Calibration method and system of point cloud coordinate system, storage medium and electronic device

Abstract

The invention discloses a point cloud coordinate system calibration method and system, a storage medium and an electronic device, and the method comprises the steps: obtaining target point cloud data in at least one scanning period through a multi-line laser radar; determining edge points of a lane according to the point cloud data; determining the direction of the lane according to the edge points of the lane; and calibrating the point cloud coordinate system of the multi-line laser radar according to the direction of the lane.

Description

Technical Field

[0001] This application relates to the field of calibration of point cloud coordinate systems. Specifically, it relates to a method and system for calibrating a point cloud coordinate system, a storage medium, and an electronic device. Background Art

[0002] LiDAR is a technology that measures distances and creates maps or images by emitting laser pulses and measuring the time of odd returns. In the prior art, in related fields such as map making and vehicle perception, it is usually necessary to determine the lanes in the point cloud collected by the LiDAR, and calibrate the point cloud coordinate system of the LiDAR according to the determined lane direction, so as to ensure the accurate perception and precise positioning of the vehicle.

[0003] The conventional method for determining the lanes in the point cloud is to calculate the lane position based on the free-flow point cloud density, or manually calibrate the lanes. However, calculating the lane position based on the free-flow point cloud density mainly uses the characteristic that the point cloud density will increase when an object passes through, and obtains the trajectory through the density distribution statistically over a period of time, and then calculates the approximate position where the lane is located. This requires long-term statistics, and the density distribution is easily affected by the vehicle crossing the lane, resulting in incorrect lane analysis. The manual calibration method is also prone to errors due to its high dependence on manual labor.

[0004] It can be seen that the calibration method of the point cloud coordinate system in the related technology has the problem of low accuracy in calibrating the point cloud coordinate system. Summary of the Invention

[0005] Embodiments of this application provide a method and system for calibrating a point cloud coordinate system, a storage medium, and an electronic device, so as to at least solve the problem of low accuracy in calibrating the point cloud coordinate system in the related technology.

[0006] According to one aspect of the embodiments of this application, a method for calibrating a point cloud coordinate system is provided, including: obtaining target point cloud data within at least one scanning period through a multi-line LiDAR; determining the edge points of the lane according to the point cloud data; determining the direction of the lane according to the edge points of the lane; and calibrating the point cloud coordinate system of the multi-line LiDAR according to the direction of the lane.

[0007] According to another aspect of the embodiments of the present application, there is also provided a calibration system for a point cloud coordinate system, including: a multi-line lidar for scanning a lane and the surroundings of the lane, wherein the multi-line lidar includes N laser lines; a data processing unit for obtaining target point cloud data within at least one scanning period through the multi-line lidar; determining edge points of the lane according to the point cloud data; determining the direction of the lane according to the edge points of the lane; and calibrating the point cloud coordinate system of the multi-line lidar according to the direction of the lane.

[0008] According to still another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the above-mentioned calibration method for the point cloud coordinate system when running.

[0009] According to still another aspect of the embodiments of the present application, there is also provided an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the above-mentioned processor executes the above-mentioned calibration method for the point cloud coordinate system through the computer program.

[0010] In the embodiments of the present application, a method for determining a lane by using the change of multiple point clouds continuously scanned by the same laser line in a multi-line lidar is adopted. Target point cloud data within at least one scanning period is obtained through the multi-line lidar; edge points of the lane are determined according to the point cloud data; the direction of the lane is determined according to the edge points of the lane; and the point cloud coordinate system of the multi-line lidar is calibrated according to the direction of the lane. Since the flatness of the lane and the roadside ground is different, and the objects on the lane and the sundries on the roadside ground are also different, based on the continuity characteristics of the point clouds scanned by each laser line of the multi-line lidar within at least one scanning period, the positions of the objects corresponding to different points can be determined from the point cloud data corresponding to each laser line within at least one scanning period. Based on the change of the continuous points in the point cloud data corresponding to each laser line, the edge between the lane and the roadside ground can be determined. There is no need to obtain vehicle point cloud information for a long time, nor to rely on manual calibration, which can shorten the time for identifying the lane, reduce the influence of the external environment (such as vehicle lane crossing, manual operation), and achieve the technical effect of improving the accuracy of calibrating the point cloud coordinate system, thereby solving the problem that the accuracy of the calibration method for the point cloud coordinate system in the related art is relatively low. Description of the Drawings

