Intelligent vehicle lamp system and control method thereof

Abstract

The invention relates to the technical field of intelligent traffic, in particular to an intelligent vehicle lamp system and a control method thereof.Optical sensing equipment is used for collecting environment information around a vehicle, a pre-projection image is determined according to the environment information, optimal projection parameters are calculated according to the reflectivity and flatness of a projection plane, and the parameters are sent to a light module; projecting according to the calculated focal length and angle parameters; and adaptively adjusting the frequency of detecting the environment information by the optical sensing equipment by using a cyclic decision detection algorithm to realize adaptive control on different roads, weather and vehicle states. According to the method, the light brightness can be automatically adjusted, unreasonable projection areas can be avoided, safety prompt projection is carried out according to road conditions, the accuracy and safety of vehicle illumination are improved, and the risk of traffic accidents is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent traffic technology, and specifically provides an intelligent vehicle lamp system and a control method thereof. Background Art

[0002] In today's Internet age, intelligence has penetrated into every aspect of our lives, and the automotive industry is no exception. Automotive intelligence refers to the use of artificial intelligence, the Internet of Things, big data and other technologies to achieve functions such as automatic driving, remote control, and intelligent interconnection of automobiles, thereby improving the safety, comfort and efficiency of automobiles. With people's pursuit of safety and comfort, automotive intelligence has become the future development direction of the automotive manufacturing industry. As one of the important functions in the driving process of a car, the headlight system also needs to be intelligent to meet the different needs of drivers.

[0003] In traditional headlight systems, drivers need to manually adjust the brightness and angle of the headlights. However, the process of manually adjusting the headlights is cumbersome and needs to adapt to different road conditions and sections. In addition, at night or in bad weather, insufficient or excessive vehicle lighting can cause problems such as blurred vision, fatigue driving, and momentary blindness, thereby increasing the risk of traffic accidents. Therefore, improving the accuracy and adaptability of vehicle lighting has become an important goal and technical topic in the research of intelligent headlights.

[0004] At present, there are intelligent car light systems such as ADB adaptive high beam, DLP digital light, Matrix matrix LED light on the market. These systems can sense the surrounding environment and targets through sensors such as cameras and radars, and adjust the brightness, angle and shape of the lights through controllers to achieve adaptive lighting for different road conditions and scenes. For example, ADB adaptive high beam can automatically dim or turn off the glare area of ​​the opposite or front vehicles while maintaining the high beam state; DLP digital light can project various patterns or logos on the road surface to remind the driver to pay attention to pedestrians, lane changes, parking and other information; Matrix matrix LED light can control the direction of the light according to the steering angle of the steering wheel to reduce the blind spot of vision when turning. However, the existing intelligent car light technology is still in the primary stage of continuous development, with low intelligence, high price, and insufficient ability to adapt to different environments and weather conditions. Therefore, a new type of intelligent car light system and control method is needed to better solve the above problems.

[0005] In order to solve the problems that traditional headlights cannot automatically adjust the brightness and angle of light, cannot cope with complex driving environments and road conditions, and the existing smart headlights are not highly intelligent and have insufficient adaptive capabilities. Summary of the invention

[0006] In order to solve the above problems, the present invention provides an intelligent vehicle lamp system and a control method thereof, which utilizes optical sensing equipment to collect vehicle surrounding environment information, realizes adaptive control of different roads, weather and vehicle conditions through reflectivity and flatness detection and compensation, realizes automatic adjustment of light brightness and angle, greatly improves the intelligence level of intelligent vehicle lamps, and has good adaptability to complex road conditions.

[0007] The present invention provides an intelligent vehicle lighting system, comprising: an optical sensing device, a controller, a lighting module and a display;

[0008] The optical sensing device is used to detect environmental information and send the environmental information to the controller;

[0009] The controller determines the pre-projection image based on the environmental information, calculates the optimal projection parameters based on the reflectivity and flatness of the projection plane, and sends the optimal projection parameters to the lighting module to compensate the pre-projection image, and projects according to the compensated focal length and angle parameters;

[0010] The display is used for information display and human-computer interaction.

[0011] Preferably, the optical sensing device includes an image acquisition device and a depth sensor, the image acquisition device is used to identify image information of the environment, and the depth sensor is used to capture depth information of the environment.

