A vehicle lamp and intelligent control system

Abstract

This invention relates to the field of image processing technology, specifically to a vehicle lighting and intelligent control system, comprising the following steps: an environmental perception module that collects images of the surrounding environment through an onboard camera, performs resolution optimization processing on the images, and generates an optimized image; based on the optimized image, deep learning analysis is used to identify target environmental signs, including tunnels and school areas, and generate environmental sign recognition results. In this invention, in addition to adjusting the vehicle lights, the lighting mode is further fine-tuned in conjunction with real-time vehicle speed and weather changes to improve the matching degree between lighting and real-time driving needs, ensuring optimal lighting effects in different driving environments; by real-time monitoring of the light adjustment effect and driver feedback, lighting performance data is collected in a timely manner, and the intelligent vehicle lighting control system achieves dynamic adaptive adjustment through continuous feedback optimization, continuously improving the stability and safety of lighting performance.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and more particularly to a vehicle lighting and intelligent control system. Background Technology

[0002] Image processing technology refers to the techniques used by computers to analyze, enhance, recognize, and understand acquired image information. It mainly involves steps such as image acquisition, preprocessing, feature extraction, pattern recognition, target detection, and classification. Current technologies lack effective integration of real-time dynamic factors such as vehicle speed and weather conditions, making it difficult to fine-tune vehicle headlight illumination modes in real time. This results in the actual lighting effect failing to consistently meet the needs of drivers and changing environments. Therefore, improvements are needed. Summary of the Invention

[0003] The purpose of this invention is to address the shortcomings of existing technologies by proposing a vehicle lighting and intelligent control system.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent control system, comprising the following steps:

[0005] The environmental perception module collects images of the surrounding environment through an on-board camera, performs resolution optimization processing on the images, and generates optimized images. Based on the optimized images, deep learning analysis is used to identify target environmental signs, including tunnels and school areas, and generate environmental sign recognition results.

[0006] The light adjustment module adjusts the brightness of the vehicle lights based on the environmental sign recognition results, calculates the required light parameters, and generates preliminary light adjustment parameters; based on the preliminary light adjustment parameters, it further optimizes the light projection angle according to road conditions to generate final light adjustment parameters.

[0007] The lighting mode selection module adjusts the final parameters based on the light, and fine-tunes the lighting mode by combining the current vehicle speed and weather conditions, generating an optimized lighting mode result;

[0008] The feedback optimization module utilizes the lighting mode optimization results to monitor the lighting effect and driver feedback in real time, collects lighting performance data, and generates lighting performance feedback data.

[0009] Preferably, the step of obtaining the optimized image is as follows:

[0010] The vehicle-mounted camera is activated, capturing a continuous sequence of images of the surrounding environment. Color balance and brightness are then adjusted to obtain the processed environmental image.

[0011] Based on the processed environmental image, a high-pass filter is applied to remove noise from the image, and edge detection is used to enhance the object edges in the image to obtain a resolution-optimized environmental image.

[0012] Based on the resolution-optimized environmental image, the features in the image are refined through image sharpening to generate an optimized image.

[0013] Preferably, the steps for obtaining the environmental sign recognition result are as follows:

[0014] Based on the optimized image, image features are extracted, and road, building and traffic signs are separated from the background area by image segmentation to obtain environmental sign candidate areas;

[0015] Based on the candidate regions of environmental signs, a deep learning model is applied for classification, the input feature vector is used for target matching, the matching degree is calculated and environmental signs are filtered to generate environmental sign classification results.

[0016] Based on the environmental sign classification results, a confidence assessment is performed to eliminate misidentified targets, determine the location and category of the target environmental sign, and generate environmental sign recognition results.

[0017] Preferably, the step of obtaining the preliminary light adjustment parameters is as follows:

[0018] Based on the environmental sign recognition results, the relationship between the recognized environmental sign type and the vehicle's current position is determined, the real-time distance between the vehicle and the environmental sign is calculated, and the light adjustment requirement data is obtained.

[0019] Based on the light adjustment requirement data, the required headlight brightness adjustment is calculated using the following formula:

[0020]

[0021] in, This represents the required headlight brightness adjustment. This represents the highest setting value for the headlight brightness. The minimum setting value representing the brightness of the headlights. This represents the real-time measured distance between the vehicle and the environmental sign. Represents a safe reference distance. This represents the height difference between the road where the vehicle is currently traveling and the environmental sign. This represents the initial angle of the headlight beam.

[0022] Based on the required headlight brightness adjustment, the headlight brightness is adjusted synchronously in real time to obtain preliminary light adjustment parameters.

[0023] Preferably, the step of obtaining the final parameters for light adjustment is as follows:

[0024] Based on the preliminary light adjustment parameters, the light reflectivity of the road surface is detected, the light reflection characteristics are analyzed, the initial scattering range of the light projection is calculated, and the light projection adjustment data is obtained.

[0025] Based on the light projection adjustment data, the optimized light projection angle is calculated using the following formula:

[0026]

[0027] in, This represents the optimized light projection angle. This represents the height of the headlights relative to the road. Represents the height of the target area. This represents the horizontal distance between the vehicle and the target area. Represents the light reflectivity of the road surface. Represents standard light reflectance;

[0028] Based on the optimized light projection angle, the angle of the headlight beam is adjusted to generate the final light adjustment parameters.

[0029] Preferably, the step of obtaining the lighting mode optimization result is as follows:

[0030] Based on the final parameters of the light adjustment, the real-time speed information of the current vehicle is obtained, the road visibility and the surrounding ambient light are detected, and the lighting mode adjustment data is obtained.

[0031] Based on the lighting mode adjustment data, the lighting mode optimization index is calculated using the following formula:

[0032]

[0033] in, Represents the lighting mode optimization index, This represents the vehicle's current speed. Represents the influence factor of light. This represents the light intensity detected in the current environment. Represents the ambient light intensity around the vehicle. This represents the detection distance between the vehicle and the obstacle in front.

[0034] Based on the lighting mode optimization index, a headlight adjustment strategy is selected to obtain the lighting mode optimization result.

[0035] Preferably, the steps for obtaining the lighting performance feedback data are as follows:

[0036] Based on the lighting mode optimization results, the brightness distribution of the current vehicle headlight illumination area is obtained, and combined with the road reflection data obtained by the front camera of the vehicle, lighting monitoring data is obtained.

[0037] Based on the lighting monitoring data, the lighting performance evaluation value is calculated using the following formula:

[0038]

[0039] in, Represents the evaluation value of lighting performance. This represents the average brightness of the area illuminated by the headlights. Represents the reflectance of the road surface. Represents the background brightness from the driver's perspective. Represents the monitoring time interval. This represents the driver's average driving speed during the monitoring period. This represents the recommended driving speed under current conditions;

[0040] Based on the lighting performance evaluation values, the deviation between the driver's manual adjustment behavior and the system adjustment is analyzed, effective lighting adjustment trends are extracted, and lighting performance feedback data is generated.

[0041] The present invention also provides a vehicle light, applicable to the intelligent control system of any of the above claims, comprising: a heat dissipation lamp housing with a vent on its outer wall, a heat dissipation fan corresponding to the vent installed inside the heat dissipation lamp housing, a conductive component for power supply being snapped onto one end of the heat dissipation lamp housing, a copper substrate being provided inside the heat dissipation lamp housing, LED light source chips being provided on both sides of the copper substrate, a connection terminal for electrical connection of two LED light source chips being provided at one end of the copper substrate, a bifurcated portion adapted to the heat dissipation fan being provided at the other end of the copper substrate, an electronic control chip being provided on one side of the copper substrate, heat conduction pipes being provided on both sides of the outer side of the copper substrate, and the heat dissipation fan being located between the electronic control chip and the conductive component;

[0042] The heat dissipation lamp housing has a cavity inside for accommodating the cooling fan and conductive components, and an opening on the outside of the heat dissipation lamp housing corresponding to the light-emitting surface of the LED light source chip is located on the outside near the ventilation port.