[0011] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0012] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0013] Figure 1 It is a schematic diagram of the hardware environment of an optional method for calibrating a point cloud coordinate system according to an embodiment of the present application;

[0014] Figure 2 It is a schematic flowchart of an optional method for calibrating a point cloud coordinate system according to an embodiment of the present application;

[0015] Figure 3 It is a schematic diagram of another optional method for calibrating a point cloud coordinate system according to an embodiment of the present application;

[0016] Figure 4 It is a schematic diagram of yet another optional method for calibrating a point cloud coordinate system according to an embodiment of the present application;

[0017] Figure 5 It is a structural block diagram of an optional electronic device according to an embodiment of the present application. Detailed implementation manners

[0018] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily need to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0020] According to one aspect of the embodiments of the present application, a method for calibrating a point cloud coordinate system is provided. Optionally, in this embodiment, the above method for calibrating a point cloud coordinate system can be applied to, for example, Figure 1 the hardware environment shown in the figure including a multi-line lidar 102 and a server 104. As shown in Figure 1 the figure, the server 104 is connected to the multi-line lidar 102 through a network, and can be used to calibrate the point cloud coordinate system based on the point cloud data of the multi-line lidar 102. A database can be set up on the server or independently of the server to provide data storage services for the server 104.

[0021] The above network may include, but is not limited to, at least one of the following: a wired network, a wireless network. The above wired network may include, but is not limited to, at least one of the following: a wide area network, a metropolitan area network, a local area network. The above wireless network may include, but is not limited to, at least one of the following: WIFI (Wireless Fidelity), Bluetooth.

[0022] The method for calibrating the point cloud coordinate system in the embodiments of the present application can be executed by the server 104, or can also be jointly executed by the server 104 and the multi-line lidar 102. Taking the method for calibrating the point cloud coordinate system in this embodiment executed by the server 104 as an example, Figure 2 is a schematic flowchart of an optional method for calibrating a point cloud coordinate system according to the embodiments of the present application. As shown in Figure 2 the figure, the process of this method may include the following steps:

[0023] Step S202, obtaining target point cloud data within at least one scanning period through the multi-line lidar;

[0024] Step S204, determining the edge points of the lane according to the point cloud data;

[0025] Step S206, determining the direction of the lane according to the edge points of the lane;

[0026] Step S208, calibrating the point cloud coordinate system of the multi-line lidar according to the direction of the lane.

[0027] The method for calibrating the point cloud coordinate system in this embodiment can be applied to the scenario of determining the direction of the lane in the radar point cloud. Here, the radar may refer to a lidar (Light Detection and Ranging). High-precision three-dimensional spatial information can be generated according to the point cloud data scanned by the lidar. When applying in the fields of map making and vehicle perception, it is usually necessary to obtain the direction of the lane in the radar point cloud to ensure the accurate perception and precise positioning of the vehicle.

[0028] In the prior art, for determining the lane direction in a radar point cloud, it is usually based on the density distribution of the point cloud points within a period of time. By utilizing the characteristic that the point cloud density increases when an object passes through, the density distribution over a period of time is statistically analyzed, and the trajectory is obtained based on the density distribution to calculate the approximate position where the lane line is located, or the lane line is manually calibrated.

[0029] The method based on free flow statistics has certain drawbacks. One is that it requires relatively long-term statistics. The other is that it is difficult to find a suitable density statistical grid because the vehicle sizes vary greatly and there are phenomena such as cross-lane driving. There may be a situation where it is difficult to obtain the travel trajectory of the road target based on density. Manually obtaining the lane line direction not only consumes a large amount of manpower and time but also is prone to deviation.

[0030] In order to solve at least some of the above problems, in this embodiment, the position change of the continuously scanned points in the point cloud data scanned by a multi-line lidar can be used. By utilizing the characteristics of the flat road surface and diverse roadside sundries, the boundary points between the road surface and the roadside are detected. It is not necessary for a target to pass through the lane. Only a few point cloud frames without objects passing through the lane are required. By the position change of each point in the point cloud data corresponding to each laser line of the multi-line lidar, the lane edge points are determined. By aggregating multiple lane edge points, the lane edge line can be fitted, and further the direction and position of the lane in the point cloud coordinate system of the lidar can be determined.

