A rail transit obstacle recognition method and device based on time-series point cloud superposition

Abstract

The present application is applicable to the field of point cloud processing technology, and provides a rail transit obstacle identification method based on time-series point cloud superposition, including: obtaining the current frame front point cloud data of the train at the current moment, the current frame front point cloud data is used to characterize the three-dimensional coordinate information of the object in the to-be-detected area determined according to the train's running line at the current moment, superimposing the points in the current frame front point cloud data and the points in the pre-acquired k consecutive moments of the historical frame front point cloud data to obtain the current frame superimposed point cloud data, the historical frame front point cloud data is used to characterize the three-dimensional coordinate information of the object in the to-be-detected area at the historical moment before the current moment, and according to the position information corresponding to the points in the current frame superimposed point cloud data, the train is identified for rail transit obstacles, and the obstacle identification result of the train in the running line is obtained. The present invention can solve the problem that the accuracy of train detection and identification of obstacles is low due to the laser point cloud being too sparse.

Description

Technical Field

[0001] The present application belongs to the field of point cloud processing technology, and in particular, relates to a rail transit obstacle identification method and device based on time-series point cloud superposition. Background Art

[0002] LiDAR is the main sensor for high-precision obstacle detection. LiDAR measures the distance, angle and other information between the target object and the LiDAR by emitting laser beams, thereby constructing a point cloud map of the surrounding environment. Based on the rich spatial information of the point cloud data in the point cloud map, it can identify target objects such as obstacles and defective products. It is widely used in the fields of intelligent driving, robot navigation, drone obstacle avoidance, product inspection, etc. However, as the detection distance increases, the point cloud formed by the laser beam on the target object will become gradually sparse, the measured point cloud data points will gradually decrease, and the accuracy of obstacle detection based on the point cloud map and real-time measured point cloud data will gradually decrease.

[0003] In the field of intelligent driving technology, with the improvement of rail transit safety standards, the obstacle detection distance is required to be farther and farther. When a stationary train or a moving train detects obstacles at a long distance, the accuracy of detecting and identifying obstacles is low because the laser point cloud is too sparse. Summary of the invention

[0004] The embodiments of the present application provide a rail transit obstacle identification method, device and storage medium based on time-series point cloud superposition, which can solve the problem of low accuracy in detecting and identifying obstacles due to sparse laser point clouds when a stationary train or a moving train detects obstacles at a long distance.

[0005] In a first aspect, an embodiment of the present application provides a rail transit obstacle identification method based on time-series point cloud superposition, comprising:

[0006] Acquire the current frame foreground scenic spot cloud data at the current moment during the running process of the train, wherein the current frame foreground scenic spot cloud data is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the current moment, and the to-be-detected area is determined according to the running route of the train;

[0007] Superimpose the points in the foreground point cloud data of the current frame with the points in the foreground point cloud data of k consecutive historical frames acquired in advance, to obtain the superimposed point cloud data of the current frame corresponding to the foreground point cloud data of the current frame, wherein the foreground point cloud data of the historical frame is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the historical moment before the current moment, and k is a constant;

[0008] According to the position information corresponding to the points in the current frame superimposed point cloud data, rail transit obstacle identification is performed on the train during operation to obtain the obstacle identification result of the train in the operation line.

[0009] In a possible implementation manner of the first aspect, superimposing points in the foreground point cloud data of the current frame with points in the foreground point cloud data of k consecutive historical frames acquired in advance to obtain current frame superimposed point cloud data corresponding to the foreground point cloud data of the current frame includes:

[0010] According to the pre-constructed point cloud map, the points in the pre-acquired foreground point cloud data of the historical frames at k consecutive moments are respectively converted into a first coordinate system to obtain k historical frames of first foreground point cloud data, wherein the pre-constructed point cloud map is determined based on the running route of the train based on the simultaneous positioning and map construction method;

[0011] According to the coordinate system corresponding to the foreground point cloud data of the current frame, respectively perform a second coordinate system transformation on the points in the first foreground point cloud data of the k historical frames to obtain the second foreground point cloud data of the k historical frames;

[0012] The points in the k second foreground point cloud data of the historical frames are superimposed on the foreground point cloud data of the current frame to obtain the superimposed point cloud data of the current frame corresponding to the foreground point cloud data of the current frame.

[0013] In a possible implementation manner of the first aspect, performing rail transit obstacle identification on the train in operation according to the position information corresponding to the point in the current frame superimposed point cloud data to obtain an obstacle identification result of the train in the operation line includes:

[0014] According to the position information corresponding to each point in the current frame superimposed point cloud data, the points in the current frame superimposed point cloud data are filtered and clustered to obtain obstacle clusters;

[0015] Selecting a static point that meets a second preset condition from the obstacle cluster, wherein the second preset condition is determined according to the motion state of each point in the obstacle cluster;

[0016] Determining an obstacle bounding box according to the static points in the obstacle cluster;

[0017] According to the obstacle bounding box, an obstacle recognition result of the train in the running line is determined.

[0018] In a possible implementation manner of the first aspect, filtering and clustering points in the current frame superimposed point cloud data according to position information corresponding to each point in the current frame superimposed point cloud data to obtain an obstacle cluster, includes:

[0019] According to the position information corresponding to each point in the current frame superimposed point cloud data, the number of first similar points of each point in the current frame superimposed point cloud data is counted, wherein the first similar point of each point in the current frame superimposed point cloud data is a point cloud in the current frame superimposed point cloud data that is in the same plane as the point;

[0020] According to the number of the first similar points of each point in the current frame superimposed point cloud data, current frame superimposed obstacle point cloud data that meets a first preset condition is screened out from the current frame superimposed point cloud data, wherein the first preset condition is determined according to a preset threshold value of the number of similar points;

[0021] Clustering all points in the obstacle point cloud data superimposed on the current frame to obtain a plurality of initial clustering clusters;

[0022] The obstacle cluster is selected from the multiple initial clusters according to the number of points in each of the initial clusters.

[0023] In a possible implementation manner of the first aspect, counting the number of first similar points of each point in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data includes:

[0024] Determine the distance from the train corresponding to each point in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data, wherein the distance from the train corresponding to each point in the current frame superimposed point cloud data is the distance between the point and the train;

[0025] For any point in the current frame overlay point cloud data:

[0026] According to the distance from the vehicle corresponding to each point in the current frame superimposed point cloud data, calculate the difference in the distance from the vehicle between other points in the current frame superimposed point cloud data and the point, wherein the other points in the current frame superimposed point cloud data are points in the current frame superimposed point cloud data other than the point;

[0027] Selecting, from all other points in the current frame superimposed point cloud data, a point whose distance from the point to the vehicle is less than a preset first threshold value as the first similar point to the point;

[0028] Count the number of the first similar points to the point.

