Pixel vehicle lamp control method and device, vehicle, storage medium and program product

Abstract

The invention relates to a pixel vehicle lamp control method and device, a vehicle, a storage medium and a program product, relates to the technical field of vehicle lamp control, and can guarantee the real-time performance and reliability of ADB control of a high-pixel vehicle lamp. The method comprises the following steps: acquiring a real-time image in front of a vehicle; an interested target in the real-time image is determined, attribute marking is carried out on pixel points corresponding to the interested target in the real-time image, an intermediate image is obtained, and the attribute marks are used for representing the category of the interested target to which the pixel points belong; and converting the intermediate image into a target image according to a mapping relationship between pixel points in the real-time image and pixel lamps in target pixel vehicle lamps on the vehicle, and controlling light of the target pixel vehicle lamps according to the target image.

Description

Technical Field

[0001] The present disclosure relates to the technical field of vehicle light control, and in particular, to a method, device, vehicle, storage medium and program product for controlling a pixel vehicle light. Background Art

[0002] ADB (Adaptive Driving Beam) is based on multiple independently controlled LEDs to achieve brightness control of specific areas. However, for ADB control of high-pixel headlights with a resolution of more than 10,000 pixels, the calculation complexity will increase exponentially or even exponentially, and the real-time and reliability of ADB control of high-pixel headlights cannot be guaranteed. Summary of the invention

[0003] In order to address the deficiencies of the prior art, the present disclosure provides a method, device, vehicle, storage medium and program product for controlling a pixel vehicle light.

[0004] In order to achieve the above objectives, in a first aspect, the present disclosure provides a method for controlling a pixel vehicle light, the method comprising: Get real-time images in front of the vehicle; Determine an object of interest in the real-time image, and perform attribute marking on pixel points corresponding to the object of interest in the real-time image to obtain an intermediate image, wherein the attribute marking is used to characterize the category of the object of interest to which the pixel point belongs; According to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, the intermediate image is converted into a target image, and according to the target image, the light of the target pixel lights is controlled.

[0005] In a second aspect, the present disclosure provides a control device for a pixel vehicle light, comprising: A camera device configured to obtain a real-time image in front of the vehicle; A domain controller is configured to determine an object of interest in the real-time image, and to perform attribute marking on pixel points corresponding to the object of interest in the real-time image to obtain an intermediate image, wherein the attribute marking is used to characterize the category of the object of interest described by the pixel point; The area controller is configured to convert the intermediate image into a target image according to a mapping relationship between pixel points in the real-time image and pixel lights in the target pixel lights on the vehicle, and control the light of the target pixel lights according to the target image.

[0006] In a third aspect, the present disclosure provides a vehicle, comprising at least two pixel lights and a control device for the pixel lights according to the second aspect.

[0007] In a fourth aspect, the present disclosure provides a readable storage medium having a computer program stored thereon, which implements the method described in the first aspect when executed by a processor.

[0008] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0009] Through the above technical solution, the target of interest in the real-time image is determined, and the pixel points corresponding to the target of interest in the real-time image are marked with attributes to obtain an intermediate image. According to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, the intermediate image is converted into a target image, and the light of the target pixel lights is controlled according to the target image. Controlling the light of the pixel lights at the pixel level can be specific to the control of each pixel light in the pixel lights, so when controlling the high beam lighting, the pixel lights can be retained to the greatest extent for high beam lighting, which greatly improves the illumination efficiency of the pixel lights. The entire control process can convert the intermediate image after attribute marking into a target image according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, so as to control the light of the target pixel lights according to the target image, without comparing the azimuth angle of the target object within the field of view processed by the camera with the illumination area of ​​each light source in the pixel lights, and the amount of calculation involved is small, which ensures the real-time and reliability of the ADB control of the pixel lights.

[0010] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 is a flowchart of a method for controlling a pixel vehicle light according to an exemplary embodiment of the present disclosure.

[0012] Figure 2 is another flow chart of a method for controlling a pixel vehicle lamp according to an exemplary embodiment of the present disclosure.

[0013] Figure 3 is a block diagram of a control device for a pixel vehicle lamp according to an exemplary embodiment of the present disclosure.

