Gap detection method and device based on laser radar

Abstract

The invention relates to a gap detection method and device based on a laser radar, and the method comprises the steps: obtaining a plurality of frames of point clouds collected by the laser radar for a target gap in a detection period, and in the plurality of frames of point clouds, each frame of point cloud corresponds to a vertical angle resolution and a horizontal angle resolution, the multiple frames of point clouds correspond to at least two different vertical angle resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angle resolutions; fusing the multiple frames of point clouds to obtain fused point clouds; target detection is carried out on the fusion point cloud, a gap detection result is determined, and the gap detection result includes that foreign matter exists in the gap or does not exist in the gap. According to the method, the fused point cloud is obtained by fusing the multiple frames of point clouds with point cloud distribution differences, and compared with any frame of point cloud in the multiple frames of point clouds, the fused point cloud has more dense points. Therefore, the accuracy of the detection result can be improved by performing foreign matter detection on the target gap through fusing the point cloud.

Description

Technical Field

[0001] This application belongs to the technical field of rail transit, and particularly relates to a method and device for gap detection based on lidar. Background Art

[0002] In urban rail transit, platform screen doors are generally installed on the platform for safety reasons. There is a certain gap between the screen door and the train door. For example, there is a certain gap between the full-height platform screen door and the train door in the subway; in addition, for some ground subway platforms or light rail platforms, semi-height platform screen doors are generally designed, and there is also a certain gap between the semi-height platform screen door and the train door at this time; even in some special subway platforms, some trains do not stop and pass through at high speed. At this time, a relatively large gap is set between the full-height platform screen door and the train door installed on the platform, and the width of the gap can sometimes reach more than 1.2 meters. When the train is running, if there are foreign objects such as people or objects in the gap between the screen door and the train door, major accidents may occur. To ensure the safety of train operation, it is necessary to detect foreign objects in the gap between the screen door and the train door before the train departs: if there are foreign objects in the gap, an alarm prompt is issued; if there are no foreign objects in the gap, the train can leave normally.

[0003] As a radar system that emits laser beams to detect the position, speed and other characteristic quantities of targets, lidar is often used to detect foreign objects in the gap between the screen door and the train door because of its characteristics of being not interfered by ambient light and being able to perform three-dimensional detection. One solution is to fix a lidar at one end of the gap to scan the entire gap. The point cloud formed by the lidar scanning at the proximal end closer to the lidar is relatively dense, but the point cloud formed by the lidar scanning at the distal end farther from the lidar is relatively sparse; and the accuracy of the foreign object detection result based on the sparse point cloud is poor. For example, small foreign objects often cannot be detected.

[0004] Therefore, how to improve the accuracy of foreign object detection in the gap between the screen door and the train door has become an urgent technical problem to be solved. Summary of the Invention

[0005] The embodiments of this application provide a method and device for gap detection based on lidar, which can improve the accuracy of foreign object detection in the gap between the screen door and the train door.

[0006] In a first aspect, the embodiments of this application provide a method for gap detection based on lidar, including:

[0007] Obtain multiple frames of point clouds collected by a lidar for a target gap within a detection period. In the multiple frames of point clouds: each frame of point cloud corresponds to a vertical angular resolution and a horizontal angular resolution, the multiple frames of point clouds correspond to at least two different vertical angular resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angular resolutions;

[0008] Fuse the multiple frames of point clouds to obtain a fused point cloud;

[0009] Perform target detection on the fused point cloud to determine the gap detection result, where the gap detection result includes that there is a foreign object in the gap or there is no foreign object in the gap.

[0010] In the above method, by collecting multiple frames of point clouds with a lidar within a detection period, at least two different vertical angular resolutions or at least two different horizontal angular resolutions are used in the multiple frames of point clouds; different vertical angular resolutions or different horizontal angular resolutions result in differences in the point cloud distribution in the multiple frames of point clouds. The fused point cloud obtained by fusing multiple frames of point clouds with different point cloud distributions has denser points than any single frame of point cloud in the multiple frames of point clouds. Therefore, detecting foreign objects in the target gap through the fused point cloud can improve the accuracy of the detection result.

[0011] In one embodiment, in the multiple frames of point clouds, the vertical angular resolutions of different frames of point clouds are different; and / or, in the multiple frames of point clouds, the horizontal angular resolutions of different frames of point clouds are different.

[0012] In one embodiment, in the multiple frames of point clouds: if the vertical angular resolution of the first frame of point cloud is less than the vertical angular resolution of the second frame of point cloud, then the horizontal angular resolution of the first frame of point cloud is less than the horizontal angular resolution of the second frame of point cloud, and the first frame of point cloud and the second frame of point cloud are any two different frames of point clouds in the multiple frames of point clouds.

[0013] In one embodiment, the target gap includes multiple sub-regions, and any two sub-regions do not completely overlap or do not overlap; wherein, fusing the multiple frames of point clouds to obtain a fused point cloud includes:

[0014] Match the multiple frames of point clouds with the multiple sub-regions to determine at least one frame of point cloud corresponding to each sub-region; determine the points in the target frame of point cloud that are within the range of the target sub-region as target points, where the target frame of point cloud is any one frame of point cloud in the multiple frames of point clouds, and the target sub-region is the sub-region corresponding to the target frame of point cloud among the multiple sub-regions; splice all the target points to obtain the fused point cloud.

[0015] In one embodiment, among multiple sub-regions: the distances between different sub-regions and the lidar are different; if the distance between the first sub-region and the lidar is greater than the distance between the second sub-region and the lidar, the horizontal angular resolution of each frame of point cloud corresponding to the first sub-region is less than the horizontal angular resolution of each frame of point cloud corresponding to the second sub-region; the first sub-region and the second sub-region are any two different sub-regions among the multiple sub-regions.

[0016] In a second aspect, an embodiment of the present application provides a gap detection device based on a lidar. The device includes units for performing each step of the method in any one of the above first aspects.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in any one of the above first aspects is implemented.

[0018] In a fourth aspect, an embodiment of the present application provides a gap detection system. The system includes a lidar and the electronic device described in any one of the above second aspects. The lidar is communicatively connected to the electronic device.

[0019] In one embodiment, the lidar is a MEMS lidar. Among the multiple frames of point clouds collected by the MEMS lidar: each frame of point cloud corresponds to a horizontal galvanometer frequency and a vertical galvanometer frequency. The multiple frames of point clouds correspond to at least two different horizontal galvanometer frequencies, and / or the multiple frames of point clouds correspond to at least two different vertical galvanometer frequencies.