[0043] Furthermore, the conductive component includes a conductive plug and a rectifier board. The rectifier board has slots a for soldering the pins of the conductive plug and slots b for soldering the bifurcation of the copper substrate, respectively, around its perimeter.

[0044] Furthermore, the other end of the heat dissipation lamp housing is provided with a heat dissipation hole for one end of the heat conduction pipe to extend out, and the other ends of the two heat conduction pipes are aligned with the bifurcation of the copper substrate.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0046] In this invention, deep learning is used to accurately identify target environmental signs, automatically calculate the required light parameters, and finely adjust the brightness and illumination angle of the headlights. This ensures that the output light from the headlights precisely matches the actual road conditions, solving the problem of blurred vision caused by excessively high or low light intensity and guaranteeing a clear and comfortable driving view. Based on the headlight adjustment, the lighting mode is further fine-tuned in conjunction with real-time vehicle speed and weather changes to improve the fit between lighting and real-time driving needs, ensuring optimal lighting effects in different driving environments. By monitoring the light adjustment effect and driver feedback in real time, lighting performance data is collected in a timely manner, and the intelligent headlight control system achieves dynamic adaptive adjustment through continuous feedback optimization, continuously improving the stability and safety of lighting performance. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the steps of the present invention;

[0048] Figure 2 This is a schematic diagram of the overall external structure of the vehicle headlights in this invention;

[0049] Figure 3 This is a schematic diagram of the overall exploded structure of the vehicle headlight in this invention;

[0050] Figure 4 This is a schematic diagram of the overall external structure of the vehicle headlights in this invention from another perspective.

[0051] Figure 5 In this invention Figure 3 A magnified structural diagram at point A.

[0052] Figure label:

[0053] 1. Heat dissipation lamp housing; 10. Ventilation opening; 11. Cooling fan; 12. Opening; 13. Heat dissipation round hole; 2. Conductive component; 21. Conductive plug; 22. Rectifier board; 221. Slot a; 222. Slot b; 3. Copper substrate; 30. LED light source chip; 301. Connecting terminal; 31. Electronic control chip; 4. Heat conduction pipe. Detailed Implementation

[0054] 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 embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0055] Please see Figure 1 This invention provides a technical solution, an intelligent control system, comprising the following steps:

[0056] The environmental perception module collects images of the surrounding environment through the vehicle-mounted camera, optimizes the resolution of the images, and generates optimized images. Based on the optimized images, deep learning is used to analyze and identify target environmental signs, including tunnels and school areas, and generate environmental sign recognition results.

[0057] The light adjustment module adjusts the brightness of the headlights based on the environmental sign recognition results, calculates the required light parameters, and generates preliminary light adjustment parameters. Based on the preliminary light adjustment parameters, it further optimizes the light projection angle according to road conditions to generate the final light adjustment parameters.

[0058] The lighting mode selection module adjusts the final parameters based on the light, and fine-tunes the lighting mode by taking into account the current vehicle speed and weather conditions, generating an optimized lighting mode result;

[0059] The feedback optimization module utilizes the lighting mode optimization results to monitor the lighting effect and driver feedback in real time, collects lighting performance data, and generates lighting performance feedback data.

[0060] The steps for obtaining the optimized image are as follows:

[0061] The vehicle-mounted camera is activated, capturing a continuous sequence of images of the surrounding environment. Color balance and brightness are then adjusted to obtain the processed environmental image.

[0062] Based on the processed environmental image, a high-pass filter is applied to remove noise from the image, and edge detection is used to enhance the object edges in the image, resulting in a resolution-optimized environmental image.

[0063] Based on the resolution-optimized environmental image, the features in the image are refined through image sharpening to generate an optimized image.

[0064] Specifically, based on the acquired continuous image sequence, the color distribution of each frame is first read, and the red, green, and blue channel values ​​of each pixel are statistically analyzed one by one. If the statistical result is outside the range of 0 to 255, it is considered an outlier and discarded, thus forming preliminary pixel color data. Subsequently, based on this pixel color data, the average and variance of each channel are calculated, referring to the standard color balance range set with previous experience. For example, the balance range of the red channel is set at... to Between these points, the balance range of the green channel is set at... to Between, the balance range of the blue channel is set at to Between these points, the difference between the current pixel distribution and this balanced range is used to determine whether to perform channel enhancement or attenuation, further adjusting the overall brightness, and establishing a brightness reference value, for example... Calculate the average brightness of each frame. and If you do something wrong, Greater than the empirically set deviation threshold Then, the brightness of the entire frame is linearly corrected, for example, by letting... Then subtract the brightness value of each pixel. To achieve balanced processing, targeted restrictions and truncation are applied to extremely bright or dark areas. If some pixel values ​​still exceed the allowable range after correction, these pixel values ​​are directly cropped to 0 or 255. Finally, all frames are compared again to confirm that the aforementioned color balance and brightness range are met, thus obtaining the processed environmental image.

[0065] Based on the processed environmental image, a preliminary scan of the entire image is performed to record the distribution location of noise. To determine the noise threshold, several random regions can be selected in the entire image and the grayscale variance can be measured. If the measured variance is higher than the upper limit set by previous manual experience, the noise threshold will be determined. If the noise is significant, it can be determined that the region contains obvious noise. Then, a high-pass filter is used to remove the noise in these regions. When selecting the high-pass filter kernel, a 3×3 or 5×5 center protrusion kernel can be used. By calculating the local gray-level difference, image details are preserved while noise is reduced as much as possible. The difference between each filtered pixel and its surrounding pixels is then compared with an empirically obtained noise removal threshold. If the absolute value of the difference is greater than, for example... The value is then used to redistribute the grayscale of the pixel. Next, edge detection is performed on the noise-removed image. Specifically, the horizontal and vertical neighborhoods of each pixel in the image are traversed. When using the Sobel or Canny operator, the convolution mask and non-maximum suppression threshold need to be determined. For example, the gradient intensity is divided into the range of 0 to 255. Gradient values ​​below 30 are not marked, while gradient values ​​above 30 are marked as potential edges. These potential edges are then filtered according to whether they exceed a high threshold of 40 to select the final edge pixels. After edge detection, the preliminary enhanced contour information is obtained and compared with the high-pass filtering result of the previous step. If some local details are lost due to incorrect threshold setting, the threshold range can be fine-tuned again to finally obtain the environment image with optimized resolution.

[0066] Based on the resolution-optimized environmental image, the distribution information of each pixel in the spatial and frequency domains is read. When sharpening the image, the Laplacian operator can be used to further amplify local details. When setting the Laplacian operator, a 3×3 or 5×5 central negative coefficient template is typically considered, and a threshold is defined, for example... The intensity of sharpening is determined by multiplying the calculated Laplacian response by... Add back the original image pixel values. If some pixels exceed 255 after addition, truncate them to 255; if they are below 0, truncate them to 0. This operation can be performed independently for each channel to avoid color cast issues caused by multi-channel mixing. For high-contrast areas in the image, cropping can be performed based on previously obtained highlight and shadow thresholds, for example, a highlight threshold of 200 and a shadow threshold of 30. If local pixels exceed these two ranges after sharpening, perform equalization again. At the same time, compare the mean square error (MSE) of any potential noise. If the MSE after sharpening is greater than 15, it indicates excessive noise amplification, and the threshold needs to be reduced. The image is recalculated, and once each region of the image conforms to the pre-established brightness and sharpness range, an optimized image is generated.

[0067] The steps for obtaining environmental labeling identification results are as follows:

[0068] Based on the optimized image, image features are extracted, and road, building and traffic signs are separated from the background area through image segmentation to obtain candidate areas for environmental signs.

