Dynamic anti-dazzling high beam control system and method based on multi-sensor fusion

Abstract

The invention discloses a dynamic anti-dazzling high beam control system and method based on multi-sensor fusion, and belongs to the technical field of automobile lighting control. The related information comprises an obstacle in front of the vehicle when the vehicle runs on the curve and a light area irradiated to the surface of the obstacle by the vehicle; the bright area is the bright area deviating to the steering side of the vehicle; and the data construction module is used for constructing an information matrix according to the related information, the information matrix comprises the vehicle, the light area and the front vehicle, and the change characteristics of the light area are obtained in the information matrix. Through multi-sensor fusion, dynamic modeling, speed correlation analysis and multi-level aperture processing, intelligent sensing of the environment in front of the vehicle and accurate control of the high beam are achieved, and a new solution is provided for intelligent driving light control.

Description

Technical Field

[0001] This invention relates to the field of automotive lighting control technology, and in particular to a dynamic anti-glare high beam control system and method based on multi-sensor fusion. Background Technology

[0002] While driving at night, the use of high beams is crucial for improving the driver's field of vision. However, improper use of high beams can cause severe glare to drivers of oncoming vehicles, drivers of vehicles in front, and pedestrians, increasing the risk of traffic accidents.

[0003] Regarding this research, application CN202411655438.3 provides a high-beam intelligent interactive control system and method. This technical solution includes: a light sensor for detecting the light intensity and duration from other vehicles affecting the vehicle; a V2X module for receiving signals from the light sensor and interacting with other vehicles; a CAN transceiver for receiving instructions from the V2X module and controlling the vehicle's high beams via the CAN bus; and a central control module for receiving instructions from the V2X module and displaying a request to turn off the high beams. This control system can intelligently control the vehicle's high beams by receiving information such as the level and duration of impact from affected vehicles.

[0004] Another application, CN202210283037.4, provides a vehicle headlight control system and method to improve high-beam glare. This technical solution includes vehicle headlights, a front light sensor, a vehicle taillight, a control unit, and a rear light sensor. The headlights, front light sensor, taillight, and rear light sensor are all electrically connected to the control unit. The front light sensor receives high-beam signals from oncoming vehicles, and the rear light sensor receives high-beam signals from vehicles behind. The control unit can send signals to a domain controller system. This technical solution controls the high-beam function by the control unit, eliminating the need for driver intervention and addressing situations where drivers forget, don't know how to use, or are unwilling to turn off high beams, thus ensuring driving safety.

[0005] However, the above-mentioned technical solutions still have shortcomings in terms of dynamic adjustment and optimization. Their algorithms may not be able to accurately identify targets or adjust beam distribution when dealing with complex road conditions (such as curves and slopes), resulting in poor anti-glare effect. Summary of the Invention

[0006] In view of the problems existing in the field of automotive lighting control technology, the present invention is proposed.

[0007] Therefore, one of the objectives of this invention is to provide a dynamic anti-glare high beam control system and method based on multi-sensor fusion. Through multi-sensor fusion, dynamic modeling, speed correlation analysis, and multi-level aperture processing, it achieves intelligent perception of the environment in front of the vehicle and precise control of the high beam, providing a new solution for intelligent driving lighting control.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution: On one hand, the present invention provides a dynamic anti-glare high beam control system based on multi-sensor fusion, comprising: The data acquisition module is used to collect relevant information in front of the vehicle, including obstacles in front of the vehicle when it is driving on a curve and the illuminated area of ​​the surface of the obstacle illuminated by the vehicle; the illuminated area is the illuminated area on the side of the vehicle turning. The data construction module is used to construct an information matrix based on the relevant information. The information matrix includes the vehicle, the illuminated area, and the vehicle in front. The module also acquires the change characteristics of the illuminated area within the information matrix. The data analysis module is used to analyze the correlation between the vehicle's driving speed and the change characteristics. The analysis method includes preset first driving speed and second driving speed. The first driving speed is the same driving speed collected, the driving speed is the same driving speed for 5 to 10 seconds, and the second driving speed is the driving speed after the first driving speed. A data fusion processing module, comprising a differentiation unit, a calculation unit, and a judgment unit; The distinguishing unit is used to divide the bright area into at least 5 layers of aperture based on the center point of the bright area, with the diameter of each layer of aperture being at least 10cm, and to mark the 5th layer of aperture as the outer aperture; and to obtain the brightness of the outer aperture; The calculation unit is used to calculate the change in brightness. When the change in brightness decreases on the side that the vehicle is turning towards, at the first or second driving speed, the unit obtains the direction corresponding to the decrease on the outer aperture and marks the corresponding direction as the monitoring direction. The judgment unit responds to the monitored location; when the brightness of the monitored location shows a decreasing trend, it turns off the vehicle's high beams; otherwise, it does not turn them off.

