Front vehicle tracking method, system, device and storage medium based on laser point cloud

Abstract

The present invention provides a method, system, device and storage medium for tracking a front vehicle based on laser point cloud, the method comprising the following steps: N reflectors are set at the rear of the front vehicle, and the vertical center axis of the reflector has a preset relative position with the front vehicle; the rear vehicle collects a point cloud set in a preset front area at a preset frequency through a laser radar, and based on the point cloud set, a plane point set based on the horizontal plane projection point; by fitting a circle in the plane point set, it is determined whether N circles can be obtained; if so, the relative position of the front vehicle relative to the rear vehicle is obtained according to the center coordinates, radius and preset relative position of the circle; the preset front area is updated to generate a first area based on the center coordinates of the circle; if not, the preset front area is updated to a second area with a larger spatial range. The present invention can optimize the point cloud range of the next time according to the last tracking result, thereby greatly reducing the amount of point cloud computing, speeding up the recognition speed, and improving driving safety.

Description

Background Art

[0002] With the development of unmanned driving technology, unmanned vehicles are gradually involved in multiple scenarios to assist daily tasks. How to achieve unmanned driving in the region has become a focus of attention in the field. In order to improve work efficiency and ensure work safety, a tractor is usually selected to guide the work vehicle. By sensing the position of the tractor, the movement trajectory of the current work vehicle is guided and the safety of the following vehicle is ensured.

[0003] Since the distance between vehicles is constantly changing, in order to enhance the robustness of recognition, a larger recognition range needs to be set, and all point clouds within the recognition range need to be subsequently calculated. Although the front vehicle can be recognized, a large amount of data will significantly increase the amount of calculation and prolong the time required for recognition, which in turn reduces driving safety. Therefore, how to accurately sense the position of the tractor while taking into account robustness and ensure the continuous and stable tracking of the rear vehicle has become a difficult problem to be solved.

[0004] In view of this, the present invention provides a preceding vehicle tracking method, system, device and storage medium based on laser point cloud.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] In response to the problems in the prior art, the purpose of the present invention is to provide a front vehicle tracking method, system, device and storage medium based on laser point cloud, which overcomes the difficulties of the prior art and can optimize the next point cloud range according to the previous tracking results, thereby greatly reducing the cloud computing volume, accelerating the recognition speed and improving driving safety.

[0007] An embodiment of the present invention provides a method for tracking a preceding vehicle based on a laser point cloud, comprising the following steps:

[0008] N reflectors are arranged at the rear of the front vehicle, and the vertical center axis of the reflectors has a preset relative position with the front vehicle, N≥1;

[0009] The rear vehicle collects a point cloud set in a preset front area through a laser radar at a preset frequency, and obtains a plane point set based on the plane coordinates of the projection points of the point cloud set in a plane coordinate system established based on a horizontal plane;

[0010] By fitting a circle in the plane point set, determining whether N circles can be obtained;

[0011] When N circles can be obtained, the center coordinates and radius of the circles are obtained, and the relative position of the front vehicle with respect to the rear vehicle is obtained according to the center coordinates, radius and the preset relative position;

[0012] generating a first area based at least on the circle center coordinates, and updating the preset front area to the first area; and

[0013] When N circles cannot be obtained, the preset front area is updated to a preset second area, and the spatial range of the second area is larger than the spatial range of the first area.

[0014] Preferably, N reflectors are arranged at the rear of the leading vehicle, and the vertical center axis of the reflectors has a preset relative position with the leading vehicle, including:

[0015] N cylindrical reflectors are arranged at the rear of the front vehicle, and the central axis of the cylindrical reflector has a preset relative position with the front vehicle.

[0016] Preferably, N cylindrical reflectors are arranged at the rear of the leading vehicle, and the central axis of the cylindrical reflectors has a preset relative position with the leading vehicle, including:

[0017] Two cylindrical reflectors with reflective surfaces are arranged at the rear of the front vehicle, the reference center point between the coordinates of the central axis of the cylindrical reflectors in the horizontal plane is located on the central axis of the front vehicle, and the reflected light passing through the reflective surface meets the preset high reflection parameter;

[0018] A positional relationship between the projection of the reference center point on the horizontal plane and the projection of the body center point of the preceding vehicle on the horizontal plane is established.

[0019] Preferably, the rear vehicle collects a point cloud set in a preset front area by using a laser radar at a preset frequency, and obtains a plane point set based on the plane coordinates of the projection points of the point cloud set in a plane coordinate system established based on a horizontal plane, including:

[0020] The rear vehicle collects point clouds in a preset front area through a laser radar to obtain a point cloud set;

[0021] Filtering points in the point cloud set that do not meet preset high reflection parameters;

[0022] The plane coordinates of the projection points of the filtered point cloud set on the horizontal plane are collected to obtain a plane point set.

[0023] Preferably, the determining whether N circles can be obtained by fitting circles in the plane point set comprises:

[0024] Randomly select coordinates of three points that are not on the same straight line in the plane point set M times, fit a circle based on the three coordinates, and obtain an equation of a circular trajectory;

[0025] Counting the number of points in the plane point set whose distance from the circular trajectory meets a preset threshold, and respectively establishing sets of points constituting the first circular trajectory;

[0026] The circular trajectory with the largest number of points satisfying the preset threshold value among the M times is used as the contour trajectory of the first cylindrical reflector projected on the horizontal plane;

[0027] Filtering points in the set of points corresponding to the first cylindrical reflector from the set of plane points;

[0028] The filtered plane point set is subjected to P random selections of coordinates of three points that are not on the same straight line, and a circle is fitted based on the three coordinates to obtain an equation of a circular trajectory;

[0029] Counting the number of points in the plane point set whose distance from the circular trajectory meets a preset threshold, and respectively establishing sets of points constituting the first circular trajectory; and

[0030] The circular trajectory with the largest number of points satisfying the preset threshold in P times is used as the contour trajectory of the second cylindrical reflector projected on the horizontal plane.