[0031] It should be noted that the above at least one scanning period can be the time taken for the multi-line lidar to rotate one week. Within one scanning period, the multi-line lidar can perform a scan every time it rotates to a certain angle. The lane in this embodiment refers to a complete road, and the lane edge points refer to the intersection points between the lane and the roadside. The direction of the lane can refer to the direction of the lane in the initial point cloud coordinate system of the multi-line lidar, which has nothing to do with the driving direction of the lane and refers to the direction of the complete road in the point cloud coordinate. Taking the coordinate system as a two-dimensional coordinate system as an example, in the initial point cloud coordinate system (such as Figure 3 part a), the dotted lines fitted are two lane edge lines.

[0032] Calibrating the point cloud coordinate system of the multi-line lidar according to the lane direction can refer to calibrating the initial point cloud coordinate system according to the direction of the lane in the initial point cloud coordinate system, and adjusting the initial point cloud coordinate system to a coordinate system in which one coordinate axis is parallel to the lane line (such as Figure 3 part b).

[0033] Optionally, the target point cloud data is the N×M point cloud data scanned by N laser lines in an multi-line lidar at M moments. At least one scanning period includes M moments. Determine the edge points of the lane according to the target point cloud data, where N is a positive integer greater than or equal to 2, and M is a positive integer greater than or equal to 2, including:

[0034] Divide the N×M point cloud data into N groups of point cloud data, where each group of point cloud data in the N groups of point cloud data includes the M point cloud data scanned by one of the N laser lines at M moments;

[0035] Determine the edge points of the lane according to the positions of the M points in each group of point cloud data, and obtain N groups of edge points.

[0036] In this embodiment, the point cloud data scanned by the multi-line lidar can be divided, and the N groups of point cloud data obtained by the division are analyzed separately. It should be noted that the above M moments can correspond to one scanning period of the multi-line lidar. Each of the M moments corresponds to the moment when the multi-line lidar rotates to a certain angle and scans. The time difference between any two adjacent moments among the M moments can be the same or different, and this embodiment does not limit this. Correspondingly, the scanned N×M point cloud data can be a frame of point cloud data scanned by the multi-line lidar in one scanning period.

[0037] Optionally, dividing the N×M point cloud data into N groups of point cloud data includes:

[0038] Divide the N×M point cloud data according to the line order of the multi-line lidar to obtain N groups of point cloud data, where the line order is the order of multiple laser lines of the multi-line lidar.

[0039] For example, taking a 32-line lidar as an example, a frame of point cloud data can include the point cloud data scanned by the laser beams of 32 channels of the 32-line lidar in one scanning period. One scanning period can be 100 ms. The order of multiple laser lines can correspond to 32 channels.

[0040] For the N groups of point cloud data obtained by dividing the N×M point cloud data, the N groups of point cloud data can be analyzed separately. According to the order of each scanned point, by analyzing the position change of the M points in each group of point cloud data, determine the point with a large position change, and use this point as a point on the lane edge.

[0041] Through the above steps S202 to S208, target point cloud data within at least one scanning period is obtained by a multi-line lidar; edge points of the lane are determined based on the point cloud data; the direction of the lane is determined based on the edge points of the lane; and the point cloud coordinate system of the multi-line lidar is calibrated based on the direction of the lane, solving the problem in the related art that the calibration method of the point cloud coordinate system has a low accuracy in calibrating the point cloud coordinate system, and improving the accuracy of calibrating the point cloud coordinate system.

[0042] In an exemplary embodiment, based on the positions of M points in each group of point cloud data, edge points of the lane are determined to obtain N groups of edge points, including:

[0043] S11. According to the i-th group of point cloud data among the N groups of point cloud data, the differences between the coordinates of every two adjacent points in the i-th group of points corresponding to the i-th group of point cloud data are determined to obtain the i-th group of differences, where the i-th group of point cloud data includes the coordinates of each point in the i-th group of points, and i is a positive integer greater than or equal to 1;

[0044] S12. According to the i-th group of differences, edge points on the edge of the lane are searched for in the i-th group of points, where the N groups of edge points include the edge points on the edge of the lane searched for in the i-th group of points, and the coordinates of every two adjacent points are the coordinates of points scanned at two adjacent moments among M moments of the same laser line.

