Headlight control device, headlight control method, and program

Abstract

To provide a headlamp control device, a headlamp control method, and a program capable of controlling whether to set a headlamp of an own vehicle into a high-beam lit state, a shielded high-beam lit state, or a low-beam lit state, as appropriate, by using learning results.SOLUTION: A headlamp control device 18 acquires a result of learning of recognition sensitivity of a forward vehicle during lighting of a lamp included in a forward camera image of a probe vehicle suitable for each traveling position of the probe vehicle performed using the traveling position of the probe vehicle and the forward camera image of the probe vehicle when a driver of the probe vehicle performs an operation to turn OFF a function of switching a light distribution of a headlamp of the probe vehicle from a lighting state of a high beam to a lighting state of a light shielding high beam, and adjusts the recognition sensitivity of the forward vehicle during lighting of a lamp included in a forward camera image of an own vehicle 1 at each traveling position of the own vehicle 1 based on the obtained result of the learning.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a headlight control device, a headlight control method, and a program.

Background Art

[0002] Patent Document 1 describes that, during automatic lighting control in auto mode, when a driver sets the lighting / off state of a lighting lamp in manual mode overriding the automatic lighting control, a camera image at that time and the lighting / off state of the lighting lamp at that time are used as learning data. Further, Patent Document 1 describes that learning processing of an identifier using the learning data is performed on a server. Furthermore, Patent Document 1 describes that an identifier that determines the lighting / off state of a lighting lamp for an image obtained during driving of a vehicle is updated by learning. There is known a system (AHS (Adaptive High Beam System)) in which, when a preceding vehicle with its lamp lit included in a front camera image of the host vehicle is recognized, automatic control for switching the light distribution of the host vehicle's headlight from the high beam lighting state to the shaded high beam lighting state is performed, and a system (AHB (Automatic High Beam)) in which, when a preceding vehicle with its lamp lit included in a front camera image of the host vehicle is recognized, automatic control for switching the light distribution of the host vehicle's headlight from the high beam lighting state to the low beam lighting state is performed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a phenomenon where drivers of their own vehicles manually turn off the AHS / AHB function because they dislike the malfunction or failure of the AHS / AHB. If a vehicle ahead with its lights on, as captured in the forward camera image of the vehicle, is present but not recognized, the AHS / AHB will malfunction. If a vehicle ahead with its lights on, as captured in the forward camera image of the vehicle, is not present but is mistakenly identified as such, the AHS / AHB will malfunction. Simply applying the learning method described in Patent Document 1, for example, to such phenomena may result in the system arbitrarily turning off the AHS / AHB function even though the driver wants to keep it ON. If inappropriate learning occurs based on the driver's operation of continuing to use the high beams despite the presence of a vehicle with its lights on in front of the vehicle's front camera image, the system may, based on the learning results, control the vehicle's headlights to be on high beam even though there is a vehicle with its lights on in front of the vehicle's front camera image. In other words, if the vehicle's headlights are directly controlled using the learning results to be on high beam, light-blocking high beam, or low beam, inappropriate control may occur.

[0005] In view of the above, the present disclosure aims to provide a headlight control device, a headlight control method, and a program that can appropriately control whether the headlights of the vehicle are in a high beam state, a light-blocking high beam state, or a low beam state using the learning results. [Means for solving the problem]

[0006] (1) One aspect of the present disclosure includes a vehicle recognition unit that recognizes a vehicle ahead with its lights on, as included in a forward camera image of the vehicle itself; a control unit that, when the vehicle recognition unit recognizes a vehicle ahead with its lights on, performs a control to switch the light distribution of the vehicle's headlights from a high beam state to a shading high beam state, which is a high beam that shades the vehicle ahead with its lights on and its surroundings, as included in the forward camera image of the vehicle itself, or from a high beam state to a low beam state; and a control unit that controls the light distribution of the vehicle's headlights from a high beam state to a low beam state, as performed by the driver of the probe vehicle. The headlight control device comprises: an acquisition unit that acquires the results of learning the recognition sensitivity of a vehicle ahead with its lamps lit, which is included in the forward camera image of the probe vehicle and is suitable for each driving position of the probe vehicle, using the driving position of the probe vehicle and the forward camera image of the probe vehicle when the function of switching control of the headlight distribution of the probe vehicle's headlights is turned OFF, or when the function of switching control of the headlight distribution of the probe vehicle's headlights from a high beam state to a low beam state is turned OFF; and a vehicle recognition sensitivity adjustment unit that adjusts the recognition sensitivity of a vehicle ahead with its lamps lit, which is included in the forward camera image of the probe vehicle, at each driving position of the own vehicle, based on the learning results acquired by the acquisition unit.