[0031] Preferably, obtaining the center coordinates and radius of the circle, and obtaining the relative position of the leading vehicle with respect to the trailing vehicle according to the center coordinates, radius and the preset relative position, comprises:

[0032] Obtain the center coordinates O1 and O2 and the radii R1 and R2 of the two circles respectively;

[0033] Obtain the coordinates of the reference center point between the two circle center coordinates O1 and O2;

[0034] Based on the positional relationship between the reference center point and the body center point of the preceding vehicle, obtaining a projection point of the body center point of the preceding vehicle in the plane coordinate system;

[0035] Based on the positional relationship between the corner points of the four corners of the front vehicle and the center point of the body of the front vehicle, obtaining the projection points of the four corners of the front vehicle in the plane coordinate system;

[0036] The relative position of the front vehicle with respect to the rear vehicle is obtained based on the projection points of the four corners of the front vehicle in the plane coordinate system.

[0037] Preferably, generating a first area based at least on the circle center coordinates and updating the preset front area to the first area comprises:

[0038] A first area is generated based on the point cloud coordinates corresponding to the reference center point, and the preset front area is updated to the first area.

[0039] Preferably, the updating of the preset front area to a preset second area, wherein the spatial range of the second area is larger than the spatial range of the first area, comprises:

[0040] The preset front area is updated to a preset second area, and the spatial range of the second area is larger than the spatial range of the first area.

[0041] Preferably, the step of generating the first area based on the point cloud coordinates corresponding to the reference center point as the center comprises:

[0042] Generate a spherical first area based on the point cloud coordinates corresponding to the reference center point as the center and a first preset length as the radius;

[0043] The updating of the preset front area to a preset second area, wherein the spatial range of the second area is larger than the spatial range of the first area, includes:

[0044] A second spherical area is generated with the origin coordinates of the laser radar as the center and a second preset length as the radius, and the second preset length is greater than the first preset length.

[0045] An embodiment of the present invention further provides a front vehicle tracking system based on laser point cloud, which is used to implement the above-mentioned front vehicle tracking method based on laser point cloud. The front vehicle tracking system based on laser point cloud includes:

[0046] A reflector setting module is configured to set N reflectors at the rear of the front vehicle, wherein the vertical center axis of the reflectors has a preset relative position with the front vehicle, and N≥1;

[0047] A plane point set module, in which the rear vehicle collects a point cloud set in a preset front area through a laser radar at a preset frequency, and obtains a plane point set based on the plane coordinates of the projection points of the point cloud set in a plane coordinate system established based on a horizontal plane;

[0048] A plane circle fitting module, which determines whether N circles can be obtained by fitting circles in the plane point set, and if so, executes the relative position obtaining module, and if not, executes the second area updating module;

[0049] A relative position obtaining module is used to obtain the center coordinates and radius of the circle, and obtain the relative position of the leading vehicle relative to the trailing vehicle according to the center coordinates, radius and the preset relative position;

[0050] A first region updating module, generating a first region based at least on the circle center coordinates, updating the preset front region to the first region, and returning to the plane point set module; and

[0051] The second area updating module updates the preset front area to a preset second area, the spatial range of the second area is larger than the spatial range of the first area, and returns to the plane point set module.

[0052] An embodiment of the present invention further provides a preceding vehicle tracking device based on laser point cloud, comprising:

[0053] processor;

[0054] a memory in which executable instructions for the processor are stored;

[0055] The processor is configured to execute the steps of the above-mentioned preceding vehicle tracking method based on laser point cloud by executing executable instructions.

[0056] An embodiment of the present invention further provides a computer-readable storage medium for storing a program, which implements the steps of the above-mentioned leading vehicle tracking method based on laser point cloud when the program is executed.

[0057] The laser point cloud-based preceding vehicle tracking method, system, device and storage medium of the present invention can optimize the next point cloud range according to the last tracking result, thereby greatly reducing the point cloud computing volume, accelerating the recognition speed and improving driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Other features, objectives and advantages of the present invention will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following accompanying drawings.

[0059] Figure 1 It is a flow chart of the preceding vehicle tracking method based on laser point cloud of the present invention.

[0060] Figures 2 to 11 It is a schematic diagram of an implementation process of the front vehicle tracking method based on laser point cloud of the present invention.

[0061] Fig.12 It is a structural schematic diagram of the front vehicle tracking system based on laser point cloud of the present invention.

[0062] Fig.13 It is a structural schematic diagram of the front vehicle tracking device based on laser point cloud of the present invention. And

[0063] Fig.14 It is a schematic diagram of the structure of a computer-readable storage medium according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in the present application. The present application can also be implemented or applied through other different specific implementation methods, and the details in the present application can also be modified or changed in various ways according to different viewpoints and application systems without departing from the spirit of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0065] The following is a detailed description of the embodiments of the present application with reference to the accompanying drawings so that those skilled in the art can easily implement the present application. The present application can be embodied in a variety of different forms and is not limited to the embodiments described herein.

[0066] In the representations of the present application, the representations with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics represented in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the represented specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples represented in the present application and the features of the different embodiments or examples, unless they contradict each other.

[0067] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the representation of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0068] In order to clearly describe the present application, components irrelevant to the description are omitted, and the same reference symbols are given to the same or similar components throughout the specification.