[0009] In a preferred embodiment of the present invention, the data construction module acquires the change characteristics of the illuminated area within the information matrix, and the acquisition method includes dynamic modeling; the dynamic modeling is to model the change of the illuminated area over time as a dynamic process, and calculate the rate of change of the illuminated area during the dynamic process. The acquisition method also includes combining the vehicle's steering angle and the obstacle's position to calculate the distribution offset of the illuminated area on the steering side, the distribution offset including the lateral offset distance between the center point of the illuminated area and the center of the obstacle.

[0010] In a preferred embodiment of the present invention, the rate of change of the illuminated area is calculated during the dynamic process, and is obtained using the sliding window method. ; in, This represents the average rate of change of the illuminated area within the window, expressed in m² / s or pixels² / frame. In the formula, Indicated at the The bright area on the side of the frame image that is turning, in pixels² or m². Indicates the first The timestamp of the frame image This represents the size of the sliding window, which is the number of consecutive frames involved in the calculation.

[0011] In a preferred embodiment of the present invention, the calculation of the rate of change of the illuminated area during the dynamic process further includes calculating it according to the following formula: ; This represents the average rate of change of the illuminated area within the window, expressed in m² / s or pixels² / frame. In the formula, Indicates the current frame index. This represents the timestamp corresponding to the current frame index. This represents the illuminated area corresponding to the current frame index.

[0012] In a preferred embodiment of the present invention, the distribution offset of the illuminated area on the turning side is calculated according to the following formula: ; in, The center point of the bright area in the image captured by the vehicle's camera needs to be mapped to the actual location of the vehicle's coordinates; This indicates the focal length of the vehicle's camera. Indicates the distance between the vehicle and the obstacle. This represents the ordinate of the center point in the image. This indicates the offset corresponding to the installation height of the vehicle's camera.

[0013] In a preferred embodiment of the present invention, the center point of the illuminated area is marked as a reference offset point according to the calculated distribution offset. During the vehicle's turning process, if the second driving speed is higher than the first driving speed, the offset of the illuminated area is obtained based on the reference offset point. When the vehicle shifts to the turning side, if the illuminated area increases, the high beam headlights of the vehicle are turned off; otherwise, they are not turned off.

[0014] In a preferred embodiment of the present invention, if the illuminated area increases when shifting towards the turning side, the reference offset point is divided into three equally sized illuminated areas—upper, middle, and lower—towards the turning side of the vehicle. If the illuminated area of ​​the upper illuminated area increases while the illuminated areas of the middle and lower illuminated areas decrease when shifting towards the turning side, the high beams of the vehicle are not turned off.

[0015] In a preferred embodiment of the present invention, the illuminated area is divided into a left illuminated area and a right illuminated area based on the reference offset point. When shifting towards the turning side, if the illuminated area of ​​the side illuminated area corresponding to the turning side decreases while the illuminated area of ​​the non-corresponding side illuminated area increases, the high beams of the vehicle are not turned off, and the high beams of the vehicle are concentrated to illuminate the direction corresponding to the non-corresponding side illuminated area.