[0014] Figure 4 is a block diagram of a vehicle according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0015] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0016] It is worth mentioning that ADB is an intelligent high beam control system that can automatically change the vehicle's high beam light type according to road conditions. ADB headlights have multiple independently controlled LEDs, which can achieve brightness control in specific areas. For example, when the ADB system detects a target vehicle, the ADB headlights turn off the LED light source corresponding to the target area where the target vehicle is located, but retain the LED light source in other areas, thereby achieving the maximum lighting effect while avoiding dazzling other traffic participants, thereby improving driving safety.

[0017] At present, with the improvement of the level of automobile intelligence, the pixels of automobile headlights are also gradually increasing, from the previous tens of pixels and hundreds of pixels to the current tens of thousands of pixels, and the millions of pixels that can realize projection interaction. When the pixels of the headlights reach the tens of thousands, in addition to more refined lighting, more complex interactive functions can also be realized, such as projecting vehicle width lines, navigation guidance symbols, hazard warning information, sidewalks, etc. In addition, combined with the smart cockpit, the vehicle is also given entertainment attributes, such as outdoor KTV, dynamic games, etc. The LED light sources in low-pixel headlights generally use single-row matrix headlights, while the LED light sources in high-pixel headlights generally use multi-row matrix headlights.

[0018] Among them, the adaptive high beam control process for low-pixel headlights such as headlights with tens of pixels and hundreds of pixels includes: defining the irradiation area of ​​each LED light source, and then receiving the structured target information processed by the camera from the CAN bus. The target information includes the ID of the target object within the camera's field of view, the type of the target object, the distance between the target object and the camera, the azimuth of the target object compared to the camera, and the movement speed of the target object. The azimuth of the target object is compared with the irradiation area of ​​each LED light source in the low-pixel headlight to determine the target LED light source corresponding to the target object, and control the target LED light source to turn on or off.

[0019] The inventors have discovered that if high-pixel headlights also use the above-mentioned adaptive high-beam control method for low-pixel headlights to arrange and combine each light-emitting body (LED light source), the complexity of the calculation will increase exponentially or even exponentially, and the MCU (Microcontroller Unit) and / or domain controller on the vehicle cannot currently afford such a large amount of computing power, and therefore cannot guarantee the real-time and reliability of the ADB control of the high-pixel headlights.

[0020] In view of this, the present disclosure provides a control method, device, vehicle, storage medium and program product for pixel car lights, which are not limited by the pixel height of the pixel car lights and can ensure the real-time and reliability of ADB control of the pixel car lights.

[0021] Figure 1 FIG. 1 is a flow chart showing a method for controlling a pixel headlight according to an exemplary embodiment of the present disclosure. The method for controlling a pixel headlight can be applied to a vehicle equipped with a pixel headlight. Figure 1 As shown, the control method of the pixel lamp may include the following steps: In step S11 , a real-time image in front of the vehicle is acquired.

[0022] It is worth noting that real-time images in front of the vehicle can be obtained through a camera device installed on the vehicle, such as the vehicle's front-view camera, driving recorder, etc.

[0023] It should be understood that the real-time image can be any image captured within the field of view of the camera device, and thus the resolution of the real-time image may be greater than the resolution of the pixel headlights, or less than the resolution of the pixel headlights, or equal to the resolution of the pixel headlights. If the resolution of the image corresponding to the field of view of the camera device is M×N, then the resolution of the real-time image is M`×N`.

[0024] In step S12, the object of interest in the real-time image is determined, and the pixel points corresponding to the object of interest in the real-time image are attribute-labeled to obtain an intermediate image, wherein the attribute label is used to characterize the category of the object of interest to which the pixel point belongs.

[0025] It is worth noting that the real-time image includes one or more objects of interest. When the real-time image includes multiple objects of interest, the objects of interest may be the same or different. Therefore, it is necessary to mark the pixel points corresponding to the objects of interest in the real-time image with attributes, so as to control the light state of the target pixel headlights later.

[0026] In step S13, the intermediate image is converted into a target image according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, and the light of the target pixel lights is controlled according to the target image.