[0069] Throughout the specification, when a device is said to be "connected" to another device, this includes not only the case of "direct connection" but also the case of "indirect connection" by placing other elements therebetween. In addition, when a device is said to "include" a certain component, unless otherwise stated, it does not exclude other components, but means that other components may be included.

[0070] When a device is said to be "on" another device, it may be directly on the other device, but there may also be other devices between it. In contrast, when a device is said to be "directly" on another device, there are no other devices between it.

[0071] Although the terms first, second, etc. are used to represent various elements in the present invention in some examples, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first interface and the second interface, etc. are represented. Moreover, as used in the present invention, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising" and "including" indicate the existence of features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". An exception to this definition will occur only when a combination of elements, functions, steps or operations are inherently mutually exclusive in some manner.

[0072] The technical terms used herein are only used to refer to specific embodiments and are not intended to limit the present application. The singular form used herein also includes the plural form unless the sentence clearly indicates the contrary meaning. The meaning of "including" used in the specification is to specify specific characteristics, regions, integers, steps, operations, elements and / or components, and does not exclude the existence or addition of other characteristics, regions, integers, steps, operations, elements and / or components.

[0073] Although not defined differently, all terms, including technical and scientific terms used herein, have the same meaning as those generally understood by those skilled in the art to which this application belongs. Terms defined in commonly used dictionaries are additionally interpreted as having meanings consistent with the relevant technical literature and the contents of the current disclosure, and unless defined, shall not be overly interpreted as ideal or very formal meanings.

[0074] Figure 1 FIG. 1 is a flow chart of the method for tracking a preceding vehicle based on laser point cloud of the present invention. Figure 1 As shown, an embodiment of the present invention provides a front vehicle tracking method based on laser point cloud, comprising the following steps:

[0075] S110. N reflectors are arranged at the rear of the leading vehicle, and the vertical center axis of the reflectors has a preset relative position with the leading vehicle, N≥1.

[0076] S120. The rear vehicle collects a point cloud set in a preset front area through a laser radar at a preset frequency, and obtains a plane point set based on the plane coordinates of the projection points of the point cloud set in a plane coordinate system established based on a horizontal plane.

[0077] S130, by fitting a circle in the plane point set, determine whether N circles can be obtained, if so, execute step S140, if not, execute step S160.

[0078] S140, obtaining the center coordinates and radius of the circle, and obtaining the relative position of the front vehicle with respect to the rear vehicle according to the center coordinates, the radius, and the preset relative position.

[0079] S150, generating a first area based at least on the coordinates of the circle center, updating the preset front area to the first area, and returning to step S120.

[0080] S160, updating the preset front area to a preset second area, wherein the spatial range of the second area is larger than the spatial range of the first area, and returning to step S120.

[0081] The present invention can optimize the point cloud range for the next time according to the tracking result of the previous time. When the position of the leading vehicle can be accurately tracked, it can automatically switch to using a smaller detection range, thereby reducing the calculation amount of the point cloud and speeding up the recognition speed. When the position of the leading vehicle cannot be accurately tracked, it can automatically switch to using a larger detection range to enhance the robustness, thereby greatly reducing the calculation amount of the point cloud as a whole, speeding up the recognition speed and improving driving safety.

[0082] In a preferred embodiment, step S110 includes: arranging N cylindrical reflectors at the rear of the preceding vehicle, wherein the central axis of the cylindrical reflectors has a preset relative position with the preceding vehicle, N ≥ 1, but not limited thereto. If only one cylindrical reflector is arranged, the central axis of the cylindrical reflector may be arranged at the middle of the rear of the vehicle intersecting with the extension direction of the central axis of the preceding vehicle, but not limited thereto.

[0083] In a preferred embodiment, step S110 includes:

[0084] S111. Two cylindrical reflectors with reflective surfaces are arranged at the rear of the front vehicle, the reference center point of the central axis of the cylindrical reflector between the coordinates of the horizontal plane is located on the central axis of the front vehicle, and the reflected light passing through the reflective surface meets the preset high reflection parameters.

[0085] S112. Establishing a positional relationship between the projection of the reference center point on the horizontal plane and the projection of the body center point of the preceding vehicle on the horizontal plane, but not limited thereto.

[0086] In a preferred embodiment, step S120 includes:

[0087] S121. The rear vehicle collects point clouds in a preset front area through a laser radar at a preset frequency to obtain a point cloud set.

[0088] S122, filtering out points in the point cloud set that do not meet the preset high reflection parameters, so that the reflection points passing through the cylindrical reflector are clearly distinguished from other reflection points in terms of reflection parameters, thereby filtering out the reflection points that do not belong to the cylindrical reflector, so that the filtered point cloud set is basically a point cloud formed by the cylindrical reflector.

[0089] S123, collecting the plane coordinates of the projection points of the filtered point cloud set on the horizontal plane to obtain a plane point set, but the present invention is not limited thereto.

[0090] In a preferred embodiment, step S130 includes:

[0091] S131. Randomly select the coordinates of three points that are not on the same straight line in the plane point set M times, fit a circle based on the three coordinates, and obtain an equation of a circular trajectory.

[0092] S132, counting the number of points in the plane point set whose distance from the circular trajectory meets a preset threshold, and respectively establishing sets of points constituting the first circular trajectory.

[0093] S133, taking a circular trajectory with the largest number of points satisfying a preset threshold in M ​​times as a contour trajectory of the first cylindrical reflector projected on the horizontal plane.

[0094] S134. Filter the points in the set of points corresponding to the first cylindrical reflector in the plane point set.

[0095] S135, taking the coordinates of three points that are not on the same straight line at random for P times, fitting a circle based on the three coordinates, and obtaining an equation of a circular trajectory.

