High-pixel imaging method and system for vehicle lamp light distribution system

Abstract

The invention provides a vehicle lamp light distribution system high-pixel imaging method and system, and relates to the technical field of vehicle driving, and the method comprises the steps: carrying out the imaging quality evaluation of an environment image based on extracted key visual features, and obtaining a visual quality score; if it is detected that the visual quality score is lower than a preset score threshold value, light and shadow brightness analysis is performed on the environment image, and environment brightness features are determined; matching a corresponding vehicle lamp illumination scheme from a cloud database according to the environment brightness characteristics; and adjusting a light source and a secondary optical element in the vehicle lighting system according to the vehicle lamp lighting scheme so as to optimize the quality of the environment picture captured by the visual probe. By implementing the method, the excellent imaging quality of the vehicle can be maintained under the complicated illumination condition, so that the accuracy of adjusting the parameters of the vehicle lamp group based on the environment image in the related technology is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle driving technology, and in particular to a high-pixel imaging method and system for a vehicle light distribution system. Background Art

[0002] In modern transportation, vehicle lighting systems can not only improve the safety of nighttime driving, but also improve the visibility and aesthetics of vehicles. With the development of technology, vehicle lighting systems have gradually evolved from simple lighting functions to intelligent systems that can adjust and optimize light output.

[0003] In the related technologies, most of the vehicle light distribution systems are based on visual probes to capture environmental images, and then analyze the characteristics of the environmental images to determine the adjustment parameters of the vehicle light group.

[0004] However, the dynamic adjustment of the vehicle lighting group by the related technology depends on the imaging quality of the visual probe. If the pixel of the environmental image captured by the visual probe is low, the blurred environmental image is difficult to accurately extract the brightness characteristics of the environment, resulting in inaccurate final adjustment parameters. Summary of the invention

[0005] The present application provides a high-pixel imaging method and system for a vehicle lamp light distribution system, which is used to solve the problem that the pixels of the environmental images captured by the visual probe are low, resulting in inaccurate adjustment parameters finally determined.

[0006] In a first aspect, the present application provides a high-pixel imaging method for a vehicle light distribution system, which is applied to the vehicle light distribution system. The method includes: capturing an image of the environment outside the vehicle by at least one visual probe mounted on the vehicle; Based on the extracted key visual features, the imaging quality of the environment image is evaluated to obtain a visual quality score; If it is detected that the visual quality score is lower than a preset score threshold, a light and shadow brightness analysis is performed on the environment image to determine the environment brightness characteristics, where the environment brightness characteristics include the light level, highlight area and shadow area of ​​the environment; According to the environmental brightness characteristics, the corresponding vehicle lighting solution is matched from the cloud database; The light source and secondary optical components in the vehicle lighting system are adjusted according to the vehicle lighting scheme to optimize the quality of the environment picture captured by the visual probe.

[0007] Through the above-mentioned embodiments, the headlight matching system captures the environmental image through the vehicle-mounted visual probe. When it is detected that the visual quality of the environmental image is low, the corresponding headlight lighting scheme is further matched from the cloud database through light and shadow brightness analysis to refine the current existing lighting scheme, so that the vehicle can maintain excellent imaging quality even under complex lighting conditions, thereby improving the accuracy of the vehicle light group adjustment parameters based on the environmental image in the related technology.

[0008] In some embodiments, the step of evaluating the imaging quality of the environment image based on the extracted key visual features to obtain a visual quality score specifically includes: Obtain historical environmental images captured by the vehicle-mounted visual probe under different environmental conditions; Score and annotate the image quality of the historical environmental images and construct a data set; Use this dataset to train and test the deep learning model to obtain a rating prediction model; The environment image is input into the score prediction model, and the visual quality score of the environment image is output.

[0009] Through the above-mentioned embodiments, the vehicle headlight distribution system constructs a data set of historical environmental images and uses a deep learning model to evaluate the visual quality of environmental images, so as to facilitate the subsequent intelligent adjustment of the existing lighting system according to the actual visual data of the vehicle, thereby ensuring the imaging quality of the environmental pictures captured by the visual probe.

[0010] In some embodiments, before the step of matching the corresponding vehicle light illumination scheme from the cloud database according to the ambient brightness feature, the step further includes: Constructing a first mapping relationship between light level and light source intensity; constructing a second mapping relationship between the shadow area and the secondary element adjustment parameter; A mapping relationship between the environment image and the vehicle light illumination scheme is determined according to the first mapping relationship and the second mapping relationship.

