Vehicle light control method and device, vehicle and storage medium

Abstract

The invention discloses a vehicle light control method and device, a vehicle and a storage medium, and belongs to the technical field of vehicles. According to the technical scheme, under the condition that the high beam of the target vehicle is turned on, whether the target object exists in front of the target vehicle or not is determined, and therefore whether the high beam needs to be controlled or not is determined. Under the condition that the target object exists in front of the target vehicle, a target shielding area which should not be irradiated by the high beam on the target object is determined; the relative position between the target shielding area and the target vehicle is determined, the high beam is controlled through the relative position, so that the high beam keeps emitting light and does not irradiate the target shielding area, under the condition that a driver of the target vehicle has a good driving view, the influence on front vehicles or pedestrians is relieved, and the driving safety is improved. Therefore, the safety of night driving is improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicles, and more particularly, to a method and apparatus for controlling vehicle lights, a vehicle, and a storage medium in the technical field of vehicles. Background Art

[0002] When a driver is driving at night, the high beam is usually turned on. However, turning on the high beam will cause glare to the driver of an oncoming vehicle or a pedestrian, resulting in momentary blindness, making it easy to cause danger during the passing of two vehicles or the encounter of a vehicle and a pedestrian. Moreover, turning on the high beam will also affect the driver of a vehicle driving in the same direction ahead. For example, it will cause discomfort to the driver of the vehicle ahead, distract attention, and lead to the occurrence of danger.

[0003] In the related art, the above problems are often solved by turning off the high beam. However, turning off the high beam will cause the driver's field of vision of the vehicle to deteriorate, resulting in potential safety hazards for the vehicle. Summary of the Invention

[0004] Embodiments of the present application provide a method and apparatus for controlling vehicle lights, a vehicle, and a storage medium, which can keep the high beam on while preventing glare, thereby improving the driver's field of vision and the safety of night driving. The technical solutions are as follows:

[0005] On the one hand, a method for controlling vehicle lights is provided. The method includes:

[0006] When the high beam of the target vehicle is turned on, determining whether there is a target object in front of the target vehicle, where the target object includes a vehicle or a pedestrian

[0007] When there is the target object in front of the target vehicle, determining a target shielding area of the target object;

[0008] Determining a relative position between the target shielding area and the target vehicle;

[0009] Based on the relative position between the target shielding area and the target vehicle, controlling the high beam so that the high beam remains lit and does not irradiate the target shielding area.

[0010] In a possible implementation manner, when determining whether there is a target object in front of the target vehicle when the high beam of the target vehicle is turned on includes:

[0011] When the high beam of the target vehicle is turned on, obtaining visual information in front of the target vehicle through a visual sensor of the target vehicle;

[0012] Perform object recognition on the visual information to determine whether there is a target object in front of the target vehicle.

[0013] In a possible implementation, when there is the target object in front of the target vehicle, determining the target occlusion area of the target object includes:

[0014] When there is the target object in front of the target vehicle, based on the type of the target object, determine multiple key points of the target object;

[0015] Based on the multiple key points of the target object, determine the target occlusion area of the target object.

[0016] In a possible implementation, the determining multiple key points of the target object based on the type of the target object includes:

[0017] When the type of the target object is a vehicle, determine at least two headlight key points and at least two roof key points of the target object, where the headlight key points correspond to the headlights or brake lights of the vehicle, and the at least two roof key points are located above the at least two headlight key points and correspond one-to-one with the at least two headlight key points;

[0018] When the type of the target object is a pedestrian, determine the head key point and two shoulder key points of the target object.

[0019] In a possible implementation, the determining the target occlusion area of the target object based on the multiple key points of the target object includes:

[0020] When the type of the target object is a vehicle, determine the area enclosed by the at least two headlight key points and the at least two roof key points as the target occlusion area of the target object;

[0021] When the type of the target object is a pedestrian, determine the area enclosed by the head key point and the two shoulder key points as the target occlusion area of the target object.

[0022] In a possible implementation, the determining the relative position between the target occlusion area and the target vehicle includes:

[0023] Determine the distance between the target occlusion area and the target vehicle;

[0024] Determine the azimuth angle between the target occlusion area and the target vehicle.

[0025] In a possible implementation, the determining the distance between the target occlusion area and the target vehicle includes:

[0026] Determine the distances between multiple key points of the target occlusion area and the target vehicle through radar, and the positions of the multiple key points are related to the type of the target object;

[0027] The determining the azimuth angle between the target occlusion area and the target vehicle includes:

[0028] Determine the radar emission angles respectively corresponding to the multiple key points as the azimuth angles between the multiple key points and the target vehicle.

[0029] In a possible implementation manner, the controlling the high beam based on the relative position between the target occlusion area and the target vehicle includes:

[0030] Based on the relative position between the target occlusion area and the target vehicle, determine the lamp beads in the high beam corresponding to the target occlusion area;

[0031] Control the lamp beads corresponding to the target occlusion area to go out and keep other lamp beads lit.

[0032] In a possible implementation manner, the relative position between the target occlusion area and the target vehicle includes the distance and azimuth angle between the target occlusion area and the target vehicle, and the determining the lamp beads in the high beam corresponding to the target occlusion area based on the relative position between the target occlusion area and the target vehicle includes:

[0033] Based on the distance and azimuth angle between the target occlusion area and the target vehicle, determine the target high beam illumination range corresponding to the target occlusion area;

[0034] Compare the illumination ranges of the multiple lamp beads in the high beam at the distance with the target high beam illumination range;

[0035] Determine the lamp beads whose illumination ranges are within the target high beam illumination range as the lamp beads corresponding to the target occlusion area.

[0036] On the one hand, a vehicle lighting control device is provided, and the device includes:

[0037] A target object determination module, configured to determine whether there is a target object in front of the target vehicle when the high beam of the target vehicle is turned on, and the target object includes a vehicle or a pedestrian

[0038] An occlusion area determination module, configured to determine the target occlusion area of the target object when the target object exists in front of the target vehicle;

[0039] A relative position determination module, configured to determine the relative position between the target occlusion area and the target vehicle;

[0040] A high beam control module, configured to control the high beam based on the relative position between the target occlusion area and the target vehicle, so that the high beam remains on and does not shine on the target occlusion area.

[0041] In a possible implementation manner, the target object determination module is configured to, when the high beam of the target vehicle is turned on, obtain visual information in front of the target vehicle through a visual sensor of the target vehicle; perform target recognition on the visual information to determine whether there is a target object in front of the target vehicle.

[0042] In a possible implementation manner, the occlusion area determination module is configured to, when there is a target object in front of the target vehicle, determine a plurality of key points of the target object based on the type of the target object; and determine the target occlusion area of the target object based on the plurality of key points of the target object.

[0043] In a possible implementation manner, when the type of the target object is a vehicle, the occlusion area determination module is configured to determine at least two headlight key points and at least two roof key points of the target object, where the headlight key points correspond to the high beams or brake lights of the vehicle, and the at least two roof key points are located above the at least two headlight key points and correspond to the at least two headlight key points one by one; when the type of the target object is a pedestrian, determine the head key point and two shoulder key points of the target object.

[0044] In a possible implementation manner, when the type of the target object is a vehicle, the occlusion area determination module is configured to determine the area surrounded by the at least two headlight key points and the at least two roof key points as the target occlusion area of the target object; when the type of the target object is a pedestrian, determine the area surrounded by the head key point and the two shoulder key points as the target occlusion area of the target object.

[0045] In a possible implementation manner, the relative position determination module is configured to determine the distance between the target occlusion area and the target vehicle; and determine the azimuth angle between the target occlusion area and the target vehicle.

[0046] In a possible implementation, the relative position determination module is configured to determine the distances between multiple key points of the target occlusion area and the target vehicle through a radar, where the positions of the multiple key points are related to the type of the target object; and determine the radar emission angles corresponding to the multiple key points as the azimuth angles between the multiple key points and the target vehicle respectively.