[0029] In a possible implementation manner of the first aspect, selecting a static point that meets a second preset condition from the obstacle cluster includes:

[0030] Selecting the current frame obstacle point cloud data that meets a third preset condition from the current frame superimposed obstacle point cloud data, wherein the third preset condition is determined based on whether a point in the current frame superimposed obstacle point cloud data is a point in the current frame foreground point cloud data;

[0031] For any point in the obstacle point cloud data superimposed on the current frame:

[0032] Selecting, from all points in the obstacle point cloud data of the current frame, a point whose difference in distance from the point to the vehicle is less than a preset second threshold value as a second similar point to the point;

[0033] Count the number of the second similar points to the point;

[0034] According to the number of the second similar points to the point, determining whether the motion state of the point is static or dynamic;

[0035] According to the motion state of each point in the obstacle point cloud data superimposed on the current frame, a static point is selected from the obstacle point cloud data superimposed on the current frame.

[0036] In a possible implementation of the first aspect, obtaining the foreground scenic spot cloud data of the current frame at the current moment during the running of the train includes:

[0037] Acquire current frame point cloud data at a current moment during the operation of the train, wherein the current frame point cloud data is used to represent three-dimensional coordinate information of objects in the surrounding environment of the train;

[0038] According to the self-motion information of the train, motion compensation is performed on the points in the current frame point cloud data to obtain compensated current frame point cloud data, wherein the self-motion information of the train is estimated based on inertial measurement data of the train during operation;

[0039] Determine the running route of the train according to the current position information of the train and the pre-acquired traffic track information, wherein the current position information of the train is obtained by positioning the train according to the compensated current frame point cloud data;

[0040] Determining the area to be detected according to the running route of the train;

[0041] The current frame foreground point cloud data is filtered out from the compensated current frame point cloud data according to the position information of the midpoint of the compensated current frame point cloud data and the area to be detected.

[0042] In a second aspect, an embodiment of the present application provides a rail transit obstacle identification device based on time-series point cloud superposition, comprising:

[0043] A point cloud data acquisition module, used to acquire the point cloud data of the current frame in front of the train at the current moment during its operation, wherein the point cloud data of the current frame in front of the train is used to represent the three-dimensional coordinate information of the object in the area to be detected at the current moment, and the area to be detected is determined according to the running route of the train;

[0044] A point cloud data superposition module is used to superimpose points in the foreground point cloud data of the current frame with points in the foreground point cloud data of k consecutive moments acquired in advance, so as to obtain current frame superimposed point cloud data corresponding to the foreground point cloud data of the current frame, wherein the foreground point cloud data of the historical frame is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the historical moment before the current moment, and k is a constant;

[0045] The obstacle recognition module is used to identify rail transit obstacles for the train in operation according to the position information corresponding to the points in the superimposed point cloud data of the current frame, and obtain the obstacle recognition result of the train in the operation line.

[0046] In a third aspect, an embodiment of the present application provides a rail transit obstacle identification device based on time-series point cloud superposition, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0047] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements any of the methods described above.

[0048] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any of the methods described above.

[0049] Compared with the prior art, the embodiments of the present application have the following beneficial effects: by acquiring the current frame foreground point cloud data at the current moment during the operation of the train, the points in the current frame foreground point cloud data are superimposed with the points in the historical frame foreground point cloud data of k consecutive moments acquired in advance, so as to obtain the current frame superimposed point cloud data corresponding to the current frame foreground point cloud data, wherein the current frame foreground point cloud data is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the current moment, the to-be-detected area is determined according to the running route of the train, and the historical frame foreground point cloud data is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the historical moments before the current moment , k is a constant. Since the current frame superimposed point cloud data incorporates the foreground point cloud data of the historical frames at k consecutive moments, the point cloud in the current frame superimposed point cloud data is denser. According to the position information corresponding to each point in the current frame superimposed point cloud data with denser point cloud, the rail transit obstacle recognition is performed on the running train, so that the obstacle recognition result of the train in the running line is more accurate, and the obstacle can be recognized at a farther distance, thereby solving the problem of low accuracy in detecting and identifying obstacles due to the sparse laser point cloud when a stationary train or a moving train detects obstacles at a long distance. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 It is a flow chart of a rail transit obstacle identification method based on time-series point cloud superposition provided in one embodiment of the present application;

[0052] Figure 2 It is a flowchart of another rail transit obstacle identification method based on time-series point cloud superposition provided by another embodiment of the present application;

[0053] Figure 3 is a flowchart of another method for filtering and clustering point clouds in the current frame superimposed point cloud data provided by another embodiment of the present application;

[0054] Figure 4 It is a structural schematic diagram of a rail transit obstacle identification device based on time-series point cloud superposition provided by an embodiment of the present application;

[0055] Figure 5 It is a structural schematic diagram of a rail transit obstacle identification device based on time-series point cloud superposition provided by another embodiment of the present application. DETAILED DESCRIPTION

[0056] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0057] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0058] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0059] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0060] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0061] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0062] As the main sensor for high-precision obstacle detection, LiDAR plays an important role in obstacle detection in rail transit. When detecting obstacles at long distances, the laser point cloud obtained by LiDAR is too sparse. In order to prevent the high error recognition rate of obstacles caused by noise interference, the obstacle detection threshold cannot be set too sensitive, which makes it difficult to accurately detect obstacles or the detection distance is insufficient.

[0063] In addition, a point cloud that is too sparse may also cause problems such as excessive jitter in the detection frame and inaccurate obstacle classification.

[0064] In the field of intelligent driving technology, with the improvement of rail transit safety standards, the requirements for obstacle detection distance and detection accuracy when the train is stationary or in motion are also increasing.

[0065] At present, the main methods to achieve long-distance obstacle detection are to increase the number of lidars or to use lidars with longer detection distances and higher point cloud density to improve the accuracy of obstacle detection, but these methods are costly and difficult to implement.

[0066] It becomes particularly important to achieve long-distance obstacle detection without increasing additional hardware costs while further improving the stability of the detection frame and the accuracy of obstacle recognition.

[0067] The present application embodiment provides a rail transit obstacle recognition method based on time-series point cloud superposition, see Figure 1 , Figure 1 : is a flow chart of a rail transit obstacle identification method based on time-series point cloud superposition provided by an embodiment of the present application, including:

[0068] Step S11, obtaining the cloud data of the scenic spot in front of the current frame at the current moment during the running of the train, wherein the cloud data of the scenic spot in front of the current frame is used to represent the three-dimensional coordinate information of the object in the area to be detected at the current moment, and the area to be detected is determined according to the running line of the train;

[0069] Step S12, superimposing the points in the foreground point cloud data of the current frame with the points in the foreground point cloud data of the historical frames acquired at k consecutive moments in advance, to obtain the current frame superimposed point cloud data corresponding to the foreground point cloud data of the current frame, wherein the foreground point cloud data of the historical frames is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the historical moments before the current moment, and k is a constant;

[0070] Step S13, according to the position information corresponding to the points in the current frame superimposed point cloud data, rail transit obstacle identification is performed on the running train to obtain the obstacle identification result of the train in the running line.

[0071] It should be noted that when the train identifies rail transit obstacles, a sensor module is installed forward on the front of the train. The sensor module includes lidar, millimeter-wave radar and inertial measurement unit, etc., which can realize multi-dimensional perception of the surrounding environment ahead.

[0072] When the lidar scans an entire line (from the starting point to the end point of the train) or an entire city, all the point cloud data obtained from the scan can be compensated and dedistorted. Based on the coordinate information of the point cloud data after compensation and dedistortion, a high-precision point cloud map can be constructed through SLAM (Simultaneous localization and mapping) technology.