[0007] (2) In the headlight control device of (1), the acquisition unit acquires the detection result of the steering angle sensor of the vehicle, and the vehicle recognition sensitivity adjustment unit may set the recognition sensitivity of the vehicle ahead with its lamps lit, which is included in the forward camera image of the vehicle, to a default value when the steering angle detected by the steering angle sensor is equal to or greater than the steering angle threshold.

[0008] (3) In the headlight control device of (1), the acquisition unit acquires the detection result of the vehicle speed sensor of the own vehicle, and the vehicle recognition sensitivity adjustment unit may set the recognition sensitivity of the vehicle ahead with its lamps lit, which is included in the forward camera image of the own vehicle, to the default value when the vehicle speed detected by the vehicle speed sensor is equal to or greater than the vehicle speed threshold.

[0009] (4) One aspect of the present disclosure is a headlight control device which includes a vehicle recognition step in which the headlight control device recognizes a vehicle ahead that has its lamps lit, as included in the forward camera image of the vehicle; a control step in which, when a vehicle ahead that has its lamps lit, as included in the forward camera image of the vehicle, is recognized in the vehicle recognition step, the headlight control device performs a control to switch the light distribution of the vehicle's headlights from a high beam state to a shading high beam state, which is a high beam that shades the vehicle ahead that has its lamps lit and its surroundings as included in the forward camera image of the vehicle, or a control to switch the light distribution of the vehicle's headlights from a high beam state to a low beam state; and the headlight control device which controls the driver of the probe vehicle to switch the probe from a high beam state to a shading high beam state. The headlight control method comprises: an acquisition step of acquiring the results of learning the recognition sensitivity of a vehicle ahead with its lights on, which is suitable for each driving position of the probe vehicle, using the driving position of the probe vehicle and the forward camera image of the probe vehicle when the function of switching the light distribution of the headlights of the vehicle is turned OFF, or when the function of switching the light distribution of the headlights of the probe vehicle is turned OFF from a high beam state to a low beam state, and the results of learning the recognition sensitivity of a vehicle ahead with its lights on, which is included in the forward camera image of the probe vehicle, which is suitable for each driving position of the probe vehicle; and a vehicle recognition sensitivity adjustment step in which the headlight control device adjusts the recognition sensitivity of a vehicle ahead with its lights on, which is included in the forward camera image of the probe vehicle, at each driving position of the probe vehicle, based on the learning results acquired in the acquisition step.

[0010] (5) One aspect of the present disclosure provides a processor with a vehicle recognition step of recognizing a vehicle ahead with its lights on, which is included in the forward camera image of the own vehicle; a control step of performing a control to switch the light distribution of the own vehicle's headlights from a high beam state to a light-shielding high beam state, which is a high beam that shields the vehicle ahead with its lights on and its surroundings, which is included in the forward camera image of the own vehicle, when the vehicle recognition step recognizes the vehicle ahead with its lights on; or a control to switch the light distribution of the own vehicle's headlights from a high beam state to a low beam state; and a control to switch the light distribution of the probe vehicle's headlights from a high beam state to a light-shielding high beam state, which is when the driver of the probe vehicle recognizes the vehicle ahead with its lights on, which is included in the forward camera image of the own vehicle. This program is for executing an acquisition step of acquiring the results of learning the recognition sensitivity of vehicles ahead with their lights on, which is suitable for each driving position of the probe vehicle, using the driving position of the probe vehicle and the forward camera image of the probe vehicle when the function of light switching control is turned OFF, or the function of light distribution switching control of the probe vehicle's headlights from a high beam state to a low beam state is turned OFF, and a vehicle recognition sensitivity adjustment step of adjusting the recognition sensitivity of vehicles ahead with their lights on, which is included in the forward camera image of the probe vehicle, at each driving position of the probe vehicle, based on the learning results acquired in the acquisition step. [Effects of the Invention]

[0011] According to this disclosure, the headlights of the vehicle can be appropriately controlled using the learning results to determine whether to illuminate them as high beams, as light-blocking high beams, or as low beams. [Brief explanation of the drawing]

[0012] [Figure 1] This figure shows an example of a vehicle 1 to which the headlight control device 18 of the first embodiment is applied. [Figure 2] Figure 1 shows an example of a vehicle recognition sensitivity adjustment system SY that includes the vehicle 1 shown in Figure 1. [Figure 3] This is a flowchart illustrating an example of processing performed by the processor 183 of the headlight control device 18 of the first embodiment. [Modes for carrying out the invention]

[0013] Hereinafter, embodiments of the headlight control device, headlight control method, and program of the present disclosure will be described with reference to the drawings.

