A commercial vehicle light control method and system based on visual fusion perception

Abstract

The application discloses a commercial vehicle light control method and system based on visual fusion perception, and the method comprises the following steps: acquiring continuous frame vehicle front road image and front vehicle detection result; pre-processing the continuous frame vehicle front road image to obtain an ROI region image; performing environment light intensity detection and rain grade discrimination according to the ROI region image to determine the environment light grade and the rain grade; performing hierarchical decision based on a preset logic according to the front vehicle detection result and the determined environment light grade and rain grade, and outputting corresponding light control instructions; and the application can realize adaptive switching of vehicle high beam and low beam, and improve driving safety.

Description

Technical Field

[0001] This invention relates to a method and system for controlling the lighting of commercial vehicles based on visual fusion perception, belonging to the field of commercial vehicle control technology. Background Technology

[0002] Automobiles are a common means of transportation in modern, rapidly developing society, and are also technology- and capital-intensive industrial products. In recent years, the development of light commercial vehicles and new energy commercial vehicles has attracted increasing attention from domestic manufacturers. As the network architecture and control of commercial vehicles become more intelligent, almost all modern scientific and technological advancements can be reflected in commercial vehicle technology.

[0003] From the perspective of the current development of commercial vehicles, automotive electronics technology is one of the key technologies in modern automotive development. Modern commercial vehicle technology is not simply about crudely controlling automotive components, but about intelligent control based on the actual operating environment of commercial vehicles. Currently, existing automatic lighting control systems for commercial vehicles mostly rely on multiple independent components such as sunlight sensors and rain sensors to achieve environmental detection, which has problems such as high hardware costs, difficult layout, low detection accuracy, and susceptibility to interference. At the same time, existing lighting control is mostly for simple on / off switching, without combining ambient light intensity, rainfall level, and detection of vehicles ahead to achieve adaptive switching between high and low beams. In particular, it has not been adapted to the high speed, long braking distance, and special windshield layout of new energy commercial vehicles, and cannot meet the driving safety requirements in complex scenarios such as rainy days and nights. Moreover, it is prone to problems such as false lighting switching and glare interference, increasing driving hazards. It is evident that, in order to achieve adaptive switching between high and low beams of vehicles, there is an urgent need for a commercial vehicle lighting control method and system based on visual fusion perception. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a commercial vehicle lighting control method and system based on visual fusion perception, which can realize adaptive switching of vehicle high and low beam headlights and improve driving safety.

[0005] To achieve the above objectives, the present invention is implemented using the following technical solution: In a first aspect, the present invention provides a method for controlling the lighting of commercial vehicles based on visual fusion perception, comprising: Acquire consecutive frames of images of the road ahead of the vehicle and the detection results of the vehicle ahead; The continuous frame images of the road ahead of the vehicle are preprocessed to obtain ROI region images; Based on the ROI region image, ambient light intensity is detected and rainfall level is determined to identify the ambient light level and rainfall level. Based on the detection results of vehicles ahead and the determined ambient light and rainfall levels, the system executes hierarchical decisions based on preset logic and outputs corresponding lighting control commands.

[0006] Furthermore, the ambient light intensity detection method includes: Calculate the weighted average brightness and brightness standard deviation based on the ROI region image; A time-based filtering algorithm is used to smooth the weighted average brightness of consecutive frames, resulting in a smooth and uniform brightness after filtering. When the standard deviation of brightness does not exceed the preset threshold, the ambient light level is determined based on the smooth and uniform brightness; when the standard deviation of brightness exceeds the preset threshold, the threshold for dividing the smooth and uniform brightness and the ambient light level is corrected, and the ambient light level is determined based on the corrected parameters. The ambient light levels include strong light, weak light, dim light at night, and extremely dark.

[0007] Furthermore, the rainfall level determination method includes: Based on the brightness image of the ROI region, the edge gradient energy, high-frequency texture component, and glare ratio are determined. After normalizing the edge gradient energy, high-frequency texture components, and glare proportion to the target interval, a weighted fusion algorithm is used to calculate the rainfall quantification index. The rainfall quantization index within consecutive frames is filtered by a moving average filter to obtain the filtered rainfall quantization index. The rainfall level is determined based on the filtered rainfall quantization index; The rainfall levels include no rain, light rain, moderate rain, heavy rain, and torrential rain.