[0016] On the other hand, the present invention provides a method for use in the dynamic anti-glare high beam control system based on multi-sensor fusion as described above, comprising the following steps: Collect relevant information about the area in front of the vehicle, including obstacles in front of the vehicle when it is driving on a curve and the illuminated area of ​​the surface of the obstacle illuminated by the vehicle; the illuminated area is the illuminated area on the side of the vehicle turning. An information matrix is ​​constructed based on the relevant information. The information matrix includes the vehicle, the illuminated area, and the vehicle in front. The change characteristics of the illuminated area are obtained within the information matrix. The correlation between the vehicle's driving speed and the changing characteristics is analyzed. The analysis method includes setting a first driving speed and a second driving speed. The first driving speed is the same driving speed collected, and the driving speed is the same driving speed for 5 to 10 seconds. The second driving speed is the driving speed after the first driving speed. The bright area is divided into at least 5 apertures based on the center point of the bright area, and the diameter of each aperture is at least 10cm. The 5th aperture is marked as the outer aperture; and the brightness of the outer aperture is obtained. The change in brightness is calculated. When the change in brightness decreases on the side that the vehicle is turning towards, at the first or second driving speed, the azimuth corresponding to the decrease is obtained on the outer aperture and the corresponding azimuth is marked as the monitoring azimuth. When the brightness in the monitored area shows a decreasing trend, the vehicle's high beams are turned off; otherwise, they are not turned off.

[0017] Beneficial effects: 1. This invention uses multiple sensors to collect information on obstacles and illuminated areas in front of the vehicle in real time. Especially when driving on curves, it can accurately identify changes in the illuminated area on the side the vehicle is turning, effectively avoiding glare from high beams to vehicles or pedestrians in front, thereby significantly reducing the risk of traffic accidents caused by glare at night or in low light conditions. 2. By combining the vehicle's steering angle and obstacle position information, the system can accurately calculate the distribution offset of the illuminated area during the steering process. Even in complex road conditions such as sharp bends and continuous curves, it can ensure the accurate execution of the anti-glare function, further improving driving safety. 3. By preset a first driving speed and a second driving speed, and analyzing the correlation between driving speed and the characteristics of changes in the illuminated area, the system can quickly respond to changes in vehicle speed, ensuring that the light status can be adjusted in a timely manner at different speeds to prevent glare. 4. The system uses dynamic modeling technology to model the change of the illuminated area over time as a dynamic process and calculates the rate of change of the illuminated area, thereby more accurately judging the risk of glare. At the same time, it combines calculation methods such as the sliding window method to ensure the accuracy and stability of the rate of change calculation. 5. The system not only monitors the overall illuminated area, but also further divides it into multiple illuminated zones for layered analysis. Through multi-condition judgment (such as changes in illuminated area, trends in brightness reduction, etc.), the system can more accurately identify glare risks and take corresponding anti-glare measures, thereby maximizing the illumination range of the high beams while ensuring the anti-glare effect. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 This is a schematic diagram of the modular structure of the dynamic anti-glare high beam control system based on multi-sensor fusion according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the method flow according to an embodiment of the present invention; The diagram is labeled as follows: 110 - Data acquisition module; 120 - Data construction module; 130 - Data analysis module; 140 - Data fusion processing module; 1401 - Differentiation unit; 1402 - Calculation unit; 1403 - Judgment unit. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0020] Because existing technologies still have shortcomings in dynamic adjustment and optimization, their algorithms may not be able to accurately identify targets or adjust beam distribution when dealing with complex road conditions (such as curves and slopes), resulting in poor anti-glare effects.

[0021] Based on this, the present invention proposes a dynamic anti-glare high beam control system and method based on multi-sensor fusion. By combining the vehicle steering angle and obstacle position, it calculates the distribution offset of the illuminated area, which can accurately judge the glare risk in complex road conditions such as curves, and improve the adaptability and reliability of the system in different driving scenarios.