[0012] Preferably, the controller utilizes a cyclic decision detection algorithm to adaptively adjust the frequency at which the optical sensing device detects environmental information.

[0013] Preferably, the controller includes a processor, a storage unit and a communication unit, the processor analyzes and processes the environmental information, and uses a preset algorithm to calculate the reflectivity and flatness of the road ahead, performs color compensation according to the reflectivity, and performs graphic correction according to the flatness to obtain the best projection parameters;

[0014] The storage unit is used to store environmental information and preset algorithms;

[0015] The communication unit is used to exchange data with the lighting module and the display.

[0016] Preferably, the lighting module includes a plurality of independently controllable light-emitting elements.

[0017] A control method for an intelligent vehicle lighting system comprises the following steps:

[0018] S1. Collect visual images and depth information of the vehicle's surroundings and determine the projection plane;

[0019] S2. Determine a pre-projection image according to the visible image, perform color processing on the visible image of the projection plane, perform depth analysis on the depth of the projection plane, calculate the reflectivity and flatness of the projection plane, and calculate the deviation tensor between the projection plane and the ideal projection plane;

[0020] S3. Perform color avoidance and geometry avoidance processing on the pre-projected image according to the deviation tensor, and perform projection based on the processed data.

[0021] Preferably, the color processing is specifically as follows:

[0022] The three color channels R, G, and B of the visible image and the height and width of the projection plane form a five-dimensional feature. H represents the height of the projection plane, and W represents the width of the projection plane. Any point in the projection plane is represented as [r, g, b] (h，w) , r represents the specific value of the point in the R dimension, g represents the specific value of the point in the G dimension, b represents the specific value of the point in the B dimension, h represents the specific value of the point in the H dimension, and w represents the specific value of the point in the W dimension;

[0023] Take a global color fitting plane as the ideal plane and calculate the value of [r, g, b] for any point (h，w) The color deviation tensor of the corresponding point on the ideal plane under the three color channels of R, G, and B.

[0024] Preferably, the in-depth analysis is specifically as follows:

[0025] The depth information and the height and width of the projection plane form a three-dimensional feature. Any point in the projection plane is represented by d (h，w) , d is the specific value of the depth of the point on the projection plane; calculate any point d (h，w) The depth deviation tensor of the corresponding points on the ideal plane.

[0026] Preferably, color avoidance is specifically:

[0027] A pixel point on any frame of pre-projected image is represented by [r′, g′, b′] (h，w) , r′ represents the specific value of the pixel in the R dimension, g′ represents the specific value of the pixel in the G dimension, and b′ represents the specific value of the pixel in the B dimension;

[0028] Traverse all pixels on the pre-projected image and calculate the color deviation tensor ΔC(x,y) of any pixel, where x and y represent the coordinates of the pixel on the pre-projected image;

[0029] Set the color channel threshold to ΔT. When |ΔC(x,y)|>ΔT, take the pixel as the starting point and expand the rectangular box in the four directions of upward, downward, left and right. When the color deviation tensor of the pixel is less than or equal to the color channel threshold, stop expanding. The obtained rectangular box is a heterochromatic area, which is avoided.

[0030] Preferably, the geometric avoidance is specifically:

[0031] Establish a spatial coordinate system, where any point is represented as (x, y, z), set the projection plane to ax+by+cz+k=0, and calculate the parameters a, b, c, k through the fitting algorithm, and the depth of the projection plane can be obtained from the depth information as d0;

[0032] The projection area is calculated based on the projection plane and the corresponding depth information, expressed as:

[0033]

[0034] According to the above requirements, x and y are the maximum projection area boundary sizes that meet the depth threshold.

[0035] Preferably, in S1, a cyclic decision detection algorithm is used to adaptively adjust the frequency of collecting the vehicle's surrounding environment.