[0008] Furthermore, based on the detection results of vehicles ahead and the determined ambient light and rainfall levels, a hierarchical decision is executed based on preset logic, and corresponding lighting control commands are output, including: When in a bright light environment, regardless of the current rainfall level or whether there are vehicles ahead, output a command to turn off high beams; When in low light conditions, regardless of the current rainfall level or whether there are vehicles ahead, output a command to turn on low beams; when the rainfall reaches the level of moderate rain or above, output a prompt to turn on fog lights. In low-light conditions at night, if there is no rain or light rain and no vehicles ahead, output a command to turn on high beams; if there are vehicles ahead, output a command to switch to low beams; output a command to turn on high beams after the vehicles have moved away. In moderate or heavy rain, regardless of whether there are vehicles ahead, output a command to keep low beams and output a command to adjust the windshield wiper speed. In heavy rain, output a command to keep low beams and output a fog light activation reminder. In extremely dark environments, if there is no rain or light rain and there are no vehicles ahead, output a command to turn on high beams; if there are vehicles ahead, output a command to switch to low beams; output a command to turn on high beams after the vehicles have moved away; if the rainfall reaches the level of moderate rain or above, output a command to keep low beams.

[0009] Furthermore, it also includes: Based on the rainfall level, output wiper speed adjustment commands, where... When there is no rain, output a command to disable windshield wipers; When in light rain, output a command to adjust the wiper interval by one level. When in moderate rain, output a two-level intermittent wiper adjustment command; When in heavy rain, output a command to adjust the wiper speed to low. When in heavy rain, output a command to adjust the windshield wiper speed to high.

[0010] Furthermore, the preprocessing method includes: Convert consecutive frame images of the road ahead of the vehicle from RGB format to single-luminance images; The single-brightness image is subjected to Gaussian filtering to obtain the filtered single-brightness image; The filtered single-brightness image is subjected to ROI delineation processing to obtain the ROI region image.

[0011] Secondly, the present invention provides a commercial vehicle lighting control system based on visual fusion perception, comprising: The acquisition module is used to acquire continuous frames of images of the road ahead of the vehicle and the detection results of the vehicle ahead; The preprocessing module is used to preprocess the continuous frame images of the road in front of the vehicle to obtain ROI region images; The discrimination module is used to detect ambient light intensity and discriminate rainfall level based on the ROI region image, and determine the ambient light level and rainfall level. The decision-making module is used to perform hierarchical decision-making based on the detection results of vehicles ahead and the determined ambient light level and rainfall level, and output the corresponding lighting control commands.

[0012] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0013] Fourthly, the present invention provides a computer device, comprising: Memory, used to store computer programs / instructions; A processor for executing the computer program / instructions to implement the steps of any of the methods described above.

[0014] Fifthly, the present invention provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of any of the methods described above.

[0015] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: This invention provides a method and system for controlling the lighting of commercial vehicles based on visual fusion perception. It enables the reuse of the forward-looking vehicle camera to simultaneously complete ambient light intensity detection, rainfall level judgment, and forward vehicle target detection. It eliminates the need for additional photosensitive sensors and optical rain sensors, effectively reducing the overall vehicle hardware cost and the difficulty of windshield area layout. It is particularly suitable for the electronic and electrical integrated architecture of new energy commercial vehicles, providing effective technical support for commercial vehicles to achieve energy conservation and emission reduction goals.

[0016] This invention provides a method and system for controlling the lighting of commercial vehicles based on visual fusion perception. It employs image ROI region delineation, multi-frame temporal filtering, and multi-feature fusion algorithms to significantly improve the robustness of ambient light judgment and rainfall recognition. It can effectively avoid false triggering of detection caused by scenarios such as shade, tunnels, streetlights, and road splashes, reduce the safety hazards caused by manual operation of lights during driving, and provide reliable protection for the driving safety of commercial vehicles.

