Control system and control method of self-adaptive high beam and computer equipment

Abstract

The invention discloses a self-adaptive high beam control system, a control method and computer equipment. The self-adaptive high beam control system comprises a sensing module used for obtaining sensing data, and the sensing data comprises sensing environment data, target data and vehicle driving data; the control module is used for performing data processing, adjusting parameter optimization and decision output according to the sensing data; the execution module is used for dynamically adjusting the high beam according to the light control instruction output by the control module; the power module is used for supplying power to the sensing module, the control module and the execution module. The light can be adjusted in real time according to road conditions and target conditions, and the response speed is high.

Description

Technical Field

[0001] This invention relates to the field of automotive lighting technology, and in particular to a control system, control method, and computer equipment for adaptive high beam headlights. Background Technology

[0002] ADB (Adaptive Driving Beam) is an intelligent high-beam control system that adapts its high-beam pattern to road conditions. It transforms a single high-beam beam into a multi-zone high-beam beam using specialized optical modules and electronic control. When vehicles, pedestrians, or other targets appear on the road, the control system, composed of sensors (cameras) and drive circuits, dims or closes certain high-beam zones to avoid glare while ensuring clear high-beam illumination. The ADB system uses camera signals to determine the position and distance of oncoming vehicles and automatically adjusts the illumination area, dimming or closing the lights in areas illuminating oncoming vehicles.

[0003] Existing adaptive high beam control methods have the following drawbacks: (1) The parameters of the existing ADB control algorithm are mostly fixed values ​​or need to be manually calibrated. They cannot be dynamically adjusted according to real-time road conditions (such as multiple target intersections and vehicle speed changes), which easily leads to the phenomenon of "response lag" or "response over-response".

[0004] (2) When there are multiple targets on the road at the same time, such as oncoming vehicles, vehicles in the same direction, and pedestrians on the roadside, the existing traditional ADB control algorithm is difficult to take into account the anti-glare requirements of all targets, and is prone to problems such as glare of some targets or insufficient field of vision of the target itself (e.g., only blocking the area of ​​oncoming vehicles and ignoring the light intensity control near pedestrians).

[0005] (3) The existing ADB system has a slow response speed. When facing high-speed driving (such as vehicle speed > 100km / h) or fast-moving targets (such as pedestrians crossing the road), the adjustment command output is delayed and cannot avoid glare in time.

[0006] (4) Existing ADB control algorithms mostly adopt the "target occlusion priority" strategy (such as prioritizing the anti-glare of oncoming vehicles), which easily sacrifices the driver's effective field of vision (such as excessive occlusion leading to insufficient road lighting) and does not form a global optimal solution. Summary of the Invention

[0007] The technical problem to be solved by this invention is that existing ADB control algorithms have problems such as poor response and poor control of anti-glare requirements. This invention provides an adaptive high beam control system, control method, and computer equipment, which can improve the shortcomings of the existing technology.

[0008] The technical solution adopted by this invention to solve its technical problem is: an adaptive high beam control system, comprising: a sensing module for acquiring sensing data, the sensing data including sensing environment data, target data, and vehicle driving data; a control module for processing data, optimizing adjustment parameters, and outputting decisions based on the sensing data; an execution module for dynamically adjusting the high beam according to the lighting control commands output by the control module; and a power supply module for supplying power to the sensing module, control module, and execution module.

[0009] Optionally, the control module includes: The main control unit is used to coordinate the data interaction between the various units within the control module; The data processing unit is used to perform filtering, coordinate transformation, and target classification on the perceived data, and output the target parameter matrix and driving status parameters in the headlight coordinate system. The parameter optimization unit is used to output the optimal adjustment parameters based on the target parameter matrix and the driving state parameters using an optimization algorithm. The decision output unit is used to convert the optimal adjustment parameters into lighting control commands.

[0010] Optionally, the execution module includes: LED matrix headlights are used for lighting displays; The LED driving unit is used to receive the lighting control command and drive the LED matrix headlights to display according to the lighting control command.

[0011] The present invention also provides a control method for an adaptive high beam control system, comprising the following steps: S1. Acquire sensing data through the sensing module; S2. The control module processes the sensed data, optimizes parameters, and outputs decisions. S3. The execution module dynamically adjusts the high beams according to the lighting control commands output by the control module.