[0036] Compared with the prior art, the present invention can achieve the following beneficial effects:

[0037] The present invention obtains environmental information around the vehicle through an optical sensing device, calculates the flatness and reflectivity in front of the vehicle through an internal algorithm, and plans an avoidance plan according to the usage scenario, which can realize adaptive adjustment of the illumination range and light intensity of the headlights, so that the headlights can illuminate within the specified range, improve the safety and comfort of night driving, and realize adaptive control of different roads, weather and vehicle conditions. At the same time, it can identify vehicles, pedestrians or other objects, and project corresponding patterns or logos in front of the road to provide safety assistance or personalized display, solving the problems of low intelligence, high price, and insufficient ability to adapt to different environments and weather conditions of existing smart headlights. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is an overall framework diagram of an intelligent vehicle lighting system and a control method thereof provided according to an embodiment of the present invention;

[0039] Figure 2 It is a global analysis flow chart of an intelligent vehicle lighting system provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the following description, the same modules are represented by the same reference numerals. In the case of the same reference numerals, their names and functions are also the same. Therefore, the detailed description thereof will not be repeated.

[0041] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and do not constitute a limitation of the present invention.

[0042] The intelligent vehicle lighting system provided by the embodiment of the present invention is mainly composed of an optical sensing device, a controller, a lighting module and a display. The optical sensing device is an information collection source, which is mainly used to collect environmental information around the car, including road type, road conditions, weather conditions, road safety signs, vehicle status, pedestrian positions, etc. The optical sensing device can specifically use a variety of sensors such as a monocular camera, a TOF camera, a binocular camera or a multi-camera, and the above sensors can be used alone or in combination to meet different scene requirements. This type of equipment needs to include an image acquisition device and a depth sensor. The image acquisition device can use an ordinary visible light camera or an infrared camera to capture visual information images around the vehicle, such as road type, road conditions, pedestrian positions and road safety signs, etc.; depth sensing can use a TOF camera or a structured light camera to capture depth information around the vehicle, such as vehicle status, distance to obstacles ahead, etc.

[0043] The optical sensing device will send the collected environmental information to the controller in real time. After receiving the environmental information, the controller will analyze and process it and control the light module to provide feedback. The controller is the core component of the intelligent headlight system, including but not limited to a processor, a storage unit and a communication unit. The processor analyzes and processes the received environmental information, identifies vehicles, pedestrians, safety signs or other objects based on the environmental information, and projects them as pre-projected images in front of the road to provide safety assistance or personality display. It should be noted that the pre-projected image determined based on the environmental information does not need to be completely consistent with the image in the environmental information, but only needs to be able to reflect the environmental information and play a role in safety prompts. At the same time, the controller uses preset algorithms and rules to calculate the reflectivity and flatness of the road ahead, performs color compensation based on the reflectivity, and performs graphic correction based on the flatness to obtain the best projection parameters; the best projection parameters are compensated to the pre-projected image, and the processed image data is sent to the light module to control the light module for projection. The brightness, angle and shape of the headlights can be adjusted based on the environmental information to achieve adaptive lighting for different road conditions and scenes. For example, when environmental information reflects that the vehicle is approaching an intersection or pedestrians are crossing the road, the controller controls the headlight module to automatically switch to low beam to avoid glare to other drivers or pedestrians; when the vehicle is driving, the controller transmits lane signs, driving direction, road speed limit and other safety auxiliary information to the lighting module for projection, and projects it onto the road surface of the car to remind the driver to pay attention to driving safety; when the vehicle encounters low visibility conditions such as rain, fog, and snow, it can automatically adjust the brightness and angle according to the ambient light and reflectivity to improve the driving field of vision; when the headlights are illuminated, if obstacles block the lighting, the lighting angle or lighting range can be automatically adjusted. Through the above functions, the intelligent headlight system can further improve the accuracy and safety of vehicle lighting and reduce the risk of traffic accidents. The processor in the controller can use a single-core or multi-core processor, and a processor with high-speed computing capability and low power consumption can be selected according to actual needs and practicality. The storage unit can use random access memory (RAM) or read-only memory (ROM) to store environmental information and preset algorithms, etc. Similarly, the storage unit can select an existing memory according to actual needs; the communication unit can use a wired or wireless communication module to exchange data with the lighting module and display. In addition, the controller also stores a cyclic decision detection algorithm, which is used to control the optical perception device to perform cyclic detection of environmental information and adaptively adjust the cyclic detection frequency. At the same time, the controller does not adjust the lighting for slight changes in the environment, avoiding frequent lighting switching that causes discomfort to the driver and ensuring the lighting adjustment effect.

