A method and system for controlling high and low beams based on environmental perception

Abstract

This invention discloses a method and system for controlling high and low beam headlights based on environmental perception, belonging to the field of intelligent vehicle control technology. The method includes: acquiring the ambient illuminance of the vehicle, an image of the area in front of the vehicle, and laser point cloud data of the area in front of the vehicle; determining the state of a target object in front of the vehicle based on the image and the laser point cloud data; performing a weighted fusion of the two states of the target object to obtain the final state of the target object; and controlling the high and low beam headlights of the vehicle based on the ambient illuminance and the final state of the target object. This ensures the accuracy of the high and low beam headlight control.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicle control technology, and in particular to a method and system for controlling high and low beams based on environmental perception. Background Technology

[0002] Car headlights can be divided into two lighting modes, high beam and low beam, depending on the illumination range. High beam has a more concentrated and brighter light, which can illuminate objects at a greater distance; low beam emits a more diffuse light, which can only illuminate objects at a greater distance.

[0003] Currently, in the process of autonomous driving, visual perception or LiDAR is mainly used to determine the target objects in front of the vehicle and their status; then, the high and low beam status is switched according to the target objects in front of the vehicle and their status.

[0004] However, when driving at night, in extreme environments such as heavy snow, fog, or sandstorms, or when the camera is obstructed or malfunctioning, the visual perception function is limited. The objects in front of the vehicle and their status determined by visual perception may be inaccurate. When relying solely on visual perception to switch between high and low beams, inaccurate switching may occur.

[0005] LiDAR detects targets by reflecting and receiving laser waves, which may result in missed detections. Therefore, when switching between near and far beam modes using LiDAR detection alone, there is also the problem of inaccurate switching. Summary of the Invention

[0006] To address the problems of existing technologies, this invention provides a method and system for controlling high and low beams based on environmental perception. The technical solution is as follows:

[0007] On the one hand, a method for controlling high and low beams based on environmental perception is provided, which includes:

[0008] Acquire the ambient light level of the vehicle, the image in front of the vehicle, and the laser point cloud data in front of the vehicle;

[0009] Based on the image in front of the vehicle and the laser point cloud data in front of the vehicle, determine the state of the target object in front of the vehicle;

[0010] The states of the two targets in front of the vehicle are weighted and fused to obtain the final state of the target in front of the vehicle.

[0011] The high and low beam headlights of this vehicle are controlled according to the ambient light level and the state of the final target object in front of the vehicle.

[0012] Optionally, the states of the two targets in front of the vehicle are weighted and fused using image weights and point cloud weights;

[0013] Among them, for targets that can be determined by the front image but not by the laser point cloud data, the image weight is 1 and the point cloud weight is 0.

[0014] For targets that can be determined by laser point cloud data but not by the front image, the image weight is 0 and the point cloud weight is 1.

[0015] For targets that can be identified using both the frontal image and the laser point cloud data, the image weight and point cloud weight are between 0 and 1. The image weight and point cloud weight between 0 and 1 are determined based on the ambient light intensity.

[0016] Optionally, the image weights between 0 and 1 increase with increasing ambient light intensity; the point cloud weights between 0 and 1 decrease with increasing ambient light intensity.

[0017] Optionally, the sum of the image weights and the point cloud weights is 1.

[0018] Optionally, the target's status includes the target's speed, the distance between the target and the vehicle, and the target's lighting status.

[0019] Optionally, when the ambient light intensity is less than or equal to the set illuminance threshold and there is only a target object with a speed of 0 and no lights on within a set distance in front of the vehicle, or when the ambient light intensity is less than or equal to the set illuminance threshold and there is no target object within a set distance in front of the vehicle, the vehicle is controlled to be in high beam mode.