[0012] Optionally, the perceived data includes: ambient light intensity L, and the pixel coordinates of the target. The distance S between the target and the vehicle, and the horizontal angular velocity of the target. Bicycle speed ; The control module performs data processing on the sensed data, including: The pixel coordinates of the target Convert to headlight coordinate system ; The identified targets are filtered, invalid targets are removed, and valid targets are retained. The target types of the valid targets are then categorized. Mark; The ambient light intensity L, the distance S between the target and the vehicle, and the horizontal angular velocity of the target are given. Bicycle speed Headlight coordinate system coordinates and target type Normalization is performed separately to form the input parameter matrix. .

[0013] Optionally, the control module optimizes the adjustment parameters by including: The adjustment parameters of the high beam are defined as a particle swarm, with a particle dimension of D=3×N, where N represents the number of effective targets and D represents the particle dimension. Define particles , ,in, This represents the horizontal obstruction angle of the high beams corresponding to the kth valid target, in degrees, with a value range of [value missing]. ; This represents the vertical obstruction angle of the high beams corresponding to the kth valid target, in degrees, with a value range of [value missing]. ; This represents the light intensity attenuation coefficient of the region where the kth effective target is located, and its value ranges from [0,1]. Define a fitness function F to evaluate the quality of particles. The expression for the fitness function is: ,in, , , Indicates the weighting coefficient. Indicates the visual field evaluation index, Indicates the anti-glare evaluation index, This indicates the smoothness index of the adjustment; Initialize the particle population, update the velocity and position of each particle, calculate the fitness value of each updated particle and the fitness value of the entire population, and denote the position of the particle with the highest fitness value as the optimal individual. The position of the population with the highest fitness value is recorded as the global optimum. If the updated velocity and position of the particle exceed the constraint range, the force is sheared to the constraint boundary; iteration stops when the number of iterations reaches the iteration termination condition, and the current optimal value is output. As the optimal adjustment parameter.

[0014] Optionally, the decision output process of the control module includes: The output optimal adjustment parameters are converted into lighting control commands; the lighting control commands include: The light intensity control command converts the light intensity attenuation coefficient corresponding to each effective target into a PWM wave drive signal for the corresponding LED bead. Multi-target coordination instruction, which means that when there are multiple valid targets, lighting resources are allocated according to the priority of target type; After receiving the lighting control command, the high beam configures the parameters of the LED driver circuit to achieve dynamic adjustment of the lighting.

[0015] Optionally, the control method further includes: The adjustment effect of high beams is implemented through closed-loop feedback, that is, The actual light intensity of the target area after adjustment, the degree of overlap between the occluded area and the target, and the lighting coverage of the non-target area are collected. If the actual light intensity of the target area exceeds the target glare threshold, it is marked as under-adjusted, and its weight is increased during optimization in the next frame. ; If the lighting coverage of non-target areas is less than 70%, it is marked as excessive occlusion, and its weight is increased during optimization in the next frame. ; If the overlap between the occlusion area and the target is less than 95%, then adjust the initialization range of the particles.

[0016] Optional, target filtering includes: Based on the size range of valid targets, a dynamic size threshold is set. If the size of the identified target exceeds the dynamic size threshold, it is judged as an erroneous target and is removed.

[0017] The present invention also provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of a control method for an adaptive high beam control system.

[0018] The beneficial effects of this invention are: This invention combines a parameter optimization algorithm with an adaptive high-beam system, enabling real-time adjustment of the headlights based on road conditions with a fast response time. When multiple targets are present, the optimization algorithm can meet the anti-glare requirements of all targets. It also responds promptly in high-speed driving or when targets are moving rapidly. Attached Figure Description

[0019] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0020] Figure 1 This is an architecture diagram of the adaptive high beam control system of the present invention.

[0021] Figure 2 This is an architecture diagram of the control module of the present invention.

[0022] Figure 3 This is an architecture diagram of the execution module of the present invention.

[0023] Figure 4 This is a flowchart of the control method of the present invention. Detailed Implementation

[0024] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0025] Example 1 like Figures 1 to 3 As shown, the adaptive high beam control system of this embodiment includes: a sensing module, a control module, an execution module, and a power supply module. The sensing module is used to acquire sensing data, including environmental data, target data, and vehicle driving data. The control module is used to process the sensing data, optimize adjustment parameters, and output decisions. The execution module is used to dynamically adjust the high beam according to the lighting control commands output by the control module. The power supply module is used to supply power to the sensing module, control module, and execution module.

