Self-adaptive high beam control method and system based on multi-target fusion

Abstract

The invention discloses a self-adaptive high beam control method and system based on multi-target fusion, and the method comprises the steps: obtaining a light spot target, a vehicle control target and a point cloud target of a target vehicle, and carrying out the fusion processing of the light spot target, the vehicle control target and the point cloud target, the method comprises the following steps: acquiring a light spot fusion target, a vehicle control fusion target and a point cloud fusion target, performing fusion processing on the light spot fusion target, the vehicle control fusion target and the point cloud fusion target to acquire adaptive high beam fusion target information, and sending the adaptive high beam fusion target information to a light control unit, therefore, the self-adaptive high beam control of the matrix headlight is realized. According to the method, the stability of ADB dark area control is improved, the ADB function cannot flicker to the front vehicle due to the change of the target state in the driving process, the interference of light flickering to a driver of the front vehicle is avoided, and the driving safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to an adaptive high beam control method and system based on multi-objective fusion. Background Art

[0002] With the rapid development of the automotive industry, related technologies are also being updated and iterated rapidly. Among them, smart matrix headlights have become standard features on many models. Adaptive Driving Beam (ADB), a key feature of smart matrix headlights, precisely controls the on and off states of individual LEDs in the matrix headlights. This ensures that all other vehicle targets within the forward-facing camera's field of view are within the dark zone created by the headlights, preventing the vehicle's high beams from dazzling drivers of other vehicles. At the same time, sufficient and even lighting is provided in areas outside the vehicle's field of view, creating a clear field of vision for the driver, thereby improving driving safety for both the driver and other vehicles.

[0003] However, in actual application scenarios, complex road conditions lead to inaccurate ADB dark zone control, resulting in the phenomenon of flashing vehicles in front. The ADB function can currently track up to 8 targets at the same time. In complex road conditions with heavy traffic in the same or opposite directions, frequent lane changes, overtaking, and turns by target vehicles, and the continuous disappearance of targets and the continuous appearance of new targets, it is very easy to have problems such as inaccurate target recognition and easy target loss, causing the matrix headlights to flash the vehicle in front, seriously affecting the user experience. The existing technical solutions are mainly designed based on the principle of precise ADB dark zone control of a single vehicle target, but in scenarios with a large number of vehicle targets and rapidly changing states, it is difficult to avoid problems such as inaccurate target recognition and easy target loss. Therefore, for scenarios with particularly complex traffic conditions, a new control strategy is urgently needed to solve the above problems. Summary of the Invention

[0004] The purpose of the present invention is to provide an adaptive high beam control method and system based on multi-target fusion. By using a multi-target fusion strategy, the method effectively buffers and weakens the impact of rapid changes in ADB target states on the final ADB dark zone control effect, thereby solving the technical problems of inaccurate target recognition and easy target loss in existing ADB dark zone control schemes.

[0005] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] The present invention provides an adaptive high beam control method and system based on multi-objective fusion, which includes:

[0007] Obtain the light spot target, vehicle control target and point cloud target of the target vehicle;

[0008] The light spot target, the vehicle control target and the point cloud target are respectively fused to obtain a light spot fusion target, a vehicle control fusion target and a point cloud fusion target;

[0009] Performing fusion processing on the spot fusion target, the vehicle control fusion target, and the point cloud fusion target to obtain adaptive high beam fusion target information;

[0010] The adaptive high beam fusion target information is sent to a lighting control unit to implement adaptive high beam control of the matrix headlights.

[0011] In one embodiment of the present invention, obtaining the light spot target, vehicle control target, and point cloud target of the target vehicle includes:

[0012] The vehicle-mounted forward-looking camera is used to capture the light emitted by the target vehicle's headlights or taillights to obtain the target vehicle's light spot target;

[0013] Use the on-board front-view camera to perform image recognition on the target vehicle to obtain the control target of the target vehicle;

[0014] The target vehicle is detected using the vehicle-mounted forward-looking radar to obtain the point cloud target of the target vehicle.

[0015] In one embodiment of the present invention, the light spot target, the vehicle control target, and the point cloud target are fused separately to obtain a light spot fusion target, a vehicle control fusion target, and a point cloud fusion target, including:

[0016] Performing preset condition judgment on the light spot target to determine the current working condition of the vehicle;

[0017] According to the current working condition of the vehicle, the fixed target information is directly output to the light control unit or the light spot target is fused using a first preset multi-target fusion logic to obtain a light spot fusion target;

[0018] Using a second preset multi-objective fusion logic to perform fusion processing on the vehicle control target to obtain a vehicle control fusion target;

[0019] The vehicle control target and the point cloud target are fused once, and a third preset multi-target fusion logic is used to perform a secondary fusion process on the result of the primary fusion to obtain a point cloud fusion target.

[0020] In one embodiment of the present invention, a preset condition judgment is performed on the light spot target to determine the current working condition of the vehicle, including:

[0021] When the light spot target meets the preset conditions, it is determined that the current working condition of the vehicle is the first working condition;

[0022] When the light spot target does not meet the preset condition, it is determined that the current working condition of the vehicle is the second working condition.

[0023] In one embodiment of the present invention, when the light spot target meets a preset condition, determining that the current operating condition of the vehicle is the first operating condition includes:

[0024] When the number of light spot targets detected within a preset range in front of the vehicle is greater than or equal to a preset number and the duration reaches a preset time, it is determined that the current operating condition of the vehicle is the first operating condition.

[0025] In one embodiment of the present invention, according to the current working condition of the vehicle, the method of directly outputting fixed target information to the light control unit or using a first preset multi-target fusion logic to fuse the spot target to obtain a spot fusion target includes:

[0026] If it is determined that the current operating condition of the vehicle is the first operating condition, the fixed target information is directly output to the light control unit;

[0027] If it is determined that the current operating condition of the vehicle is the second operating condition, the light spot target is fused using the first preset multi-target fusion logic to obtain a light spot fusion target.

[0028] In one embodiment of the present invention, if it is determined that the current operating condition of the vehicle is the first operating condition, then directly outputting fixed target information to the light control unit includes:

[0029] If it is determined that the current working condition of the vehicle is the first working condition, all detected light spot targets are replaced as a whole with a preset fixed target, and the fixed target information corresponding to the preset fixed target is directly output to the light control unit.

[0030] In one embodiment of the present invention, the spot fusion target, the vehicle control fusion target, and the point cloud fusion target are fused to obtain adaptive high beam fusion target information, including:

[0031] fusing the light spot fusion target, the vehicle control fusion target, and the point cloud fusion target using a fourth preset multi-target fusion logic to obtain an adaptive high beam fusion target, wherein the adaptive high beam fusion target includes a same-direction fusion target and a opposite-direction fusion target;

[0032] Parameters of the same-direction fusion target and the opposite-direction fusion target are extracted respectively to obtain adaptive high-beam fusion target information.

[0033] In one embodiment of the present invention, the adaptive high beam fusion target information includes the closest distance relative to the vehicle, the left and right maximum boundary angles, the direction relative to the vehicle, the horizontal angular velocity and the minimum vertical angle relative to the vehicle.

[0034] Based on the same inventive concept, another embodiment of the present invention further provides an adaptive high beam control system based on multi-objective fusion. The system is implemented using the adaptive high beam control method based on multi-objective fusion as described in any of the above embodiments, including:

[0035] Information acquisition module, used to obtain the light spot target, vehicle control target and point cloud target of the target vehicle;

[0036] A first fusion module is used to fuse the light spot target, the vehicle control target and the point cloud target respectively to obtain a light spot fusion target, a vehicle control fusion target and a point cloud fusion target;

[0037] A second fusion module is used to fuse the light spot fusion target, the vehicle control fusion target and the point cloud fusion target to obtain adaptive high beam fusion target information;

[0038] The lighting control module is used to send the adaptive high beam fusion target information to the lighting control unit to realize the adaptive high beam control of the matrix headlight.

[0039] As described above, the present invention provides an adaptive high-beam control method based on multi-target fusion. This method obtains a spot target, a vehicle control target, and a point cloud target of a target vehicle, and then fuses these spot targets, vehicle control targets, and point cloud targets to obtain a spot fusion target, a vehicle control fusion target, and a point cloud fusion target. These spot fusion targets, vehicle control fusion targets, and point cloud fusion targets are then fused to obtain adaptive high-beam fusion target information. This adaptive high-beam fusion target information is then transmitted to a lighting control unit to implement adaptive high-beam control of matrix headlights. This method deeply exploits the information characteristics of the spot target, vehicle control target, and point cloud targets. By utilizing a multi-target fusion strategy, it integrates and processes target data from different sources, effectively buffering and reducing the impact of rapid changes in ADB target states on the final ADB dark zone control effect. This significantly improves the stability of ADB dark zone control and ensures that the ADB function does not flash to the preceding vehicle due to target state changes during driving, thus avoiding interference to the preceding vehicle driver caused by light flashing and improving driving safety. Of course, any product implementing the present invention does not necessarily need to simultaneously achieve all of the aforementioned advantages. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A flowchart of an adaptive high beam control method based on multi-objective fusion is provided as an exemplary embodiment of the present application.

[0042] Figure 2 This is a schematic diagram of the application of multi-objective fusion logic provided by an exemplary embodiment of the present application.

[0043] Figure 3 A system flow chart of an adaptive high beam control method based on multi-objective fusion provided by an exemplary embodiment of the present application.

[0044] Figure 4 A schematic structural diagram of an adaptive high beam control system based on multi-objective fusion provided in another embodiment of the present application. DETAILED DESCRIPTION

[0045] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0046] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0047] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, publicly known structures and devices are shown in block diagram form rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0048] In intelligent driving assistance systems, onboard forward-facing cameras and radars have inherent limitations when it comes to identifying external vehicle targets. Constrained by complex and changing road conditions and the inherent performance limitations of the hardware, achieving 100% accurate recognition and stable output is difficult. In real-world driving scenarios, occasional instances of inaccurate target recognition and temporary target loss are inevitable. This limitation directly impacts the proper functioning of the Adaptive Driving Beam (ADB) feature. The core of ADB is to dynamically adjust the illumination area of ​​the matrix headlights based on dynamic information such as the position, speed, and distance of the vehicle ahead, thereby generating a dark zone of a specific shape and size to avoid glare for the driver ahead. However, due to the instability of target recognition by the forward-facing cameras and radar, the dark zone generated by the ADB feature cannot fully and accurately cover the vehicle ahead. Consequently, some of the matrix headlight light directly strikes the vehicle ahead, causing a flashing effect on the driver ahead. This flashing effect is not only extremely annoying and distracting to the driver ahead, but can also cause temporary visual impairment, seriously threatening driving safety and increasing the risk of traffic accidents.

[0049] In order to solve the technical problems of inaccurate target recognition and easy target loss in the existing ADB dark area control scheme, the present invention innovatively proposes an adaptive high beam control method based on multi-target fusion. By using a multi-target fusion strategy, this method effectively buffers and significantly weakens the impact of rapid changes in ADB target state on the final ADB dark area control effect, thereby significantly improving the stability of ADB dark area control.

[0050] See also Figure 1 As shown, in an exemplary embodiment of the present application, the adaptive high beam control method based on multi-objective fusion includes the following steps:

[0051] S100: Acquire the light spot target, vehicle control target and point cloud target of the target vehicle;

[0052] S200: performing fusion processing on the light spot target, the vehicle control target, and the point cloud target respectively to obtain a light spot fusion target, a vehicle control fusion target, and a point cloud fusion target;

[0053] S300: Fusing the light spot fusion target, the vehicle control fusion target, and the point cloud fusion target to obtain adaptive high beam fusion target information;

[0054] S400: Sending the adaptive high beam fusion target information to a lighting control unit to implement adaptive high beam control of the matrix headlights.

[0055] The following will discuss in detail the steps in the above-mentioned adaptive high beam control method based on multi-objective fusion.

[0056] First, step S100 is executed to obtain the light spot target, vehicle control target and point cloud target of the target vehicle;

[0057] In an exemplary embodiment of the present application, step S100 further includes the following steps:

[0058] S110: Using the on-board forward-looking camera to capture the light emitted by the target vehicle's headlights or taillights to obtain the target vehicle's light spot target;

[0059] S120: Performing image recognition on the target vehicle using the onboard front-view camera to obtain a control target of the target vehicle;

[0060] S130: Detecting the target vehicle using the vehicle-mounted forward-looking radar to obtain a point cloud target of the target vehicle.

[0061] Specifically, multimodal perception data of the target vehicle is acquired through the fusion of multiple sensors. The multimodal perception data includes spot targets, vehicle control targets, and point cloud targets. More specifically, the on-board front-looking camera (FLC) captures light emitted by the headlights or taillights of external target vehicles in the direction of the ego vehicle's travel. An image processing algorithm is used to extract the spot area, thereby obtaining the target vehicle control target. Target detection is performed based on the image captured by the on-board front-looking camera, thereby obtaining the target vehicle control target. The on-board forward-looking radar (FLR) detects the point cloud of the target vehicle, thereby obtaining the target vehicle point cloud target. It should be noted that in this embodiment, the on-board forward-looking radar includes a millimeter-wave radar and a lidar. It is worth noting that in this embodiment, the acquired spot targets, vehicle control targets, and point cloud targets all include key relevant information such as the number of target vehicles, their specific location, speed, direction, and distance from the ego vehicle.

[0062] Next, see Figure 2 As shown, step S200 is executed, that is, the light spot target, the vehicle control target and the point cloud target are fused respectively to obtain a light spot fusion target, a vehicle control fusion target and a point cloud fusion target.

[0063] In an exemplary embodiment of the present application, step S200 further includes the following steps:

[0064] S210: performing a preset condition judgment on the light spot target to determine the current working condition of the vehicle;

[0065] S220: According to the current working condition of the vehicle, directly outputting the fixed target information to the light control unit or using a first preset multi-target fusion logic to fuse the light spot target to obtain a light spot fusion target;

[0066] S230: Using a second preset multi-objective fusion logic to fuse the vehicle control objectives to obtain a vehicle control fusion objective;

[0067] S240: Fusing the vehicle control target with the point cloud target once, and performing a secondary fusion process on the result of the primary fusion using a third preset multi-target fusion logic to obtain a point cloud fusion target.

[0068] In an exemplary embodiment of the present application, step S210 further includes the following steps:

[0069] S211: When the light spot target meets the preset conditions, it is determined that the current operating condition of the vehicle is the first operating condition;

[0070] S212: When the light spot target does not meet the preset condition, it is determined that the current operating condition of the vehicle is the second operating condition.

[0071] Specifically, see Figure 3 As shown, the characteristics of the light spot target are analyzed according to the preset judgment criteria. If the characteristics of the light spot target meet the scenario defined by the preset conditions, the judgment of the first working condition is triggered. In this embodiment, when the number of light spot targets detected within the preset range in front of the vehicle is greater than or equal to the preset number and the duration of this state reaches a preset time, it is determined that the current working condition of the vehicle is the first working condition. It should be noted that the number of light spot targets corresponds to the number of target vehicles. More specifically, when any of the following conditions is met and the state lasts for 2 seconds, it can be determined that the vehicle is currently in the first working condition:

[0072] Overtaking two oncoming vehicles within a range of 0 to 100 meters;

[0073] Overtaking 4 oncoming vehicles / vehicles ahead within a range of 0 to 100 meters;

[0074] Overtaking three oncoming vehicles within a range of 0 to 150 meters;

[0075] Overtaking 6 oncoming vehicles / vehicles ahead within a range of 0 to 150 meters;

[0076] Overtaking 4 oncoming vehicles within a range of 0 to 200 meters;

[0077] More than 7 oncoming vehicles / vehicles ahead within a range of 0 to 200 meters;

[0078] There are more than 8 oncoming vehicles / vehicles ahead.

[0079] It should be noted that the preset conditions in this embodiment are only exemplary settings. In actual applications, the preset conditions can be customized according to different application scenarios and requirements.

[0080] In an exemplary embodiment of the present application, step S220 further includes the following steps:

[0081] S221: If it is determined that the current operating condition of the vehicle is the first operating condition, directly outputting fixed target information to the light control unit;

[0082] S222: If it is determined that the current operating condition of the vehicle is the second operating condition, a first preset multi-target fusion logic is used to fuse the light spot targets to obtain a light spot fusion target.

[0083] It should be noted that, in this embodiment, if it is determined that the current operating condition of the vehicle is the first operating condition, all detected light spot targets are replaced as a whole with a preset fixed target, and the fixed target information corresponding to the preset fixed target is directly output to the light control unit.

[0084] Specifically, see Figure 3 As shown, when the system determines that the vehicle is in the first operating condition, it indicates that the vehicle is currently in a complex scenario with multiple vehicles converging. In this scenario, there are numerous external target vehicles on the road. If each target vehicle is processed individually, the system's computational burden and complexity will increase, potentially leading to untimely or inaccurate lighting control. Therefore, in this embodiment, the Toomanycar logic processing mechanism is adopted. All detected light spot targets are treated as a whole and directly replaced with a preset fixed target. The fixed target information corresponding to the preset fixed target is then directly output to the lighting control unit. Notably, the fixed target information corresponding to the preset fixed target is set to: left and right angles and angular velocities are both ±35°, and the distance is fixed at 20 meters. By integrating all external vehicle targets into a single fixed target, the control logic can be greatly simplified, thereby improving the control stability of the ADB function. For example, in traffic congestion, when the road is densely packed with vehicles, the system can treat these vehicles as a single target. The lighting control unit then intelligently adjusts the lighting range and brightness based on information such as the position and distance of this single target to ensure driving safety.

[0085] Next, step S300 is executed, that is, fusing the light spot fusion target, the vehicle control fusion target, and the point cloud fusion target to obtain adaptive high beam fusion target information.

[0086] In an exemplary embodiment of the present application, step S300 further includes the following steps:

[0087] S310: Using a fourth preset multi-target fusion logic, fusing the light spot fusion target, the vehicle control fusion target, and the point cloud fusion target to obtain an adaptive high beam fusion target, where the adaptive high beam fusion target includes a same-direction fusion target and a opposite-direction fusion target.

[0088] S320: Extract parameters of the same-direction fusion target and the opposite-direction fusion target respectively to obtain adaptive high-beam fusion target information.

[0089] It should be noted that, in this embodiment, the adaptive high beam fusion target information includes the closest distance relative to the vehicle, the left and right maximum boundary angles, the direction relative to the vehicle, the horizontal angular velocity and the minimum vertical angle relative to the vehicle.

[0090] Specifically, the system refines the output settings of the fused target information to ensure precise and intelligent lighting control unit adjustment. First, the system selects the distance of the target closest to the ego vehicle as a key output signal. Second, the system outputs the maximum left and right boundary angles to ensure the lighting control unit fully covers the target's horizontal range. Third, the system outputs the target's direction relative to the ego vehicle, allowing the lighting control unit to dynamically adjust its lighting strategy based on the target's motion. For example, when an oncoming target is detected, the lighting control unit quickly reduces the brightness of the high beam or adjusts the illumination angle to prevent direct glare from directly hitting the driver of the oncoming vehicle, thereby ensuring driving safety. When a target is detected in the same direction, the low beam illumination range is adjusted based on the target's distance and speed, ensuring a clear view of the road ahead. Furthermore, the system outputs the target's horizontal angular velocity, enabling the lighting control unit to predict the target's future position and adjust the lighting angle in advance. Finally, the system outputs the target's vertical angle relative to the ego vehicle to ensure the light reaches the target at its lowest point.

[0091] More specifically, see Figure 3As shown, the system performs a Toomanycar logic judgment on the light spot target. If it meets the requirements, the Toomanycar fixed fusion target is output to the lighting control unit. If it does not meet the requirements, the light spot target is fused according to the first preset multi-target fusion logic to generate a same-direction light spot fusion target and an opposite-direction light spot fusion target. At the same time, the system fuses the vehicle control target according to the second preset multi-target fusion logic to generate a same-direction vehicle control fusion target and an opposite-direction vehicle control fusion target. In addition, the system will first perform a fusion on the vehicle control target and the point cloud target. Since the vehicle control target and the point cloud target come from different sensors, their coordinate systems, timestamps and other data may be different. The main purpose of this fusion is to align these data to ensure that the vehicle control target and the point cloud target are comparable in time and space dimensions. After completing the first fusion, the system performs a second fusion on the first fusion result according to the third preset multi-target fusion strategy to generate a same-direction point cloud fusion target and an opposite-direction point cloud fusion target. Finally, according to the fourth preset multi-target fusion logic, the system fuses the light spot fusion target, the vehicle control fusion target and the point cloud fusion target again to generate a same-direction fusion target and a opposite-direction fusion target, and outputs the information of these two fusion targets to the lighting control unit.

[0092] It should be noted that the first preset multi-target fusion logic, the second preset multi-target fusion logic, the third preset multi-target fusion logic and the fourth preset multi-target fusion logic use the same set of logical rules by default. Of course, in other embodiments, these logical rules can also be set to be different according to actual needs.

[0093] Finally, step S400 is executed, that is, the adaptive high beam fusion target information is sent to the lighting control unit to implement adaptive high beam control of the matrix headlight.

[0094] Specifically, the lighting control unit receives adaptive high-beam fusion target information and accurately controls the matrix headlights based on this information. Specifically, it dynamically changes the lighting pattern by adjusting parameters such as the brightness, illumination angle, and illumination range of each lamp in the matrix headlights.

[0095] In summary, the present invention provides an adaptive high-beam control method based on multi-target fusion. This method acquires a target vehicle's spot target, vehicle control target, and point cloud target, and fuses the spot target, vehicle control target, and point cloud target separately to obtain a spot fusion target, a vehicle control fusion target, and a point cloud fusion target. These spot fusion target, vehicle control fusion target, and point cloud fusion target are then fused to obtain adaptive high-beam fusion target information. This adaptive high-beam fusion target information is then sent to a lighting control unit to implement adaptive high-beam control of matrix headlights. This method deeply exploits the information characteristics of the spot target, vehicle control target, and point cloud target. By utilizing a multi-target fusion strategy, it integrates and processes target data from different sources, effectively buffering and weakening the impact of rapid changes in ADB target states on the final ADB dark zone control effect. This significantly improves the stability of ADB dark zone control and ensures that the ADB function does not flash to the preceding vehicle due to target state changes during driving, thus avoiding interference to the preceding vehicle driver caused by light flashing and improving driving safety.

[0096] Based on the same inventive concept, please refer to Figure 4 As shown, another embodiment of the present invention further provides an adaptive high beam control system 100 based on multi-objective fusion. The system is implemented using the adaptive high beam control method based on multi-objective fusion as described in any of the above embodiments, including:

[0097] The information acquisition module 110 is used to obtain the light spot target, vehicle control target and point cloud target of the target vehicle;

[0098] The first fusion module 120 is used to fuse the light spot target, the vehicle control target and the point cloud target respectively to obtain a light spot fusion target, a vehicle control fusion target and a point cloud fusion target;

[0099] The second fusion module 130 is used to fuse the light spot fusion target, the vehicle control fusion target and the point cloud fusion target to obtain adaptive high beam fusion target information;

[0100] The lighting control module 140 is used to send the adaptive high beam fusion target information to the lighting control unit to implement adaptive high beam control of the matrix headlights.

[0101] It should be noted that the adaptive high-beam control system 100 based on multi-objective fusion includes the adaptive high-beam control method based on multi-objective fusion described in any of the above embodiments. Since the adaptive high-beam control system 100 based on multi-objective fusion provided in this embodiment and the adaptive high-beam control method based on multi-objective fusion provided in any of the above embodiments are based on the same inventive concept and thus have at least the same beneficial effects, they will not be described in detail here.

[0102] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. An adaptive high beam control method based on multi-objective fusion, characterized in that: include: Obtain the light spot target, vehicle control target and point cloud target of the target vehicle; The light spot target, the vehicle control target and the point cloud target are respectively fused to obtain a light spot fusion target, a vehicle control fusion target and a point cloud fusion target; Performing fusion processing on the spot fusion target, the vehicle control fusion target, and the point cloud fusion target to obtain adaptive high beam fusion target information; The adaptive high beam fusion target information is sent to a lighting control unit to implement adaptive high beam control of the matrix headlights.

2. The adaptive high beam control method based on multi-objective fusion according to claim 1, characterized in that: The step of obtaining the light spot target, vehicle control target, and point cloud target of the target vehicle includes: The vehicle-mounted forward-looking camera is used to capture the light emitted by the target vehicle's headlights or taillights to obtain the target vehicle's light spot target; Use the on-board front-view camera to perform image recognition on the target vehicle to obtain the control target of the target vehicle; The target vehicle is detected using the vehicle-mounted forward-looking radar to obtain the point cloud target of the target vehicle.

3. The adaptive high beam control method based on multi-objective fusion according to claim 1, characterized in that: The light spot target, the vehicle control target and the point cloud target are respectively fused to obtain a light spot fusion target, a vehicle control fusion target and a point cloud fusion target, including: Performing preset condition judgment on the light spot target to determine the current working condition of the vehicle; According to the current working condition of the vehicle, the fixed target information is directly output to the light control unit or the light spot target is fused using a first preset multi-target fusion logic to obtain a light spot fusion target; Using a second preset multi-objective fusion logic to perform fusion processing on the vehicle control target to obtain a vehicle control fusion target; The vehicle control target and the point cloud target are fused once, and a third preset multi-target fusion logic is used to perform a secondary fusion process on the result of the primary fusion to obtain a point cloud fusion target.

4. The adaptive high beam control method based on multi-objective fusion according to claim 3, characterized in that: The preset conditions of the light spot target are judged to determine the current working condition of the vehicle, including: When the light spot target meets the preset conditions, it is determined that the current working condition of the vehicle is the first working condition; When the light spot target does not meet the preset condition, it is determined that the current working condition of the vehicle is the second working condition.

5. The adaptive high beam control method based on multi-objective fusion according to claim 4, characterized in that: When the light spot target meets the preset conditions, it is determined that the current working condition of the vehicle is the first working condition, including: When the number of light spot targets detected within a preset range in front of the vehicle is greater than or equal to a preset number and the duration reaches a preset time, it is determined that the current operating condition of the vehicle is the first operating condition.

6. The adaptive high beam control method based on multi-objective fusion according to claim 4, characterized in that: According to the current working condition of the vehicle, the fixed target information is directly output to the light control unit or the light spot target is fused using the first preset multi-target fusion logic to obtain the light spot fusion target, including: If it is determined that the current operating condition of the vehicle is the first operating condition, the fixed target information is directly output to the light control unit; If it is determined that the current operating condition of the vehicle is the second operating condition, the light spot target is fused using the first preset multi-target fusion logic to obtain a light spot fusion target.

7. The adaptive high beam control method based on multi-objective fusion according to claim 6, characterized in that: If it is determined that the current operating condition of the vehicle is the first operating condition, the fixed target information is directly output to the light control unit, including: If it is determined that the current working condition of the vehicle is the first working condition, all detected light spot targets are replaced as a whole with a preset fixed target, and the fixed target information corresponding to the preset fixed target is directly output to the light control unit.

8. The adaptive high beam control method based on multi-objective fusion according to claim 1, characterized in that: The light spot fusion target, the vehicle control fusion target, and the point cloud fusion target are fused to obtain adaptive high beam fusion target information, including: fusing the light spot fusion target, the vehicle control fusion target, and the point cloud fusion target using a fourth preset multi-target fusion logic to obtain an adaptive high beam fusion target, wherein the adaptive high beam fusion target includes a same-direction fusion target and a opposite-direction fusion target; Parameters of the same-direction fusion target and the opposite-direction fusion target are extracted respectively to obtain adaptive high-beam fusion target information.

9. The adaptive high beam control method based on multi-objective fusion according to claim 8, characterized in that: The adaptive high beam fusion target information includes the closest distance relative to the vehicle, the left and right maximum boundary angles, the direction relative to the vehicle, the horizontal angular velocity and the minimum vertical angle relative to the vehicle.

10. An adaptive high beam control system based on multi-objective fusion, characterized in that: The system is implemented by the adaptive high beam control method based on multi-objective fusion according to any one of claims 1 to 9, comprising: Information acquisition module, used to obtain the light spot target, vehicle control target and point cloud target of the target vehicle; A first fusion module is used to fuse the light spot target, the vehicle control target and the point cloud target respectively to obtain a light spot fusion target, a vehicle control fusion target and a point cloud fusion target; A second fusion module is used to fuse the light spot fusion target, the vehicle control fusion target and the point cloud fusion target to obtain adaptive high beam fusion target information; The lighting control module is used to send the adaptive high beam fusion target information to the lighting control unit to realize the adaptive high beam control of the matrix headlight.

Images