[0073] Since the train runs on the track, the train running route has a strict correspondence with the track area. By compensating the point cloud data after de-distortion processing, the precise position of the track centerline can be automatically marked in the constructed point cloud map.

[0074] Specifically, when the train is running, the laser radar in front of the train obtains the current frame point cloud data. The current frame point cloud data is obtained by scanning the surrounding environment of the train through the laser radar at the current moment. The current frame point cloud data is used to represent the three-dimensional coordinate information of objects in the surrounding environment of the train at the current moment. The current frame point cloud data includes the point cloud and the coordinate information of each point in the point cloud. After the current frame point cloud data is compensated and dedistorted, the compensated current frame point cloud data is obtained. The compensated current frame point cloud data offsets the impact of the train operation on each point in the current frame point cloud data.

[0075] For a running train, obstacles in its running route will affect it, while obstacles outside the running route will not affect it, so only obstacles in the running route need to be detected. Based on the compensated current frame point cloud data, the position of the train can be determined through laser SLAM (Simultaneous localization and mapping) technology, and then based on the position information of the track centerline marked in the pre-built point cloud map, the running route of the train can be determined. The running route of the train represents the running track of the train or the running track of the train. According to the running route of the train and the pre-set detection range, the area to be detected can be determined. For example, the detection range can be set to the width of the train.

[0076] According to the area to be detected, the point cloud that does not belong to the area to be detected in the compensated current frame point cloud data is filtered out, and the current frame foreground point cloud data is obtained after filtering. Among them, the current frame foreground point cloud data is used to represent the three-dimensional coordinate information of the object in the area to be detected at the current moment.

[0077] For point cloud data acquired at any time, the foreground point cloud data corresponding to the time can be obtained by performing the same operation as the current frame point cloud data. For example, for historical frame point cloud data acquired at a historical moment before the current moment, the corresponding historical frame foreground point cloud data can be obtained.

[0078] All points in the current frame's foreground scenic spot cloud data are superimposed with all points in the previously acquired k consecutive moments' foreground scenic spot cloud data, that is, all points in the historical frame's foreground scenic spot cloud data are converted into the coordinate system corresponding to the points in the current frame's foreground scenic spot cloud data as the points in the current frame's superimposed point cloud data, and the current frame's superimposed point cloud data corresponding to the current frame's foreground scenic spot cloud data is obtained. If the current moment is t, the k historical moments before the current moment are t-1, t-2, ... tk.

[0079] It should be noted that the number of historical moments before the k current moment may be 5, and this embodiment does not specifically limit the value of k.

[0080] Specifically, under the ideal condition that all points in the current frame superimposed point cloud data are noise-free, when the accuracy of positioning the train is high, the obstacle bounding box can be determined for the rail transit obstacle identification of the train in operation based on the points in the current frame superimposed point cloud data obtained after the above superposition. All obstacle bounding boxes are the obstacle identification results in the train running line. The area surrounded by each obstacle bounding box is an obstacle, and the obstacle bounding box is the boundary of the obstacle. Since all the points in the current frame superimposed point cloud data obtained after the above superposition significantly enhance the point cloud density, the obstacle identification result obtained by identifying the points in the current frame superimposed point cloud data has been significantly improved in accuracy.

[0081] When there is noise in the points in the current frame superimposed point cloud data, the points in the current frame superimposed point cloud data can be filtered according to the position information corresponding to each point in the current frame superimposed point cloud data to obtain the current frame superimposed obstacle point cloud data, and according to the points in the current frame superimposed obstacle point cloud data, rail transit obstacles are identified for the running train to obtain the obstacle identification result of the train in the running line.

[0082] It should be noted that the target object may be any artificially set target object. This embodiment includes but is not limited to the recognition of rail transit obstacles, and the above method can be used to achieve it in the field of laser obstacle perception.

[0083] It can be understood that the technical solution provided in this embodiment obtains the current frame foreground point cloud data at the current moment during the operation of the train, and superimposes the points in the current frame foreground point cloud data with the points in the historical frame foreground point cloud data of k consecutive moments obtained in advance, so as to obtain the current frame superimposed point cloud data corresponding to the current frame foreground point cloud data, wherein the current frame foreground point cloud data is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the current moment, the to-be-detected area is determined according to the running line of the train, and the historical frame foreground point cloud data is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the historical moments before the current moment. information, k is a constant. Since the current frame superimposed point cloud data incorporates the foreground point cloud data of k consecutive moments of the historical frames, the points in the current frame superimposed point cloud data are denser. According to the position information corresponding to the points in the current frame superimposed point cloud data with denser point clouds, rail transit obstacles are identified for the running train, so that the obstacle identification result of the train in the running line is more accurate, and the obstacle can be identified at a farther distance, thereby solving the problem of low accuracy in detecting and identifying obstacles due to the sparse laser point cloud when the train is stationary or the running train detects obstacles at a long distance.

[0084] In a possible implementation, in step S12, the points in the foreground point cloud data of the current frame are superimposed with the points in the foreground point cloud data of the historical frames acquired at k consecutive moments in advance to obtain the current frame superimposed point cloud data corresponding to the foreground point cloud data of the current frame, including:

[0085] Step S121, according to the pre-constructed point cloud map, the points in the pre-acquired foreground point cloud data of k consecutive moments of the historical frames are respectively converted into the first coordinate system to obtain the first foreground point cloud data of k historical frames, wherein the pre-constructed point cloud map is determined based on the running route of the train based on the simultaneous positioning and map construction method;

[0086] Step S122, according to the coordinate system corresponding to the foreground point cloud data of the current frame, respectively perform a second coordinate system transformation on the points in the first foreground point cloud data of k historical frames to obtain the second foreground point cloud data of k historical frames;

[0087] Step S123, superimposing the points in the second foreground point cloud data of k historical frames onto the foreground point cloud data of the current frame to obtain the superimposed point cloud data of the current frame corresponding to the foreground point cloud data of the current frame.

[0088] Specifically, when the points in the foreground scenic spot cloud data of the current frame are superimposed with the points in the foreground scenic spot cloud data of the historical frames acquired at k consecutive moments in advance, the current frame superimposed point cloud data corresponding to the foreground scenic spot cloud data of the current frame is obtained, including:

[0089] By pre-scanning the entire line of the train, a point cloud map can be constructed based on the simultaneous positioning and map construction method. The point cloud map includes the point cloud data in the train's line and the coordinate system of each point in the foreground point cloud data collected at each moment. For example, the frame at the current moment corresponds to the coordinate system of each point in the foreground point cloud data of the current frame, and the frames at k historical moments each correspond to the coordinate system of each point in the foreground point cloud data of the historical frame. Each frame corresponds to a coordinate system, and each frame also corresponds to a unique frame number. The foreground point cloud data includes the frame number of each point, which is used to mark the laser point cloud frame from which the point comes. The foreground point cloud data of the frame also includes the positioning posture in the coordinate system corresponding to the frame, and the positioning posture includes the position coordinates and posture information of the frame.