[0069] Based on the candidate regions of environmental signs, a deep learning model is applied for classification, the input feature vector is used for target matching, the matching degree is calculated and environmental signs are filtered to generate environmental sign classification results.

[0070] Based on the environmental label classification results, a confidence assessment is conducted to eliminate misidentified targets, determine the location and category of the target environmental label, and generate environmental label identification results.

[0071] Specifically, based on the optimized image obtained earlier, the brightness and color information of each pixel in the RGB space are first read and recorded. Then, a region growing method is used to aggregate adjacent pixels with similar features in the image. To set the aggregation conditions, the distribution range of different targets such as roads, buildings, and traffic signs in terms of color and texture can be extracted from actual observation experience. For example, the grayscale of road pixels is concentrated in... to The range and the texture gradient is lower than The grayscale of the building pixels is concentrated in to The range and texture gradient are approximately in to Between these, the color distribution of traffic signs is characterized by red or blue channel values ​​being higher. Using a primary method supplemented by clear edge gradients, the similarity of each pixel to known categories is determined based on these ranges, and the region is continuously expanded and aggregated. If the color and texture of the current pixel both fall within the range of the same category, it is classified as a region of that category; otherwise, it continues to be compared with other categories or marked as an unassigned region. To make the segmentation more accurate, a threshold segmentation can be used for secondary refinement after region growing. The threshold is set by calculation based on previous data; for example, the color threshold is determined to be... And the texture threshold is determined as If the feature difference between a pixel and the target category exceeds or Therefore, it will no longer be included in that category region. After completing the pixel-level division of the entire image, road pixels, building pixels, and traffic sign pixels are separated from the remaining background regions. When summarizing these separated connected regions, noisy regions with too small an area can be further eliminated, with the minimum connected region area set based on experience. Pixel, when the area of ​​a connected region is smaller than If the area is directly discarded, the candidate areas for environmental labeling are obtained after the above operations.

[0072] Based on the candidate environmental sign regions obtained in the previous step, the pixel feature vectors in each candidate region are first used to construct input data for deep learning model recognition. Specifically, parameters such as contour shape, typical texture, and mean brightness are obtained from each candidate region, and the position of the region in the original image coordinates is recorded. To train the deep learning model, a batch of labeled environmental sign image samples needs to be prepared, and diversity needs to be maintained in the training and validation sets. For example, traffic sign images in actual road environments can be collected. Zhang also included common building or road backgrounds as negative samples. Zhang inputs these samples into a convolutional neural network containing multiple convolutional and pooling structures for offline training, with the learning rate set to [value missing]. And use stochastic gradient descent in In each iteration, the network weights are continuously updated. Once the loss function converges, the trained model parameters are solidified. During inference, the feature vectors of the aforementioned candidate regions are fed into the network, and the matching probabilities of each category are output. These probabilities are compared with a pre-set classification threshold to determine whether a region belongs to the traffic sign category. The classification threshold can be determined by the F1 score on the validation set, for example, by taking... As a threshold, if the probability of a certain area corresponding to the traffic sign category in the network output is greater than 100%, then the threshold is set at 100%. The area is then retained as the target marker. Similarly, the building and road categories are judged and mismatched areas are removed. Finally, the corresponding predicted label is marked on each retained area, and the labels and candidate area coordinate information are summarized to generate the environmental marker classification result.

[0073] Based on the above environmental sign classification results, we first iterate through all areas predicted as traffic signs or buildings and obtain their model output probabilities. Then, we evaluate the confidence level for each area. To set a confidence threshold, we can combine previously labeled data to statistically determine the probability range where the model's prediction accuracy is high in the training set. For example, when the probability is higher than... Errors in prediction are extremely rare; if the prediction probability for a certain area is lower than... If it is determined to be a misidentification, it will be discarded. For those in between... to The results are then supplemented by shape feature comparison and observation of the difference between its actual area and the shape of typical traffic signs or buildings. If the difference is within... Within and the texture distribution difference is no greater than If the region is not selected, it is retained; otherwise, it is discarded. This multi-judgment method is used to further eliminate misidentified targets and retain regions with high confidence. Finally, the image coordinates, corresponding category labels, and matching probabilities of the retained regions are recorded. After summarizing the information of all regions that meet the confidence requirements, the environmental sign recognition result is generated.

[0074] The steps for obtaining the initial lighting adjustment parameters are as follows:

[0075] Based on the environmental sign recognition results, determine the relationship between the recognized environmental sign type and the vehicle's current position, calculate the real-time distance between the vehicle and the environmental sign, and obtain the light adjustment requirement data;

[0076] Based on the light adjustment requirements data, the required headlight brightness adjustment is calculated using the following formula:

[0077]

[0078] in, This represents the required headlight brightness adjustment. This represents the highest setting value for the headlight brightness. The minimum setting value representing the brightness of the headlights. This represents the real-time measured distance between the vehicle and the environmental sign. Represents a safe reference distance. This represents the height difference between the road where the vehicle is currently traveling and the environmental sign. This represents the initial angle of the headlight beam.

[0079] Based on the required headlight brightness adjustment, the headlights are adjusted in real time to obtain preliminary light adjustment parameters.

[0080] Specifically, based on the sign category and coordinate reference information provided by the environmental sign recognition results, the coordinate positioning data of the vehicle's current driving route is read and compared item by item with the coordinate positions of the environmental signs. The horizontal and vertical differences between the two in the plane coordinate system are calculated. The vehicle's current actual position is obtained by collecting latitude and longitude data during the vehicle's driving process and matching it with pre-established road geographic information. Combined with the geographical locations of the environmental signs already marked in the map information, the lateral and longitudinal distances between the two are calculated pair by pair. These distance values ​​are compared with pre-established confidence intervals. For example, 0 meters to 200 meters is considered a short distance range, 201 meters to 1000 meters is considered a medium distance range, and more than 1000 meters is considered a long distance range. If a calculation result significantly exceeds the confidence interval, the value is recorded for review. After confirming the true road information of the vehicle, the position data is recalibrated. Then, the straight-line distance between the vehicle and the environmental sign is expanded using the Pythagorean theorem. If the elevation difference is denoted as Zh and the plane distance is denoted as Lw, the real-time distance is available. The calculations are converted into final measurement values. In actual measurements, if the elevation difference is less than 2 meters, it can be simply ignored; otherwise, the vertical accuracy must be within 0.5 meters. The range of distance values ​​is then compared with the pre-established safety reference standards. If the distance is less than 20 meters, it is classified as a close-range range and marked as requiring further attention. If the distance is greater than 500 meters, it is marked as a long-range range and requires no special processing. Finally, based on these filtered and corrected distance data, light adjustment requirement data is created and summarized to obtain the light adjustment requirement data.

[0081] The advantage of the formula is that by introducing multiple parameters such as the actual distance between the vehicle and the environmental sign, the road elevation difference, and the initial angle of the headlight projection, it can achieve a more refined calculation of the headlight brightness, thereby obtaining a more flexible brightness adjustment number under different road conditions and environmental sign types.

[0082] The steps for obtaining the parameters are as follows: before the vehicle lighting system leaves the factory, the maximum power output of the headlights is calibrated, and the corresponding maximum brightness value is statistically analyzed. During vehicle installation and commissioning, this maximum brightness value is measured several times, and the maximum brightness values ​​under different measurement conditions are uniformly incorporated into a data sequence. Then calculate the mean of the sequence as... The baseline value is used. If subsequent tests reveal deviations in maximum brightness due to extreme environments, additional measurements are taken and the average value is updated, as shown in the following formula: ,in This indicates the number of measurements. Each measurement is performed in a dark room free from external light interference. The calibration error of the photometer needs to be controlled to within 5% beforehand. For example, if a certain model of car headlight obtains ten values ​​in ten measurements: 4500, 4580, 4420, 4550, 4510, 4490, 4570, 4600, 4520, and 4480, then the following can be calculated: .

