Light distribution control system and light distribution control method

Abstract

The present invention recognizes the outside of a vehicle, and controls the light distribution of headlamps mounted on the vehicle on the basis of the outside of the vehicle. The system comprises: an external sensor for acquiring information about an object around a vehicle; and a ground speed acquisition unit that acquires the ground speed of the object on the basis of the output of the external sensor, and variably sets the irradiation range of the headlamp on the basis of the ground speed acquired by the ground speed acquisition unit.

Description

Technical Field

[0001] The invention relates to a light distribution control system and a light distribution control method. Background Art

[0002] In recent years, vehicles such as automobiles have been put into practical use that are equipped with a light distribution control system that recognizes the outside world of the vehicle and controls the light distribution of the vehicle headlights based on the recognition result. As a light distribution control installed in a vehicle, there is a function called AHB (Auto High Beam) that uses an onboard camera or other external recognition sensor to identify an oncoming vehicle or a vehicle in front, automatically switches to low beam, and automatically switches back to high beam after passing the oncoming vehicle or the vehicle in front. In addition, there is a function called ADB (Adaptive Driving Beam) that shields the area of ​​the identified oncoming vehicle or vehicle in front and illuminates the high beam outside the shielded area.

[0003] In order to correctly block light from other vehicles such as oncoming vehicles or vehicles traveling ahead, it is necessary to use an external recognition sensor to accurately distinguish between vehicles and non-vehicles. Patent document 1 describes a technology that selects light spots such as taillights or headlights based on their shapes and determines vehicles based on their moving direction and speed. However, in the prior art, it is not always possible to make appropriate vehicle determinations. There are situations where light spots are difficult to detect due to external interference, or where vehicles without lights on cannot be identified. Therefore, when these vehicles cannot be identified, there is a problem of causing glare to drivers of other vehicles. Prior art literature Patent Literature

[0004] Patent document 1: Japanese Patent Application Publication No. 2019-156276. Summary of the invention Problem that the invention aims to solve

[0005] When performing automatic light distribution control, it is not desirable to illuminate other vehicles with high beams. However, as described above, when it is difficult to detect the lights of other vehicles due to external interference, or when the lights of other vehicles are not turned on, there is a possibility that the high beams will be illuminated because the lights of other vehicles cannot be detected. Therefore, it is desirable to develop a technology that can perform light distribution control in addition to detecting the lights of vehicles.

[0006] Furthermore, when recognizing a vehicle from an image, false detection may occur due to roadside objects, etc. If a roadside object is mistakenly detected as a vehicle, the low beam headlights may be mistakenly switched, so it is desirable to prevent false detection of roadside objects, etc. as much as possible.

[0007] An object of the present invention is to provide a light distribution control system and a light distribution control method that can detect other vehicles well and prevent erroneous detection of objects other than vehicles. Technical means of solving problems

[0008] In order to solve the above-mentioned technical problem, for example, the configuration described in the claims is adopted. The present application includes a plurality of solutions to the above-mentioned technical problems. As one example, the light distribution control system of the present invention performs external recognition of the vehicle, and based on the external recognition of the vehicle, performs light distribution control on the headlights mounted on the vehicle. Here, a light distribution control system according to an example of the present invention includes: an external sensor that obtains information about an object around a vehicle; and a ground speed acquisition unit that obtains the ground speed of the object based on an output of the external sensor, wherein an illumination range of a headlamp is variably set based on the ground speed obtained by the ground speed acquisition unit. Effects of the Invention

[0009] According to the present invention, by acquiring the ground speed of an object and controlling the illumination of the headlights of the host vehicle when the ground speed is equal to or greater than a threshold, it is possible to prevent the high beam from being illuminated to other vehicles by a method other than detecting the headlights of the vehicle. Other problems, structures, and effects than those described above will become apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a block diagram showing a configuration example of a light distribution control system according to a first embodiment of the present invention. Figure 2 This is a block diagram showing an example of the hardware configuration of a recognition processing device included in the light distribution control system according to the first embodiment of the present invention. Figure 3 This is a flowchart showing the light distribution control process according to the first embodiment of the present invention. Figure 4A is a diagram showing an example of a candidate for shading (Example 1), Figure 4B It means from Figure 4A FIG. 1 is a diagram showing an example of a state in which a light-shielding target is selected from among candidates for light-shielding. Figure 5A is a diagram showing an example of a candidate for shading (Example 2), Figure 5B It means from Figure 5A FIG. 1 is a diagram showing an example of a state in which an object that does not perform light shielding is selected from among candidates that do not perform light shielding. Figure 6 It is a block diagram showing a configuration example of a light distribution control system according to a second embodiment of the present invention. Figure 7: is a flowchart showing the light distribution control process according to the second embodiment of the present invention. DETAILED DESCRIPTION