[0020] When the ambient light intensity is less than or equal to the set illuminance threshold and there is a target object with its speed at 0 and its lights on within a set distance in front of the vehicle, or when the ambient light intensity is less than or equal to the set illuminance threshold and there is a target object with its speed at a non-zero speed within a set distance in front of the vehicle, the vehicle is controlled to be in low beam mode.

[0021] On the other hand, an environment-aware high / low beam control system is provided, which includes:

[0022] The acquisition unit is used to acquire the ambient light intensity of the vehicle, the image in front of the vehicle, and the laser point cloud data in front of the vehicle.

[0023] The target object status determination module is used to determine the status of the target object in front of the vehicle based on the image in front of the vehicle and the laser point cloud data in front of the vehicle, respectively; and to perform weighted fusion of the two target object statuses in front of the vehicle to obtain the final target object status in front of the vehicle.

[0024] The high and low beam headlight control module is used to control the high and low beam headlights of the vehicle based on the ambient light level and the status of the final target object in front of the vehicle.

[0025] On the other hand, a computer device is provided, the device comprising:

[0026] A processor, adapted to execute computer programs;

[0027] A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the near / far beam control method based on environmental perception proposed in the first aspect.

[0028] On the other hand, a computer-readable storage medium is provided, which stores a computer program adapted to be loaded and executed by a processor, namely, the environment-aware-based high / low beam control method proposed in the first aspect.

[0029] On the other hand, a computer program product is provided, the computer program product including a computer program, which, when executed by a processor, implements a high beam / low beam control method based on environmental perception proposed in the first aspect.

[0030] The beneficial effects of the technical solution provided by this invention are:

[0031] This invention provides a method and system for controlling high and low beam headlights based on environmental perception. The method determines the state of a target object in front of the vehicle based on both an image of the vehicle's front and laser point cloud data. It then performs a weighted fusion of the two target object states to obtain the final target object state. In other words, by combining laser radar detection and visual perception in determining the target object state, the method achieves greater accuracy. Finally, based on the target object state and ambient light levels, the method controls the vehicle's high and low beam headlights, ensuring the accuracy of the high and low beam control.

[0032] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0034] Figure 1This is a flowchart of a high beam / low beam control method based on environmental perception provided in an embodiment of the present invention;

[0035] Figure 2 This is an architecture diagram of a system involved in a high beam / low beam control method based on environmental perception provided in an embodiment of the present invention.

[0036] The accompanying drawings have illustrated specific embodiments of the invention, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0038] Before providing a detailed explanation of the embodiments of the present invention, the application scenarios and system architecture involved in the embodiments of the present invention will be introduced first.

[0039] First, the system architecture involved in the embodiments of the present invention will be introduced.

[0040] like Figure 2 As shown, the system includes a multi-functional forward-looking camera, a forward-facing LiDAR, a fusion arbitration perception and judgment module, a vehicle controller, and high and low beam headlights.

[0041] Among them, the multi-functional forward-facing camera is used to sense the ambient light level of the vehicle and acquire images of the area in front of the vehicle.

[0042] Forward-facing lidar is used to acquire laser point cloud data in front of the vehicle.

[0043] The fusion arbitration perception and judgment module is used to determine the state of the target object in front of the vehicle based on the image in front of the vehicle and the laser point cloud data in front of the vehicle, respectively; and to perform weighted fusion of the two states of the target object in front of the vehicle to obtain the final state of the target object in front of the vehicle.

[0044] The vehicle controller is used to control the high and low beam headlights of the vehicle based on the ambient light level and the status of the final target object in front of the vehicle.

[0045] Headlights include two lighting modes: high beam and low beam. High beams emit more concentrated and brighter light, which can illuminate objects over a greater distance. Low beams emit more diffused light, which can only illuminate objects over a larger area at close range.

[0046] Those skilled in the art should understand that the above system architecture is merely an example, and other existing or future components or modules that are applicable to this application should also be included within the scope of protection of this application, and are hereby incorporated by reference.