[0047] In a possible implementation, the high beam control module is configured to determine the lamp beads in the high beam that correspond to the target occlusion area based on the relative position between the target occlusion area and the target vehicle; and control the lamp beads corresponding to the target occlusion area to turn off and keep other lamp beads lit.

[0048] In a possible implementation, the relative position between the target occlusion area and the target vehicle includes the distance and the azimuth angle between the target occlusion area and the target vehicle. The high beam control module is configured to determine the target high beam illumination range corresponding to the target occlusion area based on the distance and the azimuth angle between the target occlusion area and the target vehicle; compare the illumination ranges of the multiple lamp beads in the high beam at the distance with the target high beam illumination range; and determine the lamp beads whose illumination ranges are within the target high beam illumination range as the lamp beads corresponding to the target occlusion area.

[0049] On the one hand, a vehicle is provided, which includes one or more processors and one or more memories. At least one program code is stored in the one or more memories, and the program code is loaded and executed by the one or more processors to implement the operations performed by the vehicle's lighting control method.

[0050] On the one hand, a computer-readable storage medium is provided, in which at least one program code is stored, and the program code is loaded and executed by a processor to implement the operations performed by the vehicle's lighting control method.

[0051] Through the technical solution provided by the embodiments of the present application, when the high beam of the target vehicle is turned on, it is determined whether there is a target object in front of the target vehicle, so as to determine whether the high beam needs to be controlled. When there is a target object in front of the target vehicle, the target occlusion area on the target object that should not be illuminated by the high beam is determined. The relative position between the target occlusion area and the target vehicle is determined, and the relative position is used to control the high beam so that the high beam remains lit and does not illuminate the target occlusion area, reducing the impact on the vehicle or pedestrian in front while keeping the driver of the target vehicle with a good driving vision, thereby improving the safety of night driving. Description of the Drawings

[0052] Figure 1 It is a schematic diagram of the implementation environment of a vehicle lighting control method provided by an embodiment of the present application;

[0053] Figure 2 It is a flowchart of a vehicle lighting control method provided by an embodiment of the present application;

[0054] Figure 3 It is a flowchart of another vehicle lighting control method provided by an embodiment of the present application;

[0055] Figure 4 It is a schematic diagram of determining a relative position provided by an embodiment of the present application;

[0056] Figure 5 It is a schematic diagram of the effect of the high beam when the technical solution provided by the embodiment of the present application is not adopted;

[0057] Figure 6 It is a schematic diagram of the effect of the high beam when the technical solution provided by the embodiment of the present application is adopted;

[0058] Figure 7 It is another schematic diagram of the effect of the high beam when the technical solution provided by the embodiment of the present application is adopted;

[0059] Figure 8 It is a schematic diagram of the structure of a vehicle lighting control device provided by an embodiment of the present application;

[0060] Figure 9 It is a schematic diagram of the structure of a vehicle provided by an embodiment of the present application. Detailed implementation manners

[0061] Next, the technical solutions in the present application will be clearly and elaborately described in conjunction with the accompanying drawings. Among them, in the description of the embodiments of the present application, unless otherwise specified, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0062] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as implying or suggesting relative importance or implicitly indicating the quantity of the technical features reflected. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0063] To illustrate the technical solutions provided in the embodiments of the present application, some terms related to the embodiments of the present application will be introduced below.

[0064] Adaptive Driving Beam (ADB): When a vehicle drives with its headlights on at night, the vehicle's headlights use sensors (usually a camera located inside the front windshield) to determine the situation of oncoming or same-direction vehicles and pedestrians on the road, and automatically switch between high and low beams, enabling the driver to focus more on driving without having to frequently switch between high and low beams.

[0065] LED (Light-Emitting Diode): A commonly used light-emitting device that emits light by the recombination of electrons and holes.

[0066] Target recognition: Refers to the process of distinguishing a special target (or a type of target) from other targets (or other types of targets). It includes both the recognition of two very similar targets and the recognition of a type of target from other types of targets.

[0067] Key point detection: A computer vision technology whose purpose is to find meaningful feature points in an image or video and locate them at each feature point. These feature points are usually called key points because they are unique in the image and can be used to represent the content or shape of the image.

[0068] After introducing the terms related to the embodiments of the present application, the implementation environment of the embodiments of the present application will be introduced below. See Figure 1 , the implementation environment of the vehicle's light control method provided in the embodiments of the present application includes an in-vehicle terminal 101 and a headlight controller 102.

[0069] The in-vehicle terminal 101 is a terminal installed in the vehicle, used to acquire data collected by multiple vehicle components of the vehicle, process the acquired data, and control the vehicle components according to the data processing results. The in-vehicle terminal 101 is connected to multiple vehicle components through a CAN (Controller Area Network) network, thereby realizing data interaction with the vehicle components.

[0070] The headlight controller 102 belongs to a type of vehicle component. The headlight controller 102 is used to control the vehicle's headlights. In the embodiments of the present application, it particularly refers to controlling the vehicle's high beams. The headlight controller 102 can receive instructions sent by the in-vehicle terminal 101 and control the high beams according to the instructions. In the embodiments of the present application, the vehicle's high beams include multiple lamp beads, and the lighting and extinguishing of each lamp bead can be independently controlled by the headlight controller 102.

[0071] After introducing the implementation environment of the embodiments of the present application, the application scenarios of the technical solutions provided by the embodiments of the present application will be introduced below. The technical solutions provided by the embodiments of the present application can be applied to various types of vehicles. For example, the technical solutions provided by the embodiments of the present application can be applied to electric vehicles, can also be applied to hybrid vehicles, and can also be applied to fuel vehicles. The embodiments of the present application do not limit this.

[0072] When the technical solution provided by the embodiment of the present application is applied to an electric vehicle, when the high beam of the electric vehicle is turned on, it is determined whether there is a target object in front of the electric vehicle, that is, it is determined whether there are vehicles and pedestrians in front of the electric vehicle. When there is a target object in front of the electric vehicle, the target shielding area of the target object is determined. The target shielding area refers to the area where the high beam should not shine. For example, the eyes of pedestrians and the eyes of the driver in the vehicle belong to the target shielding area. The relative position between the target shielding area and the electric vehicle is determined, and the high beam is controlled based on the relative position, so that the high beam remains on and does not shine on the target shielding area, reducing the impact on the vehicle or pedestrian in front while keeping the driver of the target vehicle with a good driving vision, thereby improving the safety of night driving.

[0073] It should be noted that the above is described by taking the technical solution provided by the embodiment of the present application applied to an electric vehicle as an example. When the technical solution provided by the embodiment of the present application is applied to other types of vehicles, the implementation process belongs to the same inventive concept as the above description and will not be repeated here.

[0074] In addition, the technical solutions provided by the embodiments of the present application can be applied to other types of vehicles in addition to the above several types of vehicles. The embodiments of the present application do not limit this.

[0075] After introducing the implementation environment and application scenarios of the embodiments of the present application, the technical solutions provided by the embodiments of the present application will be introduced below. See Figure 2 , taking the in-vehicle terminal as the execution entity as an example, the method includes the following steps.

[0076] 201. When the high beam of the target vehicle is turned on, the in-vehicle terminal determines whether there is a target object in front of the target vehicle, and the target object includes a vehicle or a pedestrian.

[0077] Among them, the target vehicle is a vehicle with ADB function, and the target vehicle can be an electric vehicle, a hybrid vehicle or a fuel vehicle, which is not limited in the embodiments of the present application. The turning on of the high beam of the target vehicle means that the target vehicle turns on the ADB function and the ADB function turns on the high beam; or, the turning on method of the high beam can also be not limited, which simply means that the high beam of the target vehicle is turned on to achieve decoupling from the ADB function, which is not limited in the embodiments of the present application. The high beam of the target vehicle includes multiple lamp beads, and the lighting and extinguishing of each lamp bead can be independently controlled. The vehicles in the target object include both the vehicles driving in the same direction as the target vehicle and the vehicles driving in the opposite direction to the target vehicle; correspondingly, the pedestrians in the target object include both the pedestrians facing the target vehicle and the pedestrians with their backs to the target vehicle.