[0022] The present solution will be further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0023] Reference Figures 1 to 2 As one embodiment of the present invention, this embodiment provides a dynamic anti-glare high beam control system based on multi-sensor fusion, comprising: The data acquisition module 110 is used to collect relevant information in front of the vehicle, including obstacles in front of the vehicle when it is driving on a curve and the illuminated area of ​​the vehicle's surface illuminating the obstacles; the illuminated area is the illuminated area on the side of the vehicle's turn. In this embodiment, the data acquisition module includes a sensor module; The sensor module includes a camera, radar, photosensors, and an inertial measurement unit (IMU). The camera, mounted at the front of the vehicle, captures images of the road ahead, identifying oncoming headlights, taillights of vehicles ahead, and pedestrians. It employs a high-resolution, wide-angle camera to ensure clear images are obtained under various lighting conditions. Radar includes millimeter-wave radar and lidar. Millimeter-wave radar is used to detect the distance, speed, and angle of vehicles ahead, and has the advantages of strong anti-interference ability and long detection range; lidar can provide more accurate three-dimensional environmental information, used to identify the position of obstacles and targets on the road; Photosensitive sensors, distributed at the front and sides of the vehicle, monitor the intensity and direction of ambient light in real time, providing the system with basic lighting data to help determine whether to turn on the high beams and adjust the beam intensity. An inertial measurement unit (IMU) is used to detect the vehicle's driving status, such as acceleration and angular velocity, to help the system more accurately determine the vehicle's driving direction and attitude. The data acquisition module uses sensors such as cameras, IMUs (inertial measurement units) or wheel speedometers to collect real-time information about the environment in front of the vehicle, including the location of obstacles and the area of ​​light illuminating the surface of obstacles (biased towards the steering side). Multi-sensor fusion ensures the comprehensiveness and accuracy of the data, providing a reliable basis for subsequent anti-glare decisions; It can identify obstacles in low-light conditions such as curves and nighttime, improving the system's applicability.

[0024] The data construction module 120 is used to construct an information matrix based on relevant information. The information matrix includes vehicles, illuminated areas, and vehicles ahead. The change characteristics of the illuminated area are obtained within the information matrix. The acquisition methods include dynamic modeling; dynamic modeling involves modeling the change of the illuminated area over time as a dynamic process, and calculating the rate of change of the illuminated area during the dynamic process. The acquisition method also includes combining the vehicle's steering angle (obtained via IMU or wheel speed sensor) and the position of the obstacle to calculate the distribution offset of the illuminated area on the steering side. The distribution offset includes the lateral offset distance between the center point of the illuminated area and the center of the obstacle. In this embodiment, an information matrix containing vehicles, illuminated areas, and vehicles ahead is constructed. The change of illuminated area over time is modeled as a dynamic process through dynamic modeling, and the rate of change is calculated (such as the sliding window method). The distribution offset (lateral offset distance between the center point and the center of the obstacle) is calculated in combination with the steering angle and the obstacle position. Dynamic modeling and rate of change calculation enable the system to respond quickly to dynamic adjustments in the illuminated area, improving the timeliness of anti-glare decision-making; The distribution offset calculation, combined with the steering angle, ensures accurate identification of glare risk areas in complex road conditions such as curves.

[0025] The data analysis module 130 is used to analyze the correlation between the vehicle's driving speed and the change characteristics. The analysis method includes a preset first driving speed and a preset second driving speed. The first driving speed is the same driving speed collected, and the driving speed is the same driving speed for 5 to 10 seconds. The second driving speed is the driving speed after the first driving speed. In this embodiment, a first driving speed (a stable speed of 5 to 10 seconds) and a second driving speed (the speed after acceleration) are preset, and the correlation between speed change and the characteristics of change in bright area are analyzed. Through speed correlation analysis, the system can dynamically adjust the anti-glare strategy when the vehicle accelerates or decelerates, avoiding misjudgments caused by speed changes. Furthermore, the analysis in multi-speed scenarios enhances the system's stability under different driving conditions.