[0020] In one embodiment, there are multiple lidars. The multiple lidars are spaced apart in the length direction of the target gap, and different lidars scan different regions within the target gap.

[0021] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the method described in any one of the above first aspects is implemented.

[0022] In a sixth aspect, an embodiment of the present application provides a chip, including: a processor for calling and running a computer program from a memory, so that a computer device installed with the chip executes the method described in any one of the above first aspects.

[0023] It can be understood that the beneficial effects of the above second to sixth aspects can be referred to the relevant descriptions in the above first aspect, and will not be elaborated here. Description of the Drawings

[0024] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for use in the embodiments or the description of the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0025] Figure 1a And Figure 1b are respectively schematic diagrams of laser beam lines obtained by a lidar scanning a target gap to obtain two frames of point clouds in an embodiment of the present application.

[0026] Figure 2 is a schematic flowchart of a gap detection method based on lidar provided in an embodiment of the present application;

[0027] Figure 3 is a schematic diagram of the application environment of a gap detection system provided in an embodiment of the present application;

[0028] Figure 4 is a schematic diagram of the application environment of a gap detection system provided in another embodiment of the present application;

[0029] Figure 5 is a schematic diagram of the application scenario of a gap detection system provided in yet another embodiment of the present application;

[0030] Figure 6 is a schematic diagram of the application scenario of a gap detection system provided in still another embodiment of the present application;

[0031] Figure 7 is a schematic diagram of the control principle of a gap detection system provided in an embodiment of the present application;

[0032] Figure 8 is a schematic diagram of the distribution mode of horizontal points in the point cloud in a gap detection method based on lidar provided in an embodiment of the present application;

[0033] Figure 9 is a schematic diagram of the distribution mode of horizontal points in the point cloud in a gap detection method based on lidar provided in another embodiment of the present application;

[0034] Figure 10 is a structural block diagram of a gap detection device based on lidar provided in an embodiment of the present application;

[0035] Figure 11 is an internal structure diagram of an electronic device provided in an embodiment of the present application. Detailed implementation manners

[0036] In the following description, for purposes of illustration and not limitation, specific details such as particular system architectures, technologies, etc. are set forth in order to provide a thorough understanding of embodiments of the present application. However, those skilled in the art should appreciate that the present application may be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary details.

[0037] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or their groups.

[0038] It should also be understood that the term "and / or" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0039] As used in the specification of the present application and the appended claims, the term "if" may be construed, depending on the context, as "when" or "once" or "in response to determining" or "in response to detecting". Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be construed, depending on the context, as meaning "once determined" or "in response to determining" or "once detected [the described condition or event]" or "in response to detecting [the described condition or event]".

[0040] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0041] Reference to "one embodiment" or "some embodiments" or the like described in the specification of the present application means that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0042] An embodiment of the present application provides a method for detecting a gap based on a lidar. By acquiring multiple frames of point clouds collected by the lidar for a target gap within a detection period, in the multiple frames of point clouds: each frame of point cloud corresponds to a vertical angular resolution and a horizontal angular resolution, the multiple frames of point clouds correspond to at least two different vertical angular resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angular resolutions; the multiple frames of point clouds are fused to obtain a fused point cloud; target detection is performed on the fused point cloud to determine a gap detection result, and the gap detection result includes that there is a foreign object in the gap or there is no foreign object in the gap. By collecting multiple frames of point clouds by the lidar within a detection period, at least two different vertical angular resolutions are adopted in the multiple frames of point clouds, or at least two different horizontal angular resolutions are adopted; different vertical angular resolutions or different horizontal angular resolutions make the distribution of points in the multiple frames of point clouds different. By fusing the multiple frames of point clouds with different point distributions, a fused point cloud with increased point density can be obtained. Based on the fused point cloud for target detection, the missed detection and misdetection of foreign objects can be reduced, and the accuracy of foreign object detection can be improved.

[0043] For ease of understanding, the following takes the lidar scanning a target gap to obtain a first frame of point cloud and a second frame of point cloud as an example to briefly illustrate the problem solved by the present application. Figure 1a and Figure 1b In an embodiment of the present application, it is a schematic diagram of the laser beam of the lidar scanning a target gap to obtain two frames of point clouds. As Figure 1a and Figure 1b shown, the lidar 101 scans the gap between the train 102 and the platform screen door 103, and there is an object 104 in the gap.

[0044] As Figure 1a shown, the lidar 101 scans the gap between the train 102 and the platform screen door 103 with a horizontal angular resolution of δ h1 , and obtains a first frame of point cloud. As Figure 1b shown, the lidar 101 scans the gap between the train 102 and the platform screen door 103 with a horizontal angular resolution of δ h2 , and obtains a second frame of point cloud, where δ h1 >δ h2 .

[0045] As Figure 1a shown, when the lidar scans the first frame of point cloud, due to the relatively large horizontal angular resolution, the point cloud formed by the lidar at the position of the object 104 is relatively sparse, and the laser beams emitted by the lidar do not project onto the object 104, so there are no points of the object 104 in the first frame of point cloud.

[0046] As Figure 1bAs shown in the figure, when the lidar scans the second frame of point cloud, due to the small horizontal angle resolution, the point cloud formed by the lidar at the position of the object 104 is relatively dense. One of the laser beams emitted by the lidar is projected onto the object 104, so the points of the object 104 are formed in the second frame of point cloud.

[0047] According to Figure 1a and Figure 1b it can be known that at a small horizontal angle resolution, denser point cloud can be obtained, so the detection of objects is more accurate; at the same time, by using the detection method in the embodiments of the present application, the first frame of point cloud and the second frame of point cloud can be fused. When target detection is performed according to the fused point cloud, the probability of detecting an object can be increased.

[0048] The detection method in the embodiments of the present application can fuse point clouds with different horizontal angle resolutions, point clouds with different vertical angle resolutions, or point clouds with different horizontal and vertical angle resolutions to obtain a fused point cloud, and then perform target detection according to the fused point cloud. As long as there are point clouds with different angle resolutions in at least one direction, the effect of improving object detection can be achieved, and the present application does not limit this.