[0078] 202. When the target object exists in front of the target vehicle, the in-vehicle terminal determines the target occlusion area of the target object.

[0079] Among them, the target occlusion area refers to the area that the high beam should not irradiate. For example, the eyes of pedestrians and the eyes of drivers in vehicles belong to the target occlusion area. Or rather, the target occlusion area refers to the occlusion area formed by the high beam emitted by the target vehicle in the area where the front target object is located. In some embodiments, the target occlusion area is also referred to as the high beam occlusion area.

[0080] 203. The in-vehicle terminal determines the relative position between the target occlusion area and the target vehicle.

[0081] Among them, the relative position between the target occlusion area and the target vehicle includes the distance and azimuth angle between the target occlusion area and the target vehicle, and the azimuth angle is determined based on the target vehicle.

[0082] 204. The in-vehicle terminal controls the high beam based on the relative position between the target occlusion area and the target vehicle, so that the high beam keeps emitting light and does not irradiate the target occlusion area.

[0083] Among them, the high beam includes multiple lamp beads, and controlling the high beam means controlling the lamp beads in the high beam, that is, controlling the lighting and extinguishing of the multiple lamp beads. In the embodiments of the present application, the turned-off lamp beads are the lamp beads corresponding to the target occlusion area, that is, the lamp beads whose emitted light will irradiate the target occlusion area. In some embodiments, the lamp bead is an LED lamp bead.

[0084] Through the technical solution provided by the embodiments of the present application, when the high beam of the target vehicle is turned on, it is determined whether there is a target object in front of the target vehicle, so as to determine whether the high beam needs to be controlled. When there is a target object in front of the target vehicle, the target shielding area that should not be irradiated by the high beam on the target object is determined. The relative position between the target shielding area and the target vehicle is determined, and this relative position is used to control the high beam, so that the high beam remains on and does not irradiate the target shielding area, reducing the impact on the vehicle or pedestrian in front while keeping the driver of the target vehicle with a good driving vision, thereby improving the safety of night driving.

[0085] It should be noted that the above steps 201-204 are a simple description of the vehicle's lighting control method provided by the embodiments of the present application. Below, some examples will be combined to provide a more detailed description of the vehicle's lighting control method provided by the embodiments of the present application. See Figure 3 , taking the in-vehicle terminal as the execution entity as an example, the method includes the following steps.

[0086] 301. When the adaptive high beam function of the target vehicle is turned on, the in-vehicle terminal obtains the ambient light information around the target vehicle.

[0087] Among them, the target vehicle is a vehicle with an adaptive high beam (ADB) function. When the adaptive high beam function is turned on, it can realize the automatic control of the high beam, that is, it can turn on / off the high beam according to the actual situation, and the driver no longer needs to pay attention to the use of the vehicle's lights and can focus on driving. The target vehicle is an electric vehicle, a hybrid vehicle or a fuel vehicle, and the embodiments of the present application do not limit this. The ambient light information can reflect the situation of the ambient light, that is, the ambient light information can reflect the intensity of the ambient light. In some embodiments, the ambient light information includes the ambient light intensity.

[0088] In a possible implementation manner, when the adaptive high beam function of the target vehicle is turned on, the in-vehicle terminal obtains the ambient light information around the target vehicle through the ambient light sensor of the target vehicle.

[0089] Among them, the ambient light sensor is installed outside the target vehicle, and the ambient light sensor determines the ambient light information using the principle of photoelectric conversion. When the ambient light information includes the ambient light intensity, the ambient light sensor is also the ambient light intensity sensor.

[0090] In this implementation manner, when the adaptive high beam function is turned on, the ambient light information around the target vehicle can be obtained through the ambient light sensor, and the acquisition efficiency of the ambient light information is relatively high.

[0091] For example, when the adaptive high beam function of the target vehicle is turned on, the in-vehicle terminal determines the operating state of the ambient light sensor. When the operating state of the ambient light sensor is normal operation, the in-vehicle terminal obtains the ambient light information collected by the ambient light sensor. When the operating state of the ambient light sensor is non-operation or abnormal operation, the in-vehicle terminal determines the preset ambient light information corresponding to the current moment as the ambient light information around the target vehicle. Among them, the correspondence between the moment and the preset ambient light information is set by the technical personnel according to the actual situation, and the embodiments of the present application do not limit this.

[0092] Optionally, before step 301, the in-vehicle terminal can also perform the following steps.

[0093] In a possible implementation manner, the in-vehicle terminal initializes the adaptive high beam function to ensure the normal use of the adaptive high beam function subsequently.

[0094] Among them, initialization means assigning variables to default values, setting controls to default states, and getting things ready that are not prepared.

[0095] For example, the in-vehicle terminal obtains the power supply parameters, power source parameters, power source parameters, vehicle system parameters, and vehicle driving parameters of the headlight controller. When the power supply parameters, power source parameters, power source parameters, vehicle system parameters, and vehicle driving parameters meet the initialization conditions, the in-vehicle terminal initializes the adaptive high beam function.

[0096] For example, the power supply parameters include the power supply state and supply voltage of the headlight controller, the power source parameters include the power source mode and power valid signal, the power source parameters include the engine state or high voltage state, the vehicle system parameters include the vehicle system fault parameters, and the vehicle driving parameters include the vehicle speed and vehicle speed valid signal. When the power supply state of the headlight controller is normal power supply, the supply voltage is within the normal voltage range, the power source mode is on, the power valid signal is valid, the engine state is started or the high voltage state is high voltage, the vehicle system fault parameters indicate that the vehicle system has no fault, the vehicle speed is less than or equal to the first vehicle speed threshold and the vehicle speed valid signal is valid, the in-vehicle terminal initializes the adaptive high beam function.

[0097] It should be noted that the above preconditions for initializing the adaptive high beam function are only examples, and the technical personnel can add, adjust, or delete the above conditions according to the actual situation. The embodiments of the present application do not limit this.

[0098] The following describes the process of starting after the initialization of the adaptive high beam function.

[0099] In a possible implementation, the in-vehicle terminal determines the power state of the vehicle system, the lighting state, the state of the adaptive high beam function, the state of the low beam lights, the state of the adaptive high beam function enable switch, the state of the ambient light sensor, the road surface lighting state, and the vehicle speed. When the power state of the vehicle system, the lighting state, the state of the adaptive high beam function, the state of the low beam lights, the state of the adaptive high beam function enable switch, the state of the ambient light sensor, the road surface lighting state, and the vehicle speed meet the enabling conditions, the in-vehicle terminal enables the adaptive high beam function.

[0100] For example, the in-vehicle terminal determines the power state of the vehicle system, the lighting state, the state of the adaptive high beam function, the state of the low beam lights, the state of the adaptive high beam function enable switch, the state of the ambient light sensor, the state of the camera, the road surface lighting state, and the vehicle speed. When the power state of the vehicle system is on, the lighting state is automatic lighting, the state of the adaptive high beam function is normal, the state of the low beam lights is fault-free and on, the state of the adaptive high beam function enable switch is on, the state of the ambient light sensor is normal, the state of the camera is normal, the road surface lighting state is normal, and the vehicle speed is greater than or equal to the second vehicle speed threshold, the in-vehicle terminal enables the adaptive high beam function.

[0101] 302. When the ambient light information meets the preset conditions, the in-vehicle terminal turns on the high beam lights of the target vehicle.

[0102] Among them, the high beam lights of the target vehicle include multiple lamp beads, and the lighting and extinguishing of each lamp bead can be independently controlled. The multiple lamp beads form a preset array, and the light emitted by different lamp beads can illuminate different positions in front of the target vehicle. The combination of the light emitted by the multiple lamp beads forms the light emitted by the high beam lights. The preset array is set by the technical personnel according to the actual situation, and the embodiments of the present application do not limit this. Turning on the high beam lights means turning on all or part of the lamp beads in the high beam lights. The ambient light information meeting the preset conditions means that the ambient light around the target vehicle is weak and the high beam lights need to be turned on for lighting. The preset conditions are set by the technical personnel according to the actual situation, and the embodiments of the present application do not limit this. In some embodiments, each lamp bead has a lamp bead identifier, and the lamp bead identifiers of different lamp beads are different. Different lamp beads can be distinguished through the lamp bead identifier. In the subsequent process of controlling the high beam lights, different lamp beads can be found according to the lamp bead identifier for control. In some embodiments, the lamp bead is an LED lamp bead.