[0090] For the historical frame foreground cloud data of k consecutive moments and the current frame foreground cloud data, they correspond to their own coordinate systems. Assume that the positioning pose corresponding to the current frame is , the positioning poses corresponding to the historical frames at k consecutive moments are , ,……, , the positioning posture is a positioning posture with 6 degrees of freedom.

[0091] For all points in the historical frame foreground cloud data corresponding to the nth frame in the historical frames of k consecutive moments, where n is any constant from 1 to k, which can be 1 or k, obtain the positioning pose of the nth frame For each point in the historical frame foreground point cloud data of the nth frame, the first coordinate system conversion is performed to convert it into the coordinates in the world map coordinate system, and the historical frame first foreground point cloud data of the nth frame is obtained. Among them, the coordinates of each point in the historical frame first foreground point cloud data of the nth frame are the coordinates in the world map coordinate system.

[0092] The positioning pose corresponding to the current frame is , according to the coordinate system corresponding to the foreground point cloud data of the current frame, each point in the first foreground point cloud data of the historical frame of the nth frame is subjected to a second coordinate system transformation, and is transformed into the coordinates in the coordinate system corresponding to the foreground point cloud data of the current frame, and the second foreground point cloud data of the historical frame of the nth frame is obtained. Among them, the coordinates of each point in the second foreground point cloud data of the historical frame of the nth frame are the coordinates in the coordinate system corresponding to the current frame.

[0093] For the points in the foreground point cloud data of the historical frames at k consecutive moments, the second foreground point cloud data of k historical frames are obtained through the first coordinate system conversion and the second coordinate system conversion according to their respective corresponding coordinate systems.

[0094] All points in the second foreground point cloud data of k historical frames are superimposed with all points in the foreground point cloud data of the current frame to obtain the superimposed point cloud data of the current frame corresponding to the foreground point cloud data of the current frame. The coordinates corresponding to each point in the superimposed point cloud data of the current frame are all coordinates in the coordinate system corresponding to the current frame. The superimposed point cloud data of the current frame also includes the frame number corresponding to the frame from which each point comes, which is used to mark the unique frame from which each point of the superimposed point cloud data of the current frame comes.

[0095] In an implementable example, k=5, and all points in the historical frame foreground point cloud data corresponding to 5 consecutive frames are superimposed on the current frame foreground point cloud data for superposition processing. Assume that point p is a point in the point cloud of the historical frame foreground point cloud data corresponding to the nth frame, and its coordinates are Q=(x,y,z), and the positioning pose of the nth frame is , perform the first coordinate transformation on point p, After that, the second coordinate system transformation is performed on point p, and the positioning posture corresponding to the current frame is , , get the coordinates of point p in the coordinate system corresponding to the current frame.

[0096] It can be understood that by superimposing the points in the foreground point cloud data of k consecutive historical frames onto the foreground point cloud data of the current frame, the point cloud density of the points in the superimposed point cloud data of the current frame obtained after superposition is improved and denser than the current frame. By identifying obstacles through the points in the superimposed point cloud data of the current frame after superposition, the detection distance can be significantly improved, and small obstacles can be effectively identified, thereby improving the accuracy of identifying obstacles. In addition, only the points in the foreground point cloud data are superimposed, thereby improving the efficiency of superposition and making the recognition efficiency of the entire process of obstacle identification higher.

[0097] In a possible implementation, this embodiment also provides another rail transit obstacle identification method based on time-series point cloud superposition, see the attached Figure 2 , Figure 2 It is a flow chart of another rail transit obstacle identification method based on time-series point cloud superposition provided by another embodiment of the present application. In step S13, according to the position information corresponding to the point in the current frame superposition point cloud data, rail transit obstacle identification is performed on the train in the running process to obtain the obstacle identification result of the train in the running line, including:

[0098] Step S131, filtering and clustering the points in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data to obtain obstacle clusters;

[0099] Step S132, selecting a static point that meets a second preset condition from the obstacle cluster, wherein the second preset condition is determined according to the motion state of each point in the obstacle cluster;

[0100] Step S133, determining an obstacle bounding box according to the static points in the obstacle cluster;

[0101] Step S134, determining the obstacle recognition result of the train on the running line according to the obstacle bounding box.

[0102] Specifically, according to the position information corresponding to each point in the current frame superimposed point cloud data, rail transit obstacle recognition is performed on the train in operation, and the obstacle recognition result of the train in the running line is obtained, including:

[0103] Since some points are caused by the movement of the train, in order to prevent the problem of low accuracy in identifying obstacles due to noise accumulation, for example, identifying the bounding box composed of point clouds that are not obstacles as obstacles, it is necessary to filter the points in the current frame superimposed point cloud data. According to the position information corresponding to each point in the current frame superimposed point cloud data, the number of points on the plane parallel to the car is counted. Since there are many points in a plane for real obstacles, the number of points on a plane parallel to the car is small, and these points are noise points. The noise points in the current frame superimposed point cloud data are filtered out to obtain the current frame superimposed obstacle point cloud data.

[0104] After clustering the points in the obstacle point cloud data superimposed on the current frame, an obstacle cluster is obtained. There can be one, multiple, or zero obstacle clusters.

[0105] It should be noted that the points in the obstacle point cloud data superimposed in the current frame can be clustered by using the Euclidean clustering method, that is, clustering is performed according to the distance between the point clouds. Different thresholds can be set according to different distances. K-means clustering, density-based spatial clustering and other clustering methods can also be used for clustering. This embodiment does not specifically limit the clustering method.

[0106] Since the motion state of each point in the obstacle point cloud data superimposed in the current frame can be static or moving, for each point in the obstacle cluster, it is determined whether it is a static point or a dynamic point according to the motion state of each point. The static motion state is used as the basis for satisfying the second preset condition, as a static point, the static point cloud is used to represent a static object, and the dynamic point cloud is used to represent a moving object. The point with a static motion state is selected from the obstacle cluster as a static point that meets the second preset condition.

[0107] According to the static points in the obstacle clusters obtained above, an obstacle bounding box is determined, wherein all the static points in each obstacle cluster constitute the obstacle bounding box, and the obstacle bounding box is the boundary of the obstacle.

[0108] According to the obstacle bounding box, the obstacle recognition result of the train in the running line is determined. The obstacle recognition result may include whether the running line at the current moment includes an obstacle, and, when an obstacle is included, the obstacle information such as the position, shape, size and category of the obstacle.

[0109] It can be understood that by filtering and clustering the points in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data, an obstacle cluster is obtained, and a static point that meets the second preset condition is selected from the obstacle cluster, and an obstacle bounding box is determined according to the static points in the obstacle cluster, and the obstacle recognition result of the train in the running line is determined according to the obstacle bounding box. Due to the filtering, the noise accumulation can be prevented from affecting the accuracy of the obstacle recognition result, the false detection rate can be reduced, and the accuracy of the point cloud data and the reliability of the obstacle recognition result can be ensured. In addition, all dynamic points are used in the clustering process, which effectively prevents the occurrence of the target splitting phenomenon. For example, for transparent glass, it can effectively avoid the phenomenon that the upper and lower boundaries of the glass are easily identified as an obstacle by clustering only the point cloud data of the upper and lower boundaries of the glass, making the identified obstacle more complete. Finally, the final obstacle bounding box is determined by the static points, which reduces the interference caused by the dynamic points in the foreground point cloud data and ensures the accuracy of obstacle recognition.

