Intelligent vehicle light system and control method thereof

Abstract

The application relates to the technical field of intelligent traffic, and particularly provides an intelligent vehicle lamp system and a control method thereof. The system collects environmental information around a vehicle by using an optical sensing device, determines a pre-projection image according to the environmental information, calculates optimal projection parameters according to the reflectivity and flatness of a projection plane, sends the parameters to a light module, and projects according to the calculated focal length and angle parameters. A cyclic decision detection algorithm is used to adaptively adjust the frequency of the optical sensing device in detecting environmental information, so that adaptive control of different roads, weather and vehicle states is realized. The application can automatically adjust light brightness, avoid unreasonable projection areas, and project safety prompts according to road conditions, thereby improving the accuracy and safety of vehicle lighting and reducing the risk of traffic accidents.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, specifically providing an intelligent vehicle lighting system and its control method. Background Technology

[0002] In today's internet age, intelligent technology has permeated every aspect of our lives, and the automotive industry is no exception. Automotive intelligence refers to the use of technologies such as artificial intelligence, the Internet of Things, and big data to achieve functions like autonomous driving, remote control, and intelligent connectivity, thereby improving the safety, comfort, and efficiency of vehicles. With people's increasing pursuit of safety and comfort, automotive intelligence has become the future development direction of the automotive manufacturing industry. As one of the important functions during vehicle operation, the lighting system also needs to be intelligent to meet the different needs of drivers.

[0003] In traditional vehicle lighting systems, drivers need to manually adjust the brightness and angle of the headlights. However, manually adjusting the headlights is cumbersome and requires adapting to different road conditions and sections. Furthermore, at night or in inclement weather, insufficient or excessive vehicle lighting can lead to blurred vision, driver fatigue, 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 challenge in intelligent vehicle lighting research.

[0004] Currently, intelligent vehicle lighting systems such as ADB adaptive high beam, DLP digital lighting, and Matrix LED lighting have emerged on the market. These systems use sensors such as cameras and radar to perceive the surrounding environment and targets, and use controllers to adjust the brightness, angle, and shape of the headlights to achieve adaptive lighting for different road conditions and scenarios. For example, ADB adaptive high beam can automatically dim or turn off the glare area for oncoming or forward vehicles while maintaining high beam; DLP digital lighting can project various patterns or markings on the road surface to remind drivers of pedestrians, lane changes, parking information, etc.; Matrix LED lighting can control the direction of the headlights according to the steering wheel angle, reducing blind spots when cornering. However, existing intelligent vehicle lighting technologies are still in the early stages of development, with low levels of intelligence, high prices, and insufficient adaptability to different environments and weather conditions. Therefore, a new type of intelligent vehicle lighting system and control method is needed to better solve these problems.

[0005] To address the issues of traditional vehicle lights not being able to automatically adjust brightness and angle, thus failing to cope with complex driving environments and road conditions, and the low level of intelligence and insufficient adaptive capabilities of existing intelligent vehicle lights. Summary of the Invention

[0006] To address the aforementioned problems, this invention provides an intelligent vehicle lighting system and its control method. By utilizing optical sensing devices to collect information about the vehicle's surrounding environment and detecting and compensating for reflectivity and flatness, it achieves adaptive control for different road conditions, weather conditions, and vehicle statuses. This enables automatic adjustment of light brightness and angle, greatly enhancing the intelligence level of the intelligent vehicle lighting and providing better 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] Optical sensing devices are used to detect environmental information and send it to the controller;

[0009] The controller determines the pre-projected image based on 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 for the pre-projected image. The image is then projected according to the compensated focal length and angle parameters.

[0010] Displays are 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 uses 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 environmental information, calculates the reflectivity and smoothness of the road surface ahead using a preset algorithm, performs color compensation based on the reflectivity, and performs graphic correction based on the smoothness to obtain the optimal 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 multiple independently controllable light-emitting elements.

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

[0018] S1. Collect visible images and depth information of the environment around the vehicle and determine the projection plane;

[0019] S2. Determine the pre-projected image based on 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 geometric avoidance processing on the pre-projected image based on the deviation tensor, and then project the image based on the processed data.

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

[0022] The R, G, and B color channels of the visible image are combined with the height and width of the projection plane to form a five-dimensional feature, where 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 dimension R, g represents the specific value of the point in dimension G, b represents the specific value of the point in dimension B, h represents the specific value of the point in dimension H, and w represents the specific value of the point in dimension W.