[0044] The lighting module includes but is not limited to the use of multiple independently controllable LED lamp beads, DLP chips or DMD chips and other light-emitting elements. These light-emitting elements can receive the projection image sent by the controller and project the processed image data. During projection, the projection shape can be adjusted by independently controlling each light-emitting element. In addition, these light-emitting elements can also adjust the lighting parameters such as working mode, brightness and angle to achieve the effect of smart car lights. The light-emitting element can adopt an LED or laser-based light source, which has the characteristics of high brightness, high efficiency and long life, and can provide bright and lasting lighting effects. According to different light-emitting principles and projection methods, smart car light modules can be divided into many types, including matrix LED headlights, digital LED headlights, laser headlights, etc. Each type has different characteristics and application scenarios, and can be selected and applied according to specific needs.

[0045] The display communicates with the controller, and can use a liquid crystal display, projector, etc. for information display and human-computer interaction. The display receives the control parameters sent by the controller, and displays the control parameters and vehicle status, such as the working mode, brightness parameters, angle parameters, projection shape and the corresponding meaning of the projection shape of the intelligent headlight system, etc. It can also display the fault prompts, warning prompts, operation prompts and other information of the headlight system. In addition, it can interact with the user through a touch screen or voice control, so that the user can set and adjust the headlight system. The display can be a screen integrated on the dashboard or center console, or a head-up display (HUD) projected on the windshield, so that the user can view relevant information of the headlight system.

[0046] like Figure 1 As shown, for the above-mentioned intelligent vehicle lighting system, the embodiment of the present invention further proposes a control method based on color avoidance and geometric avoidance, and explains it in combination with a specific scenario, wherein the optical sensing device is used to collect environmental image information and depth information, and selects RealSense TM D435 binocular camera (hereinafter referred to as binocular camera), the RGB channel resolution of the binocular camera is 1920×1080, the field of view angle range is 69°×42°, the resolution of the Depth channel is 1280×720, and the field of view angle range is 87°×58°; the lighting module is used for projection lighting, and Texas Instruments DLP5531-Q1 (hereinafter referred to as projection car light) is selected; the controller selects DLPC230-Q1 DMD controller, and the above devices are integrated with TPS99001-Q1 system management; the projection scene is the road surface. The specific steps include the following:

[0047] S1. Before collecting information, the binocular camera needs to be calibrated to ensure the accuracy of the data. Use the binocular camera to shoot objects of known color and transmit the color information to the controller for color calibration. Fix the binocular camera in a suitable position to ensure that the field of view of the binocular camera can cover the entire area in front of the vehicle. Since the positions of the binocular camera, projection lights and driver are different and their relative positions remain unchanged, in order to ensure subsequent accurate modeling and precise control, use measurement tools to calibrate the positional relationship between the three, and obtain the corresponding origin coordinates P, C, and U. With the coordinates of the projection lights as a reference, measure the six-dimensional posture state of the binocular camera and the driver relative to the origin of the projection lights in detail to obtain the posture transformation matrix of the binocular camera relative to the projection lights. The pose transformation matrix of the driver relative to the projection lamp In terms of equipment calibration, the optical parameters of the binocular camera and the projection headlight are measured through the existing scheme, and the internal parameters of the binocular camera and the projection headlight are calibrated, so that the photo effect of the double-sided camera is consistent with the real picture, and the projection effect of the projection equipment is consistent with the specified projection picture.

[0048] After correction and calibration, the binocular camera collects visible image information and depth information of the vehicle's surrounding environment, including road type, road conditions, weather conditions, vehicle status, pedestrian position, etc., and intercepts the overlapping field of view of RGB and Depth of the binocular camera, 69°×42°, as effective information. The pixel resolution of RGB is 1920×1080, and the pixel resolution of Depth is intercepted to: 1016×521, and the projection plane is determined based on the environmental information. The visible image and depth information are analyzed and processed separately, and finally the mapping relationship between the RGB image and the depth image is established according to the RGB and Depth camera external parameter matrices.