[0011] <First embodiment> Below, refer to Figure 1 5 to 5 illustrate a light distribution control system and a light distribution control method according to a first embodiment of the present invention.

[0012] [Configuration of light distribution control system] Figure 1 It is a diagram showing the configuration of a light distribution control system according to the present embodiment. Figure 1 The light distribution control system 1 shown is mounted on a vehicle equipped with headlights (not shown), and includes a recognition processing device 10 and a vehicle control device 20. Based on the recognition result of the recognition processing device 10, the vehicle control device 20 controls the light distribution of the vehicle headlights.

[0013] In addition, the light distribution control system 1 includes an external sensor 14 that is disposed in front of the vehicle and acquires information in front of the vehicle. The external sensor 14 is a sensor that performs external sensing processing to acquire information in front of or around the vehicle. As the external sensor 14, a stereo camera, a monocular camera, a millimeter wave radar, a LiDAR (Light Detection And Ranging, laser radar), etc. can be used. A stereo camera is a camera that uses multiple cameras to capture images in front of or around a vehicle. A monocular camera is a camera that uses a single camera to capture images in front of or around a vehicle. A millimeter-wave radar is a device that acquires the distance and angle of objects in front of or around a vehicle. LiDAR is a device that acquires three-dimensional information in front of or around a vehicle.

[0014] In addition, as the external sensor 14, there are cases where these sensors are used alone, and cases where a monocular camera or a millimeter wave radar is used in combination. In addition, other sensors than the above can also be used as long as they are sensors that detect the surroundings of the vehicle.

[0015] The recognition processing device 10 and the vehicle control device 20 are both computers. Figure 2 , which is a hardware configuration example of the recognition processing device 10 and the vehicle control device 20 as a computer. Figure 2 In FIG. 1 , although the recognition processing device 10 is shown, the vehicle control device 20 can also be configured with the same hardware as the recognition processing device 10 . The recognition processing device 10 includes a central processing unit (CPU) 11 as a processor, a read only memory (ROM) 11 a , a random access memory (RAM) 11 b , a storage device 12 , a network interface 11 c , an input unit 11 d , and an output unit 11 e . The CPU 11 may be composed of an MPU (Micro Processor Unit). The storage device 12 may be, for example, a HDD (Hard Disk Drive), an SSD (Solid State Drive), or a semiconductor memory. The storage device 12 may also serve as the ROM 11a.

[0016] The input unit 11d converts various information input from the external sensor 14 to the recognition processing device 10 or the vehicle control device 20 into information that can be calculated by the CPU 11. The ROM 11a or the storage device 12 is a recording medium that stores a control program for executing calculation processing described later and various information required for executing the calculation processing.

[0017] The CPU 11 performs predetermined calculation processing on the signal input to the input unit 11d and the signal taken from the ROM 11a, the RAM 11b or the storage device 12 according to the control program stored in the ROM 11a. The output unit 11e outputs instructions for controlling the output object or information used by the output object. Here, in the case of the recognition processing device 10, the output object is the light distribution control unit 21 of the vehicle control device 20, and in the case of the vehicle control device 20, the output object is the headlight of the vehicle whose light distribution is controlled.

[0018] In addition, the identification processing device 10 or the vehicle control device 20 being composed of a computer with a CPU is only an example. For example, a part or all of the identification processing device 10 or the vehicle control device 20 may also be implemented by dedicated hardware such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0019] Back to Figure 1 As for the structure of the recognition processing device 10, the recognition processing device 10 includes a ground speed acquisition unit 13. The ground speed acquisition unit 13 performs ground speed acquisition processing to acquire the relative speed of the object in front of the vehicle based on the information acquired by the external sensor 14. For example, the ground speed acquisition unit 13 uses three-dimensional information acquired by a stereo camera or LiDAR, etc. to recognize the obstacle in front of the vehicle as a three-dimensional object, and obtains the ground speed based on the time series data of the distance information of the recognized three-dimensional object.