[0027] In the embodiment of the present disclosure, the target of interest in the real-time image is determined, and the pixel points corresponding to the target of interest in the real-time image are marked with attributes to obtain an intermediate image. According to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, the intermediate image is converted into a target image, and the light of the target pixel lights is controlled according to the target image. The light of the pixel lights is controlled at the pixel level, which can be specifically controlled to each pixel light in the pixel lights. Therefore, when controlling the high beam lighting, the pixel lights can be retained to the greatest extent for high beam lighting, which greatly improves the illumination efficiency of the pixel lights. The entire control process can convert the intermediate image after attribute marking into a target image according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, so as to control the light of the target pixel lights according to the target image. There is no need to compare the azimuth angle of the target object within the field of view processed by the camera with the illumination area of ​​each light source in the pixel lights, and the amount of calculation involved is small, which ensures the real-time and reliability of the ADB control of the pixel lights.

[0028] In order to help those skilled in the art better understand the control method of the pixel vehicle light provided by the present disclosure, the steps of the method are described in detail below.

[0029] In a feasible implementation manner, the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle can be obtained as follows: Determine the field of view and first resolution of a camera device on the vehicle for acquiring real-time images, the illumination area and second resolution of the target pixel headlight, and the relative position of the camera device and the target pixel headlight on the vehicle; Determine a target object that is simultaneously in the field of view and the illumination area, and a distance between the target object and the camera device; Determine, according to the first resolution, first coordinate information of a pixel point corresponding to the target object in the image acquired by the camera device, and determine, according to the second resolution, second coordinate information of each pixel light in the target pixel headlight whose illumination area covers the target object; According to the relative position and distance, a conversion relationship between the first coordinate information and the second coordinate information is determined, and the conversion relationship is determined as a mapping relationship between a pixel point in the real-time image and a pixel light in a target pixel light on the vehicle.

[0030] It is worth noting that the pixel headlight is composed of multiple pixel lights. The angles of the front camera and the pixel headlight can be adjusted, so there are multiple mapping relationships between the pixel points in the image obtained by the front camera and the pixel lights in the target pixel headlight. The mapping relationship at each angle can be determined in the following way: A world coordinate system is constructed with the front axle of the vehicle as the center, the position and direction of the front-view camera in the world coordinate system are determined, and the position and direction of the target pixel headlight in the world coordinate system are determined according to the relative position; the first coordinate information is converted into the world coordinate system according to the distance to obtain the first intermediate coordinate information, and the second coordinate information is converted into the world coordinate system to obtain the second intermediate coordinate information; the average value of the coordinates of all pixels in the first intermediate coordinate information is determined to obtain the first centroid (x A ,y A 、z A ), and determine the average value of all pixel light coordinates of the second intermediate coordinate information to obtain the second centroid (x B ,y B 、z B ); determine the distance between the first centroid and the second centroid , and the direction of movement of the first centroid to the second centroid direction = (x B -x A ,y B -y A , z B -z A ), and according to the distance and direction, obtain the mapping relationship between the pixel point in the real-time image at the angle and the pixel light in the target pixel headlight on the vehicle.

[0031] It should be understood that the field of view of the front-view camera is larger than the illumination area of ​​the pixel headlights, and because the camera is a light-sensitive sensor, its detection effect is much better during the day than at night. However, the pixel headlights will dazzle other traffic participants at night. Therefore, the front-view camera must also have the ability to recognize light sources so that it can detect vehicles with lights on at night or reflective objects at a longer distance.

[0032] It is worth noting that the camera device of the present disclosure may be a smart front-view camera multiplexing ADAS (Advanced Driver Assistance System), which may be installed on the front windshield of the vehicle or on the back of the rearview mirror inside the vehicle. The front-view camera in the embodiment of the present disclosure may be a Bosch MPC2 camera, which has a horizontal field of view of 50°, a vertical field of view of 28°, and a resolution of 1280×960.

[0033] It should be understood that the mapping relationship between the pixel points in the image acquired by the front-view camera and the pixel lights in the target pixel headlights can be a mapping relationship map determined in advance, or can be determined during the control process of the pixel headlights, and the present disclosure does not limit this.