[0017] This invention provides a method and system for controlling the lighting of commercial vehicles based on visual fusion perception. It integrates ambient light level, rainfall level and forward vehicle detection results to make hierarchical decisions, achieving adaptive matching between high and low beam control and visibility in rainy and nighttime conditions. This effectively reduces glare interference from oncoming traffic and simultaneously links components such as wipers and fog lights, significantly improving safety and driving comfort at night and in rainy weather. It is precisely adapted to the usage scenarios of commercial vehicles with high speeds, heavy weights and long braking distances.

[0018] This invention provides a method and system for controlling the lighting of commercial vehicles based on visual fusion perception. The control logic response is smooth, without frequent switching jitter, and has a complete anomaly handling mechanism and flexible calibration and adaptation functions. It has strong engineering practicality and can be widely applied to various new energy commercial vehicles and light commercial vehicles. It has a wide range of applications and good promotional value. Attached Figure Description

[0019] Figure 1 This is a flowchart of a commercial vehicle lighting control method based on visual fusion perception provided in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of a commercial vehicle lighting control system based on visual fusion perception provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the cooperation between modules in Embodiment 2; Figure 4 This is a schematic diagram of the workflow of the decision-making module in Example 2. Detailed Implementation

[0020] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations thereof. In the absence of conflict, the embodiments and technical features in the embodiments can be combined with each other.

[0021] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship. Example 1

[0022] Figure 1 This is a flowchart of a commercial vehicle lighting control method based on visual fusion perception, according to Embodiment 1 of the present invention. The commercial vehicle lighting control method based on visual fusion perception provided in this embodiment can be applied to a terminal and can be executed by a commercial vehicle lighting control system based on visual fusion perception. This system can be implemented by software and / or hardware and can be integrated into the terminal, such as any smartphone, tablet, or computer device with communication capabilities. See also... Figure 1 The method implemented in this way specifically includes the following steps: Acquire consecutive frames of images of the road ahead of the vehicle and the detection results of the vehicle ahead; The continuous frame images of the road ahead of the vehicle are preprocessed to obtain ROI region images; Based on the ROI region image, ambient light intensity is detected and rainfall level is determined to identify the ambient light level and rainfall level. Based on the detection results of vehicles ahead and the determined ambient light and rainfall levels, the system executes hierarchical decisions based on preset logic and outputs corresponding lighting control commands.

[0023] The processing method provided in this embodiment involves the following steps in its application: The ambient light intensity detection method includes: Calculate the weighted average brightness and brightness standard deviation based on the ROI region image; A time-based filtering algorithm is used to smooth the weighted average brightness of consecutive frames, resulting in a smooth and uniform brightness after filtering. When the standard deviation of brightness does not exceed the preset threshold, the ambient light level is determined based on the smooth and uniform brightness; when the standard deviation of brightness exceeds the preset threshold, the threshold for dividing the smooth and uniform brightness and the ambient light level is corrected, and the ambient light level is determined based on the corrected parameters. The ambient light levels include strong light, weak light, dim light at night, and extremely dark.

[0024] Furthermore, the rainfall level determination method includes: Based on the brightness image of the ROI region, the edge gradient energy, high-frequency texture component, and glare ratio are determined. After normalizing the edge gradient energy, high-frequency texture components, and glare proportion to the target interval, a weighted fusion algorithm is used to calculate the rainfall quantification index. The rainfall quantization index within consecutive frames is filtered by a moving average filter to obtain the filtered rainfall quantization index. The rainfall level is determined based on the filtered rainfall quantization index; The rainfall levels include no rain, light rain, moderate rain, heavy rain, and torrential rain.