[0096] S136, counting the number of points in the plane point set whose distance from the circular trajectory meets a preset threshold, and respectively establishing a set of points constituting the first circular trajectory.

[0097] S137, taking the circular trajectory with the largest number of points satisfying the preset threshold in P times as the contour trajectory of the second cylindrical reflector projected on the horizontal plane, but not limited to this.

[0098] In a preferred embodiment, step S140 includes:

[0099] S141, respectively obtain the center coordinates O of the two circles 1 , O 2 and radius R 1 , R 2 .

[0100] S142, obtain two circle center coordinates O 1 , O 2 The coordinates of the reference center point between .

[0101] S143. Based on the positional relationship between the reference center point and the body center point of the preceding vehicle, obtain a projection point of the body center point of the preceding vehicle in the plane coordinate system.

[0102] S144. Based on the positional relationship between the corner points of the four corners of the front vehicle and the center point of the body of the front vehicle, the projection points of the four corners of the front vehicle in the plane coordinate system are obtained.

[0103] S145. Obtain the relative position of the front vehicle with respect to the rear vehicle based on the projection points of the four corners of the front vehicle in the plane coordinate system, but the present invention is not limited thereto.

[0104] In a preferred embodiment, step S150 includes:

[0105] A first area is generated based on the point cloud coordinates corresponding to the reference center point, the preset front area is updated to the first area, and the process returns to step S120, but is not limited thereto.

[0106] In a preferred embodiment, step S160 includes:

[0107] The preset front area is updated to a preset second area, the spatial range of the second area is larger than the spatial range of the first area, and the process returns to step S120, but is not limited thereto.

[0108] In a preferred embodiment, in step S151, a spherical first area is generated with the point cloud coordinates corresponding to the reference center point as the center and the first preset length as the radius.

[0109] In step S162, a second spherical area is generated with the origin coordinate of the laser radar as the center and the second preset length as the radius. The second preset length is greater than the first preset length. The origin coordinate of the laser radar can be the median position of the front end of the rear vehicle, but is not limited to this.

[0110] The present invention provides a method for tracking a leading vehicle based on artificial point cloud features in an environment, the method comprising: searching for a point cloud region of interest in the environment based on a pre-known following distance and reflection intensity, fitting the point cloud through prior information on the size of an artificially constructed reflective cylinder, and calculating the relative position of the leading vehicle through information on the fitted circle, thereby achieving the purpose of tracking.

[0111] like Figures 2 to 11 As shown, an implementation process of the present invention mainly includes:

[0112] First, participate Figure 2Two cylindrical reflectors 11 with reflective surfaces are arranged at the rear of the front vehicle 1, and the reference center point between the coordinates of the central axis 10 of the cylindrical reflector 11 in the horizontal plane is located on the central axis 10 of the front vehicle 1, and the reflected light passing through the reflective surface meets the preset high reflection parameter. The positional relationship between the projection of the reference center point on the horizontal plane and the projection of the center point of the body of the front vehicle 1 on the horizontal plane is established.

[0113] join Figure 3 Then the rear vehicle 2 collects point clouds in the preset front area at a preset frequency through the laser radar 21, and establishes a spatial coordinate system to obtain a point cloud set. The points in the point cloud set that do not meet the preset high reflection parameters are filtered, so that the filtered point cloud set is basically a point cloud formed by cylindrical reflectors. The plane coordinates of the projection points of the filtered point cloud set in the plane coordinate system of the horizontal plane (the X axis is the width direction of the rear vehicle, and the Y axis is the length direction of the rear vehicle), where the origin of the plane coordinate system is the center point of the front end of the rear vehicle, thereby obtaining a plane point set 30.

[0114] join Figure 4 , randomly select the coordinates of three points 31 that are not on the same straight line in the plane point set 30 M times, fit a circle based on the three coordinates, and obtain an equation of a circular trajectory 32. Count the number of points in the plane point set 30 whose spacing from the circular trajectory meets a preset threshold, and establish sets of points that constitute the first circular trajectory.

[0115] join Figure 5 , the circular trajectory with the largest number of points that meet the preset threshold in M ​​times is used as the circular contour trajectory 33 of the first cylindrical reflector 11 projected on the horizontal plane. In addition, the points in the set of points corresponding to the first cylindrical reflector 11 are filtered in the plane point set 30 to avoid the influence of these points on subsequent fitting, improve accuracy, and reduce the amount of calculation. The filtered plane point set 30 is subjected to P times of randomly selecting the coordinates of three points 34 that are not on the same straight line, and a circle is fitted based on the three coordinates to obtain the equation of a circular trajectory 35.

[0116] join Figure 6 , the number of points in the plane point set 30 whose distance from the circular trajectory meets the preset threshold is counted, and the sets of points constituting the first circular trajectory are respectively established. The circular trajectory with the largest number of points meeting the preset threshold among the P times is used as the circular contour trajectory 36 of the second cylindrical reflector 11 projected on the horizontal plane.

[0117] join Figure 7 , respectively obtain the center coordinates O of the two circles 33 and 36 1 37. O 2 38 and radius R 1 , R 2 . Get the coordinates of the two circle centers O1 , O 2 The coordinates of the reference center point 39 between. In this embodiment, the equation corresponding to the circular trajectory is obtained by the point cloud fitting method of the prior art, but it is not limited thereto.