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

[0024] Preferably, the in-depth analysis specifically includes:

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

[0026] Preferably, color avoidance specifically includes:

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

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

[0029] Set the color channel threshold to ΔT. When |ΔC(x,y)|>ΔT, expand the rectangle in four directions (up, down, left, and right) starting from that pixel. Stop expanding when the color deviation tensor of the pixel is less than or equal to the color channel threshold. The resulting rectangle is the heterochromatic region, and heterochromatic regions are avoided.

[0030] Preferably, geometric avoidance specifically includes:

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

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

[0033]

[0034] Based on the above calculations, x and y are the boundary dimensions of the maximum projection region that satisfy the depth threshold.

[0035] Preferably, in S1, the frequency of collecting data on the vehicle's surrounding environment is adaptively adjusted using a cyclic decision detection algorithm.

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

[0037] This invention acquires environmental information around the vehicle through optical sensing devices, calculates the flatness and reflectivity in front of the vehicle using internal algorithms, and plans avoidance schemes according to the usage scenario. It can adaptively adjust the illumination range and intensity of the headlights, ensuring the lights illuminate a designated area, improving safety and comfort during nighttime driving. It also enables adaptive control based on different road conditions, weather, and vehicle statuses. Simultaneously, it can identify vehicles, pedestrians, or other objects, projecting corresponding patterns or markings onto the road surface in front to provide safety assistance or personalized displays. This solves the problems of existing intelligent headlights, such as low intelligence, high cost, and insufficient adaptability to different environments and weather conditions. Attached Figure Description

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

[0039] Figure 2 This is a flowchart of the full-domain analysis of an intelligent vehicle lighting system provided according to an embodiment of the present invention. Detailed Implementation

[0040] In the following description, embodiments of the invention will be described with reference to the accompanying drawings. In the description below, the same modules are denoted by the same reference numerals. Where the same reference numerals are used, their names and functions are also the same. Therefore, their detailed description will not be repeated.

[0041] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not constitute a limitation thereof.

[0042] The intelligent vehicle lighting system provided in this invention mainly consists of an optical sensing device, a controller, a lighting module, and a display. The optical sensing device is the information acquisition source, primarily used to collect environmental information around the vehicle, including road type, road conditions, weather conditions, road safety signs, vehicle status, and pedestrian positions. Specifically, the optical sensing device can employ various sensors such as monocular cameras, TOF cameras, binocular cameras, or multi-view cameras, and these sensors can be used individually or in combination to adapt to different scenario requirements. This type of device needs to include an image acquisition device and a depth sensor. The image acquisition device can use a common 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. The depth sensor can use a TOF camera or a structured light camera to capture depth information around the vehicle, such as vehicle status and distance to obstacles ahead.

[0043] Optical sensing devices transmit collected environmental information to the controller in real time. The controller receives and analyzes this information, then controls the lighting module to provide feedback. The controller, the core component of the intelligent vehicle lighting system, includes, but is not limited to, a processor, storage unit, and communication unit. The processor analyzes the received environmental information, identifies vehicles, pedestrians, safety signs, or other objects, and projects these as pre-projected images onto the road ahead to provide safety assistance or personalized displays. It's important to note that the pre-projected image determined by the environmental information does not need to be completely identical to the image in the environmental information; it only needs to reflect the environmental information and serve as a safety warning. Simultaneously, the controller uses preset algorithms and rules to calculate the reflectivity and smoothness of the road surface ahead. Color compensation is performed based on reflectivity, and graphic correction is performed based on smoothness to obtain optimal projection parameters. These optimal projection parameters are then applied to the pre-projected image, and the processed image data is sent to the lighting module to control the projection. Based on the environmental information, the brightness, angle, and shape of the headlights can be adjusted to achieve adaptive lighting for different road conditions and scenarios. For example, when environmental information indicates that the vehicle is approaching an intersection or a pedestrian is crossing the road, the controller automatically switches the headlight module to low beam to avoid glare for other drivers or pedestrians. While the vehicle is in motion, the controller transmits safety assistance information such as lane markings, driving direction, and speed limits to the headlight module for projection onto the road surface, reminding the driver to pay attention to driving safety. When the vehicle encounters low visibility conditions such as rain, fog, or snow, the system automatically adjusts the brightness and angle based on ambient light and reflectivity to improve visibility. When the headlights are illuminating and an obstacle obstructs the light, the system automatically adjusts the lighting angle or range. Through these functions, the intelligent headlight system can further improve the accuracy and safety of vehicle lighting, reducing the risk of traffic accidents. The processor in the controller can be a single-core or multi-core processor, selected based on actual needs and practicality, featuring high-speed computing power and low power consumption. The storage unit can be either Random Access Memory (RAM) or Read-Only Memory (ROM) to store environmental information and preset algorithms. The storage unit can be any existing memory available, depending on actual needs. The communication unit can be a wired or wireless communication module for data exchange with the lighting module and display. Furthermore, the controller stores a cyclic decision-making detection algorithm to control the optical sensing device to cyclically detect environmental information and adaptively adjust the cyclic detection frequency. Simultaneously, the controller does not adjust the lights for minor environmental changes, avoiding frequent light switching that could cause driver discomfort and ensuring effective light adjustment.