[0026] The data fusion processing module 140 includes a differentiation unit 1401, a calculation unit 1402, and a judgment unit 1403. The differentiation unit 1401 is used to divide the bright area into at least 5 layers of aperture based on the center point of the bright area, each layer of aperture having a diameter of at least 10cm, and to mark the 5th layer of aperture as the outer aperture; and to obtain the brightness of the outer aperture. In this embodiment, the center point of the bright area is used as a basis to divide it into at least 5 layers of aperture (each layer with a diameter ≥ 10cm), the 5th layer is marked as the outer aperture, and the brightness of the outer aperture is obtained; This multi-level aperture division enables the system to distinguish the glare risk in different areas and prioritize the treatment of high-risk areas (such as the outer aperture). By focusing on changes in the brightness of the outer aperture, the high beams are prevented from being accidentally turned off due to fluctuations in the brightness of the central area; The calculation unit 1402 is used to calculate the change in brightness. When the change in brightness decreases on the side that is turning towards the vehicle at the first or second driving speed, the unit obtains the direction corresponding to the decrease on the outer aperture and marks the corresponding direction as the monitoring direction. In this embodiment, by analyzing the brightness change trend, the system can quickly pinpoint the location of glare risk and improve the effectiveness of anti-glare measures. Furthermore, it updates the monitoring location in real time based on changes in brightness, adapting to dynamic changes in ambient light or the position of obstacles; The judgment unit 1403 responds to the monitored direction. When the brightness of the monitored direction shows a decreasing trend, the vehicle's high beams are turned off; otherwise, they are not turned off. In this embodiment, by judging the brightness trend, the system can turn off the high beams in advance before the actual glare risk occurs, effectively protecting other road users; It will only be turned off when the brightness continues to decrease, to avoid accidental operation due to short-term fluctuations.

[0027] The rate of change of the illuminated area during the dynamic process is calculated using the sliding window method: ; in, This represents the average rate of change of the illuminated area within the window, expressed in m² / s or pixels² / frame. In the formula, Indicated at the The bright area on the side of the frame image that is turning, in pixels² or m². Indicates the first The timestamp of the frame image This indicates the size of the sliding window, which is the number of consecutive frames involved in the calculation. In this embodiment, the size of the sliding window is the number of consecutive frames involved in the calculation (e.g., ...). =10, indicating the most recent 10 frames); This formula reduces noise in single-frame data by averaging across multiple frames, thus improving the stability of the rate of change calculation. The calculation of the rate of change of the illuminated area during the dynamic process also includes calculation based on the following formula: ; This represents the average rate of change of the illuminated area within the window, expressed in m² / s or pixels² / frame. In the formula, Indicates the current frame index. This represents the timestamp corresponding to the current frame index. This represents the illuminated area corresponding to the current frame index; In this embodiment, the formula is applicable to real-time control scenarios, and the rate of change can be quickly estimated using the data from the two most recent frames. Regarding cornering, when a vehicle enters a curve, the illuminated area on the turning side increases rapidly due to the change in illumination angle. By calculating the average rate of change using a sliding window, single-frame noise (such as sudden changes in area caused by swaying leaves) can be filtered out, outputting a stable trend of change. Regarding oncoming vehicle encounters, the system needs to respond quickly when an oncoming vehicle is detected. This can be achieved by comparing the instantaneous rate of change with a threshold. >0.5m² / s), triggering the temporary shutdown of high beams; Both of the above calculation formulas are used to calculate the average rate of change of the illuminated area, but they are applicable to different scenarios or detailed calculation needs. The core connection between the two is that they both analyze the dynamic changes of the illuminated area using the sliding window method, providing a quantitative basis for anti-glare decision-making. The specific explanation is as follows: The first formula is continuous The frame image is used as a window. The difference in the illuminated area between each frame and the previous frame is calculated and divided by the time difference to obtain the instantaneous rate of change. The average rate of change is obtained by averaging all instantaneous rates of change within the window, in units of m² / s or pixels² / frame. By averaging across multiple frames, the impact of fluctuations in single-frame data is reduced, thereby improving the stability of the rate of change calculation. The second formula uses the current frame index. Tracing back from the baseline For each frame, calculate the ratio of the difference between the bright area and the timestamp, and average all ratios within the window to obtain the average rate of change. This reduces the complexity of time difference calculation by fixing a reference time (such as the first frame), making it suitable for scenarios that require fast response. If the time difference between frames is not fixed (such as when the camera frame rate fluctuates), the formula can still maintain the accuracy of the rate of change calculation through normalization. Both formulas calculate the average rate of change of the illuminated area using the sliding window method, quantifying the dynamic change of the illuminated area over time and providing data support for anti-glare decisions (such as turning off high beams). Their technical effects are complementary. The first formula, calculated through inter-frame difference, can more sensitively capture abrupt changes in the area of ​​light (such as suddenly appearing obstacles). The second formula, calculated using a fixed reference time, can more stably analyze the long-term trend of the illuminated area (such as the continuous shift when driving on a curve).