[0118] join Figure 8 Based on the positional relationship between the reference center point 39 and the body center point of the front vehicle 1, the projection point 12 of the body center point of the front vehicle 1 in the plane coordinate system is obtained. The X-axis coordinate of the projection point 12 of the body center point is equal to the X-axis coordinate of the reference center point 39, and the Y-axis coordinate of the projection point 12 of the body center point is equal to the Y-axis coordinate of the reference center point 39 and increases by (L / 2+r) along the positive direction of the Y-axis. Based on the positional relationship between the corner points of the four corners of the front vehicle 1 and the body center point of the front vehicle 1, the projection points 13, 14, 15, and 16 of the four corners of the front vehicle 1 in the plane coordinate system are obtained. Since the cylindrical reflector 11 is fixed at the rear of the vehicle, the positional relationship between the reference center point 39 and the body center point of the front vehicle 1 will not change. The position relationship between the four corners of the front vehicle 1 and the center point of the body of the front vehicle 1 is also constant. After determining the projection point 12 of the center point of the body in the plane coordinate system, the coordinates of the projection points 13, 14, 15, and 16 of the four corners of the front vehicle 1 in the plane coordinate system can be obtained through mapping.

[0119] join Fig. 9 , based on the projection points 13, 14, 15, and 16 of the four corners of the front vehicle 1 in the plane coordinate system, the relative position of the front vehicle 1 relative to the rear vehicle 2 is obtained (see Fig. 9 ).

[0120] join Fig.10 , based on the point cloud coordinates corresponding to the reference center point as the center, the first area is generated, the preset front area is updated as the first area, and the process returns to step S120. Based on the point cloud coordinates corresponding to the reference center point as the center, a spherical first area is generated with the first preset length L1 as the radius. Since the position of the front vehicle can be accurately tracked this time, the position of the front vehicle will not change much next time it is detected, so it is automatically switched to a smaller detection range to reduce the amount of point cloud calculation and speed up the recognition speed.

[0121] join Fig.11If a circular contour trajectory that meets the requirements cannot be obtained this time, the vehicle in front cannot be accurately tracked, and it is difficult to know the position of the vehicle in front next time. It is necessary to search in a wider range (more point cloud data). Based on the origin coordinates of the laser radar 21 as the center, a spherical second area is generated with a second preset length L2 as the radius, and the second preset length L2 is greater than the first preset length L1. The preset front area is updated to the preset second area, and the spatial range of the second area is greater than the spatial range of the first area. When the position of the vehicle in front cannot be accurately tracked, it automatically switches to using a larger detection range to enhance robustness, thereby greatly reducing the amount of point cloud computing as a whole, speeding up recognition speed, and improving driving safety.

[0122] Another implementation process of the present invention mainly includes:

[0123] Step (1) The present invention uses a reflective barrel with a high reflectivity surface, so that the reflective barrel area will be significantly different in the laser observation of the rear vehicle, because the points in the reflective barrel area can be extracted by the reflection intensity, and the parameters of the circle to be solved are the center coordinates and radius of the two circles in the top view, and the specific position of the front vehicle is calculated by the midpoint of the circle. First, the point cloud region of interest (ROI) is searched globally according to the reflection intensity and observation distance of the point cloud. If the tracking is successful at the last moment, the search is performed near the position of the front vehicle tracked at the last time. If the tracking fails at the last time, the search is performed within a specified distance range from the current position.

[0124] The point cloud observation set point at the current time i is recorded as:

[0125] {point│point:(px,py,pz,pinten)∈Pi},

[0126] Among them, the observation point cloud at the current time i is Pi, each point point contains the coordinates (px, py, pz) and reflection intensity pinten in the Cartesian coordinate system, and the extracted point cloud set of the area of ​​interest is Proi.

[0127] The limit of roi reflection intensity is β. If the tracking is successful at the last moment, the center point of the front vehicle position will be recorded as (x c ,y c ), first calculate the distance between each point in Pi and the projection of the center point on the XOY plane,

[0128] Right now

[0129] When the distance from the center point is less than α, it is considered to be the required ROI area point. At this time, the set of ROI area points captured is {point│pi>β,dis<α}.

[0130] If the tracking fails at the last moment, there is no center point coordinate. At this time, the distance between each observation point and the origin of the rear vehicle laser radar coordinate system is Only points whose distance is less than γ are considered as ROI area points. At this time, the set of ROI area points captured is {point│pi>β,dis<γ}.

[0131] After obtaining the ROI point cloud in step (2), it is determined whether the number meets the number conditions for successfully solving the circle feature. If so, the solution is further processed to step (3). If not, the tracking failure is returned to step (1).

[0132] Step (3) Use RANSAC (Random Sampling Consensus) to fit the circle parameters, i.e., the center coordinates and radius, and select the circle parameter model with the largest number of inner points in the iteration process. Because only three points are needed to solve the parameters of a circle, the coordinates of the three points extracted from Proi are p1 (x1, y1), p2 (x2, y2), and p3 (x3, y3). Suppose the circle parameters to be solved are (x c ,y c , r), the parametric equations for solving the relevant parameters of the circle model based on the three sampling points are:

[0133] xc=((y2-y1)*([y3]^2-[y1] ^ 2+[x3]^2-[x1]^2)-(y3-y1)*([y2]^2-[y1]^2+[x2]^2-[x1]^2)) / (2*((x3-x1)*(y2-y1)-(x2-x1)*(y3-y1)))

[0134] yc=((x2-x1)*([x3]^2-[x1]^2+[y3]^2-[y1]^2)-(x3-x1)*([x2]^2-[ x1]^2+[y2]^2-[y1]^2)) / (2*((y3-y1)*(x2-x1)-(y2-y1)*(x3-x1)))

[0135]

[0136] Calculate P roi Except for the three points where the parameters are calculated, each point is related to (x c ,y c ) to determine whether it falls near the edge of the pre-set circle. The radius of the fitted reflective barrel is 0.1 meters, the tolerance error is γ, and the coordinates of any other point in Proi are (a, b).