[0011] Through the above embodiments, the headlight distribution system constructs a mapping relationship between the light level and the light source intensity and between the shadow area and the adjustment parameter before matching the headlight lighting scheme, so that the headlight distribution system can construct a corresponding relationship between the environmental image and the headlight lighting scheme, and quickly determine the headlight lighting scheme corresponding to the current environmental image based on the corresponding relationship.

[0012] In some embodiments, after the step of matching the corresponding vehicle light illumination scheme from the cloud database according to the ambient brightness feature, the method further includes: Determine whether the vehicle lighting scheme conflicts with the current driver's active adjustment scheme; If yes, the LED light group is functionally split to obtain a first type of LED light group and a second type of LED light group, wherein the LED light group includes a plurality of LED lights; The first type LED light group and the second type LED light group are respectively controlled to execute the active adjustment scheme and the headlight illumination scheme; if not, the step of adjusting the light source and secondary optical elements in the vehicle lighting system according to the headlight illumination scheme is executed to optimize the quality of the environmental picture captured by the visual probe.

[0013] Through the above embodiments, the headlight distribution system can separate the LED light groups by function and independently control different types of LED light groups, so that it can meet the requirements of the active adjustment scheme and the headlight illumination scheme at the same time. This method can improve the imaging effect of the external environment while ensuring the driver's vehicle lighting needs.

[0014] In some embodiments, the steps of respectively controlling the first type LED light group and the second type LED light group to execute the active adjustment scheme and the vehicle light illumination scheme specifically include: Obtain the light source brightness and lighting direction corresponding to the active adjustment scheme; Adjusting the first type of LED light group to match the brightness and lighting direction of the light source; The second type of LED light group is controlled to execute the vehicle light illumination plan.

[0015] Through the above embodiments, the headlight distribution system accurately controls the brightness and lighting direction of each group of LED lights, ensuring that they can operate according to the established active adjustment plan and headlight lighting plan, thereby optimizing the lighting imaging effects in various driving environments.

[0016] In some embodiments, after the step of matching the corresponding vehicle light illumination scheme from the cloud database according to the ambient brightness feature, the method further includes: Determine the sight interference range according to the vehicle lighting scheme and the active adjustment scheme; Determine the target vehicle that enters the preset range based on the location information uploaded by other vehicles; A line of sight interference warning message is sent to the target vehicle based on the line of sight interference range.

[0017] Through the above embodiments, the headlight distribution system uses the headlight illumination scheme and the active adjustment scheme to determine the sight interference range, and sends sight interference warning information to the target vehicle entering the range. The active warning system assists the driver to deal with possible sight interference in advance, thereby reducing the probability of traffic accidents.

[0018] In some embodiments, after the step of evaluating the imaging quality of the environment image based on the extracted key visual features to obtain a visual quality score, the step further includes: If it is detected that the visual quality score is higher than or equal to a preset score threshold, the step of capturing an image of the environment outside the vehicle by using at least one visual probe installed on the vehicle is continued.

[0019] Through the above embodiment, when the vehicle light distribution system detects that the visual quality score of the ambient image is higher than or equal to the preset threshold, it continues to execute the ambient image capture operation, so that the vehicle lighting system can continue to monitor and adjust in real time, ensuring continuous optimization of light output under good visual quality.

[0020] In a second aspect, the present application provides a vehicle light distribution system, the vehicle light distribution system comprising: one or more processors and a memory; The memory is coupled to the one or more processors, and is used to store computer program code, which includes computer instructions. The one or more processors call the computer instructions so that the vehicle light distribution system can implement a high-pixel imaging method for a vehicle light distribution system provided in the above-mentioned embodiment, which will not be repeated here.

[0021] In a third aspect, the present application provides a computer-readable storage medium, including instructions. When the instructions are executed on a vehicle light distribution system, the vehicle light distribution system can implement a high-pixel imaging method for a vehicle light distribution system provided in the above-mentioned embodiment, which will not be repeated here.