[0083] The steps for obtaining parameters are as follows: Set the minimum perceptible brightness level for the same vehicle lighting system, record the actual measurement data of the headlights under the minimum safe brightness condition, and unify the values ​​obtained from each measurement into a data sequence. The same mean was obtained. For example, by concentrating several measured low brightness values ​​in the 500 to 600 range, a comprehensive result can be obtained. .

[0084] The parameter acquisition steps are as follows: using the real-time distance between the vehicle and the environmental sign recorded in the previously obtained light adjustment requirement data, a numerical sequence that has already been measured and calibrated is directly read, and this sequence is denoted as... During each vehicle travel period, a large amount of distance measurement information is collected. This information is then verified under unobstructed straight-line line-of-sight conditions. For example, if the average distance measurement result obtained when the vehicle is traveling in a certain area is 30 meters and the error is within 0.5 meters, then... .

[0085] The parameters are obtained by referring to a previously determined safe reference distance dataset. This distance is pre-calibrated based on road type and speed limit range. The safe reference distance for each road is determined through road traffic monitoring statistics and safe distance judgment standards over several consecutive months, and the corresponding safe reference distances for each road are recorded. For the current road, select its corresponding safe reference distance value. For example, on an urban road with a design speed of 60 kilometers per hour, the most common safe reference distance is 50 meters. .

[0086] The steps for obtaining the parameters are as follows: While the vehicle travels along different roads, the elevation difference between the road location and the environmental sign base or installation point is recorded using an elevation mapping system. If this elevation difference sequence is... Then select the option closest to the current driving position as... The numerical value, for example, if a vehicle is traveling on an elevated road and is 2 meters away from the ground post where the sign is located, then it will be directly... .

[0087] The steps for obtaining the parameters are as follows: using the initial calibration value of the headlight installation angle and performing actual measurements when the vehicle enters the repair shop, for example, recording the angle between the headlight beam and the horizontal line of the ground using a laser angle measuring instrument, and statistically analyzing the final angle values ​​under different installation error conditions. The average of this sequence is calculated as the initial angle of the headlight beam projection. For example, if five data points are obtained in a single measurement: 3.5 degrees, 3.4 degrees, 3.6 degrees, 3.5 degrees, and 3.5 degrees, then... .

[0088] Calculation process:

[0089] The first step is to read the required parameters. For example , , , , , ;

[0090] The second step is to calculate. ,Right now ;

[0091] The third step is to calculate the denominator. ,in , Therefore, the denominator is approximately ;

[0092] Fourth step, calculate the numerator. ;

[0093] Fifth step, first find the first term. In addition to the second item , merged to obtain ;

[0094] The results indicate that, under the current environment and parameters, the headlight brightness adjustment value is approximately 96981.57. If there are more refined brightness or safety restrictions in subsequent assessments, this value can be further trimmed or corrected. Different value ranges represent different levels of brightness output requirements. For example, if the final value is greater than 50000, it means that the brightness needs to be significantly increased at long distances or with large height differences. Otherwise, if the value is less than 5000, a lower brightness output level can be maintained.

[0095] Based on the required headlight brightness adjustment, the data recorded for each time segment during the vehicle's current driving process is sequentially iterated. The brightness adjustment is compared to a pre-established table based on vehicle speed and turning angle. If the vehicle is on a straight road and its speed is greater than 40 km / h, rapid brightness synchronization is performed based on the previously obtained brightness adjustment. Otherwise, in scenarios with a turning radius less than 30 meters, the lateral lighting requirements are compared first, and a secondary correction is made based on road lighting conditions. A lateral correction coefficient is established to measure the required diffusion angle adjustment of the headlights during turning. This coefficient is denoted as Mt and obtained by combining the turning radius data with the vehicle speed data. Within the range of values ​​statistically analyzed in the preliminary analysis... When the curve radius is less than 30 meters and the speed exceeds 35 kilometers per hour, Mt can be set to the range of 0.3 to 0.4. Then, the final correction amount is determined by comparing the actual measured direction angle with the empirical threshold. For example, if the direction angle is greater than 10 degrees, it is considered a large turn, and the brightness output is increased by about 10%. After recording, if it is found that the vehicle is in an elevated or tunnel area, geographic information can be introduced to slightly adjust the brightness. After comprehensively comparing these parameters, the headlight output value at each moment is adjusted synchronously. The effective points of all adjustment actions are associated with each vehicle status point to facilitate subsequent tracking and debugging accuracy. Finally, preliminary light adjustment parameters are generated based on the sorted adjustment information.

[0096] The steps to obtain the final parameters for light adjustment are as follows:

[0097] Based on the preliminary light adjustment parameters, the light reflectivity of the road surface is detected, the light reflection characteristics are analyzed, the initial scattering range of the light projection is calculated, and the light projection adjustment data is obtained.

[0098] Based on the light projection adjustment data, the optimized light projection angle is calculated using the following formula:

[0099]

[0100] in, This represents the optimized light projection angle. This represents the height of the headlights relative to the road. Represents the height of the target area. This represents the horizontal distance between the vehicle and the target area. Represents the light reflectivity of the road surface. Represents standard light reflectance;

[0101] Based on the optimized light projection angle, the angle of the headlight beam is adjusted to generate the final parameters for light adjustment.

[0102] Specifically, based on the preliminary light adjustment parameters obtained earlier, the actual road surface material information of the road section where the vehicle is located is first read and the corresponding reflection data is recorded. Then, the reflectance values ​​of the local road surface are measured point by point using a device equipped with photometric monitoring function. To set the detection accuracy, several scales can be divided between 0 and 1, and the measurement error is required to be less than 0.02. If some measured values ​​are found to be significantly higher than 0.8 or lower than 0.05, the measurement is repeated. After completing the calibration of several sampling points of the entire road section, the data of these sampling points that exceed or fall below the predetermined threshold range are summarized and compared a second time. For example, when the measured road section is an asphalt pavement, the common reflectance range is between 0.05 and 0.25. If a point is higher than 0.25, it is considered a bright road section and recorded. If a point is lower than 0.05, it is considered a very dark road section and recorded. These recorded points are compared with the road curvature, terrain elevation difference, and surrounding area. Information such as the degree of interference from edge light sources is correlated and organized. When reading the light reflection characteristics, the reflection behavior of each sampling point under different illumination intensities is compared with the previously obtained photometric correction formula. If the reflection coefficient of a certain point shows an increase of more than 0.2, it is marked as a high reflection risk point. If the reflection coefficient of a certain point fluctuates around 0.06, it is marked as a low reflection point. Then, a scattering range estimation model is constructed based on these marking information. The model will refer to the measurement difference between adjacent points. If it is less than 0.01, it means that the reflectivity of the area is relatively close and can be merged. If the difference is greater than 0.03, it means that the reflectivity of the area is significantly different and needs to be segmented. By comparing the average reflectivity of the entire road surface and the distribution of peak and valley values, the initial scattering range that the light projection may produce is determined. The results are coupled with the previously obtained preliminary light adjustment parameters item by item and the light projection adjustment data is output.

[0103] The advantage of the formula is that by incorporating parameters such as road height, target area height, horizontal distance, road surface reflectivity, and standard reflectivity for comprehensive calculation, the headlight beam angle can be dynamically corrected under different height differences and road surface light reflection conditions.

[0104] The steps for obtaining the parameters are as follows: First, use the distance and height measuring devices at the front of the vehicle to detect the vertical distance between the headlight position and the ground reference plane. Then, under flat road conditions, measure the height from the center point of the headlight to the ground multiple times and record a set of values. Then, combining the suspension changes under full load and empty vehicle conditions, the calculation formula is used. The average value was selected as the final headlight installation height. If the deviation between a single measurement and the average value exceeded 0.02 meters, the measurement was repeated. After several measurements, a certain model of small car obtained heights of 0.63 meters, 0.62 meters, 0.61 meters, 0.62 meters, and 0.63 meters. The average value was taken as approximately 0.622 meters and used as the final installation height. The parameter values.