[0103] In a possible implementation, the ambient light information includes the ambient light intensity. When the ambient light intensity is less than or equal to the first ambient light intensity threshold, the in-vehicle terminal sends a high beam light turn-on instruction to the headlight controller of the target vehicle, and the headlight controller turns on the high beam lights after receiving the high beam light turn-on instruction.

[0104] Among them, the first ambient light intensity threshold is set by the technician according to the actual situation, and the embodiments of the present application do not limit this.

[0105] For example, the ambient light information includes the ambient light intensity. When the ambient light intensity is less than or equal to the first ambient light intensity threshold, the in-vehicle terminal sends a high beam headlight turn-on instruction to the headlight controller of the target vehicle, and the high beam headlight turn-on instruction carries the brightness level of the high beam headlight. The headlight controller obtains the high beam headlight turn-on instruction and obtains the brightness level from the high beam headlight turn-on instruction. The headlight controller controls the high beam headlight to power on the number of lamp beads corresponding to the brightness level to turn on the high beam headlight. Among them, the correspondence between the brightness level and the number of lamp beads is set by the technician according to the actual situation, and the embodiments of the present application do not limit this.

[0106] Optionally, after step 301, the in-vehicle terminal can also execute the following steps.

[0107] In a possible implementation manner, when the ambient light information does not meet the preset conditions, the in-vehicle terminal turns on the low beam headlight or the daytime running light of the target vehicle based on the ambient light information.

[0108] In this implementation manner, the low beam headlight or the daytime running light can be turned on according to the ambient light information, improving the intelligence level of the target vehicle.

[0109] For example, the ambient light information includes the ambient light intensity. When the ambient light intensity is greater than the first ambient light intensity threshold, the in-vehicle terminal compares the ambient light intensity with a second ambient light intensity threshold, and the second ambient light intensity threshold is greater than the first ambient light intensity threshold. When the ambient light intensity is less than or equal to the second ambient light intensity threshold, the in-vehicle terminal turns on the low beam headlight of the target vehicle; when the ambient light intensity is greater than the second ambient light intensity threshold, the in-vehicle terminal turns on the daytime running light of the target vehicle.

[0110] It should be noted that the above steps 301 and 302 are optional steps. The in-vehicle terminal can either execute the above steps 301 and 302 and then execute the following step 303, or directly execute the following step 303. The embodiments of the present application do not limit this.

[0111] 303. When the high beam headlight of the target vehicle is turned on, the in-vehicle terminal determines whether there is a target object in front of the target vehicle, and the target object includes a vehicle or a pedestrian.

[0112] Among them, the activation of the high beam of the target vehicle means that the ADB function of the target vehicle is activated and the high beam is turned on by the ADB function. Alternatively, the way of turning on the high beam may not be limited, and it simply means that the high beam of the target vehicle is turned on, achieving decoupling from the ADB function. The embodiments of the present application do not limit this. The vehicles in the target objects include both the vehicles traveling in the same direction as the target vehicle and the vehicles traveling in the opposite direction to the target vehicle. Correspondingly, the pedestrians in the target objects include both the pedestrians facing the target vehicle and the pedestrians with their backs to the target vehicle.

[0113] In a possible implementation manner, when the high beam of the target vehicle is turned on, the in-vehicle terminal obtains the visual information in front of the target vehicle through the visual sensor of the target vehicle. The in-vehicle terminal performs target recognition on the visual information to determine whether there is a target object in front of the target vehicle.

[0114] Among them, since the activation of the high beam of the target vehicle will affect the objects in front of the target vehicle and will not affect the objects behind and on both sides of the target vehicle, then the visual sensor only needs to be used to obtain the visual information in front of the target vehicle, and the visual sensor is installed in front of or on the top of the target vehicle. In some embodiments, the visual sensor is also referred to as an image sensor or an image acquisition element. Correspondingly, the visual information is an image. In other embodiments, the visual sensor is also referred to as a radar, and the radar includes a lidar, a millimeter-wave radar, an ultrasonic radar, etc. The embodiments of the present application do not limit this. Correspondingly, the visual information is a point cloud.

[0115] In this implementation manner, when the high beam of the target vehicle is turned on, the visual information in front of the target vehicle is obtained through the visual sensor. By performing target recognition on the visual information, it can be determined whether there is a target object in front of the target vehicle, and the efficiency and accuracy are relatively high.

[0116] The above implementation manner will be described below by way of examples.

[0117] Example 1: When the high beam of the target vehicle is turned on, the in-vehicle terminal obtains the image in front of the target vehicle through the camera in front of or on the top of the target vehicle. The in-vehicle terminal performs target detection on the image to obtain multiple candidate objects in the image. The in-vehicle terminal determines whether there is a target object among the multiple candidate objects. Among them, the candidate object is an object that may affect the driving safety of the vehicle. For example, the candidate objects include vehicles, pedestrians, roadblocks, road signs, traffic lights, buildings, and lane lines, etc. In the embodiments of the present application, the target object belongs to the candidate object, and the target object is an object related to the high beam control.

[0118] For example, when the high beam of the target vehicle is turned on, the in-vehicle terminal obtains an image in front of the target vehicle through a camera in front of or on top of the target vehicle. The in-vehicle terminal inputs the image into a first target detection model, extracts features of the image through the first target detection model, and obtains the image features of the image. The in-vehicle terminal classifies multiple regions of the image based on the image features through the first target detection model, determines whether there are candidate objects in each region, and obtains multiple candidate objects in the image. The in-vehicle terminal determines whether there is a target object among the multiple candidate objects based on the types of the multiple candidate objects. That is, when there are candidate objects of the types of vehicle or pedestrian among the multiple candidate objects, the in-vehicle terminal determines the candidate object as the target object, that is, there is a target object in front of the target vehicle. When there are no candidate objects of the types of vehicle or pedestrian among the multiple candidate objects, the in-vehicle terminal determines that there is no target object in front of the target vehicle.

[0119] For another example, when the high beam of the target vehicle is turned on, the in-vehicle terminal obtains an image in front of the target vehicle through a camera in front of or on top of the target vehicle. The in-vehicle terminal performs template matching on the image using multiple object templates, and determines whether there is a target object on the image. The multiple object templates are templates of the target object. In some embodiments, when performing template matching on the image using the multiple object templates, the multiple object templates can be scaled and then template matching is performed, so as to improve the accuracy of template matching.

[0120] Example 2: When the high beam of the target vehicle is turned on, the in-vehicle terminal obtains the point cloud in front of the target vehicle through a radar in front of or on top of the target vehicle. The in-vehicle terminal performs target detection on the point cloud and obtains multiple candidate objects in the point cloud. The in-vehicle terminal determines whether there is a target object among the multiple candidate objects.

[0121] For example, when the high beam of the target vehicle is turned on, the in-vehicle terminal obtains the point cloud in front of the target vehicle through a radar in front of or on top of the target vehicle. The in-vehicle terminal inputs the point cloud into a second target detection model, extracts features of the point cloud through the second target detection model, and obtains the point cloud features of the point cloud. The in-vehicle terminal classifies multiple regions of the point cloud based on the point cloud features through the second target detection model, determines whether there are candidate objects in each region, and obtains multiple candidate objects in the point cloud. The in-vehicle terminal determines whether there is a target object among the multiple candidate objects based on the types of the multiple candidate objects. That is, when there are candidate objects of the types of vehicle or pedestrian among the multiple candidate objects, the in-vehicle terminal determines the candidate object as the target object, that is, there is a target object in front of the target vehicle. When there are no candidate objects of the types of vehicle or pedestrian among the multiple candidate objects, the in-vehicle terminal determines that there is no target object in front of the target vehicle.