[0025] Furthermore, based on the detection results of vehicles ahead and the determined ambient light and rainfall levels, a hierarchical decision is executed based on preset logic, and corresponding lighting control commands are output, including: When in a bright light environment, regardless of the current rainfall level or whether there are vehicles ahead, output a command to turn off high beams; When in low light conditions, regardless of the current rainfall level or whether there are vehicles ahead, output a command to turn on low beams; when the rainfall reaches the level of moderate rain or above, output a prompt to turn on fog lights. In low-light conditions at night, if there is no rain or light rain and no vehicles ahead, output a command to turn on high beams; if there are vehicles ahead, output a command to switch to low beams; output a command to turn on high beams after the vehicles have moved away. In moderate or heavy rain, regardless of whether there are vehicles ahead, output a command to keep low beams and output a command to adjust the windshield wiper speed. In heavy rain, output a command to keep low beams and output a fog light activation reminder. In extremely dark environments, if there is no rain or light rain and there are no vehicles ahead, output a command to turn on high beams; if there are vehicles ahead, output a command to switch to low beams; output a command to turn on high beams after the vehicles have moved away; if the rainfall reaches the level of moderate rain or above, output a command to keep low beams.

[0026] Furthermore, it also includes: Based on the rainfall level, output wiper speed adjustment commands, where... When there is no rain, output a command to disable windshield wipers; When in light rain, output a command to adjust the wiper interval by one level. When in moderate rain, output a two-level intermittent wiper adjustment command; When in heavy rain, output a command to adjust the wiper speed to low. When in heavy rain, output a command to adjust the windshield wiper speed to high.

[0027] Furthermore, the preprocessing method includes: Convert consecutive frame images of the road ahead of the vehicle from RGB format to single-luminance images; The single-brightness image is subjected to Gaussian filtering to obtain the filtered single-brightness image; The filtered single-brightness image is subjected to ROI delineation processing to obtain the ROI region image.

[0028] The following description, using a preferred embodiment, illustrates the content involved in the above embodiments: Step 1, System Initialization: After the vehicle is powered on, the system automatically starts the initialization process. The forward-facing vehicle camera starts simultaneously and completes a self-test, outputting the first frame of RGB raw image. If the self-test fails, the system outputs a clear fault message through the instrument panel and automatically switches to manual headlight control mode to ensure basic lighting needs. The preprocessing module, discrimination module, and decision module load preset parameters respectively, and the actuator completes the reset operation (by default, both low beam and high beam are off). The system enters standby mode. After the camera frame rate stabilizes at 25fps and continuously outputs images, the real-time detection process is started.

[0029] Step 2, Image Preprocessing: The forward-looking vehicle camera captures images of the road in front of the vehicle frame by frame, outputs RGB format image data and transmits it to the preprocessing module. The preprocessing unit first converts the RGB image to YUV422 format, extracts the Y luminance channel, and uses a 3×3 kernel Gaussian filter algorithm to eliminate image noise and avoid noise interference with subsequent detection accuracy. Then, it delineates the effective detection ROI region, removes the upper 1 / 3 of the sky area and 15% of the non-road areas on the left and right edges, retains the 70% of the core road area in the middle, and outputs the ROI region luminance image to provide accurate data support for subsequent detection. The conversion method of RGB image to YUV422 format is: Y = (299R + 587G + 114B) / 1000, and the luminance value range of the Y luminance channel is 0~255.