[0022] In a fourth aspect, the present application provides a computer program product. When the computer program product runs on a vehicle light distribution system, the vehicle light distribution system can implement a high-pixel imaging method for a vehicle light distribution system provided in the above-mentioned embodiment, which will not be repeated here.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The headlight matching system captures the environment image through the vehicle-mounted visual probe, and when poor visual quality is detected, it uses the interaction between light and shadow brightness analysis and the cloud database to accurately match the corresponding headlight lighting scheme. This method not only optimizes the imaging quality under complex lighting conditions, but also improves the accuracy of the vehicle light group adjustment parameters. Through this technology, the system can dynamically adjust in a changing environment, thereby ensuring that the vehicle lighting system is always in the best configuration state, greatly improving driving safety and comfort at night or in bad weather.

[0024] 2. The headlight distribution system splits the LED light groups by function and independently controls different types of LED light groups, so that it can meet the requirements of the driver's active adjustment plan and the headlight lighting plan at the same time. This control strategy greatly increases the flexibility and personalized adjustment capabilities of the system, allowing the vehicle to automatically optimize the lighting effect to adapt to various driving environments while maintaining personalized settings.

[0025] 3. The headlight distribution system uses the headlight illumination scheme and active adjustment scheme to determine the range of visual interference, and sends visual interference warning information to the target vehicle entering the range. This mechanism not only improves driving predictability and reaction time, but also significantly reduces the risk of traffic accidents that may be caused by visual interference. Through this active warning system, the vehicle can interact more safely with the surrounding environment and other vehicles, enhancing overall driving safety, especially in high-speed or dense traffic conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a high-pixel imaging method for a vehicle light distribution system in an embodiment of the present application; Figure 2 is another flow chart of a high-pixel imaging method for a vehicle light distribution system in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of a vehicle light distribution system in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0029] For ease of understanding, the following is a flow chart of the method provided by this embodiment. Figure 1 The figure is a flow chart of a high-pixel imaging method for a vehicle light distribution system in an embodiment of the present application.

[0030] S101 . Capture an environment image outside a vehicle by using at least one visual probe installed on the vehicle.

[0031] The headlight distribution system collects real-time environmental image information around the vehicle through one or more visual probes installed on the outside of the vehicle. These visual probes are usually placed on the front, rear, side and top of the vehicle body to cover the 360-degree field of view of the vehicle as comprehensively as possible. Among them, the visual probe can be an ordinary visible light camera, or a special-purpose imaging device such as an infrared thermal imager or a night vision enhanced camera. The headlight distribution system continuously obtains real-time image data of the vehicle's external environment through these visual probes, providing raw input for subsequent image analysis and lighting optimization.

[0032] S102: Evaluate the imaging quality of the environment image based on the extracted key visual features to obtain a visual quality score.

[0033] After obtaining the environmental image, the headlight matching system will evaluate the imaging quality of the environmental image. Specifically, the headlight matching system extracts a series of key visual features from the environmental image, including but not limited to objective indicators such as image clarity, contrast, brightness distribution, and color reproduction, and then calculates a score value reflecting the overall imaging quality based on the objective indicators. Optionally, some specific evaluation criteria can also be designed in combination with the application scenario. For example, when driving at night, the distinguishability of object outlines in darker areas can serve as an important reference. The system uses image processing algorithms to quantitatively calculate these feature indicators from the pixel data of the environmental image, and then compares them with the ideal values, and finally derives a visual quality score Q on a percentage basis.

[0034] In specific implementation, the key feature indicators can be regarded as multiple scoring factors. After scoring each factor separately, a weight coefficient is assigned, and finally the total visual quality score Q is synthesized by weighted average. For example, in a specific embodiment, the four indicators of clarity, contrast, brightness, and color are marked as q1, q2, q3, and q4, and the corresponding weight coefficients are w1, w2, w3, and w4, then the visual quality score can be expressed as: Q=w1q1+w2q2+w3q3+w4q4, where the weight coefficient satisfies the normalization condition: w1+w2+w3+w4=1.

[0035] S103: Whether the visual quality score is lower than a preset score threshold.

[0036] After making a visual quality score for the environment image, the headlight distribution system determines whether the current image meets the imaging quality requirements. Specifically, the visual quality score Q is compared with a preset threshold score Q0. If Q is lower than Q0, the current image quality is determined to be poor, and subsequent image analysis steps such as S104 are executed; otherwise, if Q is not lower than Q0, the current image quality is determined to be good enough, and the subsequent processing steps can be skipped, and the process jumps to step S101 to recapture the environment image.

[0037] S104: Perform light and shadow brightness analysis on the environment image to determine the environment brightness characteristics.