[0049] It should be understood that the gap detection method based on lidar in the embodiments of the present application is actually a non-repetitive scanning detection method. This method changes the horizontal angle resolution and / or vertical angle resolution of the lidar to achieve non-repetitive scanning of the lidar for the gap, fuses multiple frames of point clouds obtained from non-repetitive scanning to obtain a fused point cloud, and then performs target detection of the gap according to the fused point cloud.

[0050] Next, with reference to specific embodiments, the gap detection method based on lidar provided by the present application will be exemplarily described.

[0051] In one embodiment of the present application, there is provided a gap detection method based on lidar as shown in Figure 2 . It can be understood that the following description is only an example and does not constitute a limitation on the protection scope of the present application. As shown in Figure 2 , this method may include S201 to S203. Each step will be described below.

[0052] Step S201: Obtain multiple frames of point clouds collected by the lidar for a target gap within a detection period. In the multiple frames of point clouds: each frame of point cloud corresponds to a vertical angle resolution and a horizontal angle resolution, the multiple frames of point clouds correspond to at least two different vertical angle resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angle resolutions.

[0053] In an embodiment of the present application, a detection period refers to the time period from when the train door closes to when the train departs; the target gap refers to the gap between the train and the platform screen door. During a detection period, the lidar scans the target gap to collect point clouds.

[0054] It should be understood that every time the lidar completes a scan, a frame of point cloud is collected. Therefore, during a detection period, the lidar scans the target gap multiple times to collect multiple frames of point clouds.

[0055] It can be understood that each frame of point cloud is obtained by the lidar scanning the target gap at a certain horizontal angular resolution and vertical angular resolution. Therefore, the horizontal angular resolution and vertical angular resolution corresponding to each frame of point cloud are respectively the horizontal angular resolution and vertical angular resolution of the lidar when scanning the target gap to obtain this frame of point cloud.

[0056] In an embodiment of the present application, if multiple frames of point clouds correspond to at least two different vertical angular resolutions, it means that the multiple frames of point clouds are collected at more than two vertical angular resolutions. The point clouds obtained at different vertical angular resolutions have different point cloud densities in the vertical direction; if multiple frames of point clouds correspond to at least two different horizontal angular resolutions, it means that the multiple frames of point clouds are collected at more than two horizontal angular resolutions. The point clouds obtained at different horizontal angular resolutions have different point cloud densities in the horizontal direction.

[0057] It should be understood that in an embodiment of the present application, the multiple frames of point clouds can be point clouds with different horizontal angular resolutions, or point clouds with different vertical angular resolutions, or point clouds with both different horizontal angular resolutions and different vertical angular resolutions. This application does not limit this here.

[0058] In some embodiments, among the multiple frames of point clouds, the vertical angular resolutions of different frames of point clouds are different. That is, every time the lidar scans a frame of point cloud, the vertical angular resolution changes once, so that the vertical angular resolutions of different frames of point clouds in the multiple frames of point clouds are different. By using different vertical angular resolutions to obtain different frames of point clouds, the fused point cloud can fuse as many point clouds as possible at different vertical angular resolutions, thereby maximizing the accuracy of object detection in the vertical direction.

[0059] In some embodiments, in multiple frames of point clouds, the horizontal angular resolutions of different frames of point clouds are different. That is, every time the lidar scans a frame of point cloud, the horizontal angular resolution changes once, so that the horizontal angular resolutions of different frames of point clouds in multiple frames of point clouds are different. By using different horizontal angular resolutions to obtain different frames of point clouds, the fused point cloud can fuse as many point clouds as possible under different horizontal angular resolutions, thereby maximizing the accuracy of object detection in the horizontal direction.

[0060] In some other embodiments, in multiple frames of point clouds, the vertical angular resolutions of different frames of point clouds are different, and the horizontal angular resolutions of different frames of point clouds are also different. That is, every time the lidar scans a frame of point cloud, both the horizontal angular resolution and the vertical angular resolution change once, so that both the horizontal angular resolution and the vertical angular resolution of different frames of point clouds in multiple frames of point clouds are different. By using different vertical angular resolutions and different horizontal angular resolutions to obtain different frames of point clouds, the fused point cloud can fuse as many point clouds as possible under different vertical angular resolutions and horizontal angular resolutions, thereby maximizing the accuracy of object detection in the vertical direction and the horizontal direction.

[0061] It can be understood that, in some other embodiments, each vertical angular resolution or horizontal angular resolution can correspond to one frame of point cloud or multiple frames of point clouds; in addition, the number of frames of point clouds corresponding to each vertical angular resolution or horizontal angular resolution can be the same or different; the present application does not make specific limitations on this.

[0062] In some embodiments, assume that the first frame of point cloud and the second frame of point cloud are any two different frames of point clouds in multiple frames of point clouds: if the vertical angular resolution of the first frame of point cloud is less than the vertical angular resolution of the second frame of point cloud, then the horizontal angular resolution of the first frame of point cloud is less than the horizontal angular resolution of the second frame of point cloud. In this implementation manner, the point cloud with a smaller vertical angular resolution also has a smaller horizontal resolution. Such a setting increases the point density in the vertical direction of different frames of point clouds, and at the same time, the point density in the horizontal direction also increases, so that the increase or decrease of the point cloud density in the vertical direction and the horizontal direction of different frames of point clouds is synchronized, making the controllability of the point cloud density better and more convenient for subsequent utilization of the point cloud density.

[0063] Step S202: Fuse multiple frames of point clouds to obtain a fused point cloud.

[0064] In the embodiments of the present application, when fusing multiple frames of point clouds, different fusion methods can be used as long as the point density of the fused point cloud is greater than the point density in any one frame of the multiple frames of point clouds.

[0065] In some embodiments, fusing multiple frames of point clouds can be achieved by stitching all the points in the multiple frames of point clouds to obtain a fused point cloud. That is, the fused point cloud includes all the points in each frame of the multiple frames of point clouds. Such a setting maximally encrypts the density of the points in the fused point cloud and improves the accuracy of subsequent target detection.