[0047] Finally, the application scenarios of the high beam / low beam control method based on environmental perception disclosed in the embodiments of the present invention will be introduced.

[0048] This invention discloses a method for controlling high and low beam headlights based on environmental perception, which is applied to the control of high and low beam headlights in autonomous driving scenarios at night.

[0049] Currently, in the process of autonomous driving, when driving at night, the vehicle mainly uses visual perception or LiDAR to determine the target objects in front of it and their status; then, based on the distance between the target object and the vehicle, it switches between high and low beams.

[0050] When using visual perception to determine the distance between the vehicle and the target in front, if the camera performing the visual perception is limited in extreme environments such as heavy snow, fog, or sandstorms at night, it will be unable to accurately acquire all targets in front of the vehicle and their status, thus failing to achieve accurate switching between high and low beams.

[0051] LiDAR has the ability to perceive targets at extremely long distances with high precision. However, because LiDAR relies on reflecting and receiving laser waves and then analyzing the received laser waves to detect targets, it can lead to missed detections.

[0052] Therefore, current methods for controlling the switching between high and low beams cannot achieve timely and effective control of high and low beams.

[0053] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0054] This invention provides a method for controlling high and low beams based on environmental perception, with reference to... Figure 1 The method includes:

[0055] Step 101: Obtain the ambient light level of the vehicle, the image in front of the vehicle, and the laser point cloud data in front of the vehicle;

[0056] Step 102: Determine the state of the target object in front of the vehicle based on the image in front of the vehicle and the laser point cloud data in front of the vehicle respectively; perform weighted fusion on the two states of the target object in front of the vehicle to obtain the final state of the target object in front of the vehicle.

[0057] Step 103: Control the high and low beam headlights of the vehicle according to the ambient light level and the state of the final target object in front of the vehicle.

[0058] In summary, the high / low beam control method based on environmental perception provided by this invention integrates lidar detection and visual perception when determining the state of the final target object in front of the vehicle, making the determined state of the final target object in front of the vehicle more accurate. Then, based on the state of the final target object in front of the vehicle and the ambient light, the high / low beam control of the vehicle is performed, ensuring the accuracy of the high / low beam control.

[0059] Optionally, the states of the two targets in front of the vehicle are weighted and fused using image weights and point cloud weights;

[0060] Among them, for targets that can be determined by the front image but not by the laser point cloud data, the image weight is 1 and the point cloud weight is 0.

[0061] For targets that can be determined by laser point cloud data but not by the front image, the image weight is 0 and the point cloud weight is 1.

[0062] For targets that can be identified using both the frontal image and the laser point cloud data, the image weight and point cloud weight are between 0 and 1. The image weight and point cloud weight between 0 and 1 are determined based on the ambient light intensity.

[0063] Optionally, the image weights between 0 and 1 increase with increasing ambient light intensity; the point cloud weights between 0 and 1 decrease with increasing ambient light intensity.

[0064] Optionally, the sum of the image weights and the point cloud weights is 1.

[0065] In some embodiments, the ambient light level of the vehicle is perceived by an FCM multi-function forward-facing camera installed in front of the vehicle, and an image of the front of the vehicle is acquired; the type and state of the target object in front of the vehicle are determined based on the image; and the state of the target object in front of the vehicle is acquired by an FLM forward-facing lidar installed in front of the vehicle; wherein, the state of the target object includes the target object speed, the distance between the target object and the vehicle, and the light status of the target object.