[0020] Alternatively, the ground speed acquisition unit 13 uses images captured by a stereo camera or a monocular camera to calculate feature quantities such as edges or colors from images of the recognition object or other than the recognition object in advance to learn the identifier. Then, the ground speed acquisition unit 13 uses the learned identifier to recognize the newly acquired recognition object. For example, SVM (Support Vector Machine) or AdaBoost (Adaptive Boosting Algorithm) can be used in the learning of the identifier.

[0021] Furthermore, the ground speed acquisition unit 13 may perform deep learning (deep learning) such as CNN (Convolutional Neural Network) in advance using the recognition object or an image other than the recognition object. Then, the ground speed acquisition unit 13 may recognize the recognition object using the recognition network learned by CNN.

[0022] In addition, after identifying these identification objects, the ground speed acquisition unit 13 can also infer the distance information to the identification object based on the image size of the identified object, and further calculate the ground speed based on the time series data of the distance information to the identification object measured using a sensor such as a millimeter wave radar.

[0023] The vehicle control device 20 includes a light distribution control unit 21 . The light distribution control unit 21 controls the light distribution of the vehicle headlights based on the ground speed information of objects such as vehicles around the vehicle acquired by the ground speed acquisition unit 13 of the recognition processing device 10 , and variably sets the illumination range of the headlights. That is, for example, in the case of a vehicle equipped with an AHB function that automatically switches back to high beam after passing an oncoming vehicle or a vehicle traveling ahead, the light distribution control unit 21 sets the headlights to low beam when light distribution control is required. In addition, when light distribution control is not required, the light distribution control unit 21 sets the headlights to high beam.

[0024] In addition, in the case of a vehicle equipped with an ADB function that blocks light in an area with a recognized oncoming vehicle or a vehicle traveling ahead and illuminates the high beam outside the blocked area, the light distribution control unit 21 blocks light in the corresponding headlights when light distribution control is required, and illuminates the high beam in other areas.

[0025] [Processing flow for performing light distribution control of headlights] Figure 3 This is a flowchart showing the flow of processing for performing light distribution control of headlamps in the light distribution control system according to the present embodiment.

[0026] First, the ground speed acquisition unit 13 of the recognition processing device 10 acquires information from the external sensor 14, and calculates and acquires the ground speed of the objects around the vehicle based on the information from the external sensor 14 (step S101). The ground speed acquisition unit 13 acquires the ground speed for each object. For example, when an oncoming vehicle and a vehicle ahead are present in front of the vehicle, the ground speed acquisition unit 13 acquires the ground speed of each of the oncoming vehicle and the vehicle ahead.

[0027] Next, the recognition processing device 10 determines whether the speed over the ground obtained in step S101 is greater than a threshold value for each object (step S102). Here, the threshold value in step S102 is set to a fixed speed such as 40 km / h, which is suitable for recognizing a moving vehicle and an object on the road. In step S102, in determining whether the speed over the ground is equal to or greater than a threshold, a method of utilizing multiple measurement results may be considered in order to prevent erroneous determination of roadside objects, walls, and the like.

[0028] In addition, when traveling on the same road, since it is assumed that the oncoming vehicle or the vehicle ahead is traveling at the same speed as the vehicle, the threshold value of the ground speed or the number of ground speed measurements may be changed according to the vehicle speed. Furthermore, since the possibility of misjudgment increases when there are many roadside objects such as at a curve, the threshold value of the ground speed or the number of ground speed measurements may be changed according to the curvature of the road being traveled.

[0029] Then, when it is determined in step S102 that the ground speed is greater than the threshold value (Yes in step S102), the recognition processing device 10 determines that the high beam is an object to be shielded, and the vehicle control device 20 controls the headlights so as not to glare the object (step S103). The control of the headlights so as not to glare the object such as the oncoming vehicle is performed, for example, by the AHB function or the ADB function.

[0030] When it is determined in step S102 that the speed over the ground has not reached the threshold (No in step S102), the recognition processing device 10 determines that it is not a light-shielding object such as an oncoming vehicle, and in the vehicle control device 20, the headlights are controlled without changing the illumination location of the high beam of the object (step S104).