[0110] In a possible implementation, this embodiment also provides a method for filtering and clustering points in the current frame superimposed point cloud data, referring to Figure 3 , Figure 3 1 is a flow chart of another method for filtering and clustering point clouds in the current frame superimposed point cloud data provided by another embodiment of the present application. In step S131, according to the position information corresponding to each point in the current frame superimposed point cloud data, the points in the current frame superimposed point cloud data are filtered and clustered to obtain obstacle clusters, including:

[0111] Step S1311, according to the position information corresponding to each point in the current frame superimposed point cloud data, counting the number of first similar points of each point in the current frame superimposed point cloud data, wherein the first similar point of each point in the current frame superimposed point cloud data is a point cloud in the current frame superimposed point cloud data that is in the same plane as the point;

[0112] Step S1312, according to the number of first similar points of each point in the current frame superimposed point cloud data, the current frame superimposed obstacle point cloud data that meets the first preset condition is screened out from the current frame superimposed point cloud data, wherein the first preset condition is determined according to a preset threshold value of the number of similar points;

[0113] Step S1313, clustering all points in the obstacle point cloud data superimposed on the current frame to obtain multiple initial clusters;

[0114] Step S1314: selecting an obstacle cluster from the multiple initial clusters according to the number of points in each initial cluster.

[0115] Specifically, for any point in the point cloud of the current frame superimposed point cloud data, all points in the current frame superimposed point cloud data in the same plane as the point are taken as the first similar points of the point, and the number of the first similar points of the point is obtained by counting. In this way, the number of the first similar points of each point in the current frame superimposed point cloud data is obtained.

[0116] For any point in the current frame superimposed point cloud data, it is possible to determine whether the point is a noise point based on the number of the first similar points of the point. When the number of the first similar points of the point is greater than the preset threshold of the number of similar points, the point is determined not to be a noise point and the point meets the first preset condition. When the number of the first similar points of the point is not greater than the preset threshold of the number of similar points, the point is determined to be a noise point and the point does not meet the first preset condition.

[0117] It should be noted that the first preset condition is determined based on a preset threshold value of the number of similar points. The preset threshold value of the number of similar points is manually preset and can be any constant or can be set according to actual application requirements. This embodiment does not make any specific limitation on this.

[0118] Specifically, from all points in the current frame superimposed point cloud data, all noise points are filtered out, and all points that are not noise points are selected to form the points in the current frame superimposed obstacle point cloud data.

[0119] For all points in the current frame superimposed obstacle point cloud data obtained after noise removal, clustering is performed to obtain initial clustering clusters, wherein the initial clustering clusters may have zero, one or more.

[0120] For any initial cluster, when the number of points contained in the initial cluster is too small, it may be a recognition error and not a real obstacle. The initial cluster containing too few points is filtered out, and an obstacle cluster is selected from multiple initial clusters.

[0121] In a possible implementation, in step S1311, according to the position information corresponding to each point in the current frame superimposed point cloud data, counting the number of first similar points of each point in the current frame superimposed point cloud data includes:

[0122] According to the position information corresponding to each point in the current frame superimposed point cloud data, determine the distance from the train corresponding to each point in the current frame superimposed point cloud data, wherein the distance from the train corresponding to each point in the current frame superimposed point cloud data is the distance between the point and the train;

[0123] For any point in the current frame overlay point cloud data:

[0124] According to the distance from the vehicle corresponding to each point in the current frame superimposed point cloud data, the difference in the distance from the vehicle between other points in the current frame superimposed point cloud data and the point is calculated, wherein the other points in the current frame superimposed point cloud data are points in the current frame superimposed point cloud data except the point;

[0125] Selecting a point whose distance from the point to the vehicle is less than a preset first threshold from all other points in the current frame superimposed point cloud data as the first similar point to the point;

[0126] Count the number of first closest points to the point.

[0127] Specifically, for each point in the point cloud in the current frame superimposed point cloud data, the distance between each point in the current frame superimposed point cloud data and the train is determined as the distance from the train corresponding to the point. For example, the distance from the train corresponding to point p is the coordinate value of the x-axis of point p in the current frame superimposed point cloud data.

[0128] For any point in the current frame overlay point cloud data:

[0129] Select other points in the current frame superimposed point cloud data except this point, and calculate the distance difference from the car between other points in the current frame superimposed point cloud data and this point according to the distance from the car corresponding to other points in the current frame superimposed point cloud data and the distance from the car corresponding to this point. The distance difference from the car is the difference calculated by subtracting the distance between one of the two points and the car from the distance between the other of the two points and the car.

[0130] For any point in the current frame superimposed point cloud data, determine whether the difference in distance from the vehicle between any point in the other points and the point is less than a preset first threshold. When the difference in distance from the vehicle between any point in the other points and the point is less than the preset first threshold, the any point in the other points is the first similar point of the point. Select the first similar point of the point from all other points in the current frame superimposed point cloud data. Count the number of first similar points of the point.

[0131] For all points in the point cloud in the current frame superimposed point cloud data, the number of first similar points of each point is counted respectively in the above manner.

[0132] It should be noted that the first threshold is a constant and can be set as needed or according to an application scenario, and this embodiment does not specifically limit this.

[0133] In a possible implementation, in step S132, selecting a static point that meets a second preset condition from the obstacle cluster includes:

[0134] Selecting the obstacle point cloud data of the current frame that meets the third preset condition from the obstacle point cloud data superimposed on the current frame, wherein the third preset condition is determined according to whether the point cloud in the obstacle point cloud data superimposed on the current frame is the point cloud in the foreground point cloud data of the current frame;

[0135] For any point in the obstacle point cloud data superimposed on the current frame:

[0136] Selecting, from all points in the obstacle point cloud data of the current frame, a point whose distance from the point to the vehicle is less than a preset second threshold value as the second closest point to the point;

[0137] Count the number of the second closest points to the point;

[0138] According to the number of the second closest points to the point, determine whether the motion state of the point is static or dynamic;

[0139] According to the motion state of each point in the obstacle point cloud data superimposed on the current frame, a static point is selected from the obstacle point cloud data superimposed on the current frame.

[0140] Specifically, when selecting a static point satisfying the second preset condition from the obstacle cluster, it includes:

[0141] For each point in the obstacle point cloud data superimposed in the current frame, some points come from the scenic spot point cloud data before the current frame, and some points come from the superposition of points in the scenic spot point cloud data before the historical frame.

[0142] For each point in the obstacle point cloud data superimposed on the current frame, it is determined whether the point meets the third preset condition according to whether the point in the record comes from the scenic spot cloud data before the current frame or from the record of the scenic spot cloud data before the historical frame. When the point in the record comes from the scenic spot cloud data before the current frame, it is determined that the point is a point in the scenic spot cloud data before the current frame, and the third preset condition is met. The third preset condition is set in advance.