[0034] In a feasible implementation manner, attribute marking is performed on pixel points corresponding to the target of interest in the real-time image to obtain an intermediate image, which may include: Determine the category attribute corresponding to the target of interest in the real-time image, and mark the category attribute for all pixel points corresponding to the target of interest to obtain an intermediate image. The category attribute characterizes whether the target of interest is a vehicle, a traffic sign, a pedestrian, or a non-motor vehicle.

[0035] It is worth noting that the category attributes can be marked by text, Arabic numerals, or preset symbols, etc., and the present disclosure does not limit this. For example, when the category attributes are marked by Arabic numerals, each Arabic numeral represents a category attribute, such as when the target of interest is a vehicle, all the pixels corresponding to the vehicle are marked as "1", when the target of interest is a traffic sign, all the pixels corresponding to the traffic sign are marked as "2", when the target of interest is a pedestrian, all the pixels corresponding to the pedestrian are marked as "3", and when the target of interest is a non-motor vehicle, all the pixels corresponding to the non-motor vehicle are marked as "4".

[0036] For example, a scene including two objects of interest in a real-time image is used for explanation. It is determined that the first object of interest in the real-time image is a vehicle, and the second object of interest is a pedestrian. All pixel points corresponding to the first object of interest are marked as "1", and all pixel points corresponding to the second object of interest are marked as "2". The remaining pixel points in the real-time image are marked as "0" by default, indicating that there is no object of interest, and an intermediate image is obtained.

[0037] It is worth noting that there are differences in the light control methods of the pixel lights covering different targets of interest in the pixel lights, such as turning off the light of the pixel lights, reducing the brightness, turning on the light, etc. For example, when the target of interest is a vehicle, it is necessary to turn off the pixel lights whose illumination area covers the vehicle in the pixel lights; when the target of interest is a traffic sign, it is necessary to reduce the brightness of the pixel lights whose illumination area covers the traffic sign; it is necessary to turn on the pixel lights whose illumination area covers the area other than the target of interest.

[0038] In the disclosed embodiment, the category attribute corresponding to each target of interest in the real-time image is determined, and the corresponding category attribute is marked for all pixel points corresponding to each target of interest, so as to achieve the attribute marking of the pixel points corresponding to the target of interest in the real-time image and obtain an intermediate image, so as to facilitate the pixel-level control of the light of the pixel headlights.

[0039] In a feasible implementation manner, converting the intermediate image into the target image according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle may include: When the resolution of the intermediate image is greater than the resolution of the target pixel headlight, the intermediate image is subjected to pixel merging processing according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel headlights on the vehicle to obtain the target image; When the resolution of the intermediate image is smaller than the resolution of the target pixel headlights, the intermediate image is subjected to pixel expansion processing according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel headlights on the vehicle to obtain the target image.

[0040] It is worth noting that there are differences in the field of view and resolution of the camera device and the pixel headlights, and usually the field of view and resolution of the camera device are higher than those of the headlights, while the resolution of the intermediate image is the same as that of the real-time image. Therefore, by comparing the resolution of the intermediate image and the target pixel headlights, the intermediate image can be pixel merged or expanded according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel headlights on the vehicle to obtain the target image.

[0041] For example, the resolution of the intermediate image is M`×N`, and the resolution of the target pixel headlight is m×n. Usually, M`×N` is not equal to m×n. It is necessary to merge or expand the pixels in the real-time image with a resolution of M`×N` to obtain a target image with a resolution of m×n.

[0042] When M`<m or N`<n, the corresponding target pixel points need to be expanded according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, and the pixel attributes will be inherited. For example, the category attribute of a target pixel point indicates that the target pixel point belongs to the vehicle, and the target pixel point is expanded into two pixels. The category attributes of the two expanded pixels both indicate that the pixel point belongs to the vehicle.

[0043] When M`>m or N`>n, it is necessary to perform pixel merging processing on the corresponding two target pixels according to the mapping relationship between the pixels in the real-time image and the pixel lights in the target pixel lights on the vehicle. If the category attributes of the two target pixels both indicate that the pixel belongs to the vehicle, the two target pixels are merged into one pixel, and the category attribute of the merged pixel indicates that the pixel belongs to the vehicle.