[0030] Step 3, Ambient Light Intensity Detection: Based on the preprocessed ROI area brightness image, first calculate the weighted average brightness Y_avg, and at the same time calculate the brightness standard deviation to assist in judging the uniformity of ambient light brightness; use a time filtering algorithm to smooth the Y_avg of 10 consecutive frames to obtain the filtered smooth and uniform brightness Yf, effectively avoiding misjudgments caused by instantaneous light mutations such as tree shadows sweeping by or tunnel entrance and exit switching; compare the filtered Yf with a preset threshold to divide into four ambient light levels, specifically: when Y_avg > 180, it is strong light; when 100 < Y_avg ≤ 180, it is weak light; when 30 < Y_avg ≤ 100, it is dim at night; when Y_avg ≤ 30, it is extremely dark, and transmit the ambient light level signal to the decision-making module in real time. The brightness standard deviation is directly related to the subsequent ambient light level judgment. When the brightness standard deviation is small, it means that the ambient light is uniform and stable, and the ambient light level is directly divided according to the average brightness; when the brightness standard deviation exceeds the preset threshold, it is determined that there are non-uniform light scenarios such as local strong light, glare, and sudden light and dark changes, correct the average brightness judgment result, adjust the ambient light level division threshold, and delay the light switching response to suppress frequent mis-switching of high and low beams and control jitter, and improve the stability of light control under complex lighting. Specifically, when correcting the average brightness judgment result and adjusting the ambient light level division threshold, complete the basic ambient light level judgment in combination with the filtered average brightness Yf, and at the same time dynamically correct the ambient light division threshold according to the brightness standard deviation σ: when σ < 18, the light is uniform, and use the benchmark thresholds 30, 100, and 180 used above; when 18 ≤ σ < 32, there is slight light unevenness, and the thresholds are slightly increased to 38, 108, and 188; when 32 ≤ σ < 50, there are obvious medium light and dark differences and reflection interference, and the thresholds are adjusted to 45, 115, and 195 to offset the brightness overestimation caused by local strong light and rain reflection; when σ ≥ 50, it is an extreme glare and strong reflection condition, and the thresholds are adjusted to 50, 120, and 200; Among them, when calculating the weighted average brightness, the weight of the road surface area is set to 0.8, and the weight of the area near the road surface is set to 0.2; the preset threshold of the brightness standard deviation is 50.

[0031] Step 4, Rainfall level discrimination: This step is executed in parallel with the ambient light intensity detection, both based on the preprocessed ROI region image. First, use the Sobel operator (horizontal + vertical) to calculate the edge gradient energy of the ROI region, use a high-pass filter with a cut-off frequency of 10 Hz to extract the high-frequency texture components in the region, and count the proportion of pixels with a brightness greater than 220, which is the glare proportion. Normalize the three features of edge gradient energy, high-frequency texture components, and glare proportion to the range of 0 to 1 respectively, and use a weighted fusion algorithm to calculate the rainfall quantization index RIf. Perform a moving average filter on the RIf of 8 consecutive frames to obtain the average filtered rainfall quantization index RI. After excluding interference factors such as road splash, insect corpses attachment, and temporary strong light, compare it with the preset threshold to divide into five rainfall levels, specifically: no rain: RI ∈ [0, 0.2], light rain: RI ∈ (0.2, 0.4], moderate rain: RI ∈ (0.4, 0.6], heavy rain: RI ∈ (0.6, 0.8], heavy rainstorm: RI ∈ (0.8, 1.0]. The system can automatically distinguish non-rainwater interference such as fog, haze, and dirty glass, and only transmit the effective rainfall level signal to the decision-making module; Among them, the weights for calculating the rainfall quantization index using the weighted fusion algorithm are set as: edge energy 0.3, high-frequency energy 0.4, and glare proportion 0.3.

[0032] Step 5, High and low beam joint decision-making and execution: The decision-making module simultaneously receives the ambient light level, rainfall level, and the detection result of the vehicle ahead. Execute hierarchical decision-making according to the preset logic and output the corresponding high and low beam control instructions. The detection result of the vehicle ahead is completed by the front-mounted vehicle camera through the target recognition algorithm, which can accurately identify oncoming vehicle lights and the taillights of the vehicle ahead, and the recognition distance range is 50 - 200 m. The specific decision-making logic is as follows: (1) When Y_avg > 180 in a strong light environment: Regardless of the current rainfall level and whether there is a vehicle ahead, the decision outputs an instruction to turn off the high beam; if the light intensity is close to the threshold range of 100 - 180, that is, the evening transition stage, output an instruction to turn on the low beam, and turn off the low beam in other scenarios to avoid visual interference caused by lights in a strong light environment.

[0033] (2) When 100 < Y_avg ≤ 180 in a weak light environment: It is prohibited to turn on the high beam. Regardless of the current rainfall level and whether there is a vehicle ahead, the decision outputs an instruction to "turn on the low beam"; if the rainfall reaches the moderate rain level or above, synchronously link the instrument to prompt the driver to turn on the fog lamp to improve visibility in a complex environment.