[0143] From the obstacle point cloud data superimposed on the current frame, all points that meet the third preset condition are selected, that is, all points from the foreground point cloud data of the current frame are selected as the current obstacle point cloud data.

[0144] For any point in the current frame superimposed obstacle point cloud data obtained above: after the above step S1311, the difference in distance from the vehicle between the point and each point in the current frame superimposed obstacle point cloud data has been calculated, that is, the difference in distance from the vehicle between the point and each point in the current obstacle point cloud data has been calculated.

[0145] For any point in the current obstacle point cloud data, compare the difference in distance from the vehicle between the arbitrary point in the current obstacle point cloud data and the point in the above-mentioned current superimposed obstacle point cloud data; when the difference in distance from the vehicle is less than a preset second threshold, use the point in the current obstacle point cloud data as the second closest point to the point in the current superimposed obstacle point cloud data.

[0146] From all points in the obstacle point cloud data of the current frame, points whose distance from the point to the vehicle is less than a preset second threshold are selected as the second closest points to the point.

[0147] The number of the second closest points of the point is counted. According to the number of the second closest points of the point, the motion state of the point is determined to be static or moving. When the number of the second closest points of the point is greater than a preset third threshold, the motion state of the point is determined to be static, and the point is a static point. When the number of the second closest points of the point is not greater than the preset third threshold, the motion state of the point is determined to be moving, and the point is a dynamic point.

[0148] According to the motion state of each point in the obstacle point cloud data superimposed on the current frame, all static points are selected from the obstacle point cloud data superimposed on the current frame to form a static point cloud.

[0149] It should be noted that the third threshold is an artificially set constant and can also be set according to actual application scenarios. This embodiment does not make any specific limitation to this.

[0150] In a possible implementation, in step S11, obtaining the current frame foreground scenic spot cloud data at the current moment during the running of the train includes:

[0151] Acquire the current frame point cloud data at the current moment during the running of the train, wherein the current frame point cloud data is used to represent the three-dimensional coordinate information of objects in the surrounding environment of the train;

[0152] According to the train's own motion information, motion compensation is performed on the points in the current frame point cloud data to obtain the compensated current frame point cloud data, wherein the train's own motion information is estimated based on the inertial measurement data of the train during operation;

[0153] Determine the running route of the train according to the current position information of the train and the pre-acquired traffic track information, wherein the current position information of the train is obtained by positioning the train according to the compensated current frame point cloud data;

[0154] Determine the area to be inspected according to the train's running route;

[0155] According to the position information of the midpoint of the compensated current frame point cloud data and the area to be detected, the foreground point cloud data of the current frame is filtered out from the compensated current frame point cloud data.

[0156] Specifically, when obtaining the scenic spot cloud data in front of the current frame at the current moment during the running of the train, the method includes:

[0157] The laser radar is used to obtain the current frame point cloud data of the train at the current moment during its operation, wherein the current frame point cloud data is used to represent the three-dimensional coordinate information of objects in the surrounding environment of the train at the current moment.

[0158] The train's own motion information is estimated based on the inertial measurement data obtained during the train's operation. Through the train's own motion information, motion compensation is performed on each point in the current frame point cloud data to obtain the compensated current frame point cloud data.

[0159] According to the compensated point cloud data of the current frame, the train can be positioned and the current position information of the train can be obtained.

[0160] The pre-acquired point cloud map is marked with traffic track information, such as the boundary and center line of the track. According to the current position information of the train and the traffic track information in the pre-acquired point cloud map, the running route of the train is determined, and the area to be detected is determined according to the running route of the train. The area to be detected is a three-dimensional boundary area, which can also be determined according to the width of the train and the running route of the train, and can also be set manually. This embodiment does not specifically limit the setting of the area to be detected.

[0161] According to the position information of each point in the compensated current frame point cloud data and the area to be detected, the points in the current frame point cloud data outside the area to be detected are eliminated, and all the points in the current frame point cloud data within the area to be detected form the foreground point cloud data of the current frame.

[0162] It should be noted that when positioning the train, laser SLAM technology can be used to obtain high-precision global pose, or other SLAM methods can be used to obtain the global pose, and an odometer can be used to obtain the pose transformation relationship between adjacent frames, such as through visual SLAM or multi-sensor fusion methods. This embodiment does not specifically limit this.

[0163] It can be understood that the technical solution provided by this embodiment obtains the current frame foreground point cloud data at the current moment during the operation of the train, and superimposes the points in the current frame foreground point cloud data with the points in the historical frame foreground point cloud data of k consecutive moments acquired in advance, so as to obtain the current frame superimposed point cloud data corresponding to the current frame foreground point cloud data, wherein the current frame foreground point cloud data is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the current moment, the to-be-detected area is determined according to the running line of the train, and the historical frame foreground point cloud data is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the historical moment before the current moment , k is a constant. Since the current frame superimposed point cloud data incorporates the historical frame foreground point cloud data of k consecutive moments, the points in the current frame superimposed point cloud data are denser. According to the position information corresponding to each point in the current frame superimposed point cloud data with denser point cloud, rail transit obstacle recognition is performed on the running train, so that the obstacle recognition result of the train in the running line is more accurate, and the obstacle can be recognized at a farther distance, thereby solving the problem of low accuracy in detecting and identifying obstacles due to the sparse laser point cloud when the train is stationary or the running train detects obstacles at a long distance.

[0164] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0165] Corresponding to the method described in the above embodiment, Figure 4 A schematic diagram of the structure of a rail transit obstacle identification device based on time-series point cloud superposition provided in an embodiment of the present application is shown. For the sake of convenience of explanation, only the parts related to the embodiment of the present application are shown.

[0166] Reference Figure 4 , the device comprises:

[0167] The point cloud data acquisition module 31 is used to acquire the point cloud data of the current frame in front of the train at the current moment during the running process, wherein the point cloud data of the current frame in front of the train is used to represent the three-dimensional coordinate information of the object in the area to be detected at the current moment, and the area to be detected is determined according to the running line of the train;

[0168] The point cloud data superposition module 32 is used to superimpose the points in the current frame foreground point cloud data with the points in the historical frame foreground point cloud data of k consecutive moments acquired in advance, so as to obtain the current frame superimposed point cloud data corresponding to the current frame foreground point cloud data, wherein the historical frame foreground point cloud data is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the historical moment before the current moment, and k is a constant;

[0169] The obstacle recognition module 33 is used to identify rail transit obstacles for the train in operation according to the position information corresponding to the points in the current frame superimposed point cloud data, and obtain the obstacle recognition result of the train in the operation line.

[0170] In a possible implementation, when the points in the foreground scenic spot cloud data of the current frame are superimposed with the points in the foreground scenic spot cloud data of the historical frames acquired at k consecutive moments in advance to obtain the current frame superimposed point cloud data corresponding to the foreground scenic spot cloud data of the current frame, the cloud data superimposition module 32 is specifically used to perform a first coordinate system conversion on the points in the foreground scenic spot cloud data of the historical frames acquired at k consecutive moments in advance according to a pre-constructed point cloud map to obtain k historical frames of first foreground scenic spot cloud data, wherein the pre-constructed point cloud map is determined based on the running line of the train based on the simultaneous positioning and map construction method; perform a second coordinate system conversion on the points in the first foreground scenic spot cloud data of the k historical frames according to the coordinate system corresponding to the current frame foreground scenic spot cloud data to obtain k historical frames of second foreground scenic spot cloud data; and superimpose the points in the second foreground scenic spot cloud data of the k historical frames onto the foreground scenic spot cloud data of the current frame to obtain the current frame superimposed point cloud data corresponding to the foreground scenic spot cloud data of the current frame.