[0028] The offset of the illuminated area distribution on the turning side is calculated using the following formula: ; in, The center point of the bright area in the image captured by the vehicle's camera needs to be mapped to the actual location of the vehicle's coordinates; This indicates the focal length (in pixels, obtained through calibration) of the vehicle's camera. Indicates the distance between the vehicle and the obstacle (measured by lidar or binocular camera, unit: meters). This represents the vertical coordinate (in pixels) of the center point in the image. This indicates the offset (calibration parameter) corresponding to the installation height of the vehicle's camera. This formula calculates the actual position of the center point of the illuminated area in the vehicle coordinate system using the camera focal length, the distance between the vehicle and the obstacle, and the vertical coordinate of the image. The formula converts image coordinates into actual coordinates, eliminating the influence of camera installation angle and height, and improving the accuracy of offset calculation; The anti-glare strategy is dynamically adjusted by a reference offset point to ensure safety during high-speed driving.

[0029] Based on the calculated distribution offset, the center point of the illuminated area is marked as the reference offset point. During the vehicle's turning process, if the second driving speed is higher than the first driving speed, the offset of the illuminated area is obtained based on the reference offset point. When the vehicle shifts to the side of the turn, if the illuminated area increases, the vehicle's high beams are turned off; otherwise, they are not turned off.

[0030] When shifting towards the turning side, if the illuminated area increases, the reference offset point on the side of the vehicle's turn will be divided into three equally sized illuminated areas: the upper, middle, and lower ends. If the illuminated area of ​​the upper illuminated area increases while the illuminated areas of the middle and lower illuminated areas decrease when shifting towards the turning side, the vehicle's high beams will not be turned off.

[0031] Based on the reference offset point, the illuminated area is divided into a left illuminated area and a right illuminated area. When shifting towards the turning side, if the illuminated area of ​​the side corresponding to the turning side decreases while the illuminated area of ​​the non-corresponding side increases, the vehicle's high beams will not be turned off, and the vehicle's high beams will be concentrated to illuminate the direction corresponding to the non-corresponding side illuminated area. In summary, the reference offset point is divided into three zones towards the turning side: upper, middle, and lower. If the brightness of the upper zone increases while that of the middle and lower zones decreases, the high beams are not turned off. Alternatively, the points are divided into left and right brightness zones. If the brightness of the turning side decreases while that of the non-turning side increases, the high beams are concentrated on the non-turning side. Through multi-region analysis, the system can keep the high beams on in areas where the risk of glare is low, thus maximizing the illumination range. Concentrated illumination of the non-steering side area avoids glare, improves driver visibility, and enhances driving safety.

[0032] Based on the above, this application achieves intelligent perception of the environment in front of the vehicle and precise control of the high beams through multi-sensor fusion, dynamic modeling, speed correlation analysis and multi-level aperture processing. Its core advantages are to improve driving safety, driving comfort and system adaptability. At the same time, through refined layering and intelligent direction control, it optimizes the anti-glare effect and reduces the misoperation rate.