[0122] Example 3: When the high beam of the target vehicle is turned on, the in-vehicle terminal obtains the image and point cloud in front of the target vehicle through the camera in front of or on the top of the target vehicle. The in-vehicle terminal fuses the image and the point cloud to obtain visual fusion information. The in-vehicle terminal performs target detection on the visual fusion information to obtain multiple candidate objects in the visual fusion information. The in-vehicle terminal determines whether there is a target object among the multiple candidate objects.

[0123] For example, when the high beam of the target vehicle is turned on, the in-vehicle terminal obtains the image and point cloud in front of the target vehicle through the camera in front of or on the top of the target vehicle. The in-vehicle terminal fuses the image and the point cloud to obtain visual fusion information. The in-vehicle terminal inputs the visual fusion information into a third target detection model, extracts features of the visual fusion information through the third target detection model to obtain the visual fusion information features of the visual fusion information. The in-vehicle terminal classifies multiple regions of the visual fusion information based on the visual fusion information features through the third target detection model to determine whether there are candidate objects in each region, and obtains multiple candidate objects in the visual fusion information. The in-vehicle terminal determines whether there is a target object among the multiple candidate objects based on the types of the multiple candidate objects. That is, when there is a candidate object of the type of vehicle or pedestrian among the multiple candidate objects, the in-vehicle terminal determines the candidate object as the target object, that is, there is a target object in front of the target vehicle. When there is no candidate object of the type of vehicle or pedestrian among the multiple candidate objects, the in-vehicle terminal determines that there is no target object in front of the target vehicle.

[0124] 304. When there is the target object in front of the target vehicle, the in-vehicle terminal determines the target occlusion area of the target object.

[0125] The target occlusion area refers to the area that the high beam should not shine on. For example, the eyes of a pedestrian and the eyes of the driver in a vehicle belong to the target occlusion area. Or rather, the target occlusion area refers to the occlusion area formed by the high beam emitted by the target vehicle in the area where the front target object is located. In some embodiments, the target occlusion area is also referred to as the high beam occlusion area.

[0126] In a possible implementation manner, when there is the target object in front of the target vehicle, the in-vehicle terminal determines multiple key points of the target object based on the type of the target object. The in-vehicle terminal determines the target occlusion area of the target object based on the multiple key points of the target object.

[0127] The key point is a point on the target object that is significantly different from other positions or a point with a specific meaning.

[0128] In this embodiment, when there is a target object in front of the target vehicle, according to the object type of the target object, multiple key points of the target object are determined, and the multiple key points are used to determine the target occlusion area of the target object, and the determination efficiency of the target occlusion area is relatively high.

[0129] To illustrate the above embodiment more clearly, the above embodiment will be described in two parts below.

[0130] First part: When there is the target object in front of the target vehicle, the in-vehicle terminal determines multiple key points of the target object based on the type of the target object.

[0131] In a possible implementation manner, when the type of the target object is a vehicle, the in-vehicle terminal determines at least two vehicle lamp key points and at least two roof key points of the target object. The vehicle lamp key points correspond to the headlamps or brake lamps of the vehicle, and the at least two roof key points are located above the at least two vehicle lamp key points and correspond to the at least two vehicle lamp key points one by one.

[0132] Among them, the at least two vehicle lamp key points corresponding to the headlamps are used to indicate the positions of the two headlamps in front of the vehicle, and the at least two vehicle lamp key points corresponding to the brake lamps are used to indicate the positions of the two brake lamps on both sides at the rear of the vehicle. When the target object is a vehicle traveling in the same direction as the target vehicle, the at least two vehicle lamp key points are the vehicle lamp key points corresponding to the brake lamps of the vehicle, and the at least two roof key points are the roof key points at the rear of the vehicle; when the target object is a vehicle traveling in the opposite direction to the target vehicle, the at least two vehicle lamp key points are the vehicle lamp key points corresponding to the headlamps of the vehicle, and the at least two roof key points are the roof key points at the front of the vehicle. In some embodiments, the number of brake lamps of the vehicle may be more than two. For example, brake lamps may be provided at the top and bottom of the rear glass of the vehicle. In this case, the key points corresponding to each brake lamp can be found. The roof key points are used to indicate the position where the roof of the vehicle is located, and the at least two roof key points can be regarded as the key points on the upper boundary of the vehicle. Since there are multiple roof key points of the target vehicle, the roof key point above the vehicle lamp key point refers to the roof key point directly above the vehicle lamp key point. In some embodiments, the number of vehicle lamp key points is the same as the number of roof key points.

[0133] In this implementation manner, when the type of the target object is a vehicle, at least two vehicle lamp key points and at least two vehicle lamp key points of the vehicle are determined. Since the target occlusion area of the vehicle is the driver's eyes, the area indicated by the windshield of the vehicle can be regarded as the target occlusion area. Subsequently, the at least two vehicle lamp key points and the at least two vehicle lamp key points can be used to locate the target occlusion area.

[0134] For example, when the type of the target object is a vehicle, the in-vehicle terminal performs key point detection on the vehicle image area corresponding to the vehicle, and obtains at least two headlight key points of the vehicle and at least two roof key points above the at least two headlight key points.

[0135] For example, when the type of the target object is a vehicle, the in-vehicle terminal inputs the vehicle image area corresponding to the vehicle into a vehicle key point detection model, extracts features of the vehicle image area through the vehicle key point detection model, and obtains a first image area feature. The in-vehicle terminal uses the vehicle key point detection model to detect multiple sub-areas of the vehicle image area based on the first image area feature, and obtains at least two headlight key points and at least two roof key points above the at least two headlight key points. In some embodiments, when the distance between two detected headlight key points is less than or equal to a preset distance, the two headlight key points are merged into one headlight key point; correspondingly, when the distance between two detected roof key points is less than or equal to a preset distance, the two roof key points are merged into one roof key point, where the preset distance is set by those skilled in the art according to the actual situation, and the embodiments of the present application do not limit this.

[0136] In a possible implementation manner, when the type of the target object is a vehicle, the in-vehicle terminal determines four windshield key points of the target object.

[0137] Among them, the windshield key points are the four corner points of the front windshield or the rear windshield, and the four corner points can indicate the position of the front windshield or the rear windshield. When the target object is a vehicle traveling in the same direction as the target vehicle, the four windshield key points are the four corner points of the rear windshield. When the target object is a vehicle traveling in the opposite direction to the target vehicle, the four windshield key points are the four corner points of the front windshield.

[0138] In this implementation manner, when the type of the target object is a vehicle, four windshield key points of the vehicle are determined. Since the target occlusion area of the vehicle is the driver's eyes, the area indicated by the vehicle's windshield can be regarded as the target occlusion area. Using the four windshield key points can achieve the positioning of the windshield, and subsequently, the target occlusion area can be determined.

[0139] For example, when the type of the target object is a vehicle, the in-vehicle terminal performs key point detection on the vehicle image area corresponding to the vehicle, and obtains four windshield key points of the vehicle.

[0140] For example, when the type of the target object is a vehicle, the in-vehicle terminal inputs the vehicle image area corresponding to the vehicle into a vehicle key point detection model, extracts features of the vehicle image area through the vehicle key point detection model, and obtains second image area features. The in-vehicle terminal uses the vehicle key point detection model to detect multiple sub-areas of the vehicle image area based on the second image area features, and obtains four windshield key points of the vehicle.

[0141] In a possible implementation manner, when the type of the target object is a vehicle, the in-vehicle terminal determines two rearview mirror key points and multiple roof key points of the target object.

[0142] Among them, the rearview mirror key points are used to indicate the positions of the vehicle rearview mirrors.

[0143] In this implementation manner, when the type of the target object is a vehicle, two rearview mirror key points and multiple roof key points of the vehicle are determined, and subsequently, the high beam shielding area can be located by using the two rearview mirror key points and multiple roof key points.

[0144] For example, when the type of the target object is a vehicle, the in-vehicle terminal performs key point detection on the vehicle image area corresponding to the vehicle, and obtains two rearview mirror key points and multiple roof key points of the vehicle.

