Vehicle obstacle avoidance methods and devices

Abstract

This invention relates to the field of vehicle obstacle avoidance technology, and provides a vehicle obstacle avoidance method and apparatus. The vehicle obstacle avoidance method includes the following steps: acquiring laser radar data within a preset angle range ahead of the vehicle's direction of travel using a laser radar installed on the vehicle; generating a corresponding equivalent image based on the laser radar data; processing the equivalent image to identify obstacle information; and providing obstacle avoidance prompts or action control based on the obstacle information. This invention can accurately and automatically identify obstacles in the vehicle's direction of travel in low-light conditions and can take corresponding obstacle avoidance prompts or actions, thereby improving vehicle safety and saving labor costs.

Description

Technical Field

[0001] This invention relates to the field of vehicle obstacle avoidance technology, specifically to a vehicle obstacle avoidance method and a vehicle obstacle avoidance device. Background Technology

[0002] In low-light environments such as coal mines, supplemental lighting equipment is limited by safety regulations and cannot provide illumination for vehicles in mobile environments. Therefore, vehicles operating in these environments require measures to prevent collisions with obstacles. Currently used methods include manual guidance via intercom, dual-spectrum camera recognition, and millimeter-wave radar recognition; however, all of these methods have limitations. Manual guidance incurs high labor costs; dual-spectrum camera recognition only provides visual guidance and cannot provide automatic and accurate alarm prompts; and millimeter-wave radar recognition, using current algorithms, often fails to identify objects and remains insufficient to completely eliminate occasional collisions. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a vehicle obstacle avoidance method and device that can accurately and automatically identify obstacles in the vehicle's direction of travel under low-light conditions and take corresponding obstacle avoidance prompts or actions, thereby improving vehicle safety and saving labor costs.

[0004] The technical solution adopted in this invention is as follows:

[0005] A vehicle obstacle avoidance method includes the following steps: acquiring laser radar data within a preset angle range in front of the vehicle's direction of travel using a laser radar installed on the vehicle; generating a corresponding equivalent image based on the laser radar data; processing the equivalent image to identify obstacle information; and providing obstacle avoidance prompts or action control based on the obstacle information.

[0006] The preset angle range is set according to the width of the vehicle.

[0007] Generating a corresponding equivalent image based on the LiDAR data specifically includes: constructing a first grayscale image of a preset size with all pixel grayscale values ​​being a first value; converting each distance-angle data in the LiDAR data into a corresponding two-dimensional coordinate; changing the grayscale value of each pixel at each of the two-dimensional coordinates in the first grayscale image to a second value to obtain a second grayscale image, wherein the second value is different from the first value; performing an affine transformation on the second grayscale image to transform the starting point of the LiDAR data from the origin at the top left corner of the second grayscale image to the midpoint of the bottom edge, obtaining a corrected image, which serves as the equivalent image.

[0008] The equivalent image is processed to identify obstacle information, specifically including: filtering out pixel regions in the equivalent image whose grayscale value is the second value; performing connectivity processing on the pixel regions in the equivalent image whose grayscale value is the second value to obtain multiple first connected regions; expanding each first connected region in a circular pattern to obtain multiple expanded regions, wherein the expansion radius is calculated based on the distance from the center of the first connected region to the starting point of the lidar data, the maximum detection range of the lidar, and the detection accuracy data of the lidar; combining the multiple expanded regions to obtain a joint region; performing connectivity processing on the joint region to obtain multiple second connected regions; traversing the multiple second connected regions, finding the intersection of each second connected region with the pixel regions in the equivalent image whose grayscale value is the second value to obtain an intersection region, and determining whether the number of intersection regions in each second connected region reaches a preset number; determining the second connected regions whose number of intersection regions reaches the preset number as selected regions; further filtering the selected regions based on their area and the length of their bounding rectangle to obtain the obstacle target region.