[0105] The steps for obtaining parameters are as follows: for the location of the target area, use the vertical scale measurement results of the target area itself and the elevation difference between it and the road reference plane as input data.

[0106] The steps for obtaining the parameters are as follows: while the vehicle is still moving, the horizontal distance from the headlights to the target area is determined. Triangulation is then performed using the vehicle's built-in navigation positioning data and the target area's coordinate information. Alternatively, under conditions of straight-line visibility, several measurement values ​​can be obtained directly using laser ranging. Take the average value using the following formula: If the measurements are 28 meters, 29 meters, 30 meters, and 29 meters in four measurements, then... .

[0107] The steps for obtaining the parameters are as follows: using the previously obtained light projection adjustment data and multi-point reflectivity monitoring results, the road surface reflectivity of the target area is searched and matched. If the area is found to be between 0.15 and 0.25 in the measurement value set, the numerical range can be finely statistically analyzed, and then applied to the target area using the following formula: Perform a weighted summation. This represents the reflectance value at the t-th measurement point. This represents the weight value related to the lighting angle or light intensity at the measurement point, ensuring consistency of measurement conditions. If six measurement points are collected around the target area with reflectivities of 0.18, 0.20, 0.22, 0.21, 0.19, and 0.20, and the weight of each point is approximately 0.95, then the comprehensive calculation can obtain... .

[0108] The steps for obtaining the parameters are as follows: using the reference reflectance value of a conventional asphalt surface on a municipal road under standard test conditions as a benchmark, statistical departments or testing agencies will generally provide a road reference reflectance value in the range of 0.15 to 0.20. After repeated measurements within this range, 0.18 is selected as the standard light reflectance. If the actual widespread mean is found to be exactly 0.18 during the measurement, then... Substitution operation.

[0109] Calculation process:

[0110] The first step is to read the parameters of the current vehicle driving environment: , , , , ;

[0111] The second step is to calculate. Substitute the data as Take again (Because the angle value is small, the radian value is similar to it);

[0112] The third step is to calculate. Its molecules denominator Therefore, this item is ;

[0113] The fourth step is to sum the results. Convert the radian result to approximately the angle. To avoid negative angles, adjustments can be made upwards or downwards based on the vehicle mounting reference.

[0114] The results indicate that, after combining the current horizontal distance and height information with the road surface reflectivity calculation, the resulting optimized projection angle is approximately... When the value is between -2 degrees and -0.5 degrees, it means that the headlights need to be tilted slightly downwards. If it is greater than 0 degrees, it means that the headlights need to be adjusted upwards. For different value ranges, fine-tuning can be made according to the vehicle status.

[0115] Based on the optimized beam projection angle obtained earlier, the vehicle's speed, turning radius, and ambient light data are read second by second during its driving process. These values ​​are then compared against the pre-established dynamic beam adjustment rules. For example, when the turning radius is less than 40 meters and the speed exceeds 30 kilometers per hour, a lateral correction coefficient is added. If the measured lateral correction coefficient is within the range of 0.2 to 0.3, the corresponding offset value is added to the current beam projection angle. If the ambient light intensity, as measured by the sensor, falls below 200 lux, a downward tilt of 0.5 to 1 degree is added to the current angle. If the angle exceeds 600 lux, only a minor adjustment of 0.1 to 0.3 degrees is made to the original angle. After summarizing the angle correction process at each moment, a complete time-series record of the projection angle changes is formed. This record is cross-checked with the synchronized data of vehicle position and speed to check for excessive or insufficient adjustment. To ensure the accuracy of the record, the angle changes every 10 seconds are included in the comparison and the difference range between the angle and the target angle is marked. For example, if the difference is greater than 1 degree, it is included in the key inspection sequence. If the difference is within 0.3 degrees, it is considered to be within the normal deviation. Finally, after completing the time-series check, the final parameters for light adjustment are obtained.

[0116] The steps for obtaining the lighting pattern optimization results are as follows:

[0117] Based on the final parameters of light adjustment, the real-time speed information of the current vehicle is obtained, the road visibility and the surrounding ambient light are detected, and the lighting mode adjustment data is obtained.

[0118] Based on the lighting mode adjustment data, the lighting mode optimization index is calculated using the following formula:

[0119]

[0120] in, Represents the lighting mode optimization index, This represents the vehicle's current speed. Represents the influence factor of light. This represents the light intensity detected in the current environment. Represents the ambient light intensity around the vehicle. This represents the detection distance between the vehicle and the obstacle in front.

[0121] Based on the lighting mode optimization index, a headlight adjustment strategy is selected to obtain the lighting mode optimization results.

[0122] Specifically, based on the final parameters adjusted for light, the system first retrieves the vehicle's current speed data and records it frame-by-frame in sync with the vehicle's position. The speed value is then compared to the road speed limit. For example, if the speed limit is 60 km / h and the speed repeatedly approaches or exceeds 60 km / h, it's marked as a high-speed condition. Next, visibility data from adjacent moments is read. Visibility data is collected using an imaging device mounted on the front of the vehicle, collecting information such as image clarity and viewing distance, and combined with a corresponding distance scale. If visibility is less than a pre-set threshold of 300 meters based on extensive field observation experience, it's marked as a low-visibility event; if visibility is greater than 800 meters, it's marked as a high-visibility event. Then, ambient light data is compared with the speed and visibility data. For example, the light intensity unit is set to lux. During direct sunlight, it can reach tens of thousands or even hundreds of thousands of lux, while on cloudy days or at night, it can drop to hundreds or even tens of lux. Multiple time periods are selected for light measurement results comparison to obtain light fluctuations, and the fluctuations are recorded when the light intensity is below 100 lux. Light intensity is categorized as low light or high light when it exceeds 10,000 lux. These light levels are combined with vehicle speed and road visibility for assessment. If the speed is high, visibility is low, and ambient light is also dim, a higher demand value is output at the current moment. If the speed is moderate, visibility is within a safe range, and ambient light is close to normal daytime levels, a lower demand value is output. These demand values ​​are stored quantitatively in a data sequence to represent the vehicle's current tendency to adjust the lighting mode. This data sequence is paired with the timestamps corresponding to the previously generated final parameters for light adjustment, and extreme situations are checked one by one within the existing time period. If a rapid fluctuation exceeding 30% occurs within a short period, it is marked as an abnormal fluctuation point. Then, data from all adjacent time points are read for interpolation confirmation and outliers that may be caused by instantaneous interference are removed. When most data are stable or only fluctuate within a small range throughout the overall time period, the measurement results are considered true and valid. Finally, all the above speed, visibility, and light intensity values ​​are summarized to generate lighting mode adjustment data.

[0123] The advantage of this formula lies in incorporating multiple data points, such as real-time vehicle speed, light influence factor, forward illuminance, ambient light intensity, and obstacle distance, into a single expression for calculation. This takes into account various objective conditions that may occur on the road, allowing for a unified index... A comprehensive evaluation is conducted.

[0124] The parameter acquisition steps are as follows: Vehicle speed data is collected using a vehicle speed sensor installed in the vehicle. This sensor is calibrated before leaving the factory and dynamically calibrated during actual road driving. The speed values ​​collected per second are recorded to form a sequence. After filtering out obvious abnormal fluctuations using averaging or median, the average speed representing the current time period is obtained. This average speed is then combined with the vehicle's maximum permissible speed and instantaneous acceleration to establish a reliable speed range. When the speed value is detected to be stable within this range, it can be considered as... The calculated numerical value, for example, when the average driving speed recorded on urban roads is 35 kilometers per hour and the deviation from multiple measurements does not exceed 2 kilometers per hour, can be used to calculate the average speed. Used for subsequent calculations.