[0014] <First Embodiment> Figure 1 shows an example of a vehicle 1 to which the headlight control device 18 of the first embodiment is applied. Figure 2 shows an example of a vehicle recognition sensitivity adjustment system SY including the vehicle 1 shown in Figure 1. In the example shown in Figures 1 and 2, the vehicle 1 is equipped with headlights 11, a front camera 12, an HMI (Human Machine Interface) 13, a position information acquisition device 14, a vehicle speed sensor 15, a steering angle sensor 16, a communication device 17, and a headlight control device 18. The headlight 11 has the function of turning on the high beam, the function of turning on a light-blocking high beam which is a high beam that blocks light from the vehicle in front and its surroundings while the lamp is lit, as included in the forward camera image described later, and the function of turning on the low beam. The forward camera 12 takes a picture of the area in front of the vehicle 1 and transmits the forward camera image to the headlight control device 18. The HMI 13 has the function of receiving various operations from the driver of the vehicle 1 and transmits signals indicating the operations of the driver of the vehicle 1 to the headlight control device 18. Operations by the driver of the vehicle 1 include, for example, turning off the function of the light distribution switching control of the headlight 11 from the high beam state to the light-blocking high beam state.

[0015] The location information acquisition device 14 acquires information indicating the vehicle's position (e.g., latitude, longitude, and direction (i.e., the orientation of the vehicle)). The location information acquisition device 14 includes, for example, a GPS (Global Positioning System) device that measures the latitude, longitude, and direction of the vehicle. The location information acquisition device 14 may perform a well-known localization process to improve the accuracy of the information indicating the latitude, longitude, and direction of the vehicle. The location information acquisition device 14 transmits the information indicating the vehicle's position (e.g., latitude, longitude, and direction) to the headlight control device 18. The vehicle speed sensor 15 detects the vehicle speed of the vehicle 1 and transmits the detection result to the headlight control device 18. The steering angle sensor 16 detects the steering angle (angle of the steering wheel (not shown) of the vehicle 1) and transmits the detection result to the headlight control device 18. The communication device 17 communicates with the big data analysis unit SY1 and other components included in the vehicle recognition sensitivity adjustment system SY. When the communication device 17 receives an operation from the driver of the vehicle 1 to turn OFF the function of switching the light distribution of the headlights 11 from the high beam state to the light-blocking high beam state, the communication device 17 transmits information indicating that operation to the big data analysis unit SY1. The communication device 17 also transmits information indicating the driving position of the vehicle 1 at the time the HMI 13 received the operation, along with a forward camera image, to the big data analysis unit SY1. Furthermore, the communication device 17 receives the results of the learning performed by the big data analysis unit SY1 (described later) and transmits the learning results to the headlight control device 18.

[0016] The headlight control device 18 is composed of a microcomputer equipped with a communication interface (I / F) 181, a memory 182, and a processor 183. The communication interface 181 has an interface circuit for connecting the headlight control device 18 to the headlights 11, the front camera 12, the HMI 13, the position information acquisition device 14, the vehicle speed sensor 15, the steering angle sensor 16, the communication device 17, etc. The memory 182 stores programs and various data used in processing executed by the processor 183. The memory 182 also stores default values ​​for vehicle recognition sensitivity, vehicle speed threshold, steering angle threshold, etc., which will be described later. The processor 183 has the functions of an acquisition unit 3A, a vehicle recognition unit 3B, a control unit 3C, and a vehicle recognition sensitivity adjustment unit 3D. The acquisition unit 3A acquires the forward camera image transmitted from the forward camera 12. The acquisition unit 3A also acquires information indicating the vehicle's position (e.g., latitude, longitude, direction, etc.) transmitted from the position information acquisition device 14. Furthermore, the acquisition unit 3A acquires information indicating the vehicle speed of the vehicle 1 (detection result of the vehicle speed sensor 15) transmitted from the vehicle speed sensor 15. Furthermore, the acquisition unit 3A acquires information indicating the steering angle of the vehicle 1 (detection result of the steering angle sensor 16) transmitted from the steering angle sensor 16. Furthermore, the acquisition unit 3A acquires the learning results transmitted from the communication device 17.