[0009] Obstacle avoidance prompts or action control based on the obstacle information specifically includes: calculating the distance from the center of the obstacle target area to the starting point of the lidar data; and issuing corresponding alarm prompts or controlling the vehicle to perform obstacle avoidance actions based on the magnitude of the distance from the center of the obstacle target area to the starting point of the lidar data.

[0010] A vehicle obstacle avoidance device includes: an acquisition module for acquiring laser radar data within a preset angle range in front of the vehicle's direction of travel using a laser radar installed on the vehicle; a generation module for generating a corresponding equivalent image based on the laser radar data; an identification module for processing the equivalent image to identify obstacle information; and a control module for providing obstacle avoidance prompts or action control based on the obstacle information.

[0011] The preset angle range is set according to the width of the vehicle.

[0012] The generation module is specifically used for: constructing a first grayscale image of a preset size with all pixel grayscale values ​​being a first value; converting each distance-angle data in the LiDAR data into corresponding two-dimensional coordinates; changing the grayscale value of each pixel at each of the two-dimensional coordinates in the first grayscale image to a second value to obtain a second grayscale image, wherein the second value is different from the first value; performing an affine transformation on the second grayscale image to transform the starting point of the LiDAR data from the origin at the upper left corner of the second grayscale image to the midpoint of the bottom edge, thereby obtaining a corrected image, which serves as the equivalent image.

[0013] The recognition module is specifically used for: filtering out pixel regions in the equivalent image whose grayscale value is the second value; performing connectivity processing on the pixel regions in the equivalent image whose grayscale value is the second value to obtain multiple first connected regions; expanding each first connected region in a circular pattern to obtain multiple expanded regions, wherein the expansion radius is calculated based on the distance from the center of the first connected region to the starting point of the lidar data, the maximum detection range of the lidar, and the detection accuracy data of the lidar; combining the multiple expanded regions to obtain a joint region; performing connectivity processing on the joint region to obtain multiple second connected regions; traversing the multiple second connected regions, finding the intersection of each second connected region with the pixel regions in the equivalent image whose grayscale value is the second value to obtain an intersection region, and determining whether the number of intersection regions in each second connected region reaches a preset number; determining the second connected regions whose number of intersection regions reaches the preset number as selected regions; further filtering the selected regions based on their area and the length of their bounding rectangle to obtain obstacle target regions.

[0014] The control module is specifically used to: calculate the distance from the center of the obstacle target area to the starting point of the lidar data; and provide corresponding alarm prompts or control the vehicle to perform obstacle avoidance actions based on the magnitude of the distance from the center of the obstacle target area to the starting point of the lidar data.

[0015] The beneficial effects of this invention are:

[0016] This invention acquires LiDAR data within a preset angle range in front of the vehicle's direction of travel using LiDAR, generates a corresponding equivalent image based on the LiDAR data, processes the equivalent image to identify obstacle information, and finally provides obstacle avoidance prompts or action control based on the obstacle information. Thus, it can accurately and automatically identify obstacles in the vehicle's direction of travel in low-light environments and take corresponding obstacle avoidance prompts or actions, thereby improving vehicle safety and saving labor costs. Attached Figure Description

[0017] Figure 1 This is a flowchart of a vehicle obstacle avoidance method according to an embodiment of the present invention;

[0018] Figure 2 This is a block diagram of a vehicle obstacle avoidance device according to an embodiment of the present invention. Detailed Implementation

[0019] 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 embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] The vehicle obstacle avoidance method and device of the present invention are preferably applicable to vehicles that operate in low-light environments, such as monorail vehicles in coal mines and tunnels.

[0021] like Figure 1 As shown, the vehicle obstacle avoidance method of this invention includes the following steps S1-S4:

[0022] S1, acquires LiDAR data within a preset angle range in front of the vehicle's direction of travel using a LiDAR installed on the vehicle.

[0023] In one embodiment of the present invention, a 360° lidar can be selected, meaning the horizontal field of view of the lidar is 360°, and its vertical field of view can be selected according to the vehicle size and the characteristics of its working environment, for example, it can be 40°. The lidar data acquired by the lidar includes the distance-angle data of each detected target point.