[0045] In this embodiment, taking each group of point cloud data as a sample, edge points of the lane are determined respectively according to the positions of M points in each sample. It can be to search for points whose features conform to the lane edge features from the M points. The positions of the above M points can refer to the coordinates of the M points. According to the coordinate differences between each point and its adjacent points among the M points, the position changes of the M points are determined, so that points with larger changes, that is, edge points, can be searched for.

[0046] It should be noted that in a sample, if the coordinates of multiple points before the point corresponding to a certain scanning moment change continuously according to a certain rule, the coordinate differences corresponding to the multiple points before the point will not change greatly. If the coordinates of the points after this point are irregular, the coordinate differences corresponding to the points after this point will change significantly. Correspondingly, this point can be considered as an edge point.

[0047] Through this embodiment, based on the continuity of the point cloud in each group of samples, according to the differences between every two adjacent points in each group of samples, the efficiency of determining the coordinate change trend of the continuous point cloud in each group of samples can be improved, thereby improving the efficiency of determining the lane edge points.

[0048] In an exemplary embodiment, searching for edge points on the edge of the lane in the i-th group of points according to the i-th group of differences includes:

[0049] S21. When the difference of the first group of points before the p-th point in the i-th group of points satisfies the first preset condition and the difference of the second group of points after the p-th point does not satisfy the first preset condition, determine the p-th point as the edge point in the i-th group of points, where p is a positive integer greater than or equal to 1; or,

[0050] S22. When the difference of the first group of points before the p-th point in the i-th group of points does not satisfy the first preset condition and the difference of the second group of points after the p-th point satisfies the first preset condition, determine the p-th point as the edge point in the i-th group of points.

[0051] In this embodiment, when searching for edge points from the i-th group of points, the difference between all points in the i-th group of points and their surrounding adjacent points can be determined first, and then each point in the i-th group of points can be traversed in turn to judge multiple points before and after each point.

[0052] The number of points in the above first group of points can be the same as or different from the number of points in the second group of points. Numerical values can be preset for the number of points in the two groups of points, but in the actual analysis process, the actual values of the first group of points and the second group of points corresponding to the p-th point can be less than or equal to the preset values. For example, when the p-th point is the 5th point in the i-th group of points and the preset value is 10, the maximum number of points in the first group of points can only be 5, but the number of points in the second group of points can be 10.

[0053] Optionally, the above method further includes:

[0054] When a group of differences of the first group of points on the z-axis are all less than the first preset threshold and the variances of the differences of the first group of points on the x-axis and y-axis are both less than the second preset threshold, determine that the differences of the first group of points satisfy the first preset condition;

[0055] When there is a difference greater than or equal to the first preset threshold in a group of differences of the first group of points on the z-axis and / or the variance of the differences of the first group of points on the x-axis and y-axis is greater than or equal to the second preset threshold, determine that the differences of the first group of points do not satisfy the first preset condition.

[0056] In this embodiment, the above first preset condition may include a first preset threshold set for the x and y axis coordinates and a second preset threshold set for the z axis coordinate. The first preset threshold corresponding to the difference of the z axis coordinate may be 5 cm, and the second preset threshold corresponding to the variance of the differences of the x and y axis coordinates may be 0.1.

[0057] For example, if the coordinate differences of a continuous series of points on the z-axis are all less than 5 cm, and the variance of the differences of these points on the x and y axes is less than 0.1, it can be considered that these points meet the first preset condition, and these points are points on a flat lane; if there is at least one point among a continuous series of points whose coordinate difference on the z-axis is greater than 5 cm, and / or the variance of the differences of these points on the x and y axes is greater than 0.1, it can be considered that these points do not meet the first preset condition, and there are points not on the lane among these points.

[0058] If the differences of the points before the p-th point meet the first preset condition, but the differences of the points after the p-th point do not meet the first preset condition, it can be considered that the p-th point is an edge point. Correspondingly, if the differences of the points before the p-th point do not meet the first preset condition, but the differences of the points after the p-th point meet the first preset condition, it can also be considered that the p-th point is an edge point.