[0145] The above is described by taking the target object as a vehicle as an example, and the following is described by taking the target object as a pedestrian as an example.

[0146] In a possible implementation manner, when the type of the target object is a pedestrian, the in-vehicle terminal determines the top-of-head key point and two shoulder key points of the target object.

[0147] In this implementation manner, when the type of the target object is a pedestrian, the top-of-head key point and two shoulder key points of the target object are determined, and subsequently, the target shielding area can be determined by using the top-of-head key point and two shoulder key points.

[0148] For example, when the type of the target object is a pedestrian, the in-vehicle terminal performs key point detection on the pedestrian image area corresponding to the pedestrian, and obtains the top-of-head key point and two shoulder key points of the pedestrian.

[0149] For example, when the type of the target object is a pedestrian, the in-vehicle terminal inputs the pedestrian image area corresponding to the pedestrian into a pedestrian key point detection model, extracts features of the pedestrian image area through the pedestrian key point detection model, and obtains third image area features. The in-vehicle terminal uses the pedestrian key point detection model to detect multiple sub-areas of the pedestrian image area based on the third image area features, and obtains the top-of-head key point and two shoulder key points of the pedestrian.

[0150] In a possible implementation, when the type of the target object is a pedestrian, the vehicle-mounted terminal determines the head top key point, the chin key point / neck key point, and the two ear key points of the target object.

[0151] In this implementation, when the type of the target object is a pedestrian, the head top key point, the chin key point, and the two ear key points of the target object are determined. The head top key point, the chin key point / neck key point, and the two ear key points can form the head of the pedestrian, and subsequently, the area corresponding to the head is determined as the target occlusion area.

[0152] For example, when the type of the target object is a pedestrian, the vehicle-mounted terminal performs key point detection on the pedestrian image area corresponding to the pedestrian, and obtains the head top key point, the chin key point / neck key point, and the two ear key points of the pedestrian.

[0153] For instance, when the type of the target object is a pedestrian, the vehicle-mounted terminal inputs the pedestrian image area corresponding to the pedestrian into a pedestrian key point detection model, extracts the features of the pedestrian image area through the pedestrian key point detection model, and obtains the fourth image area features. The vehicle-mounted terminal uses the pedestrian key point detection model to detect multiple sub-areas of the pedestrian image area based on the fourth image area features, and obtains the head top key point, the chin key point / neck key point, and the two ear key points of the pedestrian.

[0154] Second part: The vehicle-mounted terminal determines the target occlusion area of the target object based on multiple key points of the target object.

[0155] In a possible implementation, when the type of the target object is a vehicle, the vehicle-mounted terminal determines the area enclosed by the at least two vehicle headlight key points and the at least two vehicle roof key points as the target occlusion area of the target object.

[0156] Wherein, the area enclosed by the at least two vehicle headlight key points and the at least two vehicle roof key points is a square area. The width of the square area is the distance between the two vehicle headlight key points with the farthest distance among the at least two vehicle headlight key points, and the height is the distance between the vehicle roof key point and the corresponding vehicle headlight key point. When the target object is a vehicle traveling in the same direction as the target vehicle, the square area is the area enclosed by the two brake lights on the leftmost and rightmost sides of the rear of the vehicle and the rear vehicle roof; when the target object is a vehicle traveling in the opposite direction to the target vehicle, the square area is the area enclosed by the two headlights in the front of the vehicle and the front vehicle roof. The square area covers the windshield and thus covers the driver's eyes.

[0157] In a possible implementation, when the type of the target object is a vehicle, the in-vehicle terminal determines the area enclosed by four windshield key points of the target object as the target occlusion area of the target object.

[0158] Among them, the area enclosed by the four windshield key points is the area corresponding to the windshield, and the windshield is the front windshield or the rear windshield. When the target object is a vehicle traveling in the same direction as the target vehicle, the windshield is the rear windshield; when the target object is a vehicle traveling in the opposite direction to the target vehicle, the windshield is the front windshield.

[0159] In a possible implementation, when the type of the target object is a vehicle, the in-vehicle terminal determines the area enclosed by two rearview mirror key points and multiple roof key points of the target object as the target occlusion area of the target object.

[0160] Among them, the area enclosed by the two rearview mirror key points and multiple roof key points is a trapezoidal area. The lower base of the trapezoidal area is the distance between the two rearview mirror key points, the upper base is the width of the vehicle top, and the height is the vertical distance between the rearview mirror key point and the roof key point.

[0161] In a possible implementation, when the type of the target object is a pedestrian, the in-vehicle terminal determines the area enclosed by the head top key point and the two shoulder key points of the target object as the target occlusion area of the target object.

[0162] Among them, the area enclosed by the head top key point and the two shoulder key points is a triangle, and the triangular area covers the head of the pedestrian, so it also covers the eyes of the pedestrian.

[0163] In a possible implementation, when the type of the target object is a pedestrian, the in-vehicle terminal determines the area enclosed by the head top key point, the chin key point / neck key point and the two ear key points of the target object as the target occlusion area of the target object.

[0164] Among them, the area enclosed by the head top key point, the chin key point / neck key point and the two ear key points is a rhombus area, and the rhombus area covers the head of the target object, so it also covers the eyes of the pedestrian.

[0165] In addition to the above implementation, the embodiments of the present application also provide another implementation of the above step 304.

[0166] In a possible implementation, when the target object exists in front of the target vehicle, the in-vehicle terminal recognizes the object image of the target object to obtain the target occlusion area of the target object.

[0167] In this embodiment, by directly recognizing the object image of the target object, the target occlusion area of the target object can be obtained, and the determination efficiency of the target occlusion area is relatively high.

[0168] For example, when the target object exists in front of the target vehicle, the in-vehicle terminal inputs the object image of the target object into the area recognition model. The in-vehicle terminal performs area recognition on the object image through the area recognition model to obtain the target occlusion area in the object image.

[0169] For instance, when the target object exists in front of the target vehicle, the in-vehicle terminal inputs the object image of the target object into the area recognition model. The in-vehicle terminal extracts features from the object image through the area recognition model to obtain the object image features of the object image. The in-vehicle terminal uses the object image features to recognize multiple areas on the object image through the area recognition model to obtain the target occlusion area in the object image.

[0170] Optionally, after step 303, the in-vehicle terminal can also perform the following steps.

[0171] In a possible implementation, when the target object does not exist in front of the target vehicle, the in-vehicle terminal does not control the high beam and keeps the state of the high beam unchanged.

[0172] 305. The in-vehicle terminal determines the relative position between the target occlusion area and the target vehicle.

[0173] Among them, the relative position between the target occlusion area and the target vehicle includes the distance and the azimuth angle between the target occlusion area and the target vehicle, and the azimuth angle is determined based on the target vehicle.

[0174] In a possible implementation, the in-vehicle terminal determines the distance between the target occlusion area and the target vehicle. The in-vehicle terminal determines the azimuth angle between the target occlusion area and the target vehicle.

[0175] To illustrate the above embodiments more clearly, the above embodiments will be described in two parts below.

[0176] The first part: The in-vehicle terminal determines the distance between the target occlusion area and the target vehicle.

[0177] In a possible implementation, the in-vehicle terminal determines the distances between the multiple key points of the target occlusion area and the target vehicle through radar, and the positions of the multiple key points are related to the type of the target object.

[0178] Among them, when the type of the target object is a vehicle, the multiple key points may include at least two headlight key points and at least two roof key points above the at least two headlight key points; may also include four windshield key points; may also include two rearview mirror key points and multiple roof key points. When the target occlusion area is determined using the key points, the types of the multiple key points are the same as those when determining the target occlusion area. When the type of the target object is a pedestrian, the multiple key points may include a head key point and two shoulder key points; or may include a head key point, a chin key point / neck key point, and two ear key points.

[0179] For example, the in-vehicle terminal acquires the point cloud collected by the radar. The in-vehicle terminal aligns the coordinates of the point cloud with the image in front of the target vehicle collected simultaneously. After the coordinate alignment, the in-vehicle terminal maps the multiple key points in the image to the point cloud to obtain the point cloud of each key point in the target occlusion area. The in-vehicle terminal analyzes the point cloud of each key point to obtain the distance between each key point in the target occlusion area and the target vehicle.