[0044] It is worth noting that when performing pixel merging processing, there may be situations where multiple pixels have different category attributes. In this case, the category attributes of the pixels obtained after the pixel merging processing need to be determined in combination with the priority of the category attributes.

[0045] In a feasible implementation manner, according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, pixel merging processing is performed on the intermediate image to obtain the target image, which may include: Determine a plurality of pixels to be merged in the intermediate image according to a mapping relationship between pixels in the real-time image and pixel lights in target pixel lights on the vehicle; The multiple pixels to be merged are merged into a target pixel, and a target category attribute is marked on the target pixel. The target category attribute is a category attribute with the highest preset priority among the category attributes corresponding to the multiple pixels to be merged.

[0046] It is worth noting that different categories of attributes have corresponding preset priorities, and the preset priorities can be preset according to the actual illumination function of the pixel headlights. In the embodiment of the present disclosure, the priority order of different categories of attributes can be: vehicles>pedestrians=non-motor vehicles>traffic signs.

[0047] For example, when M`>m or N`>n, it is necessary to perform pixel merging processing on the corresponding two target pixels according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle. For example, the category attribute of the first target pixel indicates that the pixel point belongs to the vehicle, and the category attribute of the second target pixel point indicates that the pixel point belongs to the traffic sign. Since the priority of the vehicle is greater than the priority of the traffic sign, the two target pixels are merged into one pixel, and the category attribute of the merged pixel indicates that the pixel point belongs to the vehicle.

[0048] In a feasible implementation manner, when there are multiple target images, controlling the light of the target pixel headlight according to the target images may include: A video stream is generated according to the plurality of target images, and the light of the target pixel headlight is controlled according to the video stream.

[0049] It is worth noting that, because the image acquisition frequency of the front-view camera is relatively high, generally 30Hz~60Hz, if the front-view camera controls the headlights according to the target image converted from the real-time image every time it acquires a real-time image, it will increase the power consumption and complexity of the pixel headlight control process, and cause the pixel headlight to overheat, thereby affecting the life of the pixel headlight. Therefore, a video stream can be generated according to multiple target images, and the light of the target pixel headlight can be controlled according to the video stream to reduce the power consumption and complexity of the pixel headlight control process, thereby reducing the temperature of the pixel headlight during operation and increasing the life of the pixel headlight.

[0050] like Figure 2 As shown, the present disclosure provides a method for controlling a pixel headlight by means of a complete control process of a left pixel headlight on a vehicle. In step S21, the front-view camera on the vehicle obtains a real-time image in front of the vehicle, and step S22 is executed.

[0051] Specifically, a real-time image in front of the vehicle is obtained through a Bosch MPC2 camera installed on the vehicle. The resolution of the real-time image is 640×160, and the resolution of the left pixel headlight on the vehicle is 320×80.

[0052] In step S22, the target of interest in the real-time image is determined, the category attribute corresponding to the target of interest in the real-time image is determined, and the category attribute is marked for all pixel points corresponding to the target of interest to obtain an intermediate image, and the category attribute characterizes that the target of interest is a vehicle, a traffic sign, a pedestrian or a non-motor vehicle. Step S23 is executed.

[0053] Specifically, vehicles, traffic signs, pedestrians or non-motor vehicles, etc. in the real-time image are determined by an image recognition algorithm, and the category attributes of each pixel in the real-time image are marked to obtain an intermediate image.

[0054] In step S23, the resolution of the intermediate image is compared with the resolution of the target pixel headlight, and step S24 or step S25 is executed.

[0055] Specifically, the resolution of the intermediate image (640×160) is compared with the resolution of the target pixel headlight (320×80). Since (640×160)>(320×80), step S24 is executed.

[0056] In step S24, when the resolution of the intermediate image is greater than the resolution of the target pixel headlight, the intermediate image is subjected to pixel merging processing according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel headlights on the vehicle to obtain the target image. Execute step S26.