[0066] In some other embodiments, the target gap can be divided into multiple sub-regions, and any two sub-regions among the multiple sub-regions do not completely overlap (i.e., partially overlap) or do not overlap (i.e., completely do not overlap). When fusing multiple frames of point clouds, it is specifically carried out according to the following steps: (1) Matching the multiple frames of point clouds with the multiple sub-regions to determine at least one frame of point cloud corresponding to each sub-region; (2) Determining the points in the target frame of point cloud that are within the range of the target sub-region as target points, where the target frame of point cloud is any one frame of the multiple frames of point clouds, and the target sub-region is the sub-region corresponding to the target frame of point cloud among the multiple sub-regions; (3) Stitching all the target points to obtain a fused point cloud. In this implementation method, by dividing the target gap into different sub-regions, determining at least one frame of point cloud corresponding to each sub-region, and stitching the points within the corresponding sub-region range of each frame of point cloud to obtain a fused point cloud, that is, taking partial points from each frame of point cloud to form a fused point cloud, the calculation amount can be reduced and the operation cost can be lowered.

[0067] Exemplarily, the distances between different sub-regions and the lidar are different. When matching the multiple frames of point clouds with the multiple sub-regions, the matching is carried out according to the horizontal angle resolution (or vertical angle resolution) of different frames of point clouds and the distances between different sub-regions and the lidar. Specifically, for a sub-region farther from the lidar, one or more frames of point clouds with a smaller horizontal angle resolution can be matched; in this way, among the multiple sub-regions: the distances between different sub-regions and the lidar are different; if the distance between the first sub-region and the lidar is greater than the distance between the second sub-region and the lidar, then the horizontal angle resolution of each frame of point cloud corresponding to the first sub-region is less than the horizontal angle resolution of each frame of point cloud corresponding to the second sub-region; where the first sub-region and the second sub-region are any two different sub-regions among the multiple sub-regions. At the position in the target gap with the same distance from the lidar, the smaller the horizontal angle resolution of the lidar, the denser the points in the obtained point cloud; therefore, for a sub-region closer to the lidar, a point cloud with a larger corresponding horizontal angle resolution is used, and for a point cloud farther from the lidar, a point cloud with a smaller corresponding horizontal angle resolution is used, so that the point cloud density within the range of different sub-regions of the fused point cloud is relatively uniform.

[0068] It should be understood that each sub-region can correspond to one or more frames of point clouds, and the number of frames of point clouds corresponding to different sub-regions can be the same or different, and the present application does not limit this.

[0069] In some embodiments, the lidar can be disposed at one end of the target gap. The length direction of the target gap is divided into multiple sub-regions, and the multiple sub-regions do not overlap. As the distance between the sub-region and the lidar increases, the horizontal angular resolution and the vertical angular resolution of the lidar scanning gradually decrease. At positions in the target gap at the same distance from the lidar, when the horizontal angular resolution and the vertical angular resolution of the lidar are smaller, the points of the obtained point cloud are denser. Therefore, for the sub-regions closer to the lidar, point clouds with relatively larger horizontal angular resolution and vertical angular resolution are adopted, and for the point clouds farther from the lidar, point clouds with relatively smaller horizontal angular resolution and vertical angular resolution are adopted, so that the point cloud density within different sub-region ranges of the fused point cloud is relatively uniform and can all exceed a certain threshold, which can improve the accuracy of target detection while avoiding excessive computational complexity.

[0070] Step S203: Perform target detection on the fused point cloud to determine the gap detection result, where the gap detection result includes that there is a foreign object in the gap or there is no foreign object in the gap.

[0071] It should be understood that any available target detection algorithm can be adopted for the target detection based on the fused point cloud, which will not be elaborated here.

[0072] In the above-described lidar-based gap detection method in the embodiments, by collecting multiple frames of point clouds by the lidar within one detection period, at least two different vertical angular resolutions or at least two different horizontal angular resolutions are adopted in the multiple frames of point clouds; the different vertical angular resolutions or different horizontal angular resolutions result in differences in the point cloud distribution in the multiple frames of point clouds. The fused point cloud obtained by fusing the multiple frames of point clouds with different point cloud distributions has denser points than any one of the multiple frames of point clouds. Therefore, by using the fused point cloud to detect foreign objects in the target gap, the accuracy of the detection result can be improved.

[0073] For the sake of easy understanding, the gap detection system in the embodiments of the present application will be exemplarily described below with reference to the accompanying drawings.

[0074] Figure 3 It is a schematic diagram of the application environment of the gap detection system in an embodiment of the present application. As Figure 3 shown, in this scenario, the gap detection system includes a lidar 301 and an electronic device 302. The lidar 301 scans the gap between the train 303 and the platform screen door 304 to obtain multiple frames of point clouds. The lidar 301 is fixedly disposed at the first end of the gap and scans in the direction of the second end of the gap.

[0075] In this scenario, the lidar 301 and the electronic device 302 are communicatively connected. The communication connection between the lidar 301 and the electronic device 302 can be a wired communication connection or a wireless communication connection, and this application does not make specific limitations thereto. The lidar 301 sends multiple frames of point clouds obtained to the electronic device 302, and the electronic device 302 fuses the multiple frames of point clouds to obtain a fused point cloud; then performs object detection on the fused point cloud to determine a gap detection result, where the gap detection result includes that there is a foreign object in the gap or there is no foreign object in the gap.

[0076] It can be understood that Figure 3 in which FIX represents the fixed door in the platform screen door, and ASD1, ASD2, ASD3, and ASD4 represent the 4 sliding doors in the platform screen door. The fixed door is immovable and only used for blocking, while the sliding doors are opposite to the train doors and open when the train doors open to allow passengers to pass through.

[0077] It should be understood that the lidar 301 and the electronic device 302 can be integrally provided in one device, and this application does not limit this.

[0078] In some embodiments, the electronic device 302 can be an embedded device.

[0079] It should be understood that in the multiple frames of point clouds obtained by scanning the lidar 301: each frame of point cloud corresponds to a vertical angular resolution and a horizontal angular resolution, the multiple frames of point clouds correspond to at least two different vertical angular resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angular resolutions.

[0080] It should be understood that for different types of lidars, different methods can be used to change the horizontal angular resolution and / or vertical angular resolution of the point cloud. It can be understood that a lidar generally includes a laser emission system, a laser reception system, a scanning system, and an information processing system. Generally, the horizontal angular resolution or vertical angular resolution of the lidar can be controlled by controlling the laser emission system or the scanning system.

[0081] The following is an exemplary description in combination with different types of lidars. It should be understood that the following description is only for illustration and should not be construed as a limitation on the protection scope of this application.