[0026] In this embodiment, the perception module includes a front-facing camera, environmental sensors (including light intensity sensors, rain sensors, etc.), vehicle speed sensors, etc. The main function of the perception module is to provide basic data for the system and collect various data. For example, the front-facing camera, installed in the rearview mirror position inside the windshield, is used to identify targets on the road ahead (including oncoming vehicles, vehicles traveling in the same direction, pedestrians, billboards), and outputs data such as the target's coordinates, angular velocity, and distance. The vehicle speed sensor is used to collect the real-time speed of the vehicle. The environmental sensors are used to collect data such as ambient light intensity. For example, the perception module communicates with the control module via a CAN or CANFD bus, and the control module communicates with the execution module via a UART or CAN bus. The power module supplies power to the various modules of the system, converting the vehicle's low-voltage battery to the voltage required by each module (e.g., 5V, 3.3V, etc.). The power module has overvoltage and overcurrent protection functions.

[0027] In this embodiment, the control module includes a main control unit, a data processing unit, a parameter optimization unit, and a decision output unit. The main control unit coordinates the data interaction between the various units within the control module. The data processing unit performs filtering, coordinate transformation, and target classification on the perceived data, and outputs the target parameter matrix and driving state parameters in the headlight coordinate system. The parameter optimization unit uses an optimization algorithm to output the optimal adjustment parameters based on the target parameter matrix and driving state parameters. The decision output unit converts the optimal adjustment parameters into lighting control commands.

[0028] Specifically, the main control unit uses an MCU with multi-threaded processing capabilities to coordinate data interaction between various modules. The data processing module denoises the perceived data, converts pixel coordinates to headlight coordinates, distinguishes target types (vehicles, pedestrians, or billboards), and outputs the target parameter matrix and driving status parameters in the headlight coordinate system. The parameter optimization unit is the core computing unit, which uses optimization algorithms to solve for the optimal adjustment parameters (e.g., light intensity distribution, occlusion area, etc.) based on the processed data. The decision output unit converts the optimal adjustment parameters output by the parameter optimization unit into standardized lighting control commands (e.g., PWM signals, UART signals, etc.) and sends them to the execution module.

[0029] In this embodiment, the execution module includes an LED matrix headlight and an LED driver unit. The LED matrix headlight is used for lighting display. The LED driver unit receives lighting control commands and drives the LED matrix headlights to display according to the commands. For example, there are two LED matrix headlights, left and right, each containing more than 200 independently controllable LED beads, supporting "zoned shading" and "gradual light intensity adjustment (0-100%)", with each LED bead having an independent driving channel. The LED driver module receives lighting control commands and drives the LED beads to perform switching actions and light intensity adjustment actions, with a response delay ≤20ms.

[0030] Example 2 like Figure 4 As shown, the control method of the adaptive high beam control system in this embodiment includes the following steps: S1, acquiring sensing data through a sensing module; S2, processing the sensing data, optimizing adjustment parameters, and outputting a decision through a control module; S3, dynamically adjusting the high beam according to the lighting control command output by the control module through an execution module.

[0031] Specifically, the perception data includes: ambient light intensity L, and the pixel coordinates of the target. The distance S between the target and the vehicle, and the horizontal angular velocity of the target. Bicycle speed The control module processes the perceived data, including: converting the target's pixel coordinates... Convert to headlight coordinate system Let i = 1, 2, ..., n, where n represents the total number of pixels; the identified targets are filtered, invalid targets are removed, and valid targets are retained, and the target type of the valid targets is classified. Mark the ambient light intensity L, the distance S between the target and the vehicle, and the horizontal angular velocity of the target. Bicycle speed Headlight coordinate system coordinates and target type Normalization is performed separately to form the input parameter matrix. .