[0044] The lighting module includes, but is not limited to, the use of multiple independently controllable LED beads, DLP chips, or DMD chips. These light-emitting elements can receive projected images sent by the controller and project the processed image data. During projection, the shape of the projection can be adjusted by independently controlling each light-emitting element. Furthermore, these light-emitting elements can adjust lighting parameters such as operating mode, brightness, and angle to achieve intelligent vehicle lighting effects. The light-emitting elements can use LED or laser-based light sources, featuring high brightness, high efficiency, and long lifespan, providing bright and lasting illumination. Based on different light-emitting principles and projection methods, intelligent vehicle lighting modules can be divided into various types, including matrix LED headlights, digital LED headlights, and laser headlights. Each type has different characteristics and application scenarios, allowing for selection and application based on specific needs.

[0045] The display communicates with the controller, and can use an LCD screen, projector, or similar device for information display and human-machine interaction. The display receives control parameters from the controller and displays these parameters along with the vehicle's status. Examples include the intelligent lighting system's operating mode, brightness parameters, angle parameters, projection shape, and the meaning of the projection shape. It can also display fault prompts, warnings, and operation prompts for the lighting system. Furthermore, it can interact with the user via touchscreen or voice control, allowing the user to set and adjust the lighting system. The display can be integrated into the instrument panel or center console, or it can be a head-up display (HUD) projected onto the windshield for easy viewing of relevant lighting system information.

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

[0047] S1. Before information acquisition, the binocular camera needs to be calibrated to ensure data accuracy. The binocular camera is used to photograph objects of known color, and the color information is transmitted to the controller for color calibration. The binocular camera is fixed in a suitable position to ensure its field of view covers the entire area in front of the vehicle. Since the positions of the binocular camera, the projection headlight, and the driver are different but their relative positions remain constant, to ensure accurate modeling and precise control, measuring tools are used to calibrate the positional relationship of the three components, obtaining their respective origin coordinates P, C, and U. Using the coordinates of the projection headlight as a reference, the six-dimensional pose states of the binocular camera and the driver relative to the origin of the projection headlight are measured in detail, obtaining the pose transformation matrix of the binocular camera relative to the projection headlight. Driver pose transformation matrix relative to the projected vehicle headlights In terms of equipment calibration, the optical parameters of the binocular camera and the projection vehicle light are measured using existing established solutions to calibrate the intrinsic parameters of the binocular camera and the projection vehicle light, so that the image taken by the binocular camera is consistent with the real image and the projection effect of the projection device is consistent with the specified projection image.

[0048] After calibration and adjustment, the binocular camera acquires visual and depth information of the vehicle's surrounding environment, including road type, road conditions, weather conditions, vehicle status, and pedestrian positions. The overlapping field of view (69° × 42°) of the RGB and Depth images from the binocular camera is extracted as valid information. The RGB pixel resolution is 1920 × 1080, and the extracted Depth pixel resolution is 1016 × 521. The projection plane is determined based on the environmental information. The visual and depth information are analyzed and processed separately, and finally, a mapping relationship between the RGB and depth images is established according to the RGB and Depth camera extrinsic parameter matrices.