[0059] It should be noted that the coordinates of each point in the point cloud data in this embodiment can refer to the coordinates in the Cartesian coordinate system. In a three-dimensional Cartesian coordinate system, each point is determined by three coordinate values (x, y, z) to determine its position in space. The x-axis can point directly in front of the lidar, the y-axis points to the left, and the z-axis is perpendicular to the ground. The origin of the coordinate system can be the installation position of the lidar or other specific reference points on the lane.

[0060] Through this embodiment, by analyzing the differences of each point in a set of points on the x-axis, y-axis, and z-axis in different ways respectively, the accuracy of determining the change degree of continuous points can be improved, thereby improving the accuracy of calibrating the point cloud coordinate system.

[0061] In an exemplary embodiment, determining the direction of a lane based on the edge points of the lane includes:

[0062] S41, performing a clustering operation on the edge points of the lane to obtain two sets of target edge points. Among them, for each set of target edge points in the two sets of target edge points, the distance between each target edge point and its adjacent target edge point is less than a third preset threshold;

[0063] S42, determining the direction of the lane according to the two sets of target edge points.

[0064] For a multi-line lidar located above the lane, in a scanning cycle, it can generally scan the point clouds of the lane and the objects on both sides of the lane. Therefore, the edge points of the lane determined in this embodiment can include the edge points on both sides of the lane. When the target point cloud data is divided in the manner of the foregoing embodiment to obtain N groups of point cloud data, the determined edge points of the lane can be N groups of edge points corresponding to the N groups of point cloud data respectively. One group of edge points in the N groups of edge points can have only one edge point on one side of the lane, or can have two edge points, and the two edge points can be the edge points on both sides of the lane respectively.

[0065] In this embodiment, clustering operations can be performed on the N groups of edge points to obtain clusters corresponding to both sides of the lane respectively. Each cluster can have multiple edge points, and the distance between adjacent edge points can be less than the third preset threshold. The clustering method can be K-means (i.e., K-means clustering algorithm), or other clustering methods, which are not limited in this embodiment.

[0066] Through this embodiment, clustering is performed on the determined edge points, which can distinguish the edge points on both sides of the lane and remove the misjudged edge points from the N groups of edge points, thereby improving the accuracy of the calibration of the point cloud coordinate system.

[0067] In an exemplary embodiment, determining the direction of the lane according to two sets of target edge points includes:

[0068] S51, respectively fitting two edge lines according to the coordinate positions of each target edge point in the two sets of target edge points, wherein both of the fitted edge lines are straight lines;

[0069] S52, determining the directions of the two edge lines in the three-dimensional coordinate system as the direction of the lane, and taking the two edge lines as the edge lines of the lane.

[0070] In this embodiment, based on the two sets of clustered edge points, edge lines corresponding to each set of edge points can be respectively fitted based on the coordinate positions of each point in each set of edge points. It should be noted that the actual lane can be straight or curved, but the fitted edge lines are straight lines, and the fitting method can be a linear regression method, and multiple edge points are fitted by the least squares method.

[0071] In the three-dimensional coordinate system where the point cloud of the lidar is located, the directions of the two edge lines can be determined as the direction of the lane, and the two edge lines can be used as a part of the edge of the lane.

[0072] Through this embodiment, by fitting the edge line to determine the lane in the lidar point cloud, the calibration efficiency of the point cloud coordinate system can be significantly improved compared with the method of determining the lane through long-term traffic flow in the related art.

[0073] The calibration method of the point cloud coordinate system in the embodiments of the present application will be explained below with reference to optional examples.

[0074] In this optional example, a method for calibrating the lane direction of lidar points is provided. By utilizing the characteristic that the points of each line of lidar are continuous, the lane edge is detected. There is no need for a target to pass on the lane, nor for long-term statistical analysis of point cloud data. Only a few frames of point cloud frames without objects passing through are required to calculate the lane line direction, which can improve the calibration efficiency of the point cloud coordinate system while enhancing the calibration accuracy of the point cloud coordinate system.