[0082] In some embodiments, the lidar is a mechanical lidar. The horizontal angular resolution can be changed by varying the rotation speed of the scanning system of the mechanical lidar. The faster the rotation speed of the scanning system, the larger the horizontal angular resolution; the slower the rotation speed of the scanning system, the smaller the horizontal angular resolution. Additionally, for the vertical angular resolution, without changing the number of laser beams, the vertical angular resolution can be changed by altering the emission angle of the laser in the laser emission system, which will not be elaborated here.

[0083] In some other embodiments, the lidar is a MEMS (Micro-Electro-Mechanical System) lidar. For a MEMS lidar, the horizontal angular resolution can be changed by varying the horizontal galvanometer frequency of the lidar, and the vertical angular resolution can be changed by varying the vertical galvanometer frequency of the lidar. That is, for a MEMS lidar, in the multiple frames of point clouds it acquires, each frame of point cloud corresponds to a horizontal galvanometer frequency and a vertical galvanometer frequency. The multiple frames of point clouds correspond to at least two different horizontal galvanometer frequencies, and / or the multiple frames of point clouds correspond to at least two different vertical galvanometer frequencies.

[0084] In some embodiments, Figure 3 shows the scanning ranges of the lidar at different horizontal galvanometer frequencies and different vertical galvanometer frequencies. As Figure 3 shown, when the horizontal galvanometer frequency and the vertical galvanometer frequency are relatively large, the scanning range of the lidar is closer to the lidar and the horizontal angle is larger; when the horizontal galvanometer frequency and the vertical galvanometer frequency are relatively small, the scanning range of the lidar is farther from the lidar and the horizontal angle is smaller.

[0085] See Figure 4 , which is a schematic diagram of the application environment of the gap detection system provided by another embodiment of the present application. As Figure 4 shown, in this scenario, the gap detection system includes a first lidar 401, a second lidar 402, and an electronic device 403. Both the first lidar 401 and the second lidar 402 are used to scan the gap between the train 404 and the platform screen door 405 to obtain multiple frames of point clouds. The first lidar 401 and the second lidar 402 are respectively fixedly arranged at one end of the gap. The coverage range of the first lidar 401 is shown as the first area 410, and the coverage range of the second lidar is shown as the second area 420.

[0086] See Figure 5 , which is a schematic diagram of the application environment of the gap detection system provided by another embodiment of the present application. As Figure 5As shown in the figure, in this scenario, the gap detection system includes a third lidar 501, a fourth lidar 502, and an electronic device 503. Both the third lidar 501 and the fourth lidar 502 are used to scan the gap between the train 504 and the platform screen door 505 to obtain multiple frames of point clouds. The third lidar 501 is fixedly installed at the first end of the gap, and the fourth lidar 502 is fixedly installed in the gap. The coverage range of the third lidar 501 is shown as the third area 510, and the coverage range of the fourth lidar is shown as the fourth area 520.

[0087] It can be understood that Figure 4 and Figure 5 in which FIX represents the fixed door in the platform screen door, and ASD represents the sliding door in the platform screen door. The fixed door is immovable and only used for shielding, while the sliding door is opposite to the train door and opens when the train door opens to allow passengers to pass through.

[0088] In Figure 4 and Figure 5 the scenario shown, multiple lidars (i.e., more than two) are set, and the multiple lidars are spaced apart in the gap length direction. This is mainly to deal with the situation where the coverage range of a single lidar cannot cover the entire gap. By setting multiple lidars, complete coverage of the gap can be achieved, ensuring the accuracy of gap foreign object detection.

[0089] It should be understood that in Figure 4 and Figure 5 the scenario shown, each lidar can obtain multiple frames of point clouds. When implementing the gap detection method based on lidar in the embodiments of the present application, all the point clouds collected by multiple lidars can be fused and then object detection is performed on the fused point clouds; or the multiple frames of point clouds collected by each lidar can be fused and object detection can be performed separately; the embodiments of the present application do not limit the specific implementation manner.

[0090] As Figure 6 shown, it is a schematic diagram of the application environment of the gap detection system provided by another embodiment of the present application. In this embodiment, the gap detection system includes a lidar 601 and an electronic device 602. The lidar 601 is used to scan the gap between the train 603 and the platform screen door 604 to obtain multiple frames of point clouds. In a detection cycle, the position of the lidar 601 in the gap will change to deal with the situation where the lidar 601 cannot detect the entire gap at one position. As Figure 6 shown, the lidar 601 moves twice in total in the gap. By moving the lidar, complete coverage of the gap can be achieved, ensuring the accuracy of gap foreign object detection. It can be understood that Figure 6In the FIX, it represents the fixed door in the platform screen door, while the ASD represents the sliding door in the platform screen door. The fixed door is immovable and only used for blocking, while the sliding door is opposite to the train door and opens when the train door opens to allow passengers to pass through.

[0091] Exemplarily, the lidar 601 can be arranged on the slide rail, and the lidar is controlled to move on the slide rail to achieve the detection and coverage of a larger area by the lidar 601; when there is enough time, the use of a single lidar can achieve the coverage of a sufficiently long gap, reducing the hardware cost and debugging cost of the lidar.

[0092] It should be understood that Figure 6 In the scene shown, the lidar can obtain multiple frames of point clouds at each position respectively. When implementing the gap detection method based on the lidar in the embodiments of the present application, all the point clouds obtained by the lidar at multiple positions can be fused, and finally target detection is performed on the fused point clouds; alternatively, the multiple frames of point clouds collected by the lidar at each position can be fused respectively and target detection can be performed respectively; the embodiments of the present application do not limit the specific implementation manner.

[0093] In some other embodiments, in the method of using the lidar to slide on the slide rail for gap detection, the horizontal angular resolution and vertical angular resolution can also be used to achieve: taking the MEMS lidar as an example, the horizontal galvanometer frequency and vertical galvanometer frequency of the MEMS lidar are fixed. The horizontal galvanometer frequency is set as fv, and the vertical galvanometer frequency is set as fh. In this way, the distribution of the laser beam lines emitted by the MEMS lidar is fixed. After the platform screen door is locked, the MEMS lidar can start to slide at a fixed speed V along the gap direction, and the point clouds obtained by the MEMS lidar scanning the gap are stitched into a 3D point cloud map. Whether there is foreign matter in the gap is determined through this 3D point cloud map.

[0094] In some other embodiments, according to parameters such as the horizontal galvanometer frequency fv, vertical galvanometer frequency fh of the MEMS lidar and different positions of the MEMS lidar in the gap, the sliding speed v of the lidar is changed i = F i (f v , f h , l), and finally a 3D point cloud map with non-uniform density can be obtained, and whether there is foreign matter in the gap is determined through this point cloud map.