[0034] (3) When 30 < Y_avg ≤ 100 in the night dim environment: If it is a rainless or light rain weather and there is no vehicle ahead, the decision outputs the "turn on high beam" command; if it is a rainless or light rain weather and there is a vehicle ahead, the decision outputs the "switch to low beam" command, and after the vehicle has left (the state of no vehicle ahead lasts for 3 seconds), it automatically switches back to high beam; if it is a moderate rain or heavy rain weather, regardless of whether there is a vehicle ahead, the decision outputs the "keep low beam" command, disables the high beam, and simultaneously activates the wiper speed regulation (medium rain corresponds to the medium gear of the wiper, heavy rain corresponds to the high gear of the wiper); if it is a rainstorm weather, the decision outputs the "keep low beam" command, disables the high beam, and synchronously activates the instrument to prompt the driver to turn on the fog lamp and reduce the driving speed to ensure driving safety.

[0035] (4) When Y_avg ≤ 30 in the extremely dark environment: If it is a rainless or light rain weather and there is no vehicle ahead, the decision outputs the "turn on high beam" command; if it is a rainless or light rain weather and there is a vehicle ahead, the decision outputs the "switch to low beam" command, and after the vehicle has left (the state of no vehicle ahead lasts for 2 seconds), it automatically switches back to high beam; if the rainfall reaches medium rain or above, the decision outputs the "keep low beam" command, disables the high beam, and synchronously activates the fog lamp and the instrument's rainy weather warning to remind the driver to drive carefully.

[0036] (5) When in a rainless environment (RI ∈ [0, 0.2]), regardless of the strength of the external environment, the wiper is prohibited from wiping. When in a light rain environment (RI ∈ (0.2, 0.4]), regardless of the strength of the external environment, the wiper is in the intermittent first gear; when in a medium rain environment (RI ∈ (0.4, 0.6]), regardless of the strength of the external environment, the wiper is in the intermittent second gear; when in a heavy rain environment (RI ∈ (0.6, 0.8]), regardless of the strength of the external environment, the wiper is in the low speed gear; when in a rainstorm environment (RI ∈ (0.8, 1.0]), regardless of the strength of the external environment, the wiper is in the high speed gear.

[0037] The decision-making module transmits the above control commands to the BDCU lighting control module, and the BDCU drives the LED high and low beam switching relay to complete the high and low beam mode switching. The switching response time ≤ 100ms to avoid the light jitter caused by frequent switching; the actuator feeds back the switching state to the decision-making module in real time to form a closed-loop control; if the switching fails, the instrument immediately outputs the prompt information of "light failure, please check", and the system automatically switches to the manual lighting control mode to ensure basic lighting.

[0038] Step Six: System Calibration and Anomaly Handling: All thresholds (ambient light threshold, rainfall quantification index threshold), weights (rainfall feature fusion weights), and time parameters (vehicle departure waiting time, number of filtered frames) of this system can be specifically calibrated according to the specific model, windshield size, and camera installation position of the new energy commercial vehicle to ensure detection accuracy and control adaptability. When the system detects camera malfunction (no image output, severely blurred image), discrimination module malfunction (abnormal ambient light / rainfall detection, such as continuous output of the same level), or actuator malfunction (failure to switch between high and low beams), the system automatically switches to manual headlight control mode and outputs corresponding fault prompts through the instrument panel, while retaining the basic low beam on function to avoid safety hazards caused by driving in the dark at night.

[0039] Example 2: This example provides a commercial vehicle lighting control system based on visual fusion perception, including: The acquisition module is used to acquire continuous frames of images of the road ahead of the vehicle and the detection results of the vehicle ahead; The preprocessing module is used to preprocess the continuous frame images of the road in front of the vehicle to obtain ROI region images; The discrimination module is used to detect ambient light intensity and discriminate rainfall level based on the ROI region image, and determine the ambient light level and rainfall level. The decision-making module is used to perform hierarchical decision-making based on the detection results of vehicles ahead and the determined ambient light level and rainfall level, and output the corresponding lighting control commands.

[0040] The specific functions of each module described above are explained in the relevant content of the method in Embodiment 1, and will not be repeated here.