[0017] In the example shown in Figures 1 and 2, the vehicle recognition sensitivity adjustment system SY includes a big data analysis unit SY1, the own vehicle 1, and multiple probe vehicles PV. Each of the multiple probe vehicle PVs transmits information indicating the operation to the Big Data Analysis Unit SY1 when the driver of the probe vehicle PV performs an operation to turn off the function that controls the light distribution switching of the probe vehicle PV's headlights from a high beam state to a light-blocking high beam state. In addition, each of the multiple probe vehicle PVs transmits information indicating the driving position of the probe vehicle PV at the time the driver of the probe vehicle PV performed the operation, as well as an image of the probe vehicle PV's front camera, to the Big Data Analysis Unit SY1. Furthermore, when the driver of each of the plurality of probe vehicles PV performs an operation to turn off the function of controlling the light distribution switching of the headlamp of the probe vehicle PV from the high beam lighting state to the low beam lighting state, each of the plurality of probe vehicles PV transmits information indicating the operation to the big data analysis unit SY1. Also, each of the plurality of probe vehicles PV transmits information indicating the traveling position of the probe vehicle PV when the driver of the probe vehicle PV performs the operation and the front camera image of the probe vehicle PV to the big data analysis unit SY1. The big data analysis unit SY1 uses the traveling position of the probe vehicle PV and the front camera image of the probe vehicle PV when the driver of the probe vehicle PV performs an operation to turn off the function of controlling the light distribution switching of the headlamp of the probe vehicle PV from the high beam lighting state to the shaded high beam lighting state, and the traveling position of the probe vehicle PV and the front camera image of the probe vehicle PV when the driver of the probe vehicle PV performs an operation to turn off the function of controlling the light distribution switching of the headlamp of the probe vehicle PV from the high beam lighting state to the low beam lighting state, and performs learning on the recognition sensitivity of the oncoming vehicle with the lamp lit in the front camera image of the probe vehicle PV suitable for each traveling position of the probe vehicle PV. Specifically, the big data analysis unit SY1, for example, uses the front camera image of each traveling position of the probe vehicle PV and the label indicating whether it is necessary to increase (that is, make it easier to recognize the oncoming vehicle with the lamp lit in the front camera image) the recognition sensitivity of the oncoming vehicle with the lamp lit in the front camera image of each traveling position of the probe vehicle PV from the default value, decrease (that is, make it more difficult to recognize the oncoming vehicle with the lamp lit in the front camera image) from the default value, or set it to the default value, and performs learning using the training data which is a dataset of the label. Furthermore, the big data analysis unit SY1 uses the model obtained by learning to determine, based on the front camera images at the driving positions of the host vehicle 1 and the plurality of probe vehicles PV, whether it is necessary to increase, decrease, or set to the default value the recognition sensitivity of the oncoming vehicle with its lamp lit included in the front camera image compared to the default value. The information indicating this is generated as the result of learning (recommended vehicle recognition sensitivity), and the result of this learning is transmitted to the host vehicle 1 and the like.

[0018] In the examples shown in FIGS. 1 and 2, as described above, when the driver of the probe vehicle PV performs an operation to turn off the function of controlling the light distribution switching of the headlamp of the probe vehicle PV from the high beam lit state to the shaded high beam lit state, the big data analysis unit SY1 uses the driving position of the probe vehicle PV and the front camera image of the probe vehicle PV at that time, and when the driver of the probe vehicle PV performs an operation to turn off the function of controlling the light distribution switching of the headlamp of the probe vehicle PV from the high beam lit state to the low beam lit state, the driving position of the probe vehicle PV and the front camera image of the probe vehicle PV at that time. Learning is performed on the recognition sensitivity of the oncoming vehicle with its lamp lit included in the front camera image of the probe vehicle PV suitable for each driving position of the probe vehicle PV. In other examples, without using the driving position of the probe vehicle PV and the front camera image of the probe vehicle PV when the driver of the probe vehicle PV performs an operation to turn off the function of controlling the light distribution switching of the headlamp of the probe vehicle PV from the high beam lit state to the low beam lit state, the big data analysis unit SY1 uses the driving position of the probe vehicle PV and the front camera image of the probe vehicle PV when the driver of the probe vehicle PV performs an operation to turn off the function of controlling the light distribution switching of the headlamp of the probe vehicle PV from the high beam lit state to the shaded high beam lit state, and learning may be performed on the recognition sensitivity of the oncoming vehicle with its lamp lit included in the front camera image of the probe vehicle PV suitable for each driving position of the probe vehicle PV.

[0019] In the examples shown in Figures 1 and 2, the vehicle recognition sensitivity adjustment unit 3D adjusts the recognition sensitivity of vehicles ahead with their lights on, as included in the forward camera image of vehicle 1 at each driving position of vehicle 1, based on the learning results (recommended vehicle recognition sensitivity) acquired by the acquisition unit 3A (that is, it either increases the recognition sensitivity from the default value to make it easier to recognize vehicles ahead, decreases the recognition sensitivity from the default value to make it harder to recognize vehicles ahead, or sets the recognition sensitivity to the default value). The vehicle recognition unit 3B recognizes the vehicle ahead with its lights illuminated, as included in the forward camera image of the vehicle 1, using the recognition sensitivity adjusted by the vehicle recognition sensitivity adjustment unit 3D. When the vehicle recognition unit 3B recognizes a vehicle ahead with its lamps lit, as included in the forward camera image of the vehicle 1, the control unit 3C performs control to switch the light distribution of the vehicle 1's headlights 11 from a high beam lit state to a light-blocking high beam lit state.