[0049] S2, such as Figure 2 As shown, the visible image corresponding to the projection plane is color processed, and the three color channels R, G, and B of the visible image of the projection plane and the height and width of the projection plane form a five-dimensional feature, which respectively represents the color space information R (red), G (green), and B (blue) of the projection plane, and the geometric space information H (height) and W (width). The plane composed of (H, W) represents the projection plane, so any point on this plane can be represented as [r, g, b] (h，w), where r represents the specific value of the point in the R dimension, g represents the specific value of the point in the G dimension, b represents the specific value of the point in the B dimension, h represents the specific value of the point in the H dimension, and w represents the specific value of the point in the W dimension. Color processing is to obtain the five-dimensional deviation tensor between the data of each dimension in the plane scene and an ideal projection plane with pure white color. Therefore, the color gamut values ​​of the three dimensions of r, g, and b are fitted to each color gamut plane based on the collected information, and the outliers are continuously stripped to fit the global color fitting plane. As an ideal plane, the color information of any point on it is recorded as [r0, g0, b0]. At any point [r, g, b] within the known global range (H, W) (h，w) The value distribution of can be used to obtain the color deviation tensor of the pixel on the visible image in the three color channels of R, G, and B and the corresponding point on the ideal plane:

[0050] ΔC(h,w)=[ΔR(h,w),ΔG(h,w),ΔB(h,w)].

[0051] The depth of the projection plane is analyzed, and the depth D of the projection plane is combined with the height H and width W of the projection plane to form a three-dimensional feature. The corresponding depth analysis algorithm is formulated according to the binocular cameras with different precisions. The precision ranges from simple to complex. The base dimension calculation method can be selected: pixel method, plane fitting method, spot method, and light method. Any point in the projection plane is represented as d (h，w) , d represents the specific value of the depth of the point on the projection plane. Depth analysis first fuses the depth information with the spatial geometric data and quantizes them. The plane fitting algorithm is selected according to the accuracy level of the binocular camera captured by the depth information. The fitting plane is obtained by fitting and continuously removing outliers. It is used as the ideal plane reference. For any point in the global range (H, W), the depth information d (h，w) , the depth deviation tensor of the position containing the depth information relative to the ideal plane can be obtained.

[0052] In addition, the controller needs to use a convolutional neural network (CNN) or other machine learning algorithms to process the collected visible images, identify pedestrians, vehicles or other objects in the visible images, and determine the pre-projected image based on the information recognized from the visible images.

[0053] S3. Perform color avoidance and geometric avoidance processing on the pre-projected image according to the deviation tensor, and project according to the processed data. When color avoidance is performed, a pixel point on any frame of the pre-projected image is represented as [r′, g′, b′] (h，w), r′ represents the specific value of the pixel point on the pre-projected image in the R dimension, g′ represents the specific value of the pixel point on the pre-projected image in the G dimension, b′ represents the specific value of the pixel point on the pre-projected image in the B dimension, and (h, w) represents the corresponding position of the point on the visible image. Since the pixel resolution of the pre-projected image is significantly higher than the deviation tensor, the deviation tensor is upsampled to make the resolution of the two equal.

[0054] Due to the existence of the color deviation tensor, it is necessary to determine the maximum rectangular frame of the heterochromatic area according to the threshold of the color channel, and divide the heterochromatic area to avoid it. The specific steps for determining the heterochromatic area are as follows:

[0055] Traverse all pixels on the pre-projected image and calculate the color deviation tensor ΔC(x, y) of any pixel, where x and y represent the coordinates of the pixel point on the pre-projected image.

[0056] The color channel threshold is set to ΔT, which is used to determine whether the color deviation of the pixel exceeds the threshold. ΔT can be appropriately designed according to the accuracy of the algorithm.

[0057] When |ΔC(x, y)|>ΔT, the rectangular box is expanded in the four directions of upward, downward, left and right with the pixel as the starting point. When the color deviation tensor of the pixel is less than or equal to the color channel threshold, the expansion is stopped and the obtained rectangular box is a heterochromatic area, which is avoided.

[0058] The following is a specific example of the rectangular frame expansion process: Assume that the starting pixel is (x1, y1) and the pixel currently expanded to is (x i ,y i ), determine whether to continue expanding based on the following example:

[0059] If |ΔC(x2,y i-1 )|≤ΔT, then (x2, y i-1 ) is the upper boundary of the rectangular box.