[0041] The following description, using a preferred embodiment, illustrates the content involved in the above embodiments: like Figures 2 to 4 As shown, the system includes a forward-facing vehicle camera, a preprocessing module, a discrimination module, a decision-making module, an execution output module, an auxiliary linkage module, a body domain controller (BDCU), instrument cluster, windshield wipers, fog lights, and a vehicle power supply. The forward-facing vehicle camera serves as the core of the system's perception input. The preprocessing, discrimination, and decision-making modules are integrated into the same controller. The execution output module is centered around the headlight actuator. The auxiliary linkage module is associated with the windshield wipers, fog lights, and instrument cluster. The vehicle power supply provides a stable 24V power supply to all components of the system, ensuring its normal operation.

[0042] The forward-facing vehicle camera uses an automotive-grade CMOS camera with a resolution of 1920×1080 and a stable frame rate of 25fps. It is installed below the rearview mirror inside the vehicle, with the lens facing forward and a 120° field of view, which can be precisely adapted to the windshield layout space of new energy commercial vehicles. The camera collects images of the road in front of the vehicle and serves as a common data source for ambient light detection, rainfall determination, and forward vehicle target detection, realizing multi-purpose reuse of a single device.

[0043] The discrimination module includes two parallel sub-modules: an ambient light detection sub-module and a rainfall level discrimination sub-module. Both sub-modules establish signal linkage with the preprocessing module and share the preprocessed image data. The ambient light detection sub-module is used to detect the ambient light intensity and output the corresponding level signal, while the rainfall level discrimination sub-module is used to determine the rainfall amount and output the corresponding level signal.

[0044] The execution output module establishes a bidirectional signal connection with the decision module. Its core is the headlight and wiper actuator, which can receive high / low beam / wiper control commands from the decision module, drive the headlights to accurately switch between high and low beam modes, and drive the wipers to switch gears. At the same time, it feeds back the execution status to the decision module in real time, forming a closed-loop control to ensure that the control commands are executed in place. The auxiliary linkage module is linked with the decision module, receives ambient light level and rainfall level signals, and synchronously outputs auxiliary control commands to realize functions such as wiper speed adjustment, fog light activation reminder, and instrument fault warning, thereby improving the overall adaptability of the system.

[0045] The vehicle domain controller (BDCU) is located inside the cab trim panel. The instrument panel is located in front of the driver's seat on the dashboard. The forward-facing vehicle camera is fixedly installed on the glass below the interior rearview mirror. The headlight actuator is connected to the left and right front headlights respectively. The left and right front headlights are symmetrically arranged on the left and right front sides of the cab. The windshield wipers and fog lights are installed according to the standard layout for commercial vehicles to ensure that the layout of each component is reasonable and the operation is reliable.

[0046] Example 3: This example provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of Examples 1.

[0047] Example 4: This example provides a computer device, including: Memory, used to store computer programs / instructions; A processor for executing the computer program / instructions to implement the steps of the method described in any of Embodiment 1.

[0048] Example 5: This example provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method described in any of Examples 1.

[0049] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

[0050] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0051] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0052] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0053] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0054] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure and not to limit its protection scope. Although this disclosure has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading this disclosure, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the pending claims.

Claims

1. A method for controlling the lighting of commercial vehicles based on visual fusion perception, characterized in that, include: Acquire consecutive frames of images of the road ahead of the vehicle and the detection results of the vehicle ahead; The continuous frame images of the road ahead of the vehicle are preprocessed to obtain ROI region images; Based on the ROI region image, ambient light intensity is detected and rainfall level is determined to identify the ambient light level and rainfall level. Based on the detection results of vehicles ahead and the determined ambient light and rainfall levels, the system executes hierarchical decisions based on preset logic and outputs corresponding lighting control commands.