[0032] For example, the conversion between pixel coordinates and headlight coordinate system coordinates can be achieved using existing methods. Target selection includes: setting a dynamic size threshold based on the size range of valid targets; if the size of the identified target exceeds the dynamic size threshold, it is judged as an incorrect target and removed. Valid targets include vehicles, pedestrians, and billboards. The raw images captured by the camera may contain both valid targets and incorrect targets (such as distant trees, roadside gravel, birds in the air, etc.). Based on the typical size range of valid targets (vehicles, pedestrians, billboards), a dynamic size threshold is set (which can be adjusted according to the driving scene), and targets exceeding the threshold are removed. For example: the height threshold for pedestrians is 1.2-2.2m, and the width threshold is 0.4-0.8m; the length threshold for small vehicles is 3.5-5.5m, and the width threshold is 1.6-2.2m; the size threshold for billboards is 0.5×0.3m (minimum) - 5×3m (maximum). Targets exceeding the threshold range (such as distant trees, roadside gravel, birds in the air) are directly judged as misidentified targets and removed. Types of effective objectives (j=1, 2, 3, 4) can be labeled as 0x1=oncoming vehicle, 0x2=same-direction vehicle, 0x3=pedestrian, 0x4=billboard.

[0033] The control module optimizes adjustment parameters by defining the high beam adjustment parameters as a particle swarm, with a particle dimension of D = 3 × N, where N represents the number of effective targets and D represents the particle dimension. (Particle definition follows.) , ,in, This represents the horizontal obstruction angle of the high beams corresponding to the kth valid target, in degrees, with a value range of [value missing]. ; This represents the vertical obstruction angle of the high beams corresponding to the kth valid target, in degrees, with a value range of [value missing]. ; Let represent the light intensity attenuation coefficient of the region where the k-th effective target is located, with a value range of [0,1], where 0 = complete occlusion and 1 = no attenuation. Define a fitness function F to evaluate the quality of particles; the expression for the fitness function is: ,in, , , Indicates the weighting coefficient. Indicates the visual field evaluation index, Indicates the anti-glare evaluation index, This represents the smoothness index. The fitness function is used to evaluate the "quality" of particles, with the core being the balance between "driver's visibility" and "anti-glare." Among these, = Effective lighting area / Maximum lighting area. The effective lighting area represents the area of ​​the road that is not shaded and is covered. The larger this value is, the better. =∑(1-glare intensity_j), where “glare intensity_j” represents the actual light intensity at the target location / glare threshold. The glare threshold can be obtained through calibration, and the larger the value of this index, the better. = |Current particle parameters - previous frame optimal parameters|, where "||" indicates taking the absolute value, and the smaller the value of this index, the better.

[0034] After defining the particles and fitness function, the optimization iteration can begin. Initialize the particle population, which contains M particles, with each particle's parameters randomly assigned within predefined constraints. Update the velocity and position of each particle using the following formula: The position update formula is: Where m = 1, 2, ..., M; t represents the iteration number. Let m represent the velocity of the m-th particle in the t-th iteration. This represents the position of the m-th particle in the t-th iteration. This represents the inertia weight (which can be dynamically adjusted to balance global and local searches). , The acceleration coefficients represent individual cognitive weight and social cognitive weight, respectively. , This represents a random number within the interval [0,1]. Calculate the updated fitness value of each particle and the fitness value of the entire population, and denote the position of the particle with the highest fitness value as the optimal individual. The position of the population with the highest fitness value is recorded as the global optimum. If the updated velocity and position of the particle exceed the constraints, the force is sheared to the constraint boundary. Iteration stops when the iteration count reaches the termination condition, and the current optimal value is output. As the optimal adjustment parameter.

[0035] It should be noted that each particle represents a set of high beam adjustment parameters. Each iteration updates these parameters by comparing the individual fitness value and the population fitness value after the current iteration with the results of the previous iteration, selecting the one with the higher fitness value. The iteration terminates when the iteration termination condition is met (e.g., the number of iterations reaches a preset number or the continuous change in the fitness value of the global optimum gbest is ≤0.01), and the final retained gbest is output as the final optimal adjustment parameter. This invention's adjustment parameter optimization method, based on the existing particle swarm optimization algorithm and considering the actual application scenarios and core requirements of adaptive high beam systems, has made targeted adaptations and optimizations to the existing algorithm. It primarily addresses the problems of slow convergence speed, insufficient adjustment accuracy, and susceptibility to local optima (leading to glare or insufficient illumination) in high beam adjustment of existing particle swarm optimization algorithms. Compared with the existing adaptive high beam system algorithm, the adjustment parameter optimization algorithm added in this invention is highly compatible with the core requirements of the adaptive high beam system, such as real-time adjustment, multi-objective optimization, and hardware adaptation. It has the advantages of fast convergence speed, strong adaptability of multi-objective optimization capability, low computational complexity, good hardware adaptability, and strong robustness.