[0031] [Example of determination status of recognition object] 4 and 5 are schematic diagrams showing examples of determination states according to the present embodiment. 4 and 5 are images of the front of the vehicle captured by the camera, and the portion surrounded by a rectangular frame in each image indicates a portion detected as a light shielding target by the recognition processing device 10 .

[0032] Figure 4A The captured image 100a shows the situation of the vehicle 102 ahead, the oncoming vehicle 101, the street light 103, and the sign 104. The vehicle 102 ahead and the oncoming vehicle 101 are traveling on the road, so the ground speed can be acquired. Therefore, in step S102, if it can be determined that the acquired ground speed is greater than the threshold value, Figure 4B As shown, the recognition processing device 10 uses the recognition result as an image 100 b and uses the preceding vehicle 102 and the oncoming vehicle 101 as light shielding objects. Furthermore, since the sign 104 and the street lamp 103 are road installations, it is determined in step S102 that the speed over the ground does not reach the certain value, so the recognition processing device 10 does not regard them as light-shielded objects in the image 100 b of the recognition result.

[0033] Figure 5A This is a captured image 200a in which only roadside objects such as a sign 201 , a sight line guide sign (arrow type) 202 , and a sight line guide sign (pole type) 203 are visible.

[0034] In this Figure 5A In the case of a situation such as the image 200a shown in FIG. 1 , in step S102, the mark 201 or the sight line guide marks 202 and 203 are determined to indicate that the ground speed has not reached a certain value. Figure 5B As shown, the mark 201 or the sight line guide marks 202, 203 are not blocked in the image 200b of the recognition result. Therefore, the light distribution control unit 21 can illuminate the high beam in the case of the AHB function. In addition, even in the ADB function, the light distribution control unit 21 can illuminate the high beam without blocking.

[0035] In addition, the scene shown in FIG. 4 or FIG. 5 is an example of a target scene, and the determination state of this embodiment example can also cope with other various situations.

[0036] As described above, according to the present embodiment, the recognition processing device 10 determines that an object detected by the external sensor 14 is a light-shielding object only when the speed relative to the ground is above a certain speed, so that it is possible to reliably distinguish between a moving vehicle and an object fixed on the road to determine the light-shielding object. Therefore, it is possible to prevent the high beam from being irradiated on other vehicles whose speed relative to the ground does not reach above the certain speed.

[0037] <Second Embodiment> Next, referring to Figure 6-7 A light distribution control system and a light distribution control method according to a second embodiment of the present invention will be described. Figure 6-7 In the first embodiment, Figure 1 The same parts as in FIG. 5 are denoted by the same reference numerals, and repeated descriptions are omitted.

[0038] [Configuration of light distribution control system] Figure 6 FIG. 2 shows the configuration of the light distribution control system according to the present embodiment. Figure 6 The recognition processing device 10 in the light distribution control system 1 ′ of the illustrated embodiment includes an image acquisition unit 15 , a light spot detection unit 16 , and a vehicle detection unit 17 in addition to the speed-over-ground acquisition unit 13 described in the first embodiment. That is, the CPU (central processing unit) 11 of the recognition processing device 10 is set to have functions as the image acquisition unit 15, the light spot detection unit 16, the vehicle detection unit 17, and the ground speed acquisition unit 13. Figure 6 The light distribution control system 1' shown is also composed of Figure 2 The computer structure shown.

[0039] The image acquisition unit 15 acquires an image captured by a camera (stereo camera or monocular camera) as the external sensor 14 . The light spot detection unit 16 detects pixels whose brightness is greater than or equal to a certain value based on the image acquired from the image acquisition unit 15, and combines the area adjacent to the pixel as a light spot area. Furthermore, the light spot detection unit 16 identifies the type of the light spot by identifying whether it is a light spot of a headlamp or taillamp of a vehicle or other light spots using brightness information of the light spot area, information of the relative distance from the vehicle, and information of the relative position from the vehicle.

[0040] The vehicle detection unit 17 detects the vehicle based on the parallax information of the image (in the case of a stereo camera) or the features of the image. At this time, the vehicle detection unit 17 may use machine learning when detecting the vehicle. That is, the vehicle detection unit 17 recognizes the vehicle using the image captured by the stereo camera or the monocular camera with the trained recognizer.