[0020] In detail, in the examples shown in Figures 1 and 2, if the vehicle speed detected by the vehicle speed sensor 15 is equal to or greater than the vehicle speed threshold, the vehicle recognition sensitivity adjustment unit 3D will set the recognition sensitivity of the vehicle in front with its lights on, as included in the forward camera image of the vehicle 1, to its default value, even if the learning result (recommended vehicle recognition sensitivity) acquired by the acquisition unit 3A indicates that the recognition sensitivity of the vehicle in front with its lights on, as included in the forward camera image of the vehicle 1, should be increased above the default value. Therefore, when the vehicle 1 is driving at high speed and it is necessary to maintain the high beams on, the control of switching the light distribution of the vehicle 1's headlights from the high beam state to the light-blocking high beam state is executed, which could potentially obstruct the driver's view of the vehicle 1. Furthermore, if the vehicle speed detected by the vehicle speed sensor 15 is equal to or greater than the vehicle speed threshold, the vehicle recognition sensitivity adjustment unit 3D will set the recognition sensitivity of the vehicle in front with its lights on, as included in the forward camera image of the vehicle 1, to the default value, even if the learning result (recommended vehicle recognition sensitivity) acquired by the acquisition unit 3A indicates that the recognition sensitivity of the vehicle in front with its lights on, as included in the forward camera image of the vehicle 1, should be lowered from the default value. Therefore, for example, abrupt changes from a state where the light-blocking high beams are on to a state where the high beams are on can be suppressed.

[0021] Furthermore, in the examples shown in Figures 1 and 2, if the steering angle detected by the steering angle sensor 16 is greater than or equal to the steering angle threshold, the vehicle recognition sensitivity adjustment unit 3D will set the recognition sensitivity of the vehicle in front with its lights on, as included in the forward camera image of the vehicle 1, to the default value, even if the learning result (recommended vehicle recognition sensitivity) acquired by the acquisition unit 3A indicates that the recognition sensitivity of the vehicle in front with its lights on, as included in the forward camera image of the vehicle 1, should be increased above the default value. Therefore, when the vehicle 1 is driving on a sharp curve and it is necessary to maintain the high beams on, the control of switching the light distribution of the vehicle 1's headlights from the high beam state to the light-blocking high beam state is executed, which could potentially obstruct the driver's view of the vehicle 1. Furthermore, if the steering angle detected by the steering angle sensor 16 is greater than or equal to the steering angle threshold, the vehicle recognition sensitivity adjustment unit 3D will set the recognition sensitivity of the vehicle in front with its lights on, as included in the forward camera image of the vehicle 1, to the default value, even if the learning result (recommended vehicle recognition sensitivity) acquired by the acquisition unit 3A indicates that the recognition sensitivity of the vehicle in front with its lights on, as included in the forward camera image of the vehicle 1, should be lowered from the default value. Therefore, for example, abrupt changes from a state where the light-blocking high beams are on to a state where the high beams are on can be suppressed.

[0022] In the examples shown in Figures 1 and 2, the vehicle itself functions as a probe vehicle PV. That is, similar to the probe vehicle PV, when the driver of the vehicle itself performs an operation to turn off the function of switching the light distribution of the vehicle's headlights from a high beam state to a light-blocking high beam state, the vehicle itself transmits information indicating that operation to the big data analysis unit SY1. The vehicle itself also transmits information indicating the vehicle's position at the time the driver of the vehicle itself performed that operation, along with an image from the vehicle's front camera, to the big data analysis unit SY1.