[0137] remember

[0138] If 0.1+γ>=dis>=0.1-γ, it means that this point meets the model of the circle being solved, and is recorded as the internal point of the current model. The number of all the points that meet the requirements among the remaining points is the number of internal points of the current model. Suppose the algorithm iterates N times in total, and each time three points are randomly selected to solve the model and then the number of internal points is counted. Then the point with the largest number of internal points is selected and the least square method is used to solve the circle parameters for all the points that are judged as internal points.

[0139] Step (4) assumes that the i-th iteration is the computational model with the most inliers, and assumes that all points marked as inliers in Proi in the i-th iteration can be used to solve the final model parameters, i.e., the coordinates of the center of the circle.

[0140] Step (5) Since the artificially constructed features are two circles, solve the first circle first. The parameters obtained are the coordinates of the center of the circle (x c ,y c ) and radius r, the points used to solve the current circle parameters are deleted from the Proi point cloud, that is, the points within α times the range of the center of the first circle are deleted, that is, the points in the Proi point cloud that satisfy {(x, y)|x>α*r+x c , y>α*r+y c}.

[0141] Step (6) uses the remaining points in Proi to solve the parameters of the remaining circle, and then performs step (3) again to obtain the parameters of another circle.

[0142] Step (7) Calculate the position of the front vehicle according to the midpoint of the two circle centers. The coordinates of the center of the left circle are (x 1 ,y 1 ), the coordinates of the center of the right circle are (x 2 ,y 2 ), the center coordinates of the two reflectors of the rear vehicle are obtained as (x f ,y f ), x f =(x 1 +x 2 ) / 2,y f =(y 1 +y 2) / 2. It is known in advance that the car body is a cuboid with a length of length and a width of width. If the car body coordinate system is at the center of the car body, it can be known that the coordinates of the four corner points of the car body frame relative to the origin are offset by (width / 2, length / 2), (width / 2, -length / 2), (-width / 2, -length / 2), (-width / 2, length / 2). Adding the offset of the intersection of the car body frame to the coordinates of the center position is equivalent to obtaining the coordinate position of the corner point in the rear car laser radar coordinate system, that is, at this time, according to the center point position obtained according to the tracking characteristics of the front car, the position of the front car can be calculated, and the purpose of tracking is achieved (the RANSAC algorithm in this embodiment belongs to the prior art, and the basic principle can be referred to https: / / zhuanlan.zhihu.com / p / 45532306. The algorithm for fitting the circle in this embodiment belongs to the prior art, and the parameters of the least squares fitting circle of multiple sampling points can be referred to https: / / blog.csdn.net / liyuanbhu / article / details / 50889951).

[0143] Fig.12 Schematic diagram of the structure of the front vehicle tracking system based on laser point cloud of the present invention. Fig.12 As shown, the front vehicle tracking system 5 based on laser point cloud of the present invention comprises:

[0144] The reflector setting module 51 sets N reflectors at the rear of the front vehicle, and the vertical center axis of the reflectors has a preset relative position with the front vehicle, N≥1.

[0145] The plane point set module 52 collects a point cloud set in a preset front area through a laser radar at a preset frequency, and obtains a plane point set based on the plane coordinates of the projection points of the point cloud set in a plane coordinate system established based on a horizontal plane.

[0146] The plane circle fitting module 53 determines whether N circles can be obtained by fitting circles in the plane point set. If so, the relative position obtaining module is executed; if not, the second area updating module is executed.

[0147] The relative position obtaining module 54 obtains the center coordinates and radius of the circle, and obtains the relative position of the front vehicle relative to the rear vehicle according to the center coordinates, radius and the preset relative position.

[0148] The first region updating module 55 generates a first region based on at least the coordinates of the circle center, updates the preset front region to the first region, and returns to the plane point collection module.

[0149] The second area updating module 56 updates the preset front area to a preset second area, the spatial range of the second area is larger than the spatial range of the first area, and returns to the plane point set module.

[0150] In a preferred embodiment, the reflector setting module 51 is configured to set N cylindrical reflectors at the rear of the leading vehicle, and the central axis of the cylindrical reflector has a preset relative position with the leading vehicle, N≥1.

[0151] In a preferred embodiment, the reflector setting module 51 is configured to set two cylindrical reflectors with reflective surfaces at the rear of the front vehicle, the reference center point between the coordinates of the central axis of the cylindrical reflector in the horizontal plane is located on the central axis of the front vehicle, and the reflected light passing through the reflective surface meets the preset high reflection parameter. A positional relationship between the projection of the reference center point on the horizontal plane and the projection of the body center point of the front vehicle on the horizontal plane is established.

[0152] In a preferred embodiment, the plane point collection module 52 is configured to allow the rear vehicle to collect point clouds in a preset front area at a preset frequency through a laser radar to obtain a point cloud collection. Points in the point cloud collection that do not meet the preset high reflection parameters are filtered. The plane coordinates of the projection points of the filtered point cloud collection on the horizontal plane are obtained to obtain a plane point collection.

[0153] In a preferred embodiment, the plane circle fitting module 53 is configured to select the coordinates of three points that are not on the same straight line in the plane point set M times, fit the circle based on the three coordinates, and obtain the equation of a circular trajectory. The number of points in the plane point set whose spacing with the circular trajectory meets the preset threshold is counted, and the sets of points constituting the first circular trajectory are established respectively. The circular trajectory with the largest number of points that meet the preset threshold in the M times is used as the contour trajectory of the first cylindrical reflector projected on the horizontal plane. The points in the set of points corresponding to the first cylindrical reflector are filtered in the plane point set. The filtered plane point set is randomly selected P times for the coordinates of three points that are not on the same straight line, and the circle is fitted based on the three coordinates to obtain the equation of a circular trajectory. The number of points in the plane point set whose spacing with the circular trajectory meets the preset threshold is counted, and the sets of points constituting the first circular trajectory are established respectively. The circular trajectory with the largest number of points that meet the preset threshold in the P times is used as the contour trajectory of the second cylindrical reflector projected on the horizontal plane.