[0049] S2, such as Figure 2 As shown, color processing is performed on the visual image corresponding to the projection plane. The R, G, and B color channels of the visual image on the projection plane are combined with the height and width of the projection plane to form a five-dimensional feature, representing the color space information R (red), G (green), and B (blue) and the geometric space information H (height) and W (width) of the projection plane, respectively. The plane formed by (H, W) represents the projection plane. Therefore, any point under this plane can be represented as [r, g, b]. (h，w)Here, r represents the specific value of the point in dimension R, g represents the specific value of the point in dimension G, b represents the specific value of the point in dimension B, h represents the specific value of the point in dimension H, and w represents the specific value of the point in dimension W. Color processing aims to obtain the five-dimensional deviation tensor between the data of each dimension in the planar scene and an ideal projection plane of pure white. Therefore, based on the collected information, the color gamut values ​​of the three dimensions r, g, and b are used to fit each color gamut plane, and outlier points are continuously removed to fit a global color fitting plane, which is used as the ideal plane. The color information of any point on it is denoted as [r0, g0, b0]. Any point [r, g, b] within the known global range (H, W) is considered as a reference point. (h，w) By analyzing the value distribution of the values, we can obtain the color deviation tensor between the pixels on the visible image and the corresponding points on the ideal plane under the R, G, and B color channels:

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

[0051] Depth analysis is performed on the projection plane, constructing a 3D feature by combining the depth D with the height H and width W of the projection plane. Different depth analysis algorithms are developed for binocular cameras of varying precision, with the precision ranging from simple to complex. The baseline dimension calculation methods include: pixel method, plane fitting method, spot method, and ray method. Any point on the projection plane is represented as d. (h，w) Let d represent the specific depth value of the point on the projection plane. Depth analysis first fuses and tensors the depth information with spatial geometric data. A plane fitting algorithm is selected based on the accuracy level of the stereo camera capturing the depth information. Through fitting and continuous outlier removal, a fitted plane is obtained and used as the ideal plane reference. For any point within the global range (H, W), the depth information d... (h，w) This allows us to calculate the depth deviation tensor of the position relative to the ideal plane, which contains depth information.

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

[0053] S3. Perform color avoidance and geometric avoidance processing on the pre-projected image based on the bias tensor, and project the image based on the processed data. During color avoidance, represent a pixel in any frame of the pre-projected image as [r′, g′, b′]. (h，w)Let r′ represent the specific value of the pixel in the pre-projected image in dimension R, g′ represent the specific value of the pixel in the pre-projected image in dimension G, b′ represent the specific value of the pixel in the pre-projected image in dimension B, and (h, w) represent the corresponding position of the point on the visible image. Since the pixel resolution of the pre-projected image is significantly higher than that of the bias tensor, the bias tensor is upsampled to make the resolutions of the two comparable.

[0054] Due to the existence of the color deviation tensor, it is necessary to determine the maximum bounding box of the dissimilar region based on the threshold of the color channel, and then divide the dissimilar region for avoidance. The specific steps for determining the dissimilar region are as follows:

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

[0056] Set the color channel threshold to ΔT to determine whether the color deviation of a pixel exceeds the threshold. ΔT can be appropriately designed based on the algorithm's accuracy.

[0057] When |ΔC(x, y)|>ΔT, starting from that pixel, the rectangle is expanded in four directions: up, down, left, and right. When the color deviation tensor of the pixel is less than or equal to the color channel threshold, the expansion stops. The resulting rectangle is a heterochromatic region, and heterochromatic regions are avoided.

[0058] A specific example of the rectangle expansion process is as follows: Assume the starting pixel is (x1, y1), and the currently expanded pixel is (x1, y1). i y i Based on the following example, determine whether to continue expanding:

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

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

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

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

[0063] Through the above process, bounding boxes that do not meet the color channel thresholds can be identified; these boxes are represented as dissimilar color regions. This process can be used to identify areas with significant color deviations in the pre-projected image. Once dissimilar color regions are identified, directional projection measures can be taken to avoid these regions, thus achieving color avoidance. This ensures the color accuracy and consistency of the projected image. This method enables automatic identification and avoidance of color deviations in pre-projected images, improving the quality and reliability of vehicle lighting effects, while also enhancing driving safety and comfort.