[0060] If |ΔC(x2,y i+1 )|≤ΔT, then (x2, y i+1 ) is the lower edge of the rectangle.

[0061] If |ΔC(x i-1 , y2)|≤ΔT, then (x i-1 , y2) is the left border of the rectangular box.

[0062] If |ΔC(x i+1 , y2)|≤ΔT, then (x i+1 , y2) is the right border of the rectangular box.

[0063] Through the above process, the rectangular box that does not meet the color channel threshold can be determined, and the rectangular box is represented as a heterochromatic area. This process can be used to identify areas with large color deviations in the pre-projected image. Once the heterochromatic area is identified, directional projection measures can be taken, that is, the projection light avoids the heterochromatic area, thereby achieving the effect of color avoidance. This ensures the color accuracy and consistency of the projected image. This method can realize the automatic identification and avoidance of color deviations in the pre-projected image, which can improve the quality and reliability of the headlight effect, while improving driving safety and comfort.

[0064] The geometric avoidance mainly includes the following steps:

[0065] A three-dimensional scene model is established based on the collected environmental information, and a spatial coordinate system is established, where the position coordinates of any point are expressed as (x, y, z), where z is equivalent to the depth information. According to the position and orientation angle of the binocular camera, a camera coordinate system is established, and the relationship between the two is replaced with each other. A projection plane is set as ax+by+cz+k=0 in the spatial coordinate system. Some points are randomly sampled and the plane equation is fitted by the least squares method. During the fitting process, the RANSAC algorithm and other methods can be used to remove outliers, improve the accuracy of plane fitting, and obtain parameters a, b, c, k. Based on the known depth information, the depth of the projection plane is determined to be d0, and the projection area is calculated based on the projection plane and the corresponding depth information, which is expressed as:

[0066]

[0067] According to the above requirements, x and y are the maximum projection area boundary sizes that meet the depth threshold, achieving the geometric obstacle avoidance effect.

[0068] The space formed by the projection area and the headlight module is the projection space. When there are obstructions in the projection space, obstacle avoidance can be performed by adjusting the projection angle or reducing the projection range. When the projection angle is too large or too small, the obstruction may be outside the projection space and cannot be detected. To solve this problem, the projection angle can be gradually adjusted, and the angle of the light source can be adjusted by a small angle range each time until the obstruction can be detected. By gradually adjusting the projection angle, a suitable angle range can be found to ensure that the obstruction can be accurately detected and geometric obstacle avoidance can be achieved. In addition, the boundary of the area can be adjusted according to the position and size of the detected obstruction to ensure that the projection space avoids the obstruction.

[0069] S4. Perform an intersection operation on the color avoidance P(img) and the geometric avoidance processing Q(img) of the pre-projection image img to obtain a common projectable area and obtain a projection image simg:

[0070] simg=MINrec(P(img),Q(img));

[0071] Simg is the image after avoidance processing. The image Simg is sent to the projection lamp for projection. During the entire projection process, the processor periodically sends commands to drive the binocular camera to periodically detect image information and depth information. After analysis and processing, the projection lamp is driven again to project the updated projection image. This cycle is repeated to improve the projection effect of the projection image without difference and attenuate the detection frequency over time, taking energy-saving measures into consideration while ensuring the projection accuracy.

[0072] Through the above processing of the pre-projected image, even under external interference conditions, the projected image is consistent with the real picture in color and geometry, and has high lighting and projection accuracy.

[0073] Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. Those skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

[0074] The above specific implementations of the present invention do not constitute a limitation on the protection scope of the present invention. Any other corresponding changes and modifications made based on the technical concept of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. An intelligent vehicle lighting system, characterized in that: include: Optical sensing devices, controllers, lighting modules and displays; The optical sensing device is used to detect environmental information and send the environmental information to the controller; The controller determines the pre-projection image based on the environmental information, calculates the optimal projection parameters based on the reflectivity and flatness of the projection plane, and sends the optimal projection parameters to the lighting module to compensate the pre-projection image, and projects according to the compensated focal length and angle parameters; The display is used for information display and human-computer interaction.