[0038] For environmental images with visual quality scores below the threshold, the headlight distribution system performs light and shadow brightness analysis and extracts a series of brightness features that quantitatively describe the lighting conditions from the environmental images, thereby characterizing the light and dark distribution law of the visual environment (i.e., environmental brightness characteristics).

[0039] Optionally, the headlight distribution system converts the RGB color space of the ambient image into the YUV brightness-chromaticity space, extracts its brightness component (Y channel), and draws a histogram of the frequency distribution of the pixel grayscale value. The horizontal axis of the histogram is the grayscale level of 0-255, and the vertical axis is the number of pixels of the grayscale value. This can directly determine the exposure condition of the image: if the histogram is concentrated in the low grayscale segment, it means that the image is dark as a whole, and if it is concentrated in the high grayscale segment, it means that the image is too bright. The histogram's mean, standard deviation, skewness and other statistics can also be further calculated to obtain brightness feature indicators such as average brightness, contrast, and brightness bias.

[0040] Taking shadow area detection as an example, the headlight distribution system can divide the environmental image into blocks and compare the average or median brightness of the pixels in each block. If the brightness of a block is significantly lower than the global average, the area can be preliminarily determined to be a shadow. On this basis, the geometric and topological properties of the shadow area, such as shape, area, and grayscale gradient, can also be analyzed to obtain high-level brightness features of the image's light and dark distribution.

[0041] S105: Match a corresponding vehicle light illumination scheme from a cloud database according to the ambient brightness characteristics.

[0042] After obtaining the brightness characteristics of the environment, the headlight distribution system will search for the best headlight lighting scheme based on it. Among them, the lighting scheme is a combination of parameters such as the headlight distribution mode, lighting intensity, irradiation direction, light color temperature, etc., which represents a specific working state of the headlight.

[0043] In specific implementation, a rule-based mode can be used to match the corresponding headlight illumination scheme from the cloud database, or a learning-based mode can be used to match the corresponding headlight illumination scheme from the cloud database. Among them, in the rule-based mode, the system pre-abstracts the correspondence between the environmental conditions and the illumination parameters summarized by experience into a series of IF-THEN judgment rules. When a set of environmental brightness features is obtained, the system performs pattern matching through the judgment rules to find one or more illumination schemes that meet the feature combination.

[0044] For example, if the image analysis yields a feature combination of "low average brightness and high shadow proportion", the system searches in the rule library for "IF average brightness < L1 AND shadow proportion > S1 THEN lighting scheme P1", where L1 and S1 are set thresholds. In this way, a series of rules are activated through the feature combination, and finally, the P1 scheme that meets all rule conditions and has the highest matching degree is selected.

[0045] Another learning-based mode is to use machine learning to establish a mapping from brightness features to lighting parameters. Specifically, environmental images of vehicle lights in multiple scenarios are collected as training samples, and each sample is labeled with an optimal lighting parameter combination. Then the system extracts the brightness feature vectors from the sample images and forms a supervised learning data pair together with the labeled parameter values. Next, a suitable machine learning algorithm (such as a regression model, reinforcement learning, etc.) is selected to train on the dataset to learn the mapping relationship between the input features and the output parameters.

[0046] S106. Adjust the light source and secondary optical components in the vehicle lighting system according to the vehicle lighting scheme to optimize the quality of the environmental pictures captured by the vision probe.

[0047] After determining the appropriate vehicle lighting scheme, the headlight distribution system further controls the vehicle lighting system to execute the requirements of the scheme and adjusts the physical parameters of the light source and optical components, thereby actually optimizing the imaging quality.

[0048] For example, the light source parameters can be adjusted by controlling the brightness and light color. For solid-state light sources such as LEDs, the system can directly adjust the drive current to control the luminous intensity of a single or a group of LED lights, realizing continuously adjustable brightness.

[0049] For another example, the lighting direction of the vehicle lights can be adjusted by changing parameters such as the position or rotation direction of secondary optical components such as lenses, reflectors, and light shields, which is not limited here.

[0050] In the above embodiment, the headlight distribution system captures the environmental image through the in-vehicle vision probe. When it detects that the visual quality of the environmental image is low, it further refines and adjusts the current existing lighting scheme by matching the corresponding vehicle lighting scheme from the cloud database through light and shadow brightness analysis, so that the vehicle can maintain excellent imaging quality under complex lighting conditions, thereby improving the accuracy of the vehicle lamp group adjustment parameters based on the environmental image in the related technology.