[0075] The process of the calibration method of the point cloud coordinate system in this optional example can be as Figure 4 shown, and may include the following steps:

[0076] Step S402: Divide a frame of point cloud data according to the line order, and each line is used as a sample.

[0077] Step S404: Traverse each point P in the sample, and take point P as the midpoint to find N consecutive points around it.

[0078] Step S406: Utilizing the characteristic of the flat ground, if all the points in front of point P are regularly continuous while the points behind it change significantly in position, then it can be determined that point P is a point at the lane edge position.

[0079] Step S408: Count all the points in the samples to obtain the point set of the lane edge.

[0080] Step S410: Fit all the points in the point set to obtain the lane edge line, and calibrate the point cloud coordinate system based on the lane line direction.

[0081] Through this optional example, the calibration accuracy and calculation efficiency of the point cloud coordinate system can be improved.

[0082] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0083] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM (Read-Only Memory), RAM (Random Access Memory), magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present application.

[0084] According to another aspect of the embodiments of the present application, there is also provided a calibration system for a point cloud coordinate system for implementing the above-mentioned calibration method for a point cloud coordinate system. The calibration system for the point cloud coordinate system may include:

[0085] A multi-line lidar for scanning the lane and the surrounding area of the lane, where the multi-line lidar includes N laser lines;

[0086] A data processing unit for obtaining target point cloud data within at least one scanning period through the multi-line lidar; determining the edge points of the lane according to the point cloud data; determining the direction of the lane according to the edge points of the lane; and calibrating the point cloud coordinate system of the multi-line lidar according to the direction of the lane.

[0087] It should be noted that the data processing unit may be a server or a component for performing the foregoing lane recognition on a certain processing device, for example, a processor, a controller, etc. The method for determining lane recognition is similar to that in the foregoing embodiments and has been described, so details are not repeated here.

[0088] Through the above-mentioned calibration system for the point cloud coordinate system, target point cloud data within at least one scanning period is obtained through the multi-line lidar; the edge points of the lane are determined according to the point cloud data; the direction of the lane is determined according to the edge points of the lane; and the point cloud coordinate system of the multi-line lidar is calibrated according to the direction of the lane, which solves the problem that the calibration method for the point cloud coordinate system in the related art has relatively low accuracy in calibrating the point cloud coordinate system and improves the accuracy of calibrating the point cloud coordinate system.

[0089] In an exemplary embodiment, the data processing unit is further configured to divide the N×M point cloud data into N groups of point cloud data, where each group of point cloud data in the N groups of point cloud data includes M point cloud data scanned by one of the N laser lines at M moments; determine the edge points of the lane according to the positions of the M points in each group of point cloud data, obtaining N groups of edge points, where the target point cloud data is the N×M point cloud data scanned by the N laser lines in the multi-line lidar at M moments, and at least one scanning period includes M moments.

[0090] In an exemplary embodiment, the data processing unit is further configured to divide the N×M point cloud data according to the line order of the multi-line lidar, obtaining N groups of point cloud data, where the line order is the order of the multiple laser lines of the multi-line lidar.

[0091] In an exemplary embodiment, the data processing unit is further configured to, according to the i-th group of point cloud data in the N groups of point cloud data, determine the difference between the coordinates of every two adjacent points in the i-th group of points corresponding to the i-th group of point cloud data, obtaining the i-th group of differences, where the i-th group of point cloud data includes the coordinates of each point in the i-th group of points, and i is a positive integer greater than or equal to 1; according to the i-th group of differences, search for the edge points on the edge of the lane in the i-th group of points, where the N groups of edge points include the edge points on the edge of the lane found in the i-th group of points, and the coordinates of every two adjacent points are the coordinates of the points scanned by the same laser line at two adjacent moments among the M moments.

[0092] In an exemplary embodiment, the data processing unit is further configured to, when the differences of the first group of points before the p-th point in the i-th group of points satisfy the first preset condition and the differences of the second group of points after the p-th point do not satisfy the first preset condition, determine that the p-th point is the edge point in the i-th group of points, where p is a positive integer greater than or equal to 1; or, when the differences of the first group of points before the p-th point in the i-th group of points do not satisfy the first preset condition and the differences of the second group of points after the p-th point satisfy the first preset condition, determine that the p-th point is the edge point in the i-th