[0036] In this embodiment, the decision-making output process of the control module includes converting the output optimal adjustment parameters into lighting control commands. The lighting control commands include: a light intensity control command, which converts the light intensity attenuation coefficient corresponding to each valid target into a PWM wave drive signal for the corresponding LED bead; and a multi-target coordination command, which allocates lighting resources according to the priority of target types when multiple valid targets exist. After receiving the lighting control commands, the high beam configures the parameters of the LED drive circuit to achieve dynamic lighting adjustment.

[0037] For example, light intensity control commands can adjust the drive current to transform intermediate values ​​according to a linear relationship (e.g., When the value is 0.3, PWM = 30%, thus controlling the brightness of the LED beads in the matrix headlights. When multiple valid targets exist, lighting resources are allocated according to the priority of target type (pedestrians > oncoming vehicles > same-direction vehicles > billboards), and the adjustment parameters are adjusted accordingly. The LED matrix is ​​mapped one-to-one to ensure that the shading area of ​​each effective target is non-overlapping and without omission, while preserving the maximum illumination range that distinguishes non-targets (such as the edges of the road and blind spots behind vehicles in front). After receiving the light control command, the LED driver unit completes the parameter configuration of the drive circuit within a specified time. The drive circuit outputs the set PWM current to the LED beads to achieve brightness adjustment and shading of the corresponding LED area.

[0038] The control method of the present invention further includes: providing closed-loop feedback on the adjustment effect of the high beam, that is, collecting the actual light intensity of the target area after adjustment, the overlap between the occluded area and the target, and the illumination coverage of the non-target area; if the actual light intensity of the target area exceeds the target glare threshold, it is marked as insufficient adjustment, and its weight is increased during the optimization in the next frame. If the lighting coverage of non-target areas is less than 70%, it is marked as excessive occlusion, and its weight is increased during optimization in the next frame. If the overlap between the occlusion area and the target is less than 95%, then adjust the initialization range of the particles.

[0039] After the execution module completes its actions, the front-facing camera initiates secondary recognition, collecting data on the actual light intensity of the adjusted target area, the overlap between the occluded area and the target, and the illumination coverage of non-target areas. The camera feeds this data back to the data processing unit, which compares it to preset thresholds. If the actual light intensity of the target area exceeds the target glare threshold, it is marked as under-adjusted, and its weight is increased during optimization in the next frame. If the lighting coverage of non-target areas is less than 70%, it is marked as excessive occlusion, and its weight is increased during optimization in the next frame. If the overlap between the occlusion area and the target is less than 95%, adjust the initial range of the particles (reducing the random fluctuation range of the angle parameter to ±2°) to improve occlusion accuracy. The feedback data can be used as a supplement for the next round of parameter optimization, updating the input parameter matrix as follows: This enables closed-loop control of "collection-optimization-execution-feedback-re-optimization," improving the accuracy of dynamic adaptive adjustment in complex scenarios.

[0040] Example 3 This embodiment provides a computer device, including: a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to perform the steps of the control method of Embodiment 2. This computer device can be a server, a computer, etc. Therefore, the structure of the computer device is not limited to a memory and a processor, and may also include other hardware devices, such as input devices, storage devices, etc., which can be determined according to the configuration of the computer device. This embodiment does not list them all.

[0041] In summary, the adaptive high beam control system, control method, and computer equipment of this invention combine an adjustment parameter optimization algorithm with an adaptive high beam system. The parameter optimization algorithm has a fast iterative convergence speed and a fast response speed, which can meet the masking requirements for high-speed driving and fast-moving targets, as well as the anti-glare requirements in multi-target scenarios. The particle encoding format of the parameter optimization algorithm can be flexibly expanded (such as adding dimensions such as "light color temperature adjustment" and "expansion of the number of zones") to adapt to future higher-precision LED matrix headlights (such as ≥500 LEDs) and more sensing parameters (such as radar distance data and weather sensor data).

[0042] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A control system for adaptive high beam headlights, characterized in that, include: The perception module is used to acquire perception data, which includes perception environment data, target data, and vehicle driving data. The control module is used to process data, optimize adjustment parameters, and output decisions based on the sensed data. An execution module is used to dynamically adjust the high beams according to the lighting control commands output by the control module; The power supply module is used to supply power to the sensing module, control module, and execution module.