[0180] Second part: The in-vehicle terminal determines the azimuth angle between the target occlusion area and the target vehicle.

[0181] In a possible implementation, the in-vehicle terminal determines the radar emission angles corresponding to the multiple key points as the azimuth angles between the multiple key points and the target vehicle respectively.

[0182] Among them, the radar emission angle corresponding to a key point refers to the emission angle when the radar emits the detection signal when measuring the distance between the key point and the vehicle through the detection signal.

[0183] See Figure 4 , taking the left headlight key point 401 and the right headlight key point 402 among the multiple key points as an example, ∠α is the azimuth angle between the left headlight key point 401 and the target vehicle 403, and the length of the line connecting the left headlight key point 401 and the target vehicle 403 is the distance between the left headlight key point 401 and the target vehicle 403. ∠β is the azimuth angle between the right headlight key point 402 and the target vehicle 403, and the length of the line connecting the right headlight key point 402 and the target vehicle 403 is the distance between the right headlight key point 402 and the target vehicle 403.

[0184] 306. The in-vehicle terminal controls the high beam based on the relative position between the target occlusion area and the target vehicle, so that the high beam remains on and does not shine on the target occlusion area.

[0185] Among them, the high beam includes multiple lamp beads, and controlling the high beam means controlling the lamp beads in the high beam, that is, controlling the lighting and extinguishing of the multiple lamp beads.

[0186] In a possible implementation, the in-vehicle terminal determines the lamp beads in the high beam corresponding to the target occlusion area based on the relative position between the target occlusion area and the target vehicle. The in-vehicle terminal controls the lamp beads corresponding to the target occlusion area to turn off and keeps the other lamp beads lit.

[0187] Wherein, the lamp beads corresponding to the target occlusion area refer to the lamp beads whose emitted light will irradiate the target occlusion area.

[0188] For example, the relative position between the target occlusion area and the target vehicle includes the distance and azimuth angle between the target occlusion area and the target vehicle. The in-vehicle terminal determines the irradiation range of the target high beam corresponding to the target occlusion area based on the distance and azimuth angle between the target occlusion area and the target vehicle. The in-vehicle terminal compares the irradiation ranges of the multiple lamp beads in the high beam at this distance with the irradiation range of the target high beam. The in-vehicle terminal determines the lamp beads whose irradiation ranges are within the irradiation range of the target high beam as the lamp beads corresponding to the target occlusion area.

[0189] Wherein, the irradiation range of the lamp beads at this distance is set by those skilled in the art according to the actual situation. Due to the limitation of the hardware structure, the irradiation ranges of the lamp beads at different distances are relatively fixed. Those skilled in the art can measure the irradiation ranges of different lamp beads at different distances through experiments, bind and store the irradiation ranges of each lamp bead at different distances, and can directly use the irradiation ranges of each lamp bead at different distances when controlling the high beam by adopting the technical solution provided in the embodiment of the present application.

[0190] For example, the relative position between the target occlusion area and the target vehicle includes the distances and azimuth angles between multiple key points of the target occlusion area and the target vehicle. The in-vehicle terminal determines multiple irradiation boundaries based on the distances and azimuth angles between the multiple key points of the target occlusion area and the target vehicle. The in-vehicle terminal determines the area enclosed by the multiple irradiation boundaries as the irradiation range of the target high beam. The in-vehicle terminal compares the irradiation ranges of the multiple lamp beads in the high beam at this distance with the irradiation range of the target high beam. The in-vehicle terminal determines the lamp beads whose irradiation ranges are within the irradiation range of the target high beam as the lamp beads corresponding to the target occlusion area.

[0191] See Figure 5 , in the case where the technical solution provided in the embodiment of the present application is not adopted, the high beam of the target vehicle 501 will irradiate the driver of the oncoming vehicle 502, causing the driver of the vehicle 502 to be dazzled and affecting driving safety. See Figure 6, after adopting the technical solution provided by the embodiment of the present application, the high beam of the target vehicle 601 will form a shadow area in front of the oncoming vehicle 602 and will not shine on the driver of the oncoming vehicle 602. The high beam of the target vehicle 601 will form a shadow area behind the vehicle 603 traveling in the same direction and will not shine on the driver of the vehicle 603 traveling in the same direction. In addition, since the high beam is not completely turned off and some of the lamp beads of the high beam are still in the lit state, it can realize the illumination of the road surface, expand the field of vision of the driver of the target vehicle, and improve the safety of night driving.

[0192] It should be noted that in the above steps 303-306, the number of target vehicles is taken as one for illustration. In the case where the number of target vehicles is multiple, the above steps 303-306 can be executed for each target vehicle respectively, so as to realize the control of the high beam, and the implementation process will not be elaborated here. See Figure 7 , when the target vehicle 701 is driving on a straight road and there are both a vehicle 702 traveling in the same direction and an oncoming vehicle 703 at the same time, the high beam of the target vehicle will neither shine on the driver of the vehicle 702 traveling in the same direction nor shine on the driver of the oncoming vehicle 703. When the target vehicle 701 is driving on a curve and there are both a vehicle 704 traveling in the same direction and two oncoming vehicles 705 and 706 at the same time, the high beam of the target vehicle will neither shine on the driver of the vehicle 704 traveling in the same direction nor shine on the drivers of the oncoming vehicles 705 and 706. At the same time, since the high beam is not completely turned off and some of the lamp beads of the high beam are still in the lit state, it can realize the illumination of the road surface, expand the field of vision of the driver of the target vehicle, and improve the safety of night driving.

[0193] All the above optional technical solutions can be combined arbitrarily to form optional embodiments of the present application, which will not be elaborated here one by one.

[0194] Through the technical solution provided by the embodiment of the present application, when the high beam of the target vehicle is turned on, it is determined whether there is a target object in front of the target vehicle, so as to determine whether the high beam needs to be controlled. When there is a target object in front of the target vehicle, the target shielding area on the target object that should not be irradiated by the high beam is determined. The relative position between the target shielding area and the target vehicle is determined, and the relative position is used to control the high beam so that the high beam remains lit and does not shine on the target shielding area, while keeping the driver of the target vehicle having a good driving vision, reducing the impact on the vehicle or pedestrian in front, and thus improving the safety of night driving.

[0195] Figure 8 is a schematic structural diagram of a vehicle lighting control device provided by an embodiment of the present application. See Figure 8, the device includes: a target object determination module 801, an occlusion area determination module 802, a relative position determination module 803, and a high beam control module 804.

[0196] The target object determination module 801 is configured to determine whether there is a target object in front of the target vehicle when the high beam of the target vehicle is turned on, and the target object includes a vehicle or a pedestrian.

[0197] The occlusion area determination module 802 is configured to determine the target occlusion area of the target object when the target object exists in front of the target vehicle.

[0198] The relative position determination module 803 is configured to determine the relative position between the target occlusion area and the target vehicle.

[0199] The high beam control module 804 is configured to control the high beam based on the relative position between the target occlusion area and the target vehicle, so that the high beam remains on and does not shine on the target occlusion area.

[0200] In a possible implementation manner, the target object determination module 801 is configured to, when the high beam of the target vehicle is turned on, obtain the visual information in front of the target vehicle through the visual sensor of the target vehicle. Perform target recognition on the visual information to determine whether there is a target object in front of the target vehicle.

[0201] In a possible implementation manner, the occlusion area determination module 802 is configured to, when the target object exists in front of the target vehicle, determine multiple key points of the target object based on the type of the target object. Determine the target occlusion area of the target object based on the multiple key points of the target object.

[0202] In a possible implementation manner, when the type of the target object is a vehicle, the occlusion area determination module 802 is configured to determine at least two vehicle light key points and at least two roof key points of the target object, where the vehicle light key points correspond to the headlamps or brake lights of the vehicle, and the at least two roof key points are located above the at least two vehicle light key points and correspond to the at least two vehicle light key points one by one. When the type of the target object is a pedestrian, determine the head key point and two shoulder key points of the target object.