[0154] In a preferred embodiment, the relative position obtaining module 54 is configured to obtain the center coordinates of the two circles respectively. 1 , O 2 and radius R 1 , R 2 . Get the coordinates of the two circle centers O 1 , O 2The coordinates of the reference center point between the front and rear vehicles are obtained. Based on the positional relationship between the reference center point and the center point of the front vehicle's body, the projection point of the front vehicle's body center in the plane coordinate system is obtained. Based on the positional relationship between the corner points of the front vehicle's four corners and the center point of the front vehicle's body, the projection points of the front vehicle's four corners in the plane coordinate system are obtained. Based on the projection points of the front vehicle's four corners in the plane coordinate system, the relative position of the front vehicle relative to the rear vehicle is obtained.

[0155] In a preferred embodiment, the first area updating module 55 is configured to generate a first area based on the point cloud coordinates corresponding to the reference center point as the center, update the preset front area to the first area, and the plane point set module 52.

[0156] In a preferred embodiment, the second area updating module 56 is configured to update the preset front area to a preset second area, the spatial range of the second area is larger than the spatial range of the first area, and return to the plane point collection module 52 .

[0157] In a preferred embodiment, the first region updating module 55 is further configured to generate a spherical first region based on the point cloud coordinates corresponding to the reference center point as the center and the first preset length as the radius. The second region updating module 56 is further configured to generate a spherical second region based on the origin coordinates of the laser radar as the center and the second preset length as the radius, and the second preset length is greater than the first preset length.

[0158] The laser point cloud-based preceding vehicle tracking system of the present invention can optimize the next point cloud range according to the last tracking result, thereby greatly reducing the amount of point cloud computing, accelerating the recognition speed, and improving driving safety.

[0159] The embodiment of the present invention further provides a preceding vehicle tracking device based on laser point cloud, comprising a processor and a memory, wherein executable instructions of the processor are stored. The processor is configured to execute the steps of the preceding vehicle tracking method based on laser point cloud by executing the executable instructions.

[0160] As described above, the laser point cloud-based preceding vehicle tracking device of the present invention can optimize the next point cloud range according to the last tracking result, thereby greatly reducing the amount of point cloud computing, accelerating the recognition speed, and improving driving safety.

[0161] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0162] Fig.13This is a schematic diagram of the structure of the front vehicle tracking device based on laser point cloud of the present invention. Fig.13 The electronic device 600 according to this embodiment of the present invention is described. Fig.13 The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0163] like Fig.13 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0164] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps of various exemplary embodiments of the present invention described in the electronic prescription circulation processing method section of this specification. For example, the processing unit 610 can execute the following steps: Figure 1 Follow the steps shown in .

[0165] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0166] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0167] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0168] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0169] The embodiment of the present invention also provides a computer-readable storage medium for storing a program, and the steps of the preceding vehicle tracking method based on laser point cloud are implemented when the program is executed. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary embodiments of the present invention described in the above-mentioned electronic prescription circulation processing method section of this specification.

[0170] As shown above, when the program of the computer-readable storage medium of this embodiment is executed, it can optimize the next point cloud range according to the last tracking result, thereby greatly reducing the amount of point cloud computing, accelerating the recognition speed, and improving driving safety.

[0171] Fig.14 Schematic diagram of the structure of the computer-readable storage medium of the present invention. Fig.14 As shown, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0172] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0173] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0174] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0175] In summary, the laser point cloud-based preceding vehicle tracking method, system, device and storage medium of the present invention can optimize the next point cloud range according to the previous tracking result, thereby greatly reducing the amount of point cloud computing, accelerating the recognition speed and improving driving safety.

[0176] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.

Claims

1. A front vehicle tracking method based on laser point cloud, characterized in that: The steps include: N reflectors are arranged at the rear of the front vehicle, and the vertical center axis of the reflectors has a preset relative position with the front vehicle, N≥1; The rear vehicle collects a point cloud set in a preset front area through a laser radar at a preset frequency, and obtains a plane point set based on the plane coordinates of the projection points of the point cloud set in a plane coordinate system established based on a horizontal plane; By fitting a circle in the plane point set, determining whether N circles can be obtained; When N circles can be obtained, the center coordinates and radius of the circles are obtained, and the relative position of the front vehicle with respect to the rear vehicle is obtained according to the center coordinates, radius and the preset relative position; Generate a first area based at least on the circle center coordinates, and update the preset front area to the first area; as well as When N circles cannot be obtained, the preset front area is updated to a preset second area, and the spatial range of the second area is larger than the spatial range of the first area.

2. The preceding vehicle tracking method based on laser point cloud according to claim 1 is characterized in that: The method of arranging N reflectors at the rear of the front vehicle, wherein the vertical center axis of the reflectors has a preset relative position with the front vehicle, comprises: N cylindrical reflectors are arranged at the rear of the front vehicle, and the central axis of the cylindrical reflector has a preset relative position with the front vehicle.

3. The preceding vehicle tracking method based on laser point cloud according to claim 2 is characterized in that: The method of arranging N cylindrical reflectors at the rear of the front vehicle, wherein the central axis of the cylindrical reflectors has a preset relative position with the front vehicle, comprises: Two cylindrical reflectors with reflective surfaces are arranged at the rear of the front vehicle, the reference center point between the coordinates of the central axis of the cylindrical reflectors in the horizontal plane is located on the central axis of the front vehicle, and the reflected light passing through the reflective surface meets the preset high reflection parameter; A positional relationship between the projection of the reference center point on the horizontal plane and the projection of the body center point of the preceding vehicle on the horizontal plane is established.