[0125] The steps for obtaining the parameters are as follows: Quantify the impact of ambient light on vehicle lighting requirements using a photometric sensor and field-of-view monitoring equipment. First, measure the corresponding light levels at different lux values ​​in the experimental environment. Then, assign an influence coefficient to each light level and perform a weighted calculation in the following form: ,in This represents the illuminance level classification value for the i-th photometric monitoring. This represents the weighted values ​​related to the observation angle or illumination stability. After multiple rounds of data collection, 0 to 50 lux can be considered the extremely dark range with corresponding high-impact mapping values, while values ​​above 10,000 lux can be considered the bright range with corresponding lower mapping values. After processing, if... If the value is approximately 15, it indicates that the current overall lighting conditions are weak or dim. An index of approximately 3 indicates sufficient ambient light and good visibility. For example, when the photometric readings are repeatedly measured between 20 and 60 lux in suburban areas with sparse streetlights at night, the final result can be calculated. .

[0126] The parameter acquisition steps are as follows: First, the light intensity in front of the vehicle is detected. Typically, a photometric sensor is installed at the front of the vehicle to detect the total intensity of light sources in the foreground field of view. This, combined with brightness values ​​observed by a camera, establishes an integrated foreground light intensity sequence. During clear days, values ​​can reach tens of thousands of lux, while at night without streetlights, they may be less than 10 lux. These observations need to be aligned to the same time slice. If the difference between multiple measurements within the same time slice does not exceed 5%, the values ​​are combined and averaged. Otherwise, additional measurements are taken in the next monitoring cycle. After the statistical process, a stable value of the forward illumination intensity is obtained as the baseline. For example, if the average value of multiple tests within a certain period is approximately 600 lux, then it can be taken as... .

[0127] The parameter acquisition process involves capturing ambient light intensity using photometric sensors installed on the sides and roof of the vehicle. These sensor readings may fluctuate within a certain range, but as long as the fluctuation is within 10%, it is considered reliable data for the same moment. This data is then cross-checked with surrounding buildings, streetlights, and other factors to ensure there are no strong reflections or localized shadows causing extreme deviations, resulting in the final average ambient light intensity. For example, if multiple measurements fluctuate between 300 and 400 lux during nighttime monitoring on a main urban road, the average ambient light intensity can be obtained. .

[0128] The steps for obtaining parameters are as follows: scanning obstacles with a radar or laser rangefinder in front of the vehicle and recording the distance data obtained in each scan. During the data collection of the same road segment, noise removal is performed on the detected obstacle distances. After eliminating sudden situations and missing values, a smoothing operation is performed on the data distribution. For example, a moving average or removing extreme values ​​before taking the mean can be used. If a relatively stable average distance is obtained after repeated measurements and alignment, it is taken as the mean. Input values, for example, after multiple measurements, it is found that the distance between the vehicle and the vehicle in front is approximately 60 meters with a fluctuation range of no more than 2 meters, then... .

[0129] Calculation process:

[0130] The first step is to read all parameters: For example, when driving on a certain section of road, the vehicle speed... Light Influence Factor Light intensity in front Ambient light intensity Obstacle detection distance ;

[0131] The second step is to calculate the molecules. ,Right now ;

[0132] The third step is to calculate the denominator. ,in Then the denominator is ;

[0133] Step 4: Calculate Part 1 ;

[0134] Step 5, Calculation Substitute ,but ;

[0135] Step 6: Multiply the first two parts together. ;

[0136] Therefore, it can be obtained The results indicate that the combined effect of the above parameters within the given time period resulted in a lighting mode optimization index approaching 12.20. A higher value indicates that the vehicle is more inclined to increase the lighting level at that moment. Further measurements... A value consistently greater than 10 indicates that further adjustments to the headlight brightness or angle are needed, while when... A value below 5 indicates low lighting demand, and a more energy-efficient lighting mode can be used.

[0137] Based on the previously obtained lighting mode optimization index, the vehicle's steering angle, road slope, and current weather conditions are first read sequentially at the same time. The steering angle value is recorded using an angle sensor and compared with a road curvature threshold. If the steering angle is greater than 10 degrees, it is recorded as a sharp turn; if the road slope exceeds 5%, it is marked as an uneven road section. Then, local weather information is considered. For example, the light attenuation coefficient may fluctuate with increasing precipitation in rainy or snowy weather. Therefore, it is necessary to compare the correlation data between headlight illuminance and visibility under different rain and snow intensities beforehand. When the rainfall reaches 5 mm per hour and the monitored light attenuation coefficient exceeds 2, it is recorded as a moderate rainfall scenario, and the existing lighting mode is recorded accordingly. The entire process involves controlling the steering angle... Information on angle, road gradient, and weather attenuation is superimposed onto the time series of the lighting mode optimization index. Each time point is observed to see if there are significant changes. If at certain moments the turning angle and weather attenuation coefficient simultaneously increase beyond the pre-set merging threshold (e.g., the angle rises above 15 degrees and the attenuation coefficient rises to 3), then weighted processing is applied to that time point to increase the lighting level by a certain amount and summarize it into an independent execution record. If the road surface returns to a relatively straight section and the light attenuation is small in subsequent periods, the lighting intensity can be reduced again or the angle can be adjusted back. The lighting parameters at each adjustment time are summarized and the corresponding vehicle speed and weather background data are marked. These adjustment information are then applied to the actual vehicle lighting strategy in subsequent steps to finally generate the lighting mode optimization result.

[0138] The steps for obtaining lighting performance feedback data are as follows:

[0139] Based on the lighting mode optimization results, the brightness distribution of the current vehicle headlight illumination area is obtained, and combined with the road reflection data obtained by the front camera of the vehicle, lighting monitoring data is obtained;

[0140] Based on the lighting monitoring data, the lighting performance evaluation value is calculated using the following formula:

[0141]

[0142] in, Represents the evaluation value of lighting performance. This represents the average brightness of the area illuminated by the headlights. Represents the reflectance of the road surface. Represents the background brightness from the driver's perspective. Represents the monitoring time interval. This represents the driver's average driving speed during the monitoring period. This represents the recommended driving speed under current conditions;

[0143] Based on the lighting performance evaluation value, the deviation between the driver's manual adjustment behavior and the system adjustment is analyzed, effective lighting adjustment trends are extracted, and lighting performance feedback data is generated.

[0144] Specifically, based on the lighting pattern optimization results, the brightness distribution of the current vehicle headlight illumination area is read. First, the brightness values ​​within the illumination range are recorded using multiple sampling methods to form an initial brightness sequence. Extremely high or low brightness data are then checked to see if they deviate from a pre-defined confidence range, such as comparing a range of 20 candela per square meter to 400 candela per square meter. If a sampling result is below 20, it is marked as an overly dark area, and the possibility of occlusion is investigated. If a sampling result is above 400, it is marked as an overly bright area, and its location is recorded. These brightness data are then combined with images captured by a front-facing camera. The road surface's visible features in the image are used to estimate the vehicle's frontal reflectivity. If the camera identifies multiple obvious reflective areas on the road surface, the coordinate range and light reflection intensity of these areas are extracted. All brightness and reflectivity data are matched with timestamps to form corresponding data entries. If multiple sets of identical coordinates appear within a time period and the reflection intensity remains stable, it is determined to be a reflective area. The system continuously records the brightness values ​​of reflective areas. If the reflection intensity at the same location decreases significantly at other times, it indicates that a vehicle may have passed through the area or the illumination angle may have changed. A secondary detection and comparison is then performed, such as taking multiple frames of data to confirm whether it is continuous or intermittent reflection. All brightness and reflection records collected in the above steps are summarized into a complete time series. These series are then compared with vehicle speed distribution and road type. If the vehicle speed reaches a peak of nearly 70 kilometers per hour during a time period and there are more than five reflective points ahead, that time period is marked as a high-risk area for further inspection. If the speed remains around 40 kilometers per hour and there are no more than two reflective areas, it is marked as a normal range. After checking these records, if no data is missing or abnormal fluctuations are found, they are considered valid monitoring outputs and retained within the usable range. Finally, these data that can reflect the brightness distribution and road reflection information within the current vehicle headlight illumination coverage area are called lighting monitoring data.