[0051] The following provides a further and more specific process description of the method provided in this embodiment. Specifically, as Figure 2 shown, it is another process schematic diagram of a high-pixel imaging method for a headlight distribution system in an embodiment of the present application.

[0052] S201, obtaining historical environmental images captured by the vehicle-mounted visual probe under different environmental conditions.

[0053] The headlight distribution system retrieves a large number of historical environmental images collected at different times, locations, and weather conditions from the storage database of the on-board visual probe. These image data are usually classified and stored according to the collection time and scene type to facilitate subsequent retrieval and use. For example, images of daytime, dusk, and night can be classified separately, or they can be distinguished according to weather conditions such as sunny days, rainy days, and foggy days, etc., which are not limited here.

[0054] S202: Score and annotate the image quality of the historical environmental images, build a data set to train a deep learning model, and obtain a score prediction model.

[0055] After obtaining a large number of historical environmental images collected in different scenarios, the headlight distribution system quantitatively evaluates and annotates the visual quality of these images. Usually, professional image quality assessors give a numerical score to the imaging effect of each image, and the higher the score, the better the image quality. This process can combine the subjective feelings of manual judgment with objective quantitative indicators with the help of some commonly used image quality assessment indicators, such as peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). At the same time, in order to improve the consistency and reliability of the scoring and annotation, multiple assessors can be selected to independently score the same image, and the average value is taken as the final quality score of the image.

[0056] Through the above method, the headlight matching system can match a score label reflecting its visual quality for each historical environmental image. These image datasets with quality labels can be directly used for supervised machine learning model training. The system uses a part of the dataset samples to train machine learning models such as deep neural networks, and uses another part of the samples to verify and test the training results, and finally obtains a reliable score prediction model. The model can learn various quality-related features of environmental images and grasp the intrinsic relationship between features and scores. This enables the headlight matching system to quickly make quality assessments on newly collected environmental images without manual labeling.

[0057] S203: Input the environment image into a rating prediction model, and output the visual quality rating of the environment image.

[0058] Specifically, the vehicle headlight distribution system inputs the image data into the rating prediction model trained in step S202. After forward propagation calculation, the model outputs a rating value between 0 and 10, representing the comprehensive visual quality level of the image.

[0059] In the above embodiment, the vehicle headlight distribution system constructs a data set of historical environmental images and uses a deep learning model to evaluate the visual quality of environmental images, so as to facilitate the subsequent intelligent adjustment of the existing lighting system according to the actual visual data of the vehicle, thereby ensuring the imaging quality of the environmental pictures captured by the visual probe.

[0060] S204: If it is detected that the visual quality score is lower than a preset score threshold, a light and shadow brightness analysis is performed on the environment image to determine the environment brightness characteristics.

[0061] This step is the same as step S104 and will not be repeated here.

[0062] S205: construct a first mapping relationship between the illumination level and the light source intensity, and a second mapping relationship between the shadow area and the secondary element adjustment parameter.

[0063] After obtaining the brightness characteristics of the ambient light, the headlight light distribution system needs to establish a mapping relationship between the brightness characteristics and the optimized control parameters, so as to achieve closed-loop control from visual perception to light distribution adjustment. Specifically, the system constructs two mapping relationships: one is to map the overall light level of the environment to the luminous intensity of the headlight light source; the other is to map the shadow area detected in the image to the adjustment parameters of the secondary optical elements of the headlight.

[0064] For the first mapping relationship, the system uses the average brightness value of the image as a representative indicator of the ambient light level, and fits the functional relationship between the average brightness and the light source intensity through a large amount of experimental data during the design phase. The function curve can be in the form of piecewise linear or high-order polynomial, with the average brightness as the independent variable and the light intensity as the dependent variable. For example, when the average brightness of the image is lower than 0.3, the light intensity increases rapidly with a large slope; when the average brightness is higher than 0.6, the light intensity slowly saturates and gradually stabilizes. In this way, the system can dynamically adjust the light source power according to the real-time brightness of the image, increase the lighting intensity when the brightness is insufficient, and appropriately reduce the luminous flux when the brightness is too high, so as to always maintain the ambient light at the optimal level.