[0171] In a possible implementation, when rail transit obstacle recognition is performed on a running train according to the position information corresponding to the points in the current frame superimposed point cloud data, and the obstacle recognition result of the train in the running line is obtained, the obstacle recognition module 33 is specifically used to filter and cluster the points in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data, and obtain the obstacle clustering cluster;

[0172] Selecting a static point that meets a second preset condition from the obstacle cluster, wherein the second preset condition is determined according to the motion state of each point in the obstacle cluster;

[0173] Determine the obstacle bounding box based on the static points in the obstacle cluster;

[0174] According to the obstacle bounding box, the obstacle recognition result of the train on the running line is determined.

[0175] In a possible implementation, when the points in the current frame superimposed point cloud data are filtered and clustered according to the position information corresponding to each point in the current frame superimposed point cloud data to obtain the obstacle clustering cluster, the obstacle identification module 33 is specifically used to count the number of first similar points of each point in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data, wherein the first similar point of each point in the current frame superimposed point cloud data is a point cloud in the current frame superimposed point cloud data that is in the same plane as the point;

[0176] According to the number of first similar points of each point in the current frame superimposed point cloud data, current frame superimposed obstacle point cloud data that meets a first preset condition is screened out from the current frame superimposed point cloud data, wherein the first preset condition is determined according to a preset threshold value of the number of similar points;

[0177] Cluster all points in the obstacle point cloud data of the current frame to obtain multiple initial clusters;

[0178] According to the number of points in each initial cluster, an obstacle cluster is selected from the multiple initial clusters.

[0179] In a possible implementation, when counting the number of first similar points of each point in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data, the obstacle recognition module 33 is specifically used to determine the distance from the vehicle corresponding to each point in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data, wherein the distance from the vehicle corresponding to each point in the current frame superimposed point cloud data is the distance between the point and the train;

[0180] For any point in the current frame overlay point cloud data:

[0181] According to the distance from the vehicle corresponding to each point in the current frame superimposed point cloud data, the difference in the distance from the vehicle between other points in the current frame superimposed point cloud data and the point is calculated, wherein the other points in the current frame superimposed point cloud data are points in the current frame superimposed point cloud data except the point;

[0182] Selecting a point whose distance from the point to the vehicle is less than a preset first threshold from all other points in the current frame superimposed point cloud data as the first similar point to the point;

[0183] Count the number of first closest points to the point.

[0184] In a possible implementation, when a static point satisfying the second preset condition is selected from the obstacle cluster, the obstacle identification module 33 is specifically configured to select the current frame obstacle point cloud data satisfying the third preset condition from the current frame superimposed obstacle point cloud data, wherein the third preset condition is determined based on whether the point in the current frame superimposed obstacle point cloud data is a point in the current frame foreground point cloud data;

[0185] For any point in the obstacle point cloud data superimposed on the current frame:

[0186] Selecting, from all points in the obstacle point cloud data of the current frame, a point whose distance from the point to the vehicle is less than a preset second threshold value as the second closest point to the point;

[0187] Count the number of the second closest points to the point;

[0188] According to the number of the second closest points to the point, determine whether the motion state of the point is static or dynamic;

[0189] According to the motion state of each point in the obstacle point cloud data superimposed on the current frame, a static point is selected from the obstacle point cloud data superimposed on the current frame.

[0190] In a possible implementation, when obtaining the current frame foreground point cloud data at the current moment during the running of the train, the point cloud data acquisition module 31 is specifically used to obtain the current frame point cloud data at the current moment during the running of the train, wherein the current frame point cloud data is used to represent the three-dimensional coordinate information of objects in the surrounding environment of the train;

[0191] According to the train's own motion information, motion compensation is performed on the points in the current frame point cloud data to obtain the compensated current frame point cloud data, wherein the train's own motion information is estimated based on the inertial measurement data of the train during operation;

[0192] Determine the running route of the train according to the current position information of the train and the pre-acquired traffic track information, wherein the current position information of the train is obtained by positioning the train according to the compensated current frame point cloud data;

[0193] Determine the area to be inspected according to the train's running route;

[0194] According to the position information of the midpoint of the compensated current frame point cloud data and the area to be detected, the foreground point cloud data of the current frame is filtered out from the compensated current frame point cloud data.

[0195] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0196] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0197] The present application also provides a rail transit obstacle recognition device based on time-series point cloud superposition, referring to Figure 5 , Figure 5 It is a structural schematic diagram of a rail transit obstacle identification device based on time-series point cloud superposition provided by another embodiment of the present application. The terminal device 6 includes: at least one processor 62, a memory 61, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, the steps in any of the above-mentioned method embodiments are implemented.

[0198] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0199] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0200] If the integrated 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, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0201] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0202] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0203] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0204] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0205] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A rail transit obstacle identification method based on time-series point cloud superposition, characterized in that: include: Acquire the current frame foreground scenic spot cloud data at the current moment during the running process of the train, wherein the current frame foreground scenic spot cloud data is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the current moment, and the to-be-detected area is determined according to the running route of the train; Superimpose the points in the foreground point cloud data of the current frame with the points in the foreground point cloud data of k consecutive historical frames acquired in advance, to obtain the superimposed point cloud data of the current frame corresponding to the foreground point cloud data of the current frame, wherein the foreground point cloud data of the historical frame is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the historical moment before the current moment, and k is a constant; According to the position information corresponding to the points in the current frame superimposed point cloud data, rail transit obstacle identification is performed on the train during operation to obtain an obstacle identification result of the train in the operation line; Wherein, the identifying of rail transit obstacles for the train in operation according to the position information corresponding to the points in the superimposed point cloud data of the current frame to obtain the obstacle identification result of the train in the operation line includes: According to the position information corresponding to each point in the current frame superimposed point cloud data, the points in the current frame superimposed point cloud data are filtered and clustered to obtain obstacle clusters; Selecting a static point that meets a second preset condition from the obstacle cluster, wherein the second preset condition is determined according to the motion state of each point in the obstacle cluster; Determining an obstacle bounding box according to the static points in the obstacle cluster; Determining an obstacle recognition result of the train on the running line according to the obstacle bounding box; The filtering and clustering of points in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data to obtain obstacle clusters includes: According to the position information corresponding to each point in the current frame superimposed point cloud data, the number of first similar points of each point in the current frame superimposed point cloud data is counted, wherein the first similar point of each point in the current frame superimposed point cloud data is a point cloud in the current frame superimposed point cloud data that is in the same plane as the point; According to the number of the first similar points of each point in the current frame superimposed point cloud data, current frame superimposed obstacle point cloud data that meets a first preset condition is screened out from the current frame superimposed point cloud data, wherein the first preset condition is determined according to a preset threshold value of the number of similar points; Clustering all points in the obstacle point cloud data superimposed on the current frame to obtain multiple initial clustering clusters; Selecting the obstacle cluster from the multiple initial clusters according to the number of points in each of the initial clusters; Wherein, according to the position information corresponding to each point in the current frame superimposed point cloud data, counting the number of first similar points of each point in the current frame superimposed point cloud data includes: determining the distance from the train corresponding to each point in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data, wherein the distance from the train corresponding to each point in the current frame superimposed point cloud data is the distance between the point and the train; For any point in the current frame overlay point cloud data: According to the distance from the vehicle corresponding to each point in the current frame superimposed point cloud data, calculate the difference in the distance from the vehicle between other points in the current frame superimposed point cloud data and the point, wherein the other points in the current frame superimposed point cloud data are points in the current frame superimposed point cloud data other than the point; Selecting, from all other points in the current frame superimposed point cloud data, a point whose distance from the point to the vehicle is less than a preset first threshold value as the first similar point to the point; Count the number of the first similar points to the point.