2. The commercial vehicle lighting control method based on visual fusion perception according to claim 1, characterized in that, The ambient light intensity detection method includes: Calculate the weighted average brightness and brightness standard deviation based on the ROI region image; A time-based filtering algorithm is used to smooth the weighted average brightness of consecutive frames, resulting in a smooth and uniform brightness after filtering. When the standard deviation of brightness does not exceed the preset threshold, the ambient light level is determined based on the smooth and uniform brightness; when the standard deviation of brightness exceeds the preset threshold, the threshold for dividing the smooth and uniform brightness and the ambient light level is corrected, and the ambient light level is determined based on the corrected parameters. The ambient light levels include strong light, weak light, dim light at night, and extremely dark.

3. The commercial vehicle lighting control method based on visual fusion perception according to claim 2, characterized in that, The rainfall level determination method includes: Based on the brightness image of the ROI region, the edge gradient energy, high-frequency texture component, and glare ratio are determined. After normalizing the edge gradient energy, high-frequency texture components, and glare proportion to the target interval, a weighted fusion algorithm is used to calculate the rainfall quantification index. The rainfall quantization index within consecutive frames is filtered by a moving average filter to obtain the filtered rainfall quantization index. The rainfall level is determined based on the filtered rainfall quantization index; The rainfall levels include no rain, light rain, moderate rain, heavy rain, and torrential rain.

4. The commercial vehicle lighting control method based on visual fusion perception according to claim 3, characterized in that, Based on the detection results of vehicles ahead and the determined ambient light and rainfall levels, a hierarchical decision-making process is executed based on preset logic, outputting corresponding lighting control commands, including: When in a bright light environment, regardless of the current rainfall level or whether there are vehicles ahead, output a command to turn off high beams; When in low light conditions, regardless of the current rainfall level or whether there are vehicles ahead, output a command to turn on low beams; when the rainfall reaches the level of moderate rain or above, output a prompt to turn on fog lights. In low-light conditions at night, if there is no rain or light rain and no vehicles ahead, output a command to turn on high beams; if there are vehicles ahead, output a command to switch to low beams; output a command to turn on high beams after the vehicles have moved away. In moderate or heavy rain, regardless of whether there are vehicles ahead, output a command to keep low beams and output a command to adjust the windshield wiper speed. In heavy rain, output a command to keep low beams and output a fog light activation reminder. In extremely dark environments, if there is no rain or light rain and there are no vehicles ahead, output a command to turn on high beams; if there are vehicles ahead, output a command to switch to low beams; output a command to turn on high beams after the vehicles have moved away; if the rainfall reaches the level of moderate rain or above, output a command to keep low beams.

5. The commercial vehicle lighting control method based on visual fusion perception according to claim 4, characterized in that, Also includes: Based on the rainfall level, output wiper speed adjustment commands, where... When there is no rain, output a command to disable windshield wipers; When in light rain, output a command to adjust the wiper interval by one level. When in moderate rain, output a two-level intermittent wiper adjustment command; When in heavy rain, output a command to adjust the wiper speed to low. When in heavy rain, output a command to adjust the windshield wiper speed to high.

6. The commercial vehicle lighting control method based on visual fusion perception according to claim 1, characterized in that, The preprocessing method includes: Convert consecutive frame images of the road ahead of the vehicle from RGB format to single-luminance images; The single-brightness image is subjected to Gaussian filtering to obtain the filtered single-brightness image; The filtered single-brightness image is subjected to ROI delineation processing to obtain the ROI region image.

7. A commercial vehicle lighting control system based on visual fusion perception, characterized in that, include: The acquisition module is used to acquire continuous frames of images of the road ahead of the vehicle and the detection results of the vehicle ahead; The preprocessing module is used to preprocess the continuous frame images of the road in front of the vehicle to obtain ROI region images; The discrimination module is used to detect ambient light intensity and discriminate rainfall level based on the ROI region image, and determine the ambient light level and rainfall level. The decision-making module is used to perform hierarchical decision-making based on the detection results of vehicles ahead and the determined ambient light level and rainfall level, and output the corresponding lighting control commands.

8. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-6.

9. A computer device, characterized in that, include: Memory, used to store computer programs / instructions; A processor for executing the computer program / instructions to implement the steps of the method according to any one of claims 1-6.

10. A computer program product comprising a computer program / instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1-6.

Images