[0057] Specifically, according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the left pixel headlight on the vehicle, the corresponding four adjacent target pixel points in the intermediate image are pixel merged, and the category attributes of the four target pixel points are vehicle, vehicle, vehicle and traffic sign, respectively. The four adjacent target pixel points are merged into one pixel point, and the category attribute is marked as vehicle, until the pixel merging process of all pixels is completed to obtain the target image. Execute step S26.

[0058] In step S25, when the resolution of the intermediate image is smaller than the resolution of the target pixel headlight, the intermediate image is subjected to pixel expansion processing according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel headlights on the vehicle to obtain the target image. Execute step S26.

[0059] In step S26, when there are multiple target images, a video stream is generated according to the multiple target images, and the light of the target pixel headlight is controlled according to the video stream.

[0060] Specifically, a video stream with a resolution of 320×80 is generated according to the multiple target images, and the light of the left pixel headlight is controlled according to the video stream.

[0061] The disclosed embodiments solve the problem that the traditional ADB control algorithm cannot support high-pixel headlight control from real-time vehicle image processing to pixel headlight control. The on / off lights in the target area are controlled at the pixel level, and the high beam lighting is retained to the greatest extent, which greatly improves the illumination efficiency of the pixel headlights and thus improves the safety of nighttime driving. In addition, through the control method of the pixel headlights, more abundant interactive functions can be realized, such as controlling the pixel headlights to project vehicle width lines, navigation guidance symbols, hazard warning information, sidewalks, etc.

[0062] Based on the same inventive concept, the present disclosure also provides a control device for a pixel vehicle light, such as Figure 3 As shown, the control device 300 of the pixel vehicle light includes a camera device 301 , a domain controller 302 and a zone controller 303 .

[0063] The camera device 301 is configured to obtain a real-time image in front of the vehicle.

[0064] The domain controller 302 is configured to determine the target of interest in the real-time image and perform attribute marking on the pixel points corresponding to the target of interest in the real-time image to obtain an intermediate image, wherein the attribute marking is used to characterize the category of the target of interest described by the pixel point.

[0065] The domain controller may be an Advanced Driver Assistance System controller (ADAS controller), which is not limited in the present disclosure.

[0066] The area controller 303 is configured to convert the intermediate image into a target image according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, and control the light of the target pixel lights according to the target image.

[0067] In the embodiment of the present disclosure, the target of interest in the real-time image is determined, and the pixel points corresponding to the target of interest in the real-time image are marked with attributes to obtain an intermediate image. According to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, the intermediate image is converted into a target image, and the light of the target pixel lights is controlled according to the target image. The light of the pixel lights is controlled at the pixel level, which can be specifically controlled to each pixel light in the pixel lights. Therefore, when controlling the high beam lighting, the pixel lights can be retained to the greatest extent for high beam lighting, which greatly improves the illumination efficiency of the pixel lights. The entire control process can convert the intermediate image after attribute marking into a target image according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, so as to control the light of the target pixel lights according to the target image. There is no need to compare the azimuth angle of the target object within the field of view processed by the camera with the illumination area of ​​each light source in the pixel lights, and the amount of calculation involved is small, which ensures the real-time and reliability of the ADB control of the pixel lights.

[0068] Optionally, when there are multiple target images, the area controller 303 is configured to generate a video stream according to the multiple target images, and control the light of the target pixel headlight according to the video stream.

[0069] Optionally, the domain controller 302 is configured to determine the category attribute corresponding to the target of interest in the real-time image, and mark the category attribute for all pixel points corresponding to the target of interest to obtain an intermediate image, wherein the category attribute characterizes that the target of interest is a vehicle, a traffic sign, a pedestrian or a non-motor vehicle.

[0070] Optionally, the regional controller 303 is configured to perform pixel merging processing on the intermediate image to obtain the target image according to a mapping relationship between pixel points in the real-time image and pixel lights in the target pixel lights on the vehicle when the resolution of the intermediate image is greater than the resolution of the target pixel headlight; When the resolution of the intermediate image is smaller than the resolution of the target pixel headlights, the intermediate image is subjected to pixel expansion processing according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel headlights on the vehicle to obtain the target image.