[0203] In a possible implementation manner, when the type of the target object is a vehicle, the occlusion area determination module 802 is configured to determine the area enclosed by the at least two vehicle light key points and the at least two roof key points as the target occlusion area of the target object. When the type of the target object is a pedestrian, determine the area enclosed by the head key point and the two shoulder key points as the target occlusion area of the target object.

[0204] In a possible implementation manner, the relative position determination module 803 is configured to determine the distance between the target occlusion area and the target vehicle, and determine the azimuth angle between the target occlusion area and the target vehicle.

[0205] In a possible implementation manner, the relative position determination module 803 is configured to determine the distances between multiple key points of the target occlusion area and the target vehicle through a radar, where the positions of the multiple key points are related to the type of the target object, and determine the radar emission angles corresponding to the multiple key points respectively as the azimuth angles between the multiple key points and the target vehicle.

[0206] In a possible implementation manner, the high beam control module 804 is configured to determine the lamp beads in the high beam corresponding to the target occlusion area based on the relative position between the target occlusion area and the target vehicle, and control the lamp beads corresponding to the target occlusion area to go out and keep other lamp beads lit.

[0207] In a possible implementation manner, the relative position between the target occlusion area and the target vehicle includes the distance and azimuth angle between the target occlusion area and the target vehicle. The high beam control module 804 is configured to determine the target high beam illumination range corresponding to the target occlusion area based on the distance and azimuth angle between the target occlusion area and the target vehicle, compare the illumination ranges of the multiple lamp beads in the high beam at this distance with the target high beam illumination range, and determine the lamp beads whose illumination ranges are within the target high beam illumination range as the lamp beads corresponding to the target occlusion area.

[0208] It should be noted that when the vehicle lighting control device provided in the above embodiments controls the vehicle lighting, only the division of the above function modules is used for illustration. In practical applications, the above functions can be allocated to different function modules according to needs, that is, the internal structure of the computer device is divided into different function modules to complete all or part of the functions described above. In addition, the vehicle lighting control device provided in the above embodiments and the vehicle lighting control method embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments and will not be repeated here.

[0209] Through the technical solution provided by the embodiments of the present application, when the high beam of the target vehicle is turned on, it is determined whether there is a target object in front of the target vehicle, so as to determine whether it is necessary to control the high beam. When there is a target object in front of the target vehicle, a target shielding area on the target object that should not be irradiated by the high beam is determined. The relative position between the target shielding area and the target vehicle is determined, and this relative position is used to control the high beam so that the high beam remains on and does not irradiate the target shielding area, reducing the impact on the vehicle or pedestrian in front while keeping the driver of the target vehicle with a good driving vision, thereby improving the safety of night driving.

[0210] The embodiments of the present application also provide a vehicle. Figure 9 It is a schematic structural diagram of a vehicle provided by the embodiments of the present application.

[0211] Generally, the vehicle 900 includes one or more processors 901 and one or more memories 902.

[0212] The processor 901 may include one or more processing cores, such as a 4-core processor, a 9-core processor, etc. The processor 901 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 901 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 901 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for the rendering and drawing of the content to be displayed on the display screen. In some embodiments, the processor 901 may also include an AI (Artificial Intelligence) processor, and the AI processor is used to process computational operations related to machine learning.

[0213] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage media in the memory 902 is used to store at least one computer program, and the at least one computer program is used to be executed by the processor 901 to implement the vehicle lighting control method provided in the method embodiments of the present application.

[0214] Those skilled in the art can understand that Figure 9 the structure shown in does not constitute a limitation on the vehicle 900, and it may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component layout.

[0215] In addition, the device provided in the embodiments of the present application may specifically be a chip, a component or a module. The chip may include a connected processor and a memory; wherein, the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the method for controlling the vehicle lighting provided in the above embodiments.

[0216] This embodiment also provides a computer-readable storage medium, in which computer program code is stored. When the computer program code runs on a computer, the computer is caused to execute the above-related method steps to implement the method for controlling the vehicle lighting provided in the above embodiments.

[0217] This embodiment also provides a computer program product. When the computer program product runs on a computer, the computer is caused to execute the above-related steps to implement the method for controlling the vehicle lighting provided in the above embodiments.

[0218] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be elaborated here.

[0219] Through the description of the above embodiments, those skilled in the art can understand that for the convenience and conciseness of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0220] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0221] The above content is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A lighting control method for a vehicle, characterized in that, The method includes: When the high beam of the target vehicle is turned on, determining whether there is a target object in front of the target vehicle, where the target object includes a vehicle or a pedestrian; When there is the target object in front of the target vehicle, determining the target occlusion area of the target object; Determining the relative position between the target occlusion area and the target vehicle; Based on the relative position between the target occlusion area and the target vehicle, controlling the high beam so that the high beam remains on and does not shine on the target occlusion area.

2. The method according to claim 1, characterized in that The determining whether there is a target object in front of the target vehicle when the high beam of the target vehicle is turned on includes: When the high beam of the target vehicle is turned on, obtaining visual information in front of the target vehicle through a visual sensor of the target vehicle; Performing target recognition on the visual information to determine whether there is a target object in front of the target vehicle.

3. The method according to claim 1, wherein The determining the target occlusion area of the target object when there is the target object in front of the target vehicle includes: When there is the target object in front of the target vehicle, determining multiple key points of the target object based on the type of the target object; Based on the multiple key points of the target object, determining the target occlusion area of the target object.

4. The method according to claim 3, wherein The determining multiple key points of the target object based on the type of the target object includes: When the type of the target object is a vehicle, determining at least two headlight key points and at least two roof key points of the target object, where the headlight key points correspond to the high beams or brake lights of the vehicle, and the at least two roof key points are located above the at least two headlight key points and correspond to the at least two headlight key points one by one; When the type of the target object is a pedestrian, determining the head key point and two shoulder key points of the target object.

5. The method according to claim 4, characterized in that, The determining the target occlusion area of the target object based on the multiple key points of the target object includes: When the type of the target object is a vehicle, determining the area enclosed by the at least two headlight key points and the at least two roof key points as the target occlusion area of the target object; When the type of the target object is a pedestrian, determining the area enclosed by the head key point and the two shoulder key points as the target occlusion area of the target object.

6. The method according to claim 1, wherein The determining the relative position between the target occlusion area and the target vehicle includes: Determining the distance between the target occlusion area and the target vehicle; Determining the azimuth angle between the target occlusion area and the target vehicle.

7. The method according to claim 6, wherein The determining the distance between the target occlusion area and the target vehicle includes: Determining the distances between the multiple key points of the target occlusion area and the target vehicle respectively through a radar, where the positions of the multiple key points are related to the type of the target object; The determining the azimuth angle between the target occlusion area and the target vehicle includes: Determining the radar emission angles corresponding to the multiple key points respectively as the azimuth angles between the multiple key points and the target vehicle.

8. The method according to claim 1, characterized in that Controlling the high beam based on the relative position between the target shielding area and the target vehicle includes: Determining the lamp beads corresponding to the target shielding area in the high beam based on the relative position between the target shielding area and the target vehicle; Controlling the lamp beads corresponding to the target shielding area to go out and keeping the other lamp beads lit.

9. A lighting control device for a vehicle, characterized in that, The device includes: A target object determination module, configured to determine whether there is a target object in front of the target vehicle when the high beam of the target vehicle is on, where the target object includes a vehicle or a pedestrian A shielding area determination module, configured to determine the target shielding area of the target object when the target object exists in front of the target vehicle; A relative position determination module, configured to determine the relative position between the target shielding area and the target vehicle; A high beam control module, configured to control the high beam based on the relative position between the target shielding area and the target vehicle, so that the high beam remains lit and does not irradiate the target shielding area.

10. A vehicle, characterized in that, The vehicle includes: A memory, configured to store executable program code; A processor, configured to call and run the executable program code from the memory, so that the vehicle executes the vehicle's lighting control method according to any one of claims 1 to 8.

Images