[0065] For the second mapping relationship, the system analyzes the geometric features of the shadow area detected in the image, such as the position, size, shape, etc., and determines how to adjust the secondary optical elements of the headlights, such as reflectors, lenses, and sunshades. The shadow area of ​​the imaging surface receives more light while minimizing the impact on other areas. Optionally, a morphological analysis is performed on the shadow area mask of the image to extract the spatial distribution characteristics of the shadow: such as the angle, eccentricity, and irregularity of the shadow area. Based on the shadow morphological characteristics, the best matching light distribution curve is found in the preset parameter space, such as changing the beam deflection angle by rotating the reflector, and changing the spot position by moving the lens. The mapping relationship between the shadow features and the parameter curve is stored in the form of a lookup table or regression model, which can achieve fast matching from shadow analysis to light distribution optimization.

[0066] S206: Determine a mapping relationship between the environment image and the vehicle light illumination scheme according to the first mapping relationship and the second mapping relationship.

[0067] After the headlight distribution system constructs two mappings between brightness characteristics and control parameters, the two mapping relationships are combined to establish an end-to-end mapping relationship between the environmental image and the headlight lighting scheme.

[0068] In the above embodiment, before matching the headlight lighting scheme, the headlight distribution system constructs a mapping relationship between the lighting level and the light source intensity and between the shadow area and the adjustment parameter, so that the headlight distribution system can construct a corresponding relationship between the ambient image and the headlight lighting scheme, and quickly determine the headlight lighting scheme corresponding to the current ambient image based on the corresponding relationship.

[0069] S207: Match a corresponding vehicle light illumination scheme from a cloud database according to the ambient brightness characteristics.

[0070] This step is the same as step S105 and will not be repeated here.

[0071] S208: Determine whether the vehicle light illumination plan conflicts with the current driver's active adjustment plan.

[0072] The headlight distribution system detects whether the optimal headlight illumination scheme based on environmental analysis (environmental image) conflicts with the active adjustment scheme currently set by the driver. Specifically, the system obtains the personalized lighting preferences set by the driver through the vehicle control interface or physical buttons, or the lighting adjustment parameters directly and actively set by the current user, such as beam height, focus distance, light color temperature and other parameters. Then, these active adjustment parameters are compared item by item with the lighting scheme of the environmental response, and the difference between the two sets of parameters is calculated.

[0073] Optionally, the system designs a multi-dimensional parameter space, where each dimension represents an adjustable lighting parameter. In this space, the active adjustment scheme and the optimized lighting scheme each form a feature point, and the spatial distance between the two points can quantify the degree of difference between the schemes. If the distance exceeds a certain threshold, it is determined that the two schemes conflict; conversely, if the distance does not exceed the threshold, it is considered that the difference is acceptable and the two schemes do not conflict.

[0074] S209, performing functional separation on the LED light groups to obtain first-category LED light groups and second-category LED light groups.

[0075] When the headlight distribution system detects that there is a large difference (conflict) between the headlight optimization solution and the driver's active setting, directly adopting the system solution may lead to a degraded driving experience and even affect the driver's normal driving. At this time, the LED light source array of the headlight can be appropriately divided in space, with some LED light groups defined as the first category, specifically responding to the driver's adjustment, and the other part defined as the second category, and the system automatically optimizes its lighting parameters based on the environmental analysis results.

[0076] In specific implementation, the system can cluster the LED array according to different optical indicators. For example, the illumination angle is selected as the first clustering criterion and the color temperature is selected as the second criterion. LEDs with smaller luminous angles (such as within ±5°) are divided into one category as high-beam groups, which are responsible for realizing road lighting at a longer distance to meet the driver's needs for observing the road conditions ahead. LEDs with larger luminous angles are used as another type of low-beam groups to provide soft, wide-angle floodlighting at close range to highlight pedestrians and objects on the roadside. When clustering by color temperature, warm white light LEDs with a color temperature lower than 4500K can be selected as one category to create a comfortable and cozy night atmosphere; and pure white light or cold white light LEDs with a color temperature higher than 4500K can be selected as another category to provide clear and sharp imaging effects and improve visibility in harsh conditions such as foggy days.

[0077] S210, adjusting the first type of LED light group according to the light source brightness and lighting direction corresponding to the active adjustment scheme, and controlling the second type of LED light group to execute the headlight illumination scheme.