[0071] Optionally, the area controller 303 is configured to determine a plurality of pixels to be merged in the intermediate image according to a mapping relationship between the pixels in the real-time image and the pixel lights in the target pixel lights on the vehicle; The multiple pixels to be merged are merged into a target pixel, and a target category attribute is marked on the target pixel. The target category attribute is a category attribute with the highest preset priority among the category attributes corresponding to the multiple pixels to be merged.

[0072] Optionally, the area controller 303 is configured to determine the field of view and the first resolution of a camera device on the vehicle for acquiring the real-time image, the illumination area and the second resolution of the target pixel headlight, and the relative position of the camera device and the target pixel headlight on the vehicle; Determine a target object that is simultaneously in the field of view and the illumination area, and a distance between the target object and the camera device; Determine, according to the first resolution, first coordinate information of a pixel point corresponding to the target object in the image acquired by the camera device, and determine, according to the second resolution, second coordinate information of each pixel light in the target pixel headlight whose illumination area covers the target object; According to the relative position and distance, a conversion relationship between the first coordinate information and the second coordinate information is determined, and the conversion relationship is determined as a mapping relationship between a pixel point in the real-time image and a pixel light in a target pixel light on the vehicle.

[0073] Regarding the control device 300 for the pixel vehicle light in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0074] Based on the same inventive concept, the present disclosure also provides a vehicle, comprising at least two pixel headlights and a control device for the pixel headlights.

[0075] In the embodiment of the present disclosure, the target of interest in the real-time image is determined, and the pixel points corresponding to the target of interest in the real-time image are marked with attributes to obtain an intermediate image. According to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, the intermediate image is converted into a target image, and the light of the target pixel lights is controlled according to the target image. The light of the pixel lights is controlled at the pixel level, which can be specifically controlled to each pixel light in the pixel lights. Therefore, when controlling the high beam lighting, the pixel lights can be retained to the greatest extent for high beam lighting, which greatly improves the illumination efficiency of the pixel lights. The entire control process can convert the intermediate image after attribute marking into a target image according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, so as to control the light of the target pixel lights according to the target image. There is no need to compare the azimuth angle of the target object within the field of view processed by the camera with the illumination area of ​​each light source in the pixel lights, and the amount of calculation involved is small, which ensures the real-time and reliability of the ADB control of the pixel lights.

[0076] For example, Figure 4As shown, the vehicle includes a control device 300 for pixel headlights, a left pixel headlight 400, and a right pixel headlight 500, and the video control device 300 for the pixel headlights is connected to the left pixel headlight 400 and the right pixel headlight 500 through video lines. The control device 300 for the pixel headlights generates a first video stream corresponding to the left pixel headlight 400 and a second video stream corresponding to the right pixel headlight 500 according to the real-time image in front of the vehicle, and controls the light of the left pixel headlight 400 according to the first video stream, and controls the light of the right pixel headlight 500 according to the second video stream.

[0077] It is worth noting that a video transmission interface is arranged in the control device 300 of the pixel headlight, and a video receiving interface is arranged at the driving end of each pixel headlight on the vehicle. The video transmission interface and the video receiving interface can be connected via a video cable. The video transmission interface and the video receiving interface include but are not limited to GMSL (Gigabit Multimedia Serial Link) and FPD-Link (Flat Panel Display Link). GMSL or FPD-Link converts multiple parallel data (including video, control, voice and other data) of the control device of the pixel headlight into a single serial data, and then converts the serial data into a parallel video format and low-speed control signal that can be received by the display panel or SoC in the pixel headlight, thereby ensuring stable long-distance data transmission between the camera device Camera, the monitor Monitor and the processor. The video stream can be transmitted between the control device of the pixel headlight and the pixel headlight through LVDS (Low-Voltage Differential Signaling) low-voltage differential signals.

[0078] It should be understood that after receiving the video stream, the pixel headlights can drive the corresponding pixel lights to light up to achieve different functions and modes, such as ADB control of high-pixel headlights. Among them, each light of the pixel headlights needs to be matched with a dedicated driver chip CMOS (Complementary Metal-Oxide-Semiconductor), ASIC (Application-Specific Integrated Circuit) or DSP (Digital Signal Processor), such as 10,000-pixel Micro LED, 1-million-pixel DMD (Digital Micromirror Device), etc.