[0095] In some other embodiments, in the case of setting multiple lidars, multiple slide rails can be used to complete joint gap detection to form an overall gap 3D point cloud map, and whether there is foreign matter in the gap is determined through this point cloud map. That is, a slide rail can be set for each lidar, so that multiple lidars can cover a larger range.

[0096] Figure 7 Schematic diagram of the control principle of the gap detection system provided by an embodiment of the present application. As Figure 7 shown, two or more controllers can be set, for example, a main controller and a slave controller are set. Generally, the main controller plays a controlling role, and when the main controller fails, the slave controller plays a controlling role. In this system, two or more controllers play a redundant function, making the system more stable.

[0097] It can be understood that the communication method between the lidar and the controller can be hard wire, CAN line, network cable, serial port, WiFi, etc., and the embodiments of the present application do not limit this.

[0098] It should be understood that Figure 7 the multiple lidars in

[0099] can be multiple lidars set on the same platform or multiple lidars set on different platforms, and the present application does not limit this.

[0100] Figure 8 Schematic diagram of the distribution mode of horizontal points in the point cloud in the lidar-based gap detection method provided by an embodiment of the present application. As Figure 8 shown, the vertical distance between the lidar 801 and the platform screen door 802 is D, and the horizontal distance where the central beam of the lidar hits the platform screen door 802 at the initial angle is L 0 , the horizontal spacing between adjacent points is L, the distance where the nth beam of the lidar is emitted is S n , the distance where the (n + 1)th lidar beam is emitted is S n+1 , the angle between the nth beam and the (n + 1)th beam is θ n , then the θn to be adjusted, the vertical distance is D, the horizontal distance is L 0 , and the relationship between the horizontal spacing L between adjacent points is shown in the following formula:

[0101]

[0102] That is:

[0103] The derivation process of the above formula is as follows:

[0104] From it can be obtained that

[0105] From the area formula:

[0106]

[0107] Finally, it can be obtained that:

[0108]

[0109]

[0110] Similarly, the vertical angle and distance relationship is similar to the above relationship and will not be elaborated here. Therefore, if equally spaced horizontal and vertical points are to be obtained, the basic parameters shown in Table 1 need to be set:

[0111] Table 1

[0112] Horizontal Vertical D Distance between radar and platform screen door Installation height of radar <![CDATA[L 0 > Horizontal distance of point cloud at initial angle Vertical distance of point cloud at initial angle L Desired horizontal equal-spacing size Desired vertical equal-spacing size n Horizontal spot of the nth laser point cloud Vertical spot of the nth laser point cloud <![CDATA[sinθ 1 > Sine value of the first laser horizontal deflection angle Sine value of the first laser vertical deflection angle

[0113] Figure 9 It is a schematic diagram of the distribution mode of horizontal points in the point cloud in the lidar-based gap detection method provided in another embodiment of this application. As Figure 9 shown, the vertical distance between the lidar 901 and the platform screen door 902 is D, and the horizontal distance at which the center line of the lidar beam hits the platform screen door 902 at the initial angle is L 0 . For the area near the movable platform screen door ASD where denser point clouds are required and relatively sparser point clouds are required near the fixed door, the point distances set at different positions ASD as shown in Figure 9 are smaller, and the point distances set at the fixed door are larger. The specific calculation method is similar to the calculation method in the example shown in Figure 8 and will not be elaborated here.

[0114] Using Figure 8 and Figure 9 shown, after determining the offset angles of the lidar beam in the horizontal and vertical directions, the horizontal and vertical angle resolutions of the lidar can be adjusted according to the offset angles, which will not be elaborated here.

[0115] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0116] Corresponding to the lidar-based gap detection method in the above embodiment, Figure 10 it shows a structural block diagram of a lidar-based gap detection device provided in an embodiment of this application. For the sake of convenience of description, only the parts related to the embodiments of this application are shown.

[0117] Referring to Figure 10, the lidar-based detection device 1000 includes: an acquisition unit 1010, a fusion unit 1020, and a detection unit 1030, where:

[0118] The acquisition unit 1010 is configured to acquire multiple frames of point clouds collected by the lidar for a target gap within a detection period. In the multiple frames of point clouds: each frame of point cloud corresponds to a vertical angular resolution and a horizontal angular resolution, the multiple frames of point clouds correspond to at least two different vertical angular resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angular resolutions;

[0119] The fusion unit 1020 is configured to fuse the multiple frames of point clouds to obtain a fused point cloud;

[0120] The detection unit 1030 is configured to perform target detection on the fused point cloud to determine a gap detection result, where the gap detection result includes that there is a foreign object in the gap or there is no foreign object in the gap.

[0121] In one embodiment, in the multiple frames of point clouds, the vertical angular resolutions of different frames of point clouds are different.

[0122] In one embodiment, in the multiple frames of point clouds, the horizontal angular resolutions of different frames of point clouds are different.

[0123] In one embodiment, in the multiple frames of point clouds: if the vertical angular resolution of the first frame of point cloud is less than the vertical angular resolution of the second frame of point cloud, then the horizontal angular resolution of the first frame of point cloud is less than the horizontal angular resolution of the second frame of point cloud, and the first frame of point cloud and the second frame of point cloud are any two different frames of point clouds in the multiple frames of point clouds.

[0124] In one embodiment, the target gap includes multiple sub-regions, any two sub-regions do not completely overlap or do not overlap, and the distances between different sub-regions and the lidar are different; the fusion unit 1020 is configured to fuse the multiple frames of point clouds to obtain a fused point cloud, including:

[0125] Matching the multiple frames of point clouds with the multiple sub-regions to determine at least one frame of point cloud corresponding to each sub-region; determining the points within the range of the target sub-region in the target frame of point cloud as target points, where the target frame of point cloud is any one frame of point cloud in the multiple frames of point clouds, and the target sub-region is the sub-region corresponding to the target frame of point cloud among the multiple sub-regions; splicing all the target points to obtain a fused point cloud.

[0126] In one embodiment, among the multiple sub-regions: the distances between different sub-regions and the lidar are different; if the distance between the first sub-region and the lidar is greater than the distance between the second sub-region and the lidar, then the horizontal angular resolution of each frame of point cloud corresponding to the first sub-region is less than the horizontal angular resolution of each frame of point cloud corresponding to the second sub-region, and the first sub-region and the second sub-region are any two different sub-regions among the multiple sub-regions.