[0145] The advantage of the formula is that by incorporating multiple factors such as average headlight illumination, road reflectivity, background brightness, monitoring time, and driving speed differences, it can quantify the vehicle's lighting performance within a given time interval, thus integrating various influencing factors into a single evaluation value.

[0146] The steps for obtaining the parameters are as follows: First, set up several detection points directly in front of the vehicle. Then, aim the photometer at the center and edge areas of the headlight illumination zone and continuously measure the brightness values ​​over a certain period of time to form a data set. Next, the measurement results from these detection points are processed to remove outliers, for example, by deleting the smallest and largest 1% of outliers. Then, the remaining data are summed and divided by the number of data entries to obtain the average brightness. If the vehicle headlights measure 150 candela per square meter at the center point at 10 meters, 80 candela per square meter at the edge point, and the measurements at other detection points mostly fall between 90 and 140 candela per square meter, then all reliable data are combined to obtain the average value, which is named [value missing]. For example, the final calculation yields Candela per square meter.

[0147] The steps for obtaining the parameters are as follows: based on the road surface reflectivity test results of the same road segment under different conditions, the reflectivity of the road surface to vehicle headlights is quantified; several measuring points on the road segment are selected and their reflectivity values ​​are collected using a spectrophotometer. If some sections are newly paved with asphalt, their reflectivity is typically between 0.05 and 0.25, while some cement sections may be between 0.20 and 0.35. The results from these measurement points are categorized according to road material, and the average value is taken for similar road sections. If extreme values ​​are found, the measurements need to be repeated and compared in the next batch of tests to obtain a unified average reflectivity coefficient representing the road surface. If, after ten or more measurements, the values ​​are consistently between 0.18 and 0.22, then a suitable reflectivity coefficient can be selected. .

[0148] The steps for obtaining the parameters are as follows: When specifically considering the background brightness from the driver's perspective, a miniature photometer needs to be placed inside the vehicle's cabin or near the headrest to measure the ambient light intensity outside the driver's field of vision. After continuous monitoring and removal of interference, the results are obtained. This set of values ​​is then subjected to a fluctuation filter within its range. If the fluctuation exceeds 20%, a second data collection is required, taking into account objective scenarios (such as suddenly entering a tunnel or streetlights going out). Once the data stabilizes, the average result is used as the final value. For example, if the detected background brightness range mostly falls between 20 and 40 candela per square meter, then it is ultimately recorded as... .

[0149] The parameter acquisition steps are as follows: When setting the monitoring time, a representative duration can be selected based on statistics of common vehicle driving conditions. For example, on most urban commuter roads, a monitoring window of 120 seconds can be used to summarize lighting performance. During on-site testing, the brightness of the headlight-illuminated area and background data are recorded once per second. After collecting these data for 120 time points, a complete evaluation process is performed. If data loss or temporary instrument malfunctions cause a small number of missing time points, the time can be extended by a few seconds until 120 valid data points are collected. For example, the final result is... The calculation is performed in seconds.

[0150] The parameter acquisition steps are as follows: using the vehicle's internal speed sensing equipment, the driver's driving speed is recorded at the second level within the monitoring time interval, and correlated with the vehicle's driving trajectory; the speed values ​​per second form a sequence. After removing obvious outliers (such as instantaneous pulses from the speedometer), the arithmetic mean is taken to form the average driving speed. For example, if the vehicle speed fluctuates between 50 and 60 kilometers per hour within a 120-second interval, the average value can be selected. kilometers per hour as .

[0151] The steps for obtaining the parameters are as follows: A suggested driving speed is pre-determined based on the current environment and road conditions. This can be set to approximately 60 kilometers per hour on urban expressways and approximately 40 kilometers per hour on rural roads. This suggested speed value is determined by the transportation department based on long-term observations and traffic flow distribution, and is stored locally in the vehicle information system. If the current road segment is designated as an urban expressway, its suggested value can be directly retrieved. kilometers per hour, denoted as .

[0152] Calculation process:

[0153] The first step is to Assuming it is approximately constant over the monitoring period, first... To simplify:

[0154]

[0155] If in the example selection , , , If the time is seconds, then we can get:

[0156]

[0157]

[0158]

[0159] The second step is to process the denominator. Calculations are performed if the average speed of the vehicle km / h and recommended speed kilometers per hour, then:

[0160]

[0161]

[0162]

[0163] Third step, combine the numerator and denominator:

[0164]

[0165] The results indicate that the final lighting performance evaluation value is approximately -5.89. If the calculated value is greater than 0, it means that the vehicle headlights meet the background requirements in terms of average brightness and road reflection during the monitoring period. The larger the value, the more sufficient the brightness coverage and the insignificant speed difference. If the calculated value is negative, it means that there is a gap between the vehicle headlight illuminance or road reflection and the driver's background perception during this period. At the same time, the speed deviation from the recommended value will also lower the evaluation value to some extent. The lighting level can be further optimized by combining manual adjustments or system adjustments in subsequent stages.

[0166] Based on the calculation results of the lighting performance evaluation value, the evaluation value at each time point within the entire monitoring period is first traversed sequentially and compared with the driver behavior data at the corresponding time. If it is found that the driver manually dims the lights at certain times when the system was originally set to high brightness, this difference in behavior is recorded. If the same situation occurs multiple times, it indicates that the driver has a strong personal bias in adjusting the system. These bias points are included in the deviation set, and the continuity of the manual adjustment behavior is judged based on their frequency. For example, if the driver's manual adjustment action is found to occur 8 times within a 120-second period, and all of them are concentrated in the acceleration or congestion range, this pattern is summarized as "tendency to dim the lights during acceleration or in congestion". The system identifies the "tendency to brighten" type and, in conjunction with the corresponding lighting performance evaluation value, observes whether these adjustments raise the evaluation value to a range close to 0 or more positive. If, after multiple manual adjustments, the evaluation value changes from around -5.0 to around -2.0, this trend is marked as "slight improvement" in the record. If, following subsequent time periods, the data continues to fluctuate between -3.0 and -1.0, it is considered "stable adjustment." Finally, all stable deviation patterns are summarized, and individual random adjustments are removed. These patterns are then broken down and organized to obtain a set of effective lighting adjustment trends that can be used in subsequent applications. These final difference patterns are then output and packaged into lighting performance feedback data.

[0167] Please see Figure 2-5 The present invention also provides a vehicle lamp, wherein a heat dissipation lamp housing 1 with a ventilation opening 10 on the outer wall is provided, a heat dissipation fan 11 corresponding to the ventilation opening 10 is installed inside the heat dissipation lamp housing 1, a conductive component 2 for power supply is attached to one end of the heat dissipation lamp housing 1, a copper substrate 3 is provided inside the heat dissipation lamp housing 1, LED lamp source chips 30 are provided on both sides of the copper substrate 3, a connection terminal 301 for electrical connection of two LED lamp source chips 30 is provided at one end of the copper substrate 3, a bifurcation portion adapted to the heat dissipation fan 11 is provided at the other end of the copper substrate 3, an electronic control chip 31 is provided on one side of the copper substrate 3, and heat conduction pipes 4 are provided on both sides of the outer side of the copper substrate 3, and the heat dissipation fan 11 is located between the electronic control chip 31 and the conductive component 2.

[0168] The heat dissipation lamp housing 1 has a cavity inside for accommodating the heat dissipation fan 11 and the conductive component 2. The heat dissipation lamp housing 1 has an opening 12 on the outside corresponding to the light-emitting surface of the LED light source chip 30. The opening 12 is located on the outside near the ventilation port 10.