[0033] This embodiment, in conjunction with the aforementioned dynamic anti-glare high beam control system based on multi-sensor fusion, also proposes a working method for this system, as follows: S10: Collect relevant information in front of the vehicle, including obstacles in front of the vehicle when it is driving on a curve and the illuminated area of ​​the vehicle's surface illuminating the obstacles; the illuminated area is the illuminated area on the side of the vehicle that is turning. S20: Construct an information matrix based on relevant information. The information matrix includes vehicles, illuminated areas, and vehicles ahead. Obtain the change characteristics of the illuminated area within the information matrix. S30: Analyze the correlation between vehicle speed and change characteristics; the analysis method includes preset first speed and second speed, the first speed is the same speed collected, the second speed is the same speed for 5 to 10 seconds, and the third speed is the speed after the first speed. S40: Divide the bright area into at least 5 apertures based on the center point of the bright area, with each aperture having a diameter of at least 10cm, and mark the 5th aperture as the outer aperture; and obtain the brightness of the outer aperture; S50: Calculate the change in brightness. When the change in brightness decreases on the side that is turning towards the vehicle at the first or second driving speed, obtain the corresponding azimuth on the outer aperture and mark the corresponding azimuth as the monitoring azimuth. S60: When the brightness of the monitored area shows a decreasing trend, turn off the vehicle's high beams; otherwise, do not turn them off.

[0034] In summary, this application achieves intelligent perception of the environment in front of the vehicle and precise control of the high beams through multi-sensor fusion, dynamic modeling, speed correlation analysis, and multi-level aperture processing, providing a new solution for intelligent driving lighting control.

[0035] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A dynamic anti-glare high beam control system based on multi-sensor fusion, characterized in that, include: The data acquisition module is used to collect relevant information in front of the vehicle, including obstacles in front of the vehicle when it is driving on a curve and the illuminated area of ​​the surface of the obstacle illuminated by the vehicle; the illuminated area is the illuminated area on the side of the vehicle turning. The data construction module is used to construct an information matrix based on the relevant information. The information matrix includes the vehicle, the illuminated area, and the vehicle in front. The module also acquires the change characteristics of the illuminated area within the information matrix. The data analysis module is used to analyze the correlation between the vehicle's driving speed and the change characteristics. The analysis method includes preset first driving speed and second driving speed. The first driving speed is the same driving speed collected, the driving speed is the same driving speed for 5 to 10 seconds, and the second driving speed is the driving speed after the first driving speed. A data fusion processing module, comprising a differentiation unit, a calculation unit, and a judgment unit; The distinguishing unit is used to divide the bright area into at least 5 layers of aperture based on the center point of the bright area, with the diameter of each layer of aperture being at least 10cm, and to mark the 5th layer of aperture as the outer aperture; and to obtain the brightness of the outer aperture; The calculation unit is used to calculate the change in brightness. When the change in brightness decreases on the side that the vehicle is turning towards, at the first or second driving speed, the unit obtains the direction corresponding to the decrease on the outer aperture and marks the corresponding direction as the monitoring direction. The judgment unit responds to the monitored location, and when the brightness of the monitored location shows a decreasing trend, it turns off the vehicle's high beams. Conversely, it will not be turned off.

2. The dynamic anti-glare high beam control system based on multi-sensor fusion as described in claim 1, characterized in that, In the data construction module, the change characteristics of the illuminated area are obtained within the information matrix. The method of obtaining the characteristics includes dynamic modeling. The dynamic modeling is to model the change of the illuminated area over time as a dynamic process, and to calculate the rate of change of the illuminated area during the dynamic process. The acquisition method also includes combining the vehicle's steering angle (obtained via IMU or wheel speed sensor) and the position of the obstacle to calculate the distribution offset of the illuminated area on the steering side, wherein the distribution offset includes the lateral offset distance between the center point of the illuminated area and the center of the obstacle.

3. The dynamic anti-glare high beam control system based on multi-sensor fusion as described in claim 2, characterized in that, The rate of change of the illuminated area is calculated during the dynamic process, and is obtained using the sliding window method: ;in, This represents the average rate of change of the illuminated area within the window, expressed in m² / s or pixels² / frame. In the formula, Indicated at the The bright area on the side of the frame image that is turning, in pixels² or m². Indicates the first The timestamp of the frame image This represents the size of the sliding window, which is the number of consecutive frames involved in the calculation.

