing target when the calculated reliability index is equal to or greater than a predetermined reliability threshold, and a light distribution control means for controlling the light distribution of the headlamp in a light distribution pattern including an irradiation area for irradiating the irradiation light and a dimming area for blocking or dimming a part of the irradiation light irradiated from the headlamp provided in the vehicle based on the presence information of the target existing in front of the vehicle, a reliability threshold changing means for changing the reliability threshold to a smaller value when the target in the image does not exist in the irradiation area than when it exists in the irradiation area, characterized in that it is a target recognition device.

2. The target recognition device according to Claim 1, wherein the reliability threshold changing means changes the reliability threshold to a smaller value by multiplying the reliability threshold by a gain coefficient of 0 or more and less than 1 when the target in the image does not exist in the irradiation area. characterized in that it is a target recognition device.

3. The target recognition device according to Claim 1 or 2, wherein the vehicle is provided with a collision avoidance control means for performing collision avoidance control for avoiding a collision between the vehicle and an object or reducing damage caused by the collision when an object recognized in front of the vehicle satisfies a predetermined collision condition, and the target recognition means transmits information on the recognized target to the collision avoidance control means to cause the collision avoidance control means to recognize the object. characterized in that it is a target recognition device.

Images