[0169] In addition to the above description, it should be noted that the conductive component 2 includes a conductive plug 21 and a rectifier board 22. The rectifier board 22 is provided with slots a221 for soldering the pins of the conductive plug 21 and slots b222 for soldering the bifurcation of the copper substrate 3 around its perimeter.

[0170] In addition to the above description, it should be noted that the other end of the heat dissipation lamp housing 1 is provided with a heat dissipation hole 13 for one end of the heat conduction pipe 4 to extend out, and the other ends of the two heat conduction pipes 4 are aligned with the bifurcation of the copper substrate 3.

[0171] In further detail, the exterior of the heat dissipation lamp housing may also be provided with through holes corresponding to the rectifier plate 22, so that the opening 12 and the through holes are connected to both ends of the ventilation port 10 respectively and form a heat dissipation air duct for the flow of hot air. When the heat dissipation fan 11 is working, hot air can be discharged through the heat dissipation air duct.

[0172] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. An intelligent control system, characterized in that, Includes the following steps: The environmental perception module collects images of the surrounding environment through the vehicle-mounted camera, performs resolution optimization processing on the images, and generates optimized images. Based on the optimized image, deep learning analysis is used to identify target environmental signs, including tunnels and school areas, and environmental sign recognition results are generated. The light adjustment module adjusts the brightness of the vehicle lights based on the environmental sign recognition results, calculates the required light parameters, and generates preliminary light adjustment parameters; based on the preliminary light adjustment parameters, it further optimizes the light projection angle according to road conditions to generate final light adjustment parameters. The lighting mode selection module adjusts the final parameters based on the light, and fine-tunes the lighting mode by combining the current vehicle speed and weather conditions, generating an optimized lighting mode result; The feedback optimization module uses the lighting mode optimization results to monitor the lighting effect and driver feedback in real time, collect lighting performance data, and generate lighting performance feedback data. The steps for obtaining the optimized image are as follows: The vehicle-mounted camera is activated, capturing a continuous sequence of images of the surrounding environment. Color balance and brightness are then adjusted to obtain the processed environmental image. Based on the processed environmental image, a high-pass filter is applied to remove noise from the image, and edge detection is used to enhance the object edges in the image to obtain a resolution-optimized environmental image. Based on the resolution-optimized environmental image, the features in the image are refined through image sharpening to generate an optimized image; The steps for obtaining the environmental label recognition results are as follows: Based on the optimized image, image features are extracted, and road, building and traffic signs are separated from the background area by image segmentation to obtain environmental sign candidate areas; Based on the candidate regions of environmental signs, a deep learning model is applied for classification, the input feature vector is used for target matching, the matching degree is calculated and environmental signs are filtered to generate environmental sign classification results. Based on the environmental sign classification results, a confidence assessment is performed to eliminate misidentified targets, determine the location and category of the target environmental sign, and generate environmental sign recognition results. The steps for obtaining the preliminary light adjustment parameters are as follows: Based on the environmental sign recognition results, the relationship between the recognized environmental sign type and the vehicle's current position is determined, the real-time distance between the vehicle and the environmental sign is calculated, and the light adjustment requirement data is obtained. Based on the light adjustment requirement data, the required headlight brightness adjustment is calculated using the following formula: in, This represents the required headlight brightness adjustment. This represents the highest set value for the brightness of the headlights. The minimum setting value representing the brightness of the headlights. This represents the real-time measured distance between the vehicle and the environmental sign. Represents a safe reference distance. This represents the height difference between the road where the vehicle is currently traveling and the environmental sign. This represents the initial angle of the headlight beam. Based on the required headlight brightness adjustment, perform real-time brightness synchronization adjustment of the headlights to obtain preliminary light adjustment parameters; The steps for obtaining the final parameters of the light adjustment are as follows: Based on the preliminary light adjustment parameters, the light reflectivity of the road surface is detected, the light reflection characteristics are analyzed, the initial scattering range of the light projection is calculated, and the light projection adjustment data is obtained. Based on the light projection adjustment data, the optimized light projection angle is calculated using the following formula: in, This represents the optimized light projection angle. This represents the height of the headlights relative to the road. Represents the height of the target area. This represents the horizontal distance between the vehicle and the target area. Represents the light reflectivity of the road surface. Represents standard light reflectance; Based on the optimized light projection angle, the angle of the headlight beam is adjusted to generate the final light adjustment parameters.

2. The intelligent control system according to claim 1, characterized in that, The steps for obtaining the lighting mode optimization results are as follows: Based on the final parameters of the light adjustment, the real-time speed information of the current vehicle is obtained, the road visibility and the surrounding ambient light are detected, and the lighting mode adjustment data is obtained. Based on the lighting mode adjustment data, the lighting mode optimization index is calculated using the following formula: in, Represents the lighting mode optimization index, This represents the vehicle's current speed. Represents the influence factor of light. This represents the light intensity detected in the current environment. Represents the ambient light intensity around the vehicle. This represents the detection distance between the vehicle and the obstacle in front. Based on the lighting mode optimization index, a headlight adjustment strategy is selected to obtain the lighting mode optimization result.

3. The intelligent control system according to claim 1, characterized in that, The steps for obtaining the lighting performance feedback data are as follows: Based on the lighting mode optimization results, the brightness distribution of the current vehicle headlight illumination area is obtained, and combined with the road reflection data obtained by the front camera of the vehicle, lighting monitoring data is obtained. Based on the lighting monitoring data, the lighting performance evaluation value is calculated using the following formula: in, Represents the evaluation value of lighting performance. This represents the average brightness of the area illuminated by the headlights. Represents the reflectance of the road surface. Represents the background brightness from the driver's perspective. Represents the monitoring time interval. This represents the driver's average driving speed during the monitoring period. This represents the recommended driving speed under current conditions; Based on the lighting performance evaluation values, the deviation between the driver's manual adjustment behavior and the system adjustment is analyzed, effective lighting adjustment trends are extracted, and lighting performance feedback data is generated.

4. A vehicle light, applicable to the intelligent control system as described in any one of claims 1-3, characterized in that, include: A heat dissipation lamp housing (1) with a vent (10) on its outer wall is provided. A heat dissipation fan (11) corresponding to the vent (10) is installed inside the heat dissipation lamp housing (1). A conductive component (2) for power supply is installed at one end of the heat dissipation lamp housing (1). A copper substrate (3) is provided inside the heat dissipation lamp housing (1). LED lamp source chips (30) are provided on both sides of the copper substrate (3). A connection terminal (301) for electrical connection of two LED lamp source chips (30) is provided at one end of the copper substrate (3). A bifurcation part adapted to the heat dissipation fan (11) is provided at the other end of the copper substrate (3). An electronic control chip (31) is provided on one side of the copper substrate (3). Heat conduction pipes (4) are provided on both sides of the outer side of the copper substrate (3). The heat dissipation lamp housing (1) has a cavity for accommodating the heat dissipation fan (11) and the conductive component (2), and the heat dissipation lamp housing (1) has an opening (12) on the outside corresponding to the light-emitting surface of the LED light source chip (30), and the opening (12) is located on the outside near the ventilation port (10).

5. The vehicle light according to claim 4, characterized in that, The conductive component (2) includes a conductive plug (21) and a rectifier board (22). The rectifier board (22) is provided with slots a (221) for soldering the pins of the conductive plug (21) and slots b (222) for soldering the bifurcation of the copper substrate (3).

6. The vehicle light according to claim 4, characterized in that, The other end of the heat dissipation lamp housing (1) is provided with a heat dissipation hole (13) for one end of the heat conduction pipe (4) to extend out, and the other ends of the two heat conduction pipes (4) are aligned with the bifurcation of the copper substrate (3).

Images