[0023] Figure 3 is a flowchart illustrating an example of processing performed by the processor 183 of the headlight control device 18 in the first embodiment. In the example shown in Figure 3, in step S10, the acquisition unit 3A acquires the forward camera image of the vehicle 1, information indicating the driving position of the vehicle 1, information indicating the vehicle speed of the vehicle 1, information indicating the steering angle of the vehicle 1, and the learning results performed by the big data analysis unit SY1. In steps S11 to S17, the vehicle recognition sensitivity adjustment unit 3D adjusts the recognition sensitivity of the vehicle ahead with its lamps lit, as included in the forward camera image of the vehicle 1 at each driving position of the vehicle 1, based on the learning results acquired in step S10. In detail, in step S11, the vehicle recognition sensitivity adjustment unit 3D determines whether the vehicle speed of its own vehicle 1, acquired in step S10, is lower than the vehicle speed threshold. If the answer is YES, the process proceeds to step S12; otherwise, the process proceeds to step S15. In step S12, the vehicle recognition sensitivity adjustment unit 3D determines whether the steering angle of the vehicle 1 acquired in step S10 is smaller than the steering angle threshold. If YES, proceed to step S13; otherwise, proceed to step S15. In step S13, the vehicle recognition sensitivity adjustment unit 3D determines whether it is necessary to set the recognition sensitivity of the vehicle in front of the vehicle with its lamps lit, as included in the front camera image of the vehicle 1, to the default value, based on the front camera image of the vehicle 1 acquired in step S10 and the learning results performed by the big data analysis unit SY1. If the answer is YES, the process proceeds to step S15; otherwise, the process proceeds to step S14. In step S14, the vehicle recognition sensitivity adjustment unit 3D determines whether it is necessary to increase the recognition sensitivity of vehicles ahead with their lights on, as included in the forward camera image of the vehicle 1, above the default value, based on the forward camera image of the vehicle 1 acquired in step S10 and the learning results performed by the big data analysis unit SY1. If the answer is YES, the process proceeds to step S16; otherwise, the process proceeds to step S17.

[0024] In step S15, the vehicle recognition sensitivity adjustment unit 3D sets the recognition sensitivity of the vehicle in front of the vehicle 1 that has its lamp lit, as included in the forward camera image of the vehicle 1, to the default value. In step S16, the vehicle recognition sensitivity adjustment unit 3D increases the recognition sensitivity of the vehicle in front of the vehicle 1 that has its lamp lit, as included in the forward camera image of the vehicle 1, above the default value. In step S17, the vehicle recognition sensitivity adjustment unit 3D lowers the recognition sensitivity of the vehicle in front of the vehicle 1 that has its lamp lit, as included in the forward camera image of the vehicle 1, from the default value. In step S18, the vehicle recognition unit 3B recognizes the vehicle ahead of its own vehicle 1 with its lights on, using the recognition sensitivity adjusted in steps S11 to S17. In step S18, if a vehicle ahead with its lights on is detected in the forward camera image of the vehicle 1, in step S19, the control unit 3C performs control to switch the light distribution of the vehicle 1's headlights 11 from a high beam state to a light-blocking high beam state.

[0025] <Second Embodiment> The vehicle 1 to which the headlight control device 18 of the second embodiment is applied is configured in the same way as the vehicle 1 to which the headlight control device 18 of the first embodiment is applied, except for the points described later.

[0026] As described above, in the vehicle 1 to which the headlight control device 18 of the first embodiment is applied, the headlights 11 have the function of turning on the high beams, the function of turning on the light-blocking high beams, and the function of turning on the low beams. On the other hand, in the vehicle 1 to which the headlight control device 18 of the second embodiment is applied, the headlights 11 have the function of turning on the high beams and the function of turning on the low beams, but do not have the function of turning on the light-blocking high beams. The operations of the driver of the vehicle 1 that the HMI 13 receives include, for example, an operation to turn off the function of the headlight 11's light distribution switching control from the high beam state to the low beam state. When the communication device 17 receives an operation from the driver of the vehicle 1 to turn off the function of the headlight 11's light distribution switching control from the high beam state to the low beam state, the communication device 17 transmits information indicating that operation to the big data analysis unit SY1. The communication device 17 also transmits information indicating the driving position of the vehicle 1 at the time the HMI 13 received that operation, along with a forward camera image, to the big data analysis unit SY1.

[0027] In an example of a vehicle recognition sensitivity adjustment system SY including the vehicle 1 to which the headlight control device 18 of the second embodiment is applied, the big data analysis unit SY1 uses the driving position of the probe vehicle PV and the front camera image of the probe vehicle PV when the driver of the probe vehicle PV turns OFF the function of switching the light distribution of the probe vehicle PV's headlights from a high beam state to a light-shielding high beam state, and the driving position of the probe vehicle PV and the front camera image of the probe vehicle PV when the driver of the probe vehicle PV turns OFF the function of switching the light distribution of the probe vehicle PV's headlights from a high beam state to a low beam state, to learn the recognition sensitivity of the vehicle ahead with the lamps included in the front camera image of the probe vehicle PV that are lit, which is suitable for each driving position of the probe vehicle PV. In another example of the vehicle recognition sensitivity adjustment system SY, which includes the vehicle 1 to which the headlight control device 18 of the second embodiment is applied, the big data analysis unit SY1 may learn the recognition sensitivity of the vehicle ahead with the lamps lit, which are included in the front camera image of the probe vehicle PV, suitable for each driving position of the probe vehicle PV, by using the driving position of the probe vehicle PV and the front camera image of the probe vehicle PV when the driver of the probe vehicle PV performs an operation to turn OFF the function of switching the light distribution of the headlights of the probe vehicle PV from a high beam state to a low beam state, without using the driving position of the probe vehicle PV and the front camera image of the probe vehicle PV when the driver of the probe vehicle PV performs an operation to turn OFF the function of switching the light distribution of the headlights of the probe vehicle PV from a high beam state to a low beam state.