[0078] After completing the LED functional zoning, the headlight distribution system actually controls two types of light groups to execute active solutions and adaptive optimization solutions respectively. Among them, the first type of LED directly adopts the lighting parameters set by the driver, including light intensity, light distribution angle, color temperature, etc., to maintain the manually controlled light type output. The second type of LED automatically adjusts its working parameters based on the results of environmental analysis, and provides necessary lighting compensation for complex road conditions without interfering with the subjective lighting area. The two sets of light types complement each other in space, jointly creating a personalized and intelligent headlight performance.

[0079] In the above embodiment, the headlight light distribution system can independently control different types of LED light groups by functional separation, so that it can meet the requirements of both the active adjustment scheme and the headlight illumination scheme. This method can improve the imaging effect of the external environment while ensuring the driver's vehicle lighting needs.

[0080] S211. Adjust the light source and secondary optical components in the vehicle lighting system according to the vehicle lighting plan to optimize the quality of the environment picture captured by the visual probe.

[0081] This step is the same as step S106 and will not be repeated here.

[0082] S212. Determine a visual interference range based on the vehicle lighting plan and the active adjustment plan.

[0083] The headlight distribution system builds a three-dimensional model of headlight illumination based on the optimized comprehensive headlight distribution plan, simulates and analyzes the propagation path and intensity distribution of the headlight beam in space, and thus predicts the area where other vehicle drivers may be disturbed by glare, that is, the visual interference range.

[0084] Specifically, the headlight distribution system constructs a detailed optical model of the headlight in the computer according to the various lighting parameters specified in the headlight lighting scheme and the active adjustment scheme, such as the geometric structure of the lamp, the surface parameters of the reflector, the refractive index of the lens, the position of the filament, etc. Then, the system uses numerical simulation methods such as ray tracing to calculate the propagation trajectory and radiation intensity changes of the light emitted by the simulated headlight in three-dimensional space. Through the tracing calculation of a large number of rays, the light intensity distribution map of the headlight illumination on the road ahead is obtained. The headlight distribution system compares the light intensity distribution map with the visual comfort threshold of the human eye to determine the road area where the light intensity exceeds the visual comfort threshold. These areas are then mapped to actual three-dimensional areas in the spatial coordinate system to form a spatial model of the line of sight interference range (i.e., line of sight interference range).

[0085] S213. Determine the target vehicle that enters the preset range based on the location information uploaded by other vehicles.

[0086] After obtaining the spatial model of the vehicle's visual interference range, the headlight distribution system further obtains the real-time position data of surrounding vehicles to determine which vehicles are in or about to enter the visual interference area, thereby identifying potential glare interference targets. By actively analyzing and predicting visual interference objects, the system can send interference warnings to target vehicles in advance to reduce the risk of traffic accidents.

[0087] S214. Sending line of sight interference warning information to the target vehicle according to the line of sight interference range.

[0088] After identifying potential sight interference target vehicles, the headlight distribution system further sends warning information to these target vehicles, prompting their drivers to take measures to avoid or alleviate the impact of glare. The sending of warning information can be achieved through the Internet of Vehicles platform, packaging the current vehicle's predicted sight interference level, duration and other parameters into a standard data frame format and sending it to the target vehicle through a wireless communication network. After receiving the data frame, the on-board system of the target vehicle decodes it and warns the driver through various forms of human-computer interaction interfaces such as instrument panel display, HUD head-up display, and voice broadcast.

[0089] In the above embodiment, the headlight distribution system uses the headlight illumination scheme and the active adjustment scheme to determine the sight interference range, and sends sight interference warning information to the target vehicle entering the range. The active warning system assists the driver to deal with possible sight interference in advance, thereby reducing the probability of traffic accidents.

[0090] The vehicle light distribution system of the embodiment of the present invention is an electronic device. Figure 3 A schematic diagram of the architecture of an electronic device suitable for implementing an embodiment of the present invention is shown.

[0091] It should be noted that Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0092] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructions (computer programs), or by controlling related hardware through instructions (computer programs), and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor, wherein a plurality of instructions are stored in the storage medium, and the instructions can be loaded by the processor to execute any step of the method provided in the embodiment of the present invention.

[0093] Specifically, the storage medium and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more signal lines. The storage medium stores computer execution instructions for implementing the data access control method, including at least one software function module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software program and module stored in the storage medium. The storage medium can be, but is not limited to, random access storage medium (Random Access Memory, referred to as: RAM), read-only storage medium (Read Only Memory, referred to as: ROM), programmable read-only storage medium (Programmable Read-Only Memory, referred to as: PROM), erasable read-only storage medium (Erasable Programmable Read-Only Memory, referred to as: EPROM), electrically erasable read-only storage medium (Electric Erasable Programmable Read-Only Memory, referred to as: EEPROM), etc. Among them, the storage medium is used to store programs, and the processor executes the program after receiving the execution instruction.