[0024] It should be understood that in the vehicle obstacle avoidance method of this invention, the role of the lidar is to detect obstacles. Of the lidar data acquired, only data related to obstacles that affect vehicle movement is of interest. Therefore, based on the vehicle's width, a horizontal field of view angle range can be set directly in front of the vehicle, and lidar data within this range can be captured. That is, the preset angle range is set based on the vehicle's width. In a specific embodiment of this invention, the preset angle range can be a range of 60° directly in front of the vehicle's direction of travel, such as a range of 155°-205°, 50°-110°, etc. The upper and lower boundaries of the preset angle range vary depending on the lidar's installation method, ensuring that the midpoint of the upper and lower boundaries lies in the vehicle's direction of travel.

[0025] S2 generates the corresponding equivalent image based on the lidar data.

[0026] Specifically, step S2 includes: S21, constructing a first grayscale image of a preset size with all pixel grayscale values ​​being a first value; S22, converting each distance-angle data in the LiDAR data into corresponding two-dimensional coordinates; S23, changing the grayscale value of each pixel at each two-dimensional coordinate in the first grayscale image to a second value to obtain a second grayscale image Image, wherein the second value is different from the first value; S24, performing an affine transformation on the second grayscale image Image, transforming the starting point of the LiDAR data from the origin at the upper left corner of the second grayscale image Image to the midpoint of the bottom edge, to obtain a corrected image ImageTrans, which serves as an equivalent image.

[0027] The first grayscale image constructed in step S21 can be understood as the image background, and the pixel at each two-dimensional coordinate can be understood as the target point detected by the lidar. In order to make the target point stand out more in the image, one of the first value and the second value can be set to 0 and the other to 255. Taking the first value as 0 and the second value as 255 as an example, the image constructed in step S21 is a pure black image. In step S23, white dots representing the target object are added to the pure black image.

[0028] The conversion method in step S22 can be as follows: In the two-dimensional coordinates (x, y), x = D * cosA, y = D * sinA. Where D is the distance from the target point to the lidar emission point in the range-angle data, and A is the horizontal field of view angle of the lidar in the range-angle data.

[0029] In step S24, the starting point of the LiDAR data is changed to the midpoint of the bottom edge because it is customary to take the midpoint of the bottom edge of the front image as the center of the side of the vehicle that is moving forward, such as the center of the front of the vehicle.

[0030] Step S2 converts the LiDAR data into pixel coordinate data of a two-dimensional image, thereby equating the position of the target point in the actual space to its position in the two-dimensional image, which facilitates subsequent processing and analysis.

[0031] S3 processes the equivalent image to identify obstacle information.

[0032] Specifically, step S3 includes: S31, filtering out pixel regions in the equivalent image with a grayscale value of the second value, taking a second value of 255 as an example, this region can be called the bright region RegionLight; S32, performing connectivity processing on the pixel regions in the equivalent image with a grayscale value of the second value (such as the bright region RegionLight) to obtain multiple first connected regions ConnectedRegions1; S33, expanding each first connected region ConnectedRegions1 in a circular pattern to obtain multiple expanded regions DilationRegions, wherein the expansion radius is calculated based on the distance from the center of the first connected region ConnectedRegions1 to the starting point of the LiDAR data, the maximum detection range of the LiDAR, and the detection accuracy data of the LiDAR; S34, uniting the multiple expanded regions DilationRegions to obtain a union region UnionRegions; S35, performing connectivity processing on the union regions UnionRegions to obtain multiple S36. Traverse multiple second connected regions ConnectedRegions2, find the intersection of each second connected region ConnectedRegions2 with the pixel region (such as the bright region RegionLight) in the equivalent image with the second gray value, and determine whether the number of intersection regions IntersectionRegions in each second connected region ConnectedRegions2 reaches a preset number; S37. Determine the second connected regions ConnectedRegions2 with the preset number of intersection regions IntersectionRegions as selected regions SelectedRegions; S38. Further filter the selected regions SelectedRegions based on the area and the length of the bounding rectangle to obtain the obstacle target region FinalRegions.

[0033] The connectivity processing in steps S32 and S35 can both employ connectivity algorithms to connect adjacent pixels with a grayscale value of 255 together, creating independent first connected regions ConnectedRegions1 and second connected regions ConnectedRegions2.

[0034] The expansion radius in step S33 is calculated by dividing the distance from the center of the first connected region ConnectedRegions1 to the starting point of the lidar data by the maximum detection range of the lidar, and then multiplying by tan(1°) to obtain the expansion radius. Here, we take the lidar detection accuracy as 1° as an example.

[0035] The joining process in step S34 involves merging all dilation regions that have adjacent or overlapping pixels to obtain larger regions.

[0036] The preset quantity in step S36 can be set according to the accuracy requirements of lidar detection, for example, it can be set to 2. Then, the second connected regions ConnectedRegions2 with a number of intersection regions less than 2 can be eliminated, and the second connected regions ConnectedRegions2 with a number of intersection regions greater than or equal to 2 can be determined as selected regions.

[0037] In step S38, selected regions with an area greater than a preset area and a bounding rectangle with a length greater than a preset length can be defined as obstacle target regions (FinalRegions). Similarly, the preset area and preset length can also be set according to the accuracy requirements of lidar detection.

[0038] The above processing in step S3 is designed to address the issue of noise in the target points detected by the lidar. The farther away an obstacle is from the lidar, the fewer points are detected. In order to eliminate noise and prevent distant obstacles from being removed as noise, the target points are dynamically expanded based on the distance and the minimum detection range, such as 1°, to ultimately obtain a relatively accurate obstacle target area.

[0039] S4 provides obstacle avoidance prompts or motion control based on obstacle information.

[0040] Specifically, the distance from the center of the obstacle target area FinalRegions to the starting point of the lidar data can be calculated, and then corresponding alarm prompts or vehicle obstacle avoidance actions can be controlled based on the magnitude of the distance from the center of the obstacle target area FinalRegions to the starting point of the lidar data.

[0041] After calculating the distance from the center of the obstacle target area (FinalRegions) to the starting point of the lidar data, the obstacle's position and distance information can be displayed on the vehicle's cockpit screen. Simultaneously, alarm prompts can be issued via sound, light, or a combination of sound and light. In one specific embodiment of the invention, the smaller the distance from the center of the obstacle target area (FinalRegions) to the starting point of the lidar data, the louder the sound alert can be, and the brighter the light alert can be, or the higher the flashing frequency can be. When the distance from the center of the obstacle target area (FinalRegions) to the starting point of the lidar data is less than a certain distance threshold, the vehicle can be directly controlled to automatically brake or automatically bypass the obstacle by replanning its trajectory.

[0042] According to the vehicle obstacle avoidance method of the present invention, the method acquires LiDAR data within a preset angle range in front of the vehicle's direction of travel using LiDAR, generates a corresponding equivalent image based on the LiDAR data, processes the equivalent image to identify obstacle information, and finally provides obstacle avoidance prompts or action control based on the obstacle information. Thus, the method can accurately and automatically identify obstacles in the vehicle's direction of travel in low-light environments and take corresponding obstacle avoidance prompts or actions, thereby improving vehicle safety and saving labor costs.

[0043] Corresponding to the vehicle obstacle avoidance method in the above embodiments, the present invention also proposes a vehicle obstacle avoidance device.

[0044] like Figure 2 As shown, the vehicle obstacle avoidance device of this embodiment includes an acquisition module 10, a generation module 20, an identification module 30, and a control module 40. The acquisition module 10 acquires laser radar data within a preset angle range ahead of the vehicle's direction of travel using a laser radar installed on the vehicle; the generation module 20 generates a corresponding equivalent image based on the laser radar data; the identification module 30 processes the equivalent image to identify obstacle information; and the control module 40 provides obstacle avoidance prompts or action control based on the obstacle information.

[0045] In one embodiment of the present invention, the preset angle range can be set according to the width of the vehicle.

[0046] In one embodiment of the present invention, the generation module 20 is specifically used to: construct a first grayscale image of a preset size, wherein all pixel grayscale values ​​are first values; convert each distance-angle data in the lidar data into corresponding two-dimensional coordinates; change the grayscale value of each pixel at each two-dimensional coordinate in the first grayscale image to a second value to obtain a second grayscale image, wherein the second value is different from the first value; perform an affine transformation on the second grayscale image to transform the starting point of the lidar data from the origin at the upper left corner of the second grayscale image to the midpoint of the bottom edge to obtain a corrected image, which serves as an equivalent image.

[0047] In one embodiment of the present invention, the identification module 30 is specifically used for: filtering out pixel regions in the equivalent image with grayscale values ​​of a second value; performing connectivity processing on the pixel regions in the equivalent image with grayscale values ​​of the second value to obtain multiple first connected regions; expanding each first connected region in a circular manner to obtain multiple expanded regions, wherein the expansion radius is calculated based on the distance from the center of the first connected region to the starting point of the lidar data, the maximum detection range of the lidar, and the detection accuracy data of the lidar; combining the multiple expanded regions to obtain a joint region; performing connectivity processing on the joint region to obtain multiple second connected regions; traversing the multiple second connected regions, finding the intersection of each second connected region with the pixel regions in the equivalent image with grayscale values ​​of the second value to obtain an intersection region, and determining whether the number of intersection regions in each second connected region reaches a preset number; determining the second connected regions with the number of intersection regions reaching the preset number as selected regions; and further filtering the selected regions based on their area and the length of their circumscribed rectangle to obtain the obstacle target region.

[0048] In one embodiment of the present invention, the control module 40 is specifically used to: calculate the distance from the center of the obstacle target area to the starting point of the lidar data; and provide corresponding alarm prompts or control the vehicle to perform obstacle avoidance actions based on the magnitude of the distance from the center of the obstacle target area to the starting point of the lidar data.

[0049] For more specific implementation methods, please refer to the embodiments of the vehicle obstacle avoidance method described above. To avoid redundancy, they will not be repeated here.

[0050] According to an embodiment of the present invention, the vehicle obstacle avoidance device acquires laser radar data within a preset angle range in front of the vehicle's direction of travel using laser radar, generates a corresponding equivalent image based on the laser radar data, processes the equivalent image to identify obstacle information, and finally provides obstacle avoidance prompts or action control based on the obstacle information. Thus, it can accurately and automatically identify obstacles in the vehicle's direction of travel in low-light environments and take corresponding obstacle avoidance prompts or actions, thereby improving vehicle safety and saving labor costs.

[0051] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. "A plurality of" means two or more, unless otherwise explicitly specified.

[0052] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0053] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0054] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0055] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0056] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0057] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0058] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0059] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0060] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A vehicle obstacle avoidance method, characterized in that, Includes the following steps: The laser radar installed on the vehicle acquires laser radar data within a preset angle range in front of the vehicle's direction of travel; Generate a corresponding equivalent image based on the lidar data; The equivalent image is processed to identify obstacle information; Obstacle avoidance prompts or action control are provided based on the obstacle information. Generating a corresponding equivalent image based on the LiDAR data specifically includes: constructing a first grayscale image of a preset size with all pixels having a first value; converting each distance-angle data point in the LiDAR data into corresponding two-dimensional coordinates; changing the grayscale value of each pixel at each of the two-dimensional coordinates in the first grayscale image to a second value to obtain a second grayscale image, wherein the second value is different from the first value; performing an affine transformation on the second grayscale image, transforming the starting point of the LiDAR data from the origin at the top left corner of the second grayscale image to the midpoint of the bottom edge, to obtain a corrected image, which serves as the equivalent image. The equivalent image is processed to identify obstacle information, specifically including: filtering out pixel regions in the equivalent image whose grayscale value is the second value; performing connectivity processing on the pixel regions in the equivalent image whose grayscale value is the second value to obtain multiple first connected regions; expanding each first connected region in a circular pattern to obtain multiple expanded regions, wherein the expansion radius is calculated based on the distance from the center of the first connected region to the starting point of the lidar data, the maximum detection range of the lidar, and the detection accuracy data of the lidar; combining the multiple expanded regions to obtain a joint region; performing connectivity processing on the joint region to obtain multiple second connected regions; traversing the multiple second connected regions, finding the intersection of each second connected region with the pixel regions in the equivalent image whose grayscale value is the second value to obtain an intersection region, and determining whether the number of intersection regions in each second connected region reaches a preset number; determining the second connected regions whose number of intersection regions reaches the preset number as selected regions; further filtering the selected regions based on their area and the length of their bounding rectangle to obtain the obstacle target region.

2. The vehicle obstacle avoidance method according to claim 1, characterized in that, The preset angle range is set according to the width of the vehicle.

3. The vehicle obstacle avoidance method according to claim 1, characterized in that, Obstacle avoidance prompts or action control based on the obstacle information specifically includes: Calculate the distance from the center of the obstacle target area to the starting point of the lidar data; Based on the distance from the center of the obstacle target area to the starting point of the lidar data, corresponding alarm prompts or control the vehicle to perform obstacle avoidance actions will be issued.

4. A vehicle obstacle avoidance device, characterized in that, include: The acquisition module is used to acquire laser radar data within a preset angle range in front of the vehicle's direction of travel using a laser radar installed on the vehicle. The generation module is used to generate a corresponding equivalent image based on the lidar data; The recognition module is used to process the equivalent image to identify obstacle information; The control module is used to provide obstacle avoidance prompts or action control based on the obstacle information. The generation module is specifically used for: constructing a first grayscale image of a preset size where all pixel grayscale values ​​are first values; converting each distance-angle data in the LiDAR data into corresponding two-dimensional coordinates; changing the grayscale value of each pixel at each of the two-dimensional coordinates in the first grayscale image to a second value to obtain a second grayscale image, wherein the second value is different from the first value; performing an affine transformation on the second grayscale image, transforming the starting point of the LiDAR data from the origin at the top left corner of the second grayscale image to the midpoint of the bottom edge, to obtain a corrected image, which serves as the equivalent image. The recognition module is specifically used for: filtering out pixel regions in the equivalent image whose grayscale value is the second value; performing connectivity processing on the pixel regions in the equivalent image whose grayscale value is the second value to obtain multiple first connected regions; expanding each first connected region in a circular pattern to obtain multiple expanded regions, wherein the expansion radius is calculated based on the distance from the center of the first connected region to the starting point of the lidar data, the maximum detection range of the lidar, and the detection accuracy data of the lidar; combining the multiple expanded regions to obtain a joint region; performing connectivity processing on the joint region to obtain multiple second connected regions; traversing the multiple second connected regions, finding the intersection of each second connected region with the pixel regions in the equivalent image whose grayscale value is the second value to obtain an intersection region, and determining whether the number of intersection regions in each second connected region reaches a preset number; determining the second connected regions whose number of intersection regions reaches the preset number as selected regions; further filtering the selected regions based on their area and the length of their bounding rectangle to obtain obstacle target regions.

5. The vehicle obstacle avoidance device according to claim 4, characterized in that, The preset angle range is set according to the width of the vehicle.

6. The vehicle obstacle avoidance device according to claim 4, characterized in that, The control module is specifically used for: Calculate the distance from the center of the obstacle target area to the starting point of the lidar data; Based on the distance from the center of the obstacle target area to the starting point of the lidar data, corresponding alarm prompts or control the vehicle to perform obstacle avoidance actions will be issued.

Images