2. The adaptive high beam control system as described in claim 1, characterized in that, The control module includes: The main control unit is used to coordinate the data interaction between the various units within the control module; The data processing unit is used to perform filtering, coordinate transformation, and target classification on the perceived data, and output the target parameter matrix and driving status parameters in the headlight coordinate system. The parameter optimization unit is used to output the optimal adjustment parameters based on the target parameter matrix and the driving state parameters using an optimization algorithm. The decision output unit is used to convert the optimal adjustment parameters into lighting control commands.

3. The adaptive high beam control system as described in claim 2, characterized in that, The execution module includes: LED matrix headlights are used for lighting displays; The LED driving unit is used to receive the lighting control command and drive the LED matrix headlights to display according to the lighting control command.

4. A control method for a control system of adaptive high beams as described in any one of claims 1-3, characterized in that, Includes the following steps: S1. Acquire sensing data through the sensing module; S2. The control module processes the sensed data, optimizes parameters, and outputs decisions. S3. The execution module dynamically adjusts the high beams according to the lighting control commands output by the control module.

5. The control method as described in claim 4, characterized in that, The sensing data includes: ambient light intensity L, and the pixel coordinates of the target. The distance S between the target and the vehicle, and the horizontal angular velocity of the target. Bicycle speed ; The control module performs data processing on the sensed data, including: The pixel coordinates of the target Convert to headlight coordinate system ; The identified targets are filtered, invalid targets are removed, and valid targets are retained. The target types of the valid targets are then categorized. Mark; The ambient light intensity L, the distance S between the target and the vehicle, and the horizontal angular velocity of the target are given. Bicycle speed Headlight coordinate system coordinates and target type Normalization is performed separately to form the input parameter matrix. .

6. The control method as described in claim 5, characterized in that, The control module optimizes the adjustment parameters, including: The adjustment parameters of the high beam are defined as a particle swarm, with a particle dimension of D=3×N, where N represents the number of effective targets and D represents the particle dimension. Define particles , ,in, This represents the horizontal obstruction angle of the high beams corresponding to the kth valid target, in degrees, with a value range of [value missing]. ; This represents the vertical obstruction angle of the high beams corresponding to the kth valid target, in degrees, with a value range of [value missing]. ; This represents the light intensity attenuation coefficient of the region where the kth effective target is located, and its value ranges from [0,1]. Define a fitness function F to evaluate the quality of particles. The expression for the fitness function is: ,in, , , Indicates the weighting coefficient. Indicates the visual field evaluation index, Indicates the anti-glare evaluation index, This indicates the smoothness index of the adjustment; Initialize the particle population, update the velocity and position of each particle, calculate the fitness value of each updated particle and the fitness value of the entire population, and denote the position of the particle with the highest fitness value as the optimal individual. The position of the population with the highest fitness value is recorded as the global optimum. If the updated velocity and position of the particle exceed the constraint range, the force is sheared to the constraint boundary; iteration stops when the number of iterations reaches the iteration termination condition, and the current optimal value is output. As the optimal adjustment parameter.

7. The control method as described in claim 6, characterized in that, The decision output process of the control module includes: The output optimal adjustment parameters are converted into lighting control commands; the lighting control commands include: The light intensity control command converts the light intensity attenuation coefficient corresponding to each effective target into a PWM wave drive signal for the corresponding LED bead. Multi-target coordination instruction, which means that when there are multiple valid targets, lighting resources are allocated according to the priority of target type; After receiving the lighting control command, the high beam configures the parameters of the LED driver circuit to achieve dynamic adjustment of the lighting.

8. The control method as described in claim 7, characterized in that, The control method further includes: The adjustment effect of high beams is implemented through closed-loop feedback, that is, The actual light intensity of the target area after adjustment, the degree of overlap between the occluded area and the target, and the lighting coverage of the non-target area are collected. If the actual light intensity of the target area exceeds the target glare threshold, it is marked as under-adjusted, and its weight is increased during optimization in the next frame. ; If the lighting coverage of non-target areas is less than 70%, it is marked as excessive occlusion, and its weight is increased during optimization in the next frame. ; If the overlap between the occlusion area and the target is less than 95%, then adjust the initialization range of the particles.

9. The control method as described in claim 5, characterized in that, Target screening includes: Based on the size range of valid targets, a dynamic size threshold is set. If the size of the identified target exceeds the dynamic size threshold, it is judged as an erroneous target and is removed.

10. A computer device, characterized in that, include: A memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the control method according to any one of claims 5 to 9.

Images