[0127] Figure 11 The internal structure diagram of the electronic device 110 provided by an embodiment of the present application is shown as Figure 11 shown. The electronic device 110 of this embodiment includes: at least one processor 1100 ( Figure 11 only one processor is shown in the figure), a memory 1101, and a computer program 1102 stored in the memory 1101 and executable on the at least one processor 1100.

[0128] In order to execute the detection method of the embodiment of the present application, when the processor 1100 executes the computer program 1102: obtain multiple frames of point clouds collected by the lidar for the target gap within a detection period. In the multiple frames of point clouds: each frame of point cloud corresponds to a vertical angular resolution and a horizontal angular resolution, the multiple frames of point clouds correspond to at least two different vertical angular resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angular resolutions; fuse the multiple frames of point clouds to obtain a fused point cloud; perform target detection on the fused point cloud to determine the gap detection result, and the gap detection result includes that there is foreign matter in the gap or there is no foreign matter in the gap.

[0129] The electronic device 110 may include, but is not limited to, the processor 1100 and the memory 1101. Those skilled in the art can understand that Figure 11 merely examples of the electronic device 110, which do not constitute a limitation to the electronic device 110, and may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0130] The so-called processor 1100 may be a central processing unit (CPU), and this processor 1100 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0131] The memory 1101 may be an internal storage unit in some embodiments, such as a hard disk or memory. The memory 1101 may also be an external storage device in other embodiments, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 1101 may also include both an internal storage unit and an external storage device. The memory 1101 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program. The memory 1101 may also be used to temporarily store data that has been output or will be output.

[0132] Those skilled in the art can understand that Figure 11 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0133] In one embodiment, an electronic device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0134] Obtain multiple frames of point clouds collected by a lidar for a target gap within a detection period. In the multiple frames of point clouds: each frame of point cloud corresponds to a vertical angular resolution and a horizontal angular resolution, the multiple frames of point clouds correspond to at least two different vertical angular resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angular resolutions; fuse the multiple frames of point clouds to obtain a fused point cloud; perform target detection on the fused point cloud to determine a gap detection result, where the gap detection result includes that there is a foreign object in the gap or there is no foreign object in the gap.

[0135] In one embodiment, in the multiple frames of point clouds, the vertical angular resolutions of different frames of point clouds are different; and / or, in the multiple frames of point clouds, the horizontal angular resolutions of different frames of point clouds are different.

[0136] In one embodiment, if the vertical angular resolution of the first frame of point cloud is less than the vertical angular resolution of the second frame of point cloud, then the horizontal angular resolution of the first frame of point cloud is less than the horizontal angular resolution of the second frame of point cloud, and the first frame of point cloud and the second frame of point cloud are any two different frames of point clouds in the multiple frames of point clouds.

[0137] In one embodiment, the target gap includes multiple sub-regions, and any two sub-regions do not completely overlap or do not overlap. When the processor executes the computer program, the following steps are implemented:

[0138] Match multiple frames of point clouds with multiple sub-regions to determine at least one frame of point cloud corresponding to each sub-region;

[0139] Determine the points in the target frame of point cloud that are within the range of the target sub-region as target points, where the target frame of point cloud is any one of the multiple frames of point clouds, and the target sub-region is the sub-region corresponding to the target frame of point cloud among the multiple sub-regions;

[0140] Stitch all the target points to obtain a fused point cloud.

[0141] In one embodiment, among the multiple sub-regions: the distances of different sub-regions from the lidar are different; if the distance between the first sub-region and the lidar is greater than the distance between the second sub-region and the lidar, then the horizontal angle resolution of each frame of point cloud corresponding to the first sub-region is less than the horizontal angle resolution of each frame of point cloud corresponding to the second sub-region, and the first sub-region and the second sub-region are any two different sub-regions among the multiple sub-regions.

[0142] The implementation principles and technical effects of the steps implemented by the processor executing the computer program in this embodiment are similar to those of the above-mentioned method for detecting gaps based on lidar, and will not be elaborated here.

[0143] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0144] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0145] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0146] Obtain multiple frames of point clouds collected by a lidar for a target gap within a detection period. In the multiple frames of point clouds: each frame of point cloud corresponds to a vertical angular resolution and a horizontal angular resolution, the multiple frames of point clouds correspond to at least two different vertical angular resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angular resolutions; fuse the multiple frames of point clouds to obtain a fused point cloud; perform target detection on the fused point cloud to determine the gap detection result, where the gap detection result includes that there is a foreign object in the gap or there is no foreign object in the gap.

[0147] In one embodiment, in the multiple frames of point clouds, the vertical angular resolutions of different frames of point clouds are different.

[0148] In one embodiment, in the multiple frames of point clouds, the horizontal angular resolutions of different frames of point clouds are different.

[0149] In one embodiment, if the vertical angular resolution of the first frame of point cloud is less than the vertical angular resolution of the second frame of point cloud, then the horizontal angular resolution of the first frame of point cloud is less than the horizontal angular resolution of the second frame of point cloud, and the first frame of point cloud and the second frame of point cloud are any two different frames of point clouds in the multiple frames of point clouds.

[0150] In one embodiment, the target gap includes multiple sub-regions, and any two sub-regions do not completely overlap or do not overlap; when the computer program is executed by a processor, the following steps are implemented:

[0151] Match the multiple frames of point clouds with the multiple sub-regions to determine at least one frame of point cloud corresponding to each sub-region;

[0152] Determine the points within the target sub-region range in the target frame of point cloud as target points, where the target frame of point cloud is any one frame of point cloud in the multiple frames of point clouds, and the target sub-region is the sub-region corresponding to the target frame of point cloud among the multiple sub-regions;

[0153] Stitch all the target points together to obtain a fused point cloud.

[0154] In one embodiment, among the multiple sub-regions: the distances between different sub-regions and the lidar are different; if the distance between the first sub-region and the lidar is greater than the distance between the second sub-region and the lidar, then the horizontal angular resolution of each frame of point cloud corresponding to the first sub-region is less than the horizontal angular resolution of each frame of point cloud corresponding to the second sub-region, and the first sub-region and the second sub-region are any two different sub-regions among the multiple sub-regions.

[0155] The implementation principles and technical effects of the steps implemented when the computer program in this embodiment is executed by a processor are similar to the principles of the above-mentioned lidar-based gap detection method, and will not be elaborated here.