[0028] As described above, in the vehicle 1 to which the headlight control device 18 of the first embodiment is applied, the control unit 3C performs a light distribution switching control of the headlights 11 of the vehicle 1 from a high beam illumination state to a light-blocking high beam illumination state when the vehicle recognition unit 3B recognizes a vehicle ahead that has its lamps lit and is included in the forward camera image of the vehicle 1. On the other hand, in the vehicle 1 to which the headlight control device 18 of the second embodiment is applied, the control unit 3C performs a light distribution switching control of the headlights 11 of the vehicle 1 from a high beam illuminated state to a low beam illuminated state when the vehicle recognition unit 3B recognizes a vehicle ahead that has its lamps illuminated and is included in the forward camera image of the vehicle 1.

[0029] As described above, in the vehicle 1 to which the headlight control device 18 of the first embodiment is applied, when the driver of the vehicle 1 performs an operation to turn OFF the function of switching the light distribution of the vehicle 1's headlights from a high beam illumination state to a light-blocking high beam illumination state, the vehicle 1 transmits information indicating that operation to the big data analysis unit SY1, and also transmits to the big data analysis unit SY1 information indicating the driving position of the vehicle 1 at the time the driver of the vehicle 1 performed that operation, as well as a front camera image of the vehicle 1. On the other hand, in the vehicle 1 to which the headlight control device 18 of the second embodiment is applied, when the driver of the vehicle 1 performs an operation to turn OFF the function of switching the light distribution of the vehicle 1's headlights from the high beam state to the low beam state, similar to the probe vehicle PV, the vehicle 1 transmits information indicating that operation to the big data analysis unit SY1, and also transmits to the big data analysis unit SY1 information indicating the driving position of the vehicle 1 at the time the driver of the vehicle 1 performed that operation, as well as a front camera image of the vehicle 1.

[0030] <Third Embodiment> A vehicle 1 to which the headlight control device 18 of the third embodiment is applied is configured in the same way as a vehicle 1 to which the headlight control device 18 of the first or second embodiment described above is applied, except for the points described later.

[0031] In the vehicle 1 to which the headlight control device 18 of the third embodiment is applied, when the driver of the vehicle 1 turns OFF the function of switching the light distribution of the vehicle 1's headlights from a high beam state to a light-shielding high beam or low beam state, the vehicle 1 does not transmit information indicating that operation to the big data analysis unit SY1, nor does the driver of the vehicle 1 transmit information indicating the vehicle 1's driving position at the time of that operation, nor does the vehicle 1 transmit the forward camera image of the vehicle 1 to the big data analysis unit SY1. In other words, the vehicle 1 does not function as a probe vehicle PV.

[0032] As described above, embodiments of the headlight control device, headlight control method, and program of the present disclosure have been explained with reference to the drawings. However, the headlight control device, headlight control method, and program of the present disclosure are not limited to the embodiments described above, and can be modified as appropriate without departing from the spirit of the present disclosure. The configurations of each example of the embodiments described above may be combined as appropriate. In each example of the embodiments described above, the processing performed in the headlight control device 18 (ECU) was described as software processing performed by executing a program. However, the processing performed in the headlight control device 18 may be hardware processing. Alternatively, the processing performed in the headlight control device 18 may be a combination of both software and hardware processing. Furthermore, the program stored in the memory 182 of the headlight control device 18 (the program that realizes the functions of the processor 183 of the headlight control device 18) may be recorded on a computer-readable storage medium such as a semiconductor memory, magnetic recording medium, or optical recording medium and provided and distributed. [Explanation of Symbols]

[0033] 1...Vehicle, 11...Headlight, 12...Front camera, 13...HMI, 14...Location information acquisition device, 15...Vehicle speed sensor, 16...Steering angle sensor, 17...Communication device, 18...Headlight control device, 181...Communication interface, 182...Memory, 183...Processor, 3A...Acquisition unit, 3B...Vehicle recognition unit, 3C...Control unit, 3D...Vehicle recognition sensitivity adjustment unit, SY...Vehicle recognition sensitivity adjustment system, SY1...Big data analysis unit, PV...Probe vehicle, NW...Network