[0041] The learned recognizer is previously trained by using a support vector machine (SVM) or AdaBoost to calculate feature quantities such as edges or colors based on the image to be recognized or other than the image to be recognized. The vehicle detection unit 17 then uses the learned recognizer to calculate feature quantities such as edges or colors based on the image acquired by the image acquisition unit 15 for recognition.

[0042] Alternatively, the recognizer may learn a recognition network in advance based on images of the recognition object or other than the recognition object using deep learning such as CNN (Convolutional Neural Network), and recognize the recognition object such as a vehicle based on the image acquired by the image acquisition unit 15 based on the learned network.

[0043] The ground speed acquisition unit 13 and Figure 1 Similarly to the first embodiment example described in , the ground speed of the object around the vehicle is acquired. Furthermore, the vehicle control device 20 performs light distribution control of the vehicle headlights based on various information on objects such as vehicles around the vehicle acquired by the recognition processing device 10 .

[0044] [Processing flow for performing light distribution control of headlights] Figure 7 This is a flowchart showing the flow of processing for performing light distribution control of headlamps in the light distribution control system according to the present embodiment. First, the light spot detection unit 16 identifies light spots that are candidates for light shielding in the light distribution control unit 21 for the image acquired by the image acquisition unit 15 (step S201). Then, the light spot detection unit 16 determines whether no light spots were detected in step S201 (step S202).

[0045] When a light spot that is a candidate for a light shielding object is identified in step S202 (No in step S202), the recognition processing device 10 determines that the candidate for the light shielding object of the light spot is a light shielding object (step S208). The result of determination as a light shielding object in step S208 is transmitted from the recognition processing device 10 to the vehicle control device 20. As a result, the vehicle control device 20 sets the control state of the headlight to a low beam or a high beam that shields the corresponding light shielding object.

[0046] When no light spot that is a candidate for a light shielding target is recognized in step S202 (YES in step S202 ), the vehicle detection unit 17 performs vehicle recognition on the image acquired by the image acquisition unit 15 (step S203 ). Furthermore, the ground speed acquisition unit 13 acquires the ground speed of the objects around the vehicle (step S204). The ground speed is acquired for each object. For example, when an oncoming vehicle and a front vehicle are in front of the vehicle, the ground speeds of the oncoming vehicle and the front vehicle are acquired.

[0047] After that, the recognition processing device 10 determines whether there is vehicle recognition in step S203 (step S205). In step S205, if it is determined that there is vehicle recognition (yes in step S205), the recognition processing device 10 determines whether the ground speed obtained in step S204 is greater than a threshold value a (step S206). Here, the threshold value a is set to 40 km / h, for example.

[0048] When it is determined in step S206 that the speed over the ground is greater than or equal to the threshold value a (Yes in step S206), the recognition processing device 10 determines the corresponding object as a light-shielding object (step S208). The determination of the light-shielding object in step S208 is transmitted from the recognition processing device 10 to the vehicle control device 20, and in the vehicle control device 20, the headlight is controlled to a state corresponding to the determination of the light-shielding object.

[0049] In addition, when it is determined in step S206 that the speed over the ground does not reach the threshold value a (No in step S206), the recognition processing device 10 determines that it is outside the light shielding target (step S209). In the determination of step S209, even if the vehicle is recognized in step S203, the recognition processing device 10 determines that there is a possibility of misrecognition of roadside objects, etc., and performs the determination of step S209.

[0050] Furthermore, in step S205, if it is determined that there is no vehicle recognition (step S205: No), it is determined whether the ground speed obtained in step S204 is above threshold value b (step S207). Here, threshold value b is set to a value greater than the above threshold value a, for example, 80 km / h.

[0051] In step S207, when it is determined that the ground speed is greater than or equal to the threshold value b (Yes in step S207), the recognition processing device 10 determines the corresponding object as a light-shielding object (step S208). The determination of the light-shielding object is transmitted from the recognition processing device 10 to the vehicle control device 20, and the headlights are controlled to a corresponding state in the vehicle control device 20.

[0052] Furthermore, in step S207 , when it is determined that the speed over the ground has not reached the threshold value b (No in step S207 ), the recognition processing device 10 determines that the recognized vehicle is outside the light shielding target (step S209 ).