[0064] Geometric avoidance mainly includes the following steps:

[0065] A 3D scene model is built based on the collected environmental information, and a spatial coordinate system is established, where the position coordinates of any point are represented as (x, y, z), and z represents the depth information. A camera coordinate system is established based on the position and orientation angle of the stereo camera, and the two coordinates are interchanged. A projection plane is defined in the spatial coordinate system as ax + by + cz + k = 0. By randomly sampling some points, the plane equation is fitted using the least squares method. During the fitting process, methods such as RANSAC can be used to remove outliers and improve the accuracy of the plane fitting, obtaining the parameters a, b, c, and k. Based on the known depth information, the depth of the projection plane is determined as d0. The projection area is calculated based on the projection plane and the corresponding depth information, represented as:

[0066]

[0067] Based on the above calculations, x and y are the maximum projection area boundary sizes that satisfy the depth threshold, thus achieving geometric obstacle avoidance.

[0068] The space formed by the projection area and the headlight module constitutes the projection space. When an obstruction exists within this space, obstacle avoidance can be achieved by adjusting the projection angle or reducing the projection range. If the projection angle is too large or too small, the obstruction may be located outside the projection space and thus undetectable. To address this, the projection angle and the angle emitted by the light source can be gradually adjusted, making small adjustments each time until the obstruction can be detected. By progressively adjusting the projection angle, a suitable range can be found to ensure accurate detection of the obstruction, achieving geometric obstacle avoidance. Furthermore, the boundaries of the area can be adjusted based on the location and size of the detected obstruction to ensure the projection space avoids it.

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

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

[0071] The simg image is the processed image. The simg image is sent to the projection headlights for projection. Throughout the projection process, the processor periodically sends commands to drive the binocular camera to periodically detect image and depth information. After analysis and processing, the projection headlights are driven again to project the updated image. This process is repeated to improve the uniformity of the projection and to reduce the detection frequency over time, ensuring projection accuracy while also considering energy conservation.

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

[0073] Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

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

Claims

1. A control method for an intelligent vehicle lighting system, characterized in that, Includes the following steps: S1. Collect visible images and depth information of the environment around the vehicle and determine the projection plane; S2. Determine the pre-projected image based on 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, calculate the reflectivity and flatness using preset algorithms and rules, and calculate the deviation tensor between the projection plane and the ideal projection plane. The color processing specifically involves: The R, G, and B color channels of the visible image are combined with the height and width of the projection plane to form a five-dimensional feature, where 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 dimension R, g represents the specific value of the point in dimension G, b represents the specific value of the point in dimension B, h represents the specific value of the point in dimension H, and w represents the specific value of the point in dimension W. Using a global color fitting plane as the ideal plane, calculate the value at any point [r, g, b]. (h,w) The color deviation tensor between the corresponding points on the ideal plane under the three color channels R, G, and B; The in-depth analysis specifically refers to: The depth information, along with the height and width of the projection plane, forms a three-dimensional feature. Any point in the projection plane is represented as d. (h,w) d is the specific value of the depth of the point on the projection plane; calculate d for any point. (h,w) The depth deviation tensor relative to the corresponding point on the ideal plane; S3. Perform color and geometric avoidance processing on the pre-projected image based on the deviation tensor, and then project the image based on the processed data. The color avoidance specifically refers to: A pixel in any frame of the pre-projected image is represented as [r′, g′, b′]. (h,w) r′ represents the specific value of the pixel in dimension R, g′ represents the specific value of the pixel in dimension G, and b′ represents the specific value of the pixel in dimension B. Iterate through all pixels in the pre-projected image and calculate the color deviation tensor ΔC(x,y) for any pixel, where x and y represent the coordinates of the pixel in the pre-projected image; Set the color channel threshold to ΔT. When |ΔC(x,y)|>ΔT, expand the rectangle in four directions (up, down, left, and right) starting from the pixel. Stop expanding when the color deviation tensor of the pixel is less than or equal to the color channel threshold. The resulting rectangle is the heterochromatic region, and heterochromatic regions are avoided. The geometric avoidance specifically refers to: Establish a spatial coordinate system, where any point is represented as (x, y, z). Set the projection plane as ax + by + cz + k = 0. Calculate the parameters a, b, c, and k using a fitting algorithm combined with a depth threshold. The depth of the projection plane can be obtained as d0 from the depth information. The projection area is calculated based on the projection plane and the corresponding depth information, and is represented as follows: Based on the above calculations, x and y are the boundary dimensions of the maximum projection region that satisfy the depth threshold.

2. The control method for the intelligent vehicle lighting system as described in claim 1, characterized in that, In S1, the frequency of collecting data on the vehicle's surrounding environment is adaptively adjusted using a cyclic decision detection algorithm.

Images