[0079] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the above-mentioned method for controlling pixel vehicle lights is implemented.

[0080] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a processor. When the computer program is executed by the processor, the steps of the above-mentioned method for controlling pixel vehicle lights are implemented.

[0081] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0082] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0083] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for controlling a pixel car light, characterized in that: The method comprises: Get real-time images in front of the vehicle; Determine an object of interest in the real-time image, and perform attribute marking on pixel points corresponding to the object of interest in the real-time image to obtain an intermediate image, wherein the attribute marking is used to characterize the category of the object of interest to which the pixel point belongs; According to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle, the intermediate image is converted into a target image, and according to the target image, the light of the target pixel lights is controlled.

2. The control method of pixel car lights according to claim 1, characterized in that: When there are multiple target images, controlling the light of the target pixel headlight according to the target image includes: A video stream is generated according to the plurality of target images, and the light of the target pixel headlight is controlled according to the video stream.

3. The control method of pixel car lights according to claim 1, characterized in that: The step of marking the pixel points corresponding to the target of interest in the real-time image with attributes to obtain an intermediate image includes: Determine the category attribute corresponding to the target of interest in the real-time image, and mark the category attribute for all pixel points corresponding to the target of interest to obtain an intermediate image, wherein the category attribute characterizes that the target of interest is a vehicle, a traffic sign, a pedestrian, or a non-motor vehicle.

4. The control method of pixel car lights according to claim 1, characterized in that: The step of converting the intermediate image into a target image according to a mapping relationship between pixel points in the real-time image and pixel lights in target pixel lights on the vehicle comprises: When the resolution of the intermediate image is greater than the resolution of the target pixel headlight, pixel merging processing is performed on the intermediate image according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel headlights on the vehicle to obtain the target image; When the resolution of the intermediate image is smaller than the resolution of the target pixel headlight, the intermediate image is subjected to pixel expansion processing according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel headlights on the vehicle to obtain the target image.

5. The control method of pixel vehicle lights according to claim 4, characterized in that: The step of performing pixel merging processing on the intermediate image according to the mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle to obtain the target image includes: Determine a plurality of pixel points to be merged in the intermediate image according to a mapping relationship between pixel points in the real-time image and pixel lights in target pixel lights on the vehicle; The plurality of pixels to be merged are merged into a target pixel, and a target category attribute is marked on the target pixel, where the target category attribute is a category attribute with the highest preset priority among the category attributes corresponding to the plurality of pixels to be merged.

6. The method for controlling a pixel vehicle light according to any one of claims 1 to 5, characterized in that: The mapping relationship between the pixel points in the real-time image and the pixel lights in the target pixel lights on the vehicle is obtained in the following manner: Determine the field of view and the first resolution of the camera device on the vehicle for acquiring the real-time image, the illumination area and the second resolution of the target pixel headlight, and the relative position of the camera device and the target pixel headlight on the vehicle; Determine a target object that is simultaneously in the field of view and the illumination area, and a distance between the target object and the camera device; Determine, according to the first resolution, first coordinate information of a pixel point corresponding to the target object in the image acquired by the camera device, and determine, according to the second resolution, second coordinate information of each pixel light in the target pixel headlight whose illumination area covers the target object; According to the relative position and the distance, a conversion relationship between the first coordinate information and the second coordinate information is determined, and the conversion relationship is determined as a mapping relationship between pixel points in the real-time image and pixel lights in target pixel lights on the vehicle.

7. A control device for a pixel car light, characterized in that: include: A camera device configured to obtain a real-time image in front of the vehicle; A domain controller is configured to determine an object of interest in the real-time image, and to perform attribute marking on pixel points corresponding to the object of interest in the real-time image to obtain an intermediate image, wherein the attribute marking is used to characterize the category of the object of interest described by the pixel point; The area controller is configured to convert the intermediate image into a target image according to a mapping relationship between pixel points in the real-time image and pixel lights in the target pixel lights on the vehicle, and control the light of the target pixel lights according to the target image.

8. A vehicle, characterized in that: The invention comprises at least two pixel lamps and the control device of the pixel lamps as claimed in claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images