4. The preceding vehicle tracking method based on laser point cloud according to claim 3 is characterized in that: The rear vehicle collects a point cloud set in a preset front area by using a laser radar at a preset frequency, and obtains a plane point set based on the plane coordinates of the projection points of the point cloud set in a plane coordinate system established based on a horizontal plane, including: The rear vehicle collects point clouds in a preset front area through a laser radar to obtain a point cloud set; Filtering points in the point cloud set that do not meet preset high reflection parameters; The plane coordinates of the projection points of the filtered point cloud set on the horizontal plane are collected to obtain a plane point set.

5. The preceding vehicle tracking method based on laser point cloud according to claim 2 is characterized in that: The step of determining whether N circles can be obtained by fitting circles in the plane point set includes: Randomly select coordinates of three points that are not on the same straight line in the plane point set M times, fit a circle based on the three coordinates, and obtain an equation of a circular trajectory; Counting the number of points in the plane point set whose distance from the circular trajectory meets a preset threshold, and respectively establishing sets of points constituting the first circular trajectory; The circular trajectory with the largest number of points satisfying the preset threshold value among the M times is used as the contour trajectory of the first cylindrical reflector projected on the horizontal plane; Filtering points in the set of points corresponding to the first cylindrical reflector from the set of plane points; The filtered plane point set is subjected to P random selections of coordinates of three points that are not on the same straight line, and a circle is fitted based on the three coordinates to obtain an equation of a circular trajectory; Counting the number of points in the plane point set whose distance from the circular trajectory meets a preset threshold, and respectively establishing sets of points constituting the first circular trajectory; and The circular trajectory with the largest number of points satisfying the preset threshold in P times is used as the contour trajectory of the second cylindrical reflector projected on the horizontal plane.

6. The preceding vehicle tracking method based on laser point cloud according to claim 2, characterized in that: The obtaining of the center coordinates and radius of the circle, and obtaining the relative position of the leading vehicle with respect to the trailing vehicle according to the center coordinates, radius and the preset relative position, comprises: Obtain the center coordinates O1 and O2 and the radii R1 and R2 of the two circles respectively; Obtain the coordinates of the reference center point between the two circle center coordinates O1 and O2; Based on the positional relationship between the reference center point and the body center point of the preceding vehicle, obtaining a projection point of the body center point of the preceding vehicle in the plane coordinate system; Based on the positional relationship between the corner points of the four corners of the front vehicle and the center point of the body of the front vehicle, obtaining the projection points of the four corners of the front vehicle in the plane coordinate system; The relative position of the front vehicle with respect to the rear vehicle is obtained based on the projection points of the four corners of the front vehicle in the plane coordinate system.

7. The preceding vehicle tracking method based on laser point cloud according to claim 6 is characterized in that: The step of generating a first area based at least on the circle center coordinates and updating the preset front area to the first area includes: A first area is generated based on the point cloud coordinates corresponding to the reference center point, and the preset front area is updated to the first area.

8. The preceding vehicle tracking method based on laser point cloud according to claim 7 is characterized in that: The updating of the preset front area to a preset second area, wherein the spatial range of the second area is larger than the spatial range of the first area, includes: The preset front area is updated to a preset second area, and the spatial range of the second area is larger than the spatial range of the first area.

9. The preceding vehicle tracking method based on laser point cloud according to claim 8, characterized in that: The generating a first area based on the point cloud coordinates corresponding to the reference center point as the center includes: Generate a spherical first area based on the point cloud coordinates corresponding to the reference center point as the center and a first preset length as the radius; The updating of the preset front area to a preset second area, wherein the spatial range of the second area is larger than the spatial range of the first area, includes: A second spherical area is generated with the origin coordinates of the laser radar as the center and a second preset length as the radius, and the second preset length is greater than the first preset length.

10. A front vehicle tracking system based on laser point cloud, characterized in that: The system comprises: A reflector setting module is configured to set N reflectors at the rear of the front vehicle, wherein the vertical center axis of the reflectors has a preset relative position with the front vehicle, and N≥1; A plane point set module, in which the rear vehicle collects a point cloud set in a preset front area through a laser radar at a preset frequency, and obtains a plane point set based on the plane coordinates of the projection points of the point cloud set in a plane coordinate system established based on a horizontal plane; A plane circle fitting module, which determines whether N circles can be obtained by fitting circles in the plane point set, and if so, executes the relative position obtaining module, and if not, executes the second area updating module; A relative position obtaining module is used to obtain the center coordinates and radius of the circle, and obtain the relative position of the leading vehicle relative to the trailing vehicle according to the center coordinates, radius and the preset relative position; A first region updating module, generating a first region based at least on the circle center coordinates, updating the preset front region to the first region, and returning to the plane point set module; and The second area updating module updates the preset front area to a preset second area, the spatial range of the second area is larger than the spatial range of the first area, and returns to the plane point set module.

11. A front vehicle tracking device based on laser point cloud, characterized in that: include: processor; a memory storing executable instructions of the processor; Wherein, the processor is configured to execute the steps of the preceding vehicle tracking method based on laser point cloud according to any one of claims 1 to 7 by executing the executable instructions.

12. A computer-readable storage medium for storing a program, characterized in that: When the program is executed, the steps of the preceding vehicle tracking method based on laser point cloud described in any one of claims 1 to 7 are implemented.

Images