[0053] As described above, in this embodiment, when there is detection of a light spot in step S202, it is immediately determined to be a light-shielded object. In addition, when there is no detection as a light spot in step S202, the light-shielded judgment is performed based on the combination of the vehicle recognition results and the ground speed results of steps S203 and S204.

[0054] Thus, for example, even if part of the sight guide marks 202 and 203 are mistakenly recognized as a vehicle in step S203 as described in FIG. 5 , the ground speed is checked in step S206 , and it can be determined in step S209 that the vehicle is not subject to light shielding. Therefore, in Figure 7 In such a scene where high beam is required, it can prevent the vehicle from mistakenly switching to low beam.

[0055] In addition, in a scene where there is a vehicle ahead or an oncoming vehicle as shown in Figure 4, even if there is no light spot detection in step S202 and no vehicle identification in step S205 due to false detection in rainy days, the vehicle ahead 102 or the oncoming vehicle 101 can be set as a shading object in step S208 by confirming the ground speed in step S207. Thus, even when it is difficult to detect a light spot or recognize a vehicle based on an image, the vehicle 102 traveling ahead or the oncoming vehicle 101 can be reliably shielded from light by utilizing the speed over the ground, thereby preventing glare.

[0056] Furthermore, the vehicle detection unit 17 of the present embodiment detects a vehicle using machine learning based on a learned identifier or the like, and can detect the vehicle more accurately, thereby controlling the headlights with higher accuracy.

[0057] As described above, according to the present embodiment, similarly to the first embodiment, it is possible to prevent the high beam from being irradiated onto other vehicles that should not be irradiated. Furthermore, in the case of the present embodiment, when performing light spot detection and vehicle detection, and judging the illumination of the headlights of the vehicle based on the detection results, appropriate control can be performed even when the respective recognition results are non-detection. That is, in the case of the present embodiment, by acquiring the ground speed relative to the objects around the vehicle and controlling the illumination of the headlights of the vehicle when the ground speed is greater than a threshold, even when it is difficult to perform light spot detection or vehicle detection based on the image due to external interference such as rain, the illumination of the headlights can be controlled based on the ground speed.

[0058] Furthermore, in the case of this embodiment, even if the result of vehicle detection is that a vehicle is present, the ground speed of the object is acquired, and if the ground speed does not reach the threshold, it is determined to be a roadside object. Thus, according to this embodiment, even if a roadside object is mistakenly detected as a vehicle, the vehicle can drive with the high beam of the headlight of the vehicle without shielding the roadside object.

[0059] Furthermore, in the case of this embodiment, the vehicle detection unit 17 uses machine learning to detect the vehicle based on the parallax information of the image or the characteristics of the image. Thus, the vehicle detection unit 17 can detect the vehicle more accurately. However, using machine learning is only an example, and the vehicle can also be detected by other methods.

[0060] [Modifications] In addition, the embodiment examples described so far have been described in detail to facilitate understanding of the present invention, and are not limited to necessarily having all the described configurations.

[0061] For example, the values ​​of 40 km / h or 80 km / h as the speed examples of the threshold values ​​described in the above-mentioned embodiment are only examples, and may be set to a higher speed or a lower speed than the above-mentioned examples. For example, when the speed acquired by the ground speed acquisition unit 13 has high accuracy and small error, the speed value of the threshold value 40 km / h of the first embodiment or the threshold value a of 40 km / h of the second embodiment may be set to a lower speed value than the above-mentioned examples. In addition, these threshold values ​​may be variably set according to the running speed of the vehicle.

[0062] In addition, in the above-mentioned embodiments, although the Figure 2 or Figure 7 The recognition processing of the traveling vehicle and other objects in the flowchart is applicable to the light distribution control of the headlights, but the recognition result in the recognition processing device 10 may be used by the vehicle control device 20 for controls other than the headlights.

[0063] For example, when the vehicle control device 20 is controlled as an autonomous driving system (AD) or an advanced driver-assistance system (ADAS), the recognition processing device 10 can control the light distribution of the headlights by performing recognition processing of a moving vehicle and other objects. In addition, AD or ADAS can be set as one of the necessary information in the vehicle recognition processing.