2. The intelligent vehicle lighting system according to claim 1, characterized in that: The optical perception device includes an image acquisition device and a depth sensor. The image acquisition device is used to identify image information of the environment, and the depth sensor is used to capture depth information of the environment.

3. The intelligent vehicle lighting system according to claim 1, characterized in that: The controller uses a cyclic decision detection algorithm to adaptively adjust the frequency of the optical sensing device detecting environmental information.

4. The intelligent vehicle lighting system according to claim 1, characterized in that: The controller includes a processor, a storage unit and a communication unit. The processor analyzes and processes environmental information and uses a preset algorithm to calculate the reflectivity and flatness of the road ahead, performs color compensation based on the reflectivity, and performs graphic correction based on the flatness to obtain optimal projection parameters. The storage unit is used to store environmental information and preset algorithms; The communication unit is used to exchange data with the lighting module and the display.

5. The intelligent vehicle lighting system according to claim 1, characterized in that: The lighting module includes a plurality of independently controllable light-emitting elements.

6. A control method for an intelligent vehicle lighting system, characterized in that: The following steps are involved: S1. Collect visual images and depth information of the vehicle's surroundings and determine the projection plane; S2. Determine a pre-projection image according to the visible image, perform color processing on the visible image of the projection plane, perform depth analysis on the depth of the projection plane, calculate the reflectivity and flatness of the projection plane, and calculate the deviation tensor between the projection plane and the ideal projection plane; S3. Perform color avoidance and geometry avoidance processing on the pre-projected image according to the deviation tensor, and perform projection based on the processed data.

7. The control method of the intelligent vehicle lighting system according to claim 6, characterized in that: The color processing is specifically as follows: The three color channels of the visible image, R, G, and B, and the height and width of the projection plane form a five-dimensional feature. H represents the height of the projection plane, and W represents the width of the projection plane. Any point in the projection plane is represented as [r, g, b] (h,w) , R represents the specific value of the point in the R dimension, G represents the specific value of the point in the G dimension, B represents the specific value of the point in the B dimension, h represents the specific value of the point in the H dimension, and w represents the specific value of the point in the W dimension; Take a global color fitting plane as the ideal plane and calculate the value of [r, g, b] at any point (h,w) The color deviation tensor of the corresponding point on the ideal plane under the three color channels of R, G, and B.

8. The control method of the intelligent vehicle lighting system according to claim 7, characterized in that: The in-depth analysis is specifically as follows: The depth information and the height and width of the projection plane form a three-dimensional feature. Any point in the projection plane is represented by d (h,w) , d is the specific value of the depth of the point on the projection plane; calculate any point d (h,w) The depth deviation tensor of the corresponding points on the ideal plane.

9. The control method of the intelligent vehicle lighting system according to claim 7, characterized in that: The color avoidance is specifically as follows: A pixel point on any frame of pre-projected image is represented by [r′, g′, b′] (h,w) , r′ represents the specific value of the pixel in the R dimension, g′ represents the specific value of the pixel in the G dimension, and b′ represents the specific value of the pixel in the B dimension; Traverse all pixels on the pre-projected image and calculate the color deviation tensor ΔC(x,y) of any pixel, where x and y represent the coordinates of the pixel on the pre-projected image; Set the color channel threshold to ΔT. When |ΔC(x,y)|>ΔT, take the pixel as the starting point and expand the rectangular box in the four directions of upward, downward, left and right. When the color deviation tensor of the pixel is less than or equal to the color channel threshold, stop expanding. The obtained rectangular box is a heterochromatic area, which is avoided.

10. The control method of the intelligent vehicle lighting system according to claim 8, characterized in that: The geometric avoidance is specifically: Establish a spatial coordinate system, where any point is represented as (x, y, z), set the projection plane to ax+by+cz+k=0, and obtain the parameters a, b, c, k through the fitting algorithm combined with the depth threshold calculation, and the depth of the projection plane can be obtained from the depth information as d0; The projection area is calculated based on the projection plane and the corresponding depth information, expressed as: According to the above requirements, x and y are the maximum projection area boundary sizes that meet the depth threshold.

11. The control method of the intelligent vehicle lighting system according to claim 6, characterized in that: In S1, a cyclic decision detection algorithm is used to adaptively adjust the frequency of collecting the vehicle's surrounding environment.

Images