2. The rail transit obstacle identification method based on time-series point cloud superposition according to claim 1, characterized in that: The step of superimposing the points in the foreground point cloud data of the current frame with the points in the foreground point cloud data of k consecutive historical frames acquired in advance to obtain the current frame superimposed point cloud data corresponding to the foreground point cloud data of the current frame includes: According to the pre-constructed point cloud map, the points in the pre-acquired foreground point cloud data of the historical frames at k consecutive moments are respectively converted into a first coordinate system to obtain k historical frames of first foreground point cloud data, wherein the pre-constructed point cloud map is determined based on the running route of the train based on the simultaneous positioning and map construction method; According to the coordinate system corresponding to the foreground point cloud data of the current frame, respectively perform a second coordinate system transformation on the points in the first foreground point cloud data of the k historical frames to obtain the second foreground point cloud data of the k historical frames; The points in the k second foreground point cloud data of the historical frames are superimposed on the foreground point cloud data of the current frame to obtain the superimposed point cloud data of the current frame corresponding to the foreground point cloud data of the current frame.

3. The rail transit obstacle identification method based on time-series point cloud superposition according to claim 1, characterized in that: The step of selecting a static point satisfying a second preset condition from the obstacle cluster includes: Selecting the current frame obstacle point cloud data that meets a third preset condition from the current frame superimposed obstacle point cloud data, wherein the third preset condition is determined based on whether a point in the current frame superimposed obstacle point cloud data is a point in the current frame foreground point cloud data; For any point in the obstacle point cloud data superimposed on the current frame: Selecting, from all points in the obstacle point cloud data of the current frame, a point whose difference in distance from the point to the vehicle is less than a preset second threshold value as a second similar point to the point; Count the number of the second similar points to the point; According to the number of the second similar points to the point, determining whether the motion state of the point is static or dynamic; According to the motion state of each point in the obstacle point cloud data superimposed on the current frame, a static point is selected from the obstacle point cloud data superimposed on the current frame.

4. The rail transit obstacle identification method based on time-series point cloud superposition according to any one of claims 1 to 3, characterized in that: The step of obtaining the scenic spot cloud data in front of the current frame at the current moment during the operation of the train includes: Acquire current frame point cloud data at a current moment during the operation of the train, wherein the current frame point cloud data is used to represent three-dimensional coordinate information of objects in the surrounding environment of the train; According to the self-motion information of the train, motion compensation is performed on the points in the current frame point cloud data to obtain compensated current frame point cloud data, wherein the self-motion information of the train is estimated based on inertial measurement data of the train during operation; Determine the running route of the train according to the current position information of the train and the pre-acquired traffic track information, wherein the current position information of the train is obtained by positioning the train according to the compensated current frame point cloud data; Determining the area to be detected according to the running route of the train; The foreground point cloud data of the current frame is filtered out from the compensated point cloud data of the current frame according to the position information of the midpoint of the compensated point cloud data of the current frame and the area to be detected.

5. A rail transit obstacle identification device based on time-series point cloud superposition, characterized in that: include: A point cloud data acquisition module, used to acquire the point cloud data of the current frame in front of the train at the current moment during its operation, wherein the point cloud data of the current frame in front of the train is used to represent the three-dimensional coordinate information of the object in the area to be detected at the current moment, and the area to be detected is determined according to the running route of the train; A point cloud data superposition module is used to superimpose points in the foreground point cloud data of the current frame with points in the foreground point cloud data of k consecutive moments acquired in advance, so as to obtain current frame superimposed point cloud data corresponding to the foreground point cloud data of the current frame, wherein the foreground point cloud data of the historical frame is used to represent the three-dimensional coordinate information of the object in the to-be-detected area at the historical moment before the current moment, and k is a constant; An obstacle recognition module, used to identify rail transit obstacles for the train in operation according to the position information corresponding to the points in the current frame superimposed point cloud data, and obtain an obstacle recognition result of the train in the operation line; Wherein, the obstacle recognition module is also used for: According to the position information corresponding to each point in the current frame superimposed point cloud data, the points in the current frame superimposed point cloud data are filtered and clustered to obtain obstacle clusters; Selecting a static point that meets a second preset condition from the obstacle cluster, wherein the second preset condition is determined according to the motion state of each point in the obstacle cluster; Determining an obstacle bounding box according to the static points in the obstacle cluster; Determining an obstacle recognition result of the train on the running line according to the obstacle bounding box; Wherein, the obstacle recognition module is also used for: According to the position information corresponding to each point in the current frame superimposed point cloud data, the number of first similar points of each point in the current frame superimposed point cloud data is counted, wherein the first similar point of each point in the current frame superimposed point cloud data is a point cloud in the current frame superimposed point cloud data that is in the same plane as the point; According to the number of the first similar points of each point in the current frame superimposed point cloud data, current frame superimposed obstacle point cloud data that meets a first preset condition is screened out from the current frame superimposed point cloud data, wherein the first preset condition is determined according to a preset threshold value of the number of similar points; Clustering all points in the obstacle point cloud data superimposed on the current frame to obtain multiple initial clustering clusters; Selecting the obstacle cluster from the multiple initial clusters according to the number of points in each of the initial clusters; Wherein, the obstacle recognition module is also used for: Determine the distance from the train corresponding to each point in the current frame superimposed point cloud data according to the position information corresponding to each point in the current frame superimposed point cloud data, wherein the distance from the train corresponding to each point in the current frame superimposed point cloud data is the distance between the point and the train; For any point in the current frame overlay point cloud data: According to the distance from the vehicle corresponding to each point in the current frame superimposed point cloud data, calculate the difference in the distance from the vehicle between other points in the current frame superimposed point cloud data and the point, wherein the other points in the current frame superimposed point cloud data are points in the current frame superimposed point cloud data other than the point; Selecting, from all other points in the current frame superimposed point cloud data, a point whose distance from the point to the vehicle is less than a preset first threshold value as the first similar point to the point; Count the number of the first similar points to the point.

6. A rail transit obstacle identification device based on time-series point cloud superposition, 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 4 is implemented.

7. 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 4 is implemented.

Images