[0064] In this way, by applying the recognition result in the recognition processing device 10 to other purposes other than the light distribution control of the headlights, it is possible to perform autonomous driving or advanced driving assistance more accurately and precisely.

[0065] In addition, Figure 1 or Figure 6 In the configuration diagram shown, control lines or information lines are shown only as necessary for explanation, and not all control lines or information lines are necessarily shown on the product. In fact, it can be considered that almost all the configurations are connected to each other.

[0066] In the example described in the present embodiment, the vehicle control device 20 controls the headlights after obtaining the recognition result from the recognition processing device 10. On the other hand, a part or all of the recognition processing may be performed by the vehicle control device 20. Alternatively, the recognition processing device 10 may directly control the control of the high beam and low beam of the headlights, or the setting of the light shielding range when the high beam is on.

[0067] In addition, in the case where the identification processing device 10 or the vehicle control device 20 is composed of an information processing device such as a computer, the program for implementing the identification processing device 10 or the vehicle control device 20 can be prepared in a non-volatile storage device or memory in the computer, and can also be placed in an external memory, IC card, SD card, optical disk or other recording medium and utilized by transmission. Explanation of symbols

[0068] 1, 1'…light distribution control system, 10…recognition processing device, 11…central processing unit (CPU), 11a…read-only memory (ROM), 11b…random access memory (RAM), 11c…network interface, 11d…input unit, 11e…output unit, 12…storage device, 13…ground speed acquisition unit, 14…external sensor, 15…image acquisition unit, 16…light spot detection unit, 17…vehicle detection unit, 20…vehicle control device, 21…light distribution control unit, 100a, 100b…image, 101…oncoming vehicle, 102…vehicle traveling ahead, 103…street light, 104…sign, 200a, 200b…image, 201…sign, 202, 203…sight guidance sign.

Claims

1. A light distribution control system, which performs external recognition of a vehicle and controls the light distribution of a headlamp mounted on the vehicle based on the external recognition of the vehicle, characterized in that: have: an external sensor that acquires information about objects surrounding the vehicle; and a ground speed acquisition unit, which acquires the ground speed of the object based on the output of the external sensor, The illumination range of the headlight is variably set based on the speed over the ground acquired by the speed over the ground acquisition unit.

2. The light distribution control system according to claim 1, characterized in that: When the ground speed acquisition unit determines that the ground speed of the object is less than a first threshold value, the irradiation direction of the headlight of the host vehicle is set to a high beam.

3. The light distribution control system according to claim 1, characterized in that: Also available: an image acquisition unit that acquires an image of the surroundings of the vehicle; and a light spot detection unit for detecting light spots included in the image, When the light spot detection unit does not detect the light spot and the ground speed of the object in the ground speed acquisition unit is equal to or greater than a first threshold, the illumination direction of the headlight of the host vehicle is set to a low beam or a high beam that shields the object.

4. The light distribution control system according to claim 3, characterized in that: The apparatus further comprises: a vehicle detection unit configured to detect a vehicle included in the image; The case where the speed-over-ground acquisition unit determines that the speed-over-ground of the object is equal to or greater than the first threshold value is a case where the vehicle detection unit has not detected a vehicle.

5. The light distribution control system according to claim 4, characterized in that: When the vehicle detection unit detects a vehicle, if the ground speed of the object in the ground speed acquisition unit is greater than or equal to a second threshold value that is faster than a first threshold value, the illumination direction of the headlight of the vehicle is set to a low beam or a high beam that blocks light from the object.

6. The light distribution control system according to claim 4, characterized in that: The vehicle detection unit detects a vehicle based on parallax information of an image and features of the image through machine learning.

7. The light distribution control system according to claim 1, characterized in that: In the speed-over-ground acquisition unit, information on the speed over the ground of the object is also used as object information required for the vehicle to perform automatic driving or advanced driving assistance.

8. A light distribution control method, which performs external recognition of a vehicle and controls the light distribution of a headlamp mounted on the vehicle based on the external recognition of the vehicle, characterized in that: include: External sensing processing to obtain information about objects surrounding the vehicle; A ground speed acquisition process, which acquires the ground speed of the object based on the information obtained by the external sensing process; as well as The light distribution control process variably sets the illumination range of the headlight based on the speed over the ground in the speed over the ground acquisition process.

Images