[0156] An embodiment of the present application provides a computer program product. When the computer program product runs on an electronic device, it enables the electronic device to execute and implement the steps in the above-mentioned various method embodiments.

[0157] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0158] Obtain multiple frames of point clouds collected by a lidar for a target gap within a detection period. In the multiple frames of point clouds: each frame of point cloud corresponds to a vertical angular resolution and a horizontal angular resolution, the multiple frames of point clouds correspond to at least two different vertical angular resolutions, and / or the multiple frames of point clouds correspond to at least two different horizontal angular resolutions; fuse the multiple frames of point clouds to obtain a fused point cloud; perform target detection on the fused point cloud to determine a gap detection result, where the gap detection result includes that there is a foreign object in the gap or there is no foreign object in the gap.

[0159] In one embodiment, in the multiple frames of point clouds, the vertical angular resolutions of different frames of point clouds are different.

[0160] In one embodiment, in the multiple frames of point clouds, the horizontal angular resolutions of different frames of point clouds are different.

[0161] In one embodiment, in the multiple frames of point clouds: if the vertical angular resolution of the first frame of point cloud is less than the vertical angular resolution of the second frame of point cloud, then the horizontal angular resolution of the first frame of point cloud is less than the horizontal angular resolution of the second frame of point cloud, and the first frame of point cloud and the second frame of point cloud are any two different frames of point clouds in the multiple frames of point clouds.

[0162] In one embodiment, the target gap includes multiple sub-regions, and any two sub-regions do not completely overlap or do not overlap; when the computer program is executed by a processor, the following steps are further implemented:

[0163] Match the multiple frames of point clouds with the multiple sub-regions to determine at least one frame of point cloud corresponding to each sub-region; determine the points within the target sub-region range in the target frame of point cloud as target points, where the target frame of point cloud is any one frame of point cloud in the multiple frames of point clouds, and the target sub-region is the sub-region corresponding to the target frame of point cloud among the multiple sub-regions; splice all the target points to obtain a fused point cloud.

[0164] In one embodiment, among the multiple sub-regions: the distances between different sub-regions and the lidar are different; if the distance between the first sub-region and the lidar is greater than the distance between the second sub-region and the lidar, then the horizontal angular resolution of each frame of point cloud corresponding to the first sub-region is less than the horizontal angular resolution of each frame of point cloud corresponding to the second sub-region, and the first sub-region and the second sub-region are any two different sub-regions among the multiple sub-regions.

[0165] In this embodiment, the steps implemented when the computer program is executed by the processor have similar implementation principles and technical effects to those of the above-described lidar-based gap detection method, which will not be elaborated here.

[0166] An embodiment of the present application further provides a chip, including: a processor configured to call and run a computer program from a memory, so that a computer device installed with the chip executes the steps in the above-described method embodiments.

[0167] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0168] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0169] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / devices and methods can be implemented in other ways. For example, the apparatus / device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in an electrical, mechanical or other forms.

[0170] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0171] In addition, the functional units in the various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0172] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable storage medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice within the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0173] The above-described embodiments are only used to illustrate the technical solutions of this application, rather than to limit it; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. A gap detection method based on laser radar, characterized in that: The method comprises: Acquire a multi-frame point cloud collected by the laser radar for the target gap within a detection cycle, wherein: each frame of the point cloud corresponds to a vertical angle resolution and a horizontal angle resolution, the multi-frame point cloud corresponds to at least two different vertical angle resolutions, and / or the multi-frame point cloud corresponds to at least two different horizontal angle resolutions; Fusing the multiple frame point clouds to obtain a fused point cloud; Target detection is performed on the fused point cloud to determine a gap detection result, where the gap detection result includes whether a foreign object exists in the gap or whether a foreign object does not exist in the gap.

2. The method according to claim 1, characterized in that In the multi-frame point cloud, the vertical angle resolutions of different frame point clouds are different. ； and / or, In the multi-frame point cloud, the horizontal angle resolutions of different frame point clouds are different.

3. The method according to claim 2, characterized in that In the multi-frame point cloud: if the vertical angle resolution of the first frame point cloud is smaller than the vertical angle resolution of the second frame point cloud, then the horizontal angle resolution of the first frame point cloud is smaller than the horizontal angle resolution of the second frame point cloud, and the first frame point cloud and the second frame point cloud are any two different frames of point clouds in the multi-frame point cloud.

4. The method according to claim 3, characterized in that The target gap includes a plurality of sub-areas, and any two sub-areas do not completely overlap or do not overlap; The step of fusing the multiple frame point clouds to obtain a fused point cloud includes: Matching the multiple frames of point cloud with the multiple sub-regions to determine at least one frame of point cloud corresponding to each sub-region; Determine a point in a target frame point cloud that is within a target sub-region as a target point, wherein the target frame point cloud is any one frame point cloud in the multiple frame point clouds, and the target sub-region is a sub-region in the multiple sub-regions that corresponds to the target frame point cloud; All target points are spliced ​​together to obtain the fused point cloud.

5. The method according to claim 4, characterized in that Among the multiple sub-areas: different sub-areas have different distances from the laser radar; if the distance between the first sub-area and the laser radar is greater than the distance between the second sub-area and the laser radar, the horizontal angular resolution of each frame point cloud corresponding to the first sub-area is smaller than the horizontal angular resolution of each frame point cloud corresponding to the second sub-area, and the first sub-area and the second sub-area are any two different sub-areas among the multiple sub-areas.

6. A gap detection device based on laser radar, characterized in that: The device comprises means for executing the steps of the method according to any one of claims 1 to 5.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A gap detection system, characterized in that: It comprises a laser radar and the electronic device described in claim 7, wherein the laser radar is communicatively connected to the electronic device.

9. The system according to claim 8, characterized in that The laser radar is a MEMS laser radar. In the multi-frame point cloud collected by the MEMS laser radar: each frame of the point cloud corresponds to a horizontal galvanometer frequency and a vertical galvanometer frequency, the multi-frame point cloud corresponds to at least two different horizontal galvanometer frequencies, and / or the multi-frame point cloud corresponds to at least two different vertical galvanometer frequencies.

10. The system according to claim 8 or 9, characterized in that There are multiple laser radars, which are arranged at intervals in the length direction of the target gap, and different laser radars scan different areas in the target gap.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images