Claims

1. A vehicle recognition unit that recognizes a vehicle ahead with its lights on, included in the forward camera image of the vehicle, When the vehicle recognition unit recognizes a vehicle ahead with its lights on, as captured in the forward camera image of the vehicle itself, the control unit performs a control to switch the light distribution of the vehicle's headlights from a high beam state to a shaded high beam state, which is a high beam that shades the vehicle ahead with its lights on and its surroundings, as captured in the forward camera image of the vehicle itself, or a control to switch the light distribution of the vehicle's headlights from a high beam state to a low beam state. An acquisition unit acquires the results of learning the recognition sensitivity of a vehicle ahead with its lamps lit, which is included in the forward camera image of the probe vehicle, when the driver of the probe vehicle performs an operation to turn OFF the function of switching the light distribution of the probe vehicle's headlights from a high beam state to a light-blocking high beam state, or an operation to turn OFF the function of switching the light distribution of the probe vehicle's headlights from a high beam state to a low beam state, and when the driver of the probe vehicle performs driving position of the probe vehicle and the forward camera image of the probe vehicle, which is appropriate for each driving position of the probe vehicle. A headlight control device comprising: a vehicle recognition sensitivity adjustment unit that adjusts the recognition sensitivity of a forward vehicle with its lamps lit, as included in the forward camera image of the vehicle at each driving position of the vehicle, based on the learning results acquired by the acquisition unit.

2. The acquisition unit acquires the detection result of the steering angle sensor of the vehicle, The headlight control device according to claim 1, wherein the vehicle recognition sensitivity adjustment unit sets the recognition sensitivity of a forward vehicle with its lamps lit, as included in the forward camera image of the own vehicle, to a default value when the steering angle detected by the steering angle sensor is equal to or greater than a steering angle threshold.

3. The acquisition unit acquires the detection result of the vehicle speed sensor of the vehicle itself, The headlight control device according to claim 1, wherein the vehicle recognition sensitivity adjustment unit sets the recognition sensitivity of a forward vehicle with its lamps lit, included in the forward camera image of the own vehicle, to a default value when the vehicle speed detected by the vehicle speed sensor is equal to or greater than a vehicle speed threshold.

4. The headlight control device performs a vehicle recognition step in which it recognizes a vehicle ahead that has its lights on, as included in the forward camera image of its own vehicle. When a vehicle ahead with its lights on, as captured in the forward camera image of the vehicle itself, is recognized in the vehicle recognition step, the headlight control device performs a control step in which it controls the light distribution of the vehicle's headlights from a high beam state to a shaded high beam state, which is a high beam that shades the vehicle ahead with its lights on and its surroundings, as captured in the forward camera image of the vehicle itself, or controls the light distribution of the vehicle's headlights from a high beam state to a low beam state. The headlight control device performs an operation to turn OFF the function of switching the light distribution of the probe vehicle's headlights from a high beam state to a light-shielding high beam state, or an operation to turn OFF the function of switching the light distribution of the probe vehicle's headlights from a high beam state to a low beam state, and acquires the results of learning the recognition sensitivity of the forward vehicle with its lamps lit, which is appropriate for each driving position of the probe vehicle, using the forward camera image of the probe vehicle and the driving position of the probe vehicle. A headlight control method comprising: a vehicle recognition sensitivity adjustment step, in which the headlight control device adjusts the recognition sensitivity of a forward vehicle whose lamp is lit, as included in the forward camera image of the vehicle at each driving position of the vehicle, based on the learning results acquired in the acquisition step.

5. In the processor, A vehicle recognition step that recognizes a vehicle ahead with its lights on, included in the forward camera image of the vehicle, If a vehicle ahead with its lights on, as captured in the forward camera image of the vehicle itself, is recognized in the vehicle recognition step, the control step includes performing a control to switch the light distribution of the vehicle's headlights from a high beam state to a shaded high beam state, which is a high beam that shades the vehicle ahead with its lights on and its surroundings, as captured in the forward camera image of the vehicle itself, or a control to switch the light distribution of the vehicle's headlights from a high beam state to a low beam state. An acquisition step to acquire the results of learning the recognition sensitivity of the vehicle ahead with its lamps lit, which is included in the forward camera image of the probe vehicle and is suitable for each driving position of the probe vehicle, when the driver of the probe vehicle performs an operation to turn OFF the function of switching the light distribution of the probe vehicle's headlights from a high beam state to a light-blocking high beam state, or an operation to turn OFF the function of switching the light distribution of the probe vehicle's headlights from a high beam state to a low beam state, and the forward camera image of the probe vehicle; A program for performing a vehicle recognition sensitivity adjustment step, which adjusts the recognition sensitivity of a vehicle ahead with its lights on, as included in the forward camera image of the vehicle at each driving position of the vehicle, based on the learning results obtained in the acquisition step.

Images