[0094] Furthermore, the software programs and modules in the above-mentioned storage medium may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components. The processor may be an integrated circuit chip having signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., which may implement or execute the various methods, steps, and logic flow diagrams disclosed in this embodiment. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0095] Since the instructions stored in the storage medium can execute the steps in any method provided in the embodiments of the present invention, the beneficial effects of any method provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0096] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A high-pixel imaging method for a vehicle light distribution system, applied to a vehicle light distribution system, characterized in that: The method comprises: capturing an image of the environment outside the vehicle by at least one visual probe mounted on the vehicle; Performing imaging quality assessment on the environment image based on the extracted key visual features to obtain a visual quality score; If it is detected that the visual quality score is lower than a preset score threshold, light and shadow brightness analysis is performed on the environment image to determine the environment brightness characteristics, where the environment brightness characteristics include the light level, highlight area and shadow area of ​​the environment; Matching a corresponding vehicle lighting solution from a cloud database according to the ambient brightness characteristics; The light source and secondary optical components in the vehicle lighting system are adjusted according to the vehicle lighting scheme to optimize the quality of the environment picture captured by the visual probe.

2. The method according to claim 1, characterized in that: The step of performing imaging quality assessment on the environment image based on the extracted key visual features to obtain a visual quality score specifically includes: Obtain historical environmental images captured by the vehicle-mounted visual probe under different environmental conditions; Scoring and annotating the image quality of the historical environmental images to construct a data set; Use the data set to train and test a deep learning model to obtain a rating prediction model; The environment image is input into the score prediction model, and the visual quality score of the environment image is output.

3. The method according to claim 1, characterized in that Before the step of matching the corresponding vehicle light illumination scheme from the cloud database according to the ambient brightness feature, the method further includes: Constructing a first mapping relationship between light level and light source intensity; constructing a second mapping relationship between the shadow area and the secondary element adjustment parameter; A mapping relationship between an environment image and a vehicle light illumination scheme is determined according to the first mapping relationship and the second mapping relationship.

4. The method according to claim 1, characterized in that: After the step of matching the corresponding vehicle light illumination scheme from the cloud database according to the ambient brightness feature, the method further includes: Determining whether the vehicle light illumination scheme conflicts with the current driver's active adjustment scheme; If yes, the LED light groups are functionally split to obtain a first type of LED light group and a second type of LED light group, wherein the LED light group includes a plurality of LED lights; Respectively controlling the first type of LED light group and the second type of LED light group to execute the active adjustment scheme and the headlight illumination scheme; If not, the step of adjusting the light source and secondary optical components in the vehicle lighting system according to the vehicle light illumination scheme to optimize the quality of the environment picture captured by the visual probe is performed.

5. The method according to claim 4, characterized in that The step of respectively controlling the first type LED light group and the second type LED light group to execute the active adjustment scheme and the vehicle light illumination scheme specifically includes: Obtaining the light source brightness and lighting direction corresponding to the active adjustment scheme; Adjusting the first type of LED light group to match the brightness and lighting direction of the light source; The second type of LED light group is controlled to execute the vehicle light illumination scheme.

6. The method according to claim 1, characterized in that After the step of matching the corresponding vehicle light illumination scheme from the cloud database according to the ambient brightness feature, the method further includes: Determining a sight interference range according to the vehicle light illumination scheme and the active adjustment scheme; Determine the target vehicle that enters the preset range based on the location information uploaded by other vehicles; Sending line of sight interference warning information to the target vehicle according to the line of sight interference range.

7. The method according to claim 1, characterized in that After the step of evaluating the imaging quality of the environment image based on the extracted key visual features to obtain a visual quality score, the method further includes: If it is detected that the visual quality score is higher than or equal to a preset score threshold, the step of capturing an image of the environment outside the vehicle by using at least one visual probe installed on the vehicle is continued.

8. A vehicle light distribution system, characterized in that: The vehicle light distribution system includes: one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the vehicle light distribution system to execute the method according to any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a vehicle lighting distribution system, the vehicle lighting distribution system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on a vehicle light distribution system, the vehicle light distribution system is enabled to execute the method according to any one of claims 1 to 7.

Images