4. The dynamic anti-glare high beam control system based on multi-sensor fusion as described in claim 3, characterized in that, Calculating the rate of change of the illuminated area during the dynamic process also includes calculating it according to the following formula: ; This represents the average rate of change of the illuminated area within the window, expressed in m² / s or pixels² / frame. In the formula, Indicates the current frame index. This represents the timestamp corresponding to the current frame index. This represents the illuminated area corresponding to the current frame index.

5. The dynamic anti-glare high beam control system based on multi-sensor fusion as described in claim 2, characterized in that, The offset of the illuminated area distribution on the turning side is calculated using the following formula: ;in, The center point of the bright area in the image captured by the vehicle's camera needs to be mapped to the actual location of the vehicle's coordinates; This indicates the focal length of the vehicle's camera. Indicates the distance between the vehicle and the obstacle. This represents the ordinate of the center point in the image. This indicates the offset corresponding to the installation height of the vehicle's camera.

6. The dynamic anti-glare high beam control system based on multi-sensor fusion as described in claim 5, characterized in that, Based on the calculated distribution offset, the center point of the illuminated area is marked as the reference offset point. During the vehicle's turning process, if the second driving speed is higher than the first driving speed, the offset of the illuminated area is obtained based on the reference offset point. When the vehicle shifts to the turning side, if the illuminated area increases, the vehicle's high beams are turned off. Conversely, it will not be turned off.

7. The dynamic anti-glare high beam control system based on multi-sensor fusion as described in claim 6, characterized in that, When shifting towards the turning side, if the illuminated area increases, the reference offset point on the turning side of the vehicle is divided into three equally sized illuminated areas: the upper end, the middle end, and the lower end. When shifting towards the turning side, if the illuminated area of ​​the upper illuminated area increases while the illuminated areas of the middle and lower illuminated areas decrease, the high beams of the vehicle are not turned off.

8. The dynamic anti-glare high beam control system based on multi-sensor fusion as described in claim 7, characterized in that, Based on the reference offset point, the illuminated area is divided into a left illuminated area and a right illuminated area. When shifting towards the turning side, if the illuminated area of ​​the side corresponding to the turning side decreases while the illuminated area of ​​the non-corresponding side increases, the high beams of the vehicle are not turned off, and the high beams of the vehicle are concentrated to illuminate the direction corresponding to the non-corresponding side illuminated area.

9. The method applied to the dynamic anti-glare high beam control system based on multi-sensor fusion as described in claim 1, characterized in that, Includes the following steps: Collect relevant information about the area in front of the vehicle, including obstacles in front of the vehicle when it is driving on a curve and the illuminated area of ​​the surface of the obstacle illuminated by the vehicle; the illuminated area is the illuminated area on the side of the vehicle turning. An information matrix is ​​constructed based on the relevant information. The information matrix includes the vehicle, the illuminated area, and the vehicle in front. The change characteristics of the illuminated area are obtained within the information matrix. The correlation between the vehicle's driving speed and the changing characteristics is analyzed. The analysis method includes setting a first driving speed and a second driving speed. The first driving speed is the same driving speed collected, and the driving speed is the same driving speed for 5 to 10 seconds. The second driving speed is the driving speed after the first driving speed. The bright area is divided into at least 5 apertures based on the center point of the bright area, and the diameter of each aperture is at least 10cm. The 5th aperture is marked as the outer aperture; and the brightness of the outer aperture is obtained. The change in brightness is calculated. When the change in brightness decreases on the side that the vehicle is turning towards, at the first or second driving speed, the azimuth corresponding to the decrease is obtained on the outer aperture and the corresponding azimuth is marked as the monitoring azimuth. When the brightness of the monitored area shows a decreasing trend, the vehicle's high beams are turned off. Conversely, it will not be turned off.

Images