[0066] Because lidar relies on receiving reflected laser waves for target detection, it may miss some targets. In relatively well-lit environments, cameras can comprehensively capture targets in front of the vehicle. Therefore, in well-lit environments, image weighting is increased and point cloud weighting is decreased to improve the accuracy of determining the state of targets in front of the vehicle based on the image. This prioritizes vision over point cloud data, ensuring the final determination of the target's state. However, in extreme environments such as nighttime heavy snow, fog, sandstorms, or when the camera is obstructed or malfunctioning, visual perception is limited, resulting in unclear or inaccurate images of the area in front of the vehicle. The image in front of the vehicle is insufficient for accurate location analysis of targets in front of the vehicle, especially targets at a relatively long distance. However, the accuracy of LiDAR in detecting the distance and speed of targets is less affected by factors such as heavy fog and lighting conditions. Therefore, in extreme environments such as driving at night in heavy snow, fog, or sandstorms, or when the camera is obstructed or malfunctioning, resulting in low ambient light, the image weight is reduced and the point cloud weight is increased to increase the proportion of the state of the target in front of the vehicle determined based on the LiDAR point cloud data in front of the vehicle. The point cloud is used as the main source and visual perception is used as a supplement to ensure the accuracy of the final determination of the state of the target in front of the vehicle.

[0067] The present invention provides a high beam / low beam control method based on environmental perception. According to different ambient light conditions, the image weight and point cloud weight between 0 and 1 are adjusted to ensure the accuracy of determining the state of the final target object in front of the vehicle under different ambient light conditions.

[0068] Optionally, a first value is obtained by determining the state of the target object in front of the vehicle based on the image in front of the vehicle; a second value is obtained by multiplying the state of the target object in front of the vehicle based on the laser point cloud data in front of the vehicle by the point cloud weight; and the first value and the second value are added together to obtain the final state of the target object in front of the vehicle.

[0069] Optionally, when the ambient light intensity is less than or equal to the set illuminance threshold and there is only a target object with a speed of 0 and no lights on within a set distance in front of the vehicle, or when the ambient light intensity is less than or equal to the set illuminance threshold and there is no target object within a set distance in front of the vehicle, the vehicle is controlled to be in high beam mode.

[0070] When the ambient light intensity is less than or equal to the set illuminance threshold and there is a target object with its speed at 0 and its lights on within a set distance in front of the vehicle, or when the ambient light intensity is less than or equal to the set illuminance threshold and there is a target object with its speed at a non-zero speed within a set distance in front of the vehicle, the vehicle is controlled to be in low beam mode.

[0071] The distance can be set to 150m.

[0072] If the ambient light intensity is less than or equal to the set illuminance threshold, it indicates that the vehicle is driving in an environment with insufficient light. If there is only a target object with a speed of 0 and no lights on within a set distance in front of the vehicle, it indicates that there is only a stationary target object within a set distance in front of the vehicle.

[0073] Optionally, the target object can also be a curve, etc. When the target object is determined to be a curve, and the ambient light intensity is less than or equal to the set illuminance threshold, and there is a curve in front of the vehicle, or the vehicle is in a curve, the vehicle is controlled to switch to low beam mode.

[0074] Optionally, the vehicle speed can also be obtained;

[0075] When the ambient light intensity is less than or equal to the set illuminance threshold and the vehicle speed is less than or equal to the speed threshold, or when the ambient light intensity is less than or equal to the set illuminance threshold and the vehicle speed is greater than the speed threshold, and there is a target object with a speed of 0 and its lights on within a set distance in front of the vehicle, or when there is a target object with a speed of non-zero within a set distance in front of the vehicle, the vehicle is controlled to be in low beam mode.

[0076] When the ambient light intensity is less than or equal to the set illuminance threshold, and when the vehicle speed is greater than the speed threshold, and there is only a target object with a speed of 0 and no lights on within the set distance in front of the vehicle, or there is no target object within the set distance in front of the vehicle, the high beam headlights of the vehicle will be turned on.

[0077] The speed threshold can be set to 30 km / h.

[0078] In summary, the environmental perception-based high / low beam control method provided by this invention can determine image weights and point cloud weights based on ambient light intensity. Using these image and point cloud weights, it performs a weighted fusion of two target states determined from the vehicle's forward image and laser point cloud data to determine the final target state. Specifically, when determining the final target state, it integrates visual detection results and laser radar detection results, with the image weight increasing with ambient light intensity and the point cloud weight decreasing with increasing ambient light intensity. This allows for the determination of the final target state under good ambient light conditions, primarily relying on visual detection and secondarily on laser radar detection, while under poor ambient light conditions, it primarily relies on laser radar detection and secondarily on visual detection. This ensures accurate acquisition of the final target state under various environmental conditions, thereby achieving accurate control of the high / low beam headlights.

[0079] This invention also provides an environmental perception-based high / low beam control system, which includes:

[0080] The acquisition unit is used to acquire the ambient light intensity of the vehicle, the image in front of the vehicle, and the laser point cloud data in front of the vehicle.

[0081] The target object status determination module is used to determine the status of the target object in front of the vehicle based on the image in front of the vehicle and the laser point cloud data in front of the vehicle, respectively; and to perform weighted fusion of the two target object statuses in front of the vehicle to obtain the final target object status in front of the vehicle.

[0082] The high and low beam headlight control module is used to control the high and low beam headlights of the vehicle based on the ambient light level and the status of the final target object in front of the vehicle.

[0083] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0084] This invention also provides a computer device, which includes:

[0085] A processor, adapted to execute computer programs;

[0086] A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the aforementioned environment-aware-based high / low beam control method.

[0087] This invention also provides a computer-readable storage medium storing a computer program adapted for loading and execution by a processor of the aforementioned environment-aware-based high / low beam control method.

[0088] This invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the aforementioned method for controlling high and low beams based on environmental perception.

[0089] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0090] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for controlling high and low beams based on environmental perception, characterized in that, The method includes: Acquire the ambient light level of the vehicle, the image in front of the vehicle, and the laser point cloud data in front of the vehicle; Based on the image in front of the vehicle and the laser point cloud data in front of the vehicle, determine the state of the target object in front of the vehicle; By using image weights and point cloud weights, the states of two targets in front of the vehicle are weighted and fused to obtain the final state of the target in front of the vehicle; where the sum of image weights and point cloud weights is 1; for targets that can be determined by the front image but not by the laser point cloud data, the image weight is 1 and the point cloud weight is 0. For targets that can be determined by laser point cloud data but not by the front image, the image weight is 0 and the point cloud weight is 1. For targets that can be identified using both the frontal image and the laser point cloud data of the vehicle, the image weight and point cloud weight are between 0 and 1. The image weight between 0 and 1 increases with increasing ambient light intensity, while the point cloud weight between 0 and 1 decreases with increasing ambient light intensity. The high and low beam headlights of this vehicle are controlled according to the ambient light level and the state of the final target object in front of the vehicle.

2. The method for controlling high and low beams based on environmental perception as described in claim 1, characterized in that, The target's status includes its speed, the distance between it and the vehicle, and the status of its lights.

3. The method for controlling high and low beams based on environmental perception as described in claim 1, characterized in that, When the ambient light intensity is less than or equal to the set illuminance threshold and there is only a target object with a speed of 0 and no lights on within a set distance in front of the vehicle, or when the ambient light intensity is less than or equal to the set illuminance threshold and there is no target object within a set distance in front of the vehicle, the vehicle is controlled to be in high beam mode. When the ambient light intensity is less than or equal to the set illuminance threshold and there is a target object with its speed at 0 and its lights on within a set distance in front of the vehicle, or when the ambient light intensity is less than or equal to the set illuminance threshold and there is a target object with its speed at a non-zero speed within a set distance in front of the vehicle, the vehicle is controlled to be in low beam mode.

4. An electronic device, characterized in that, The device includes: A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the near / far beam control method based on environmental perception as described in any one of claims 1-3.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed by a processor to provide a method for controlling high and low beams based on environmental perception as described in any one of claims 1-3.

6. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the high / low beam control method based on environmental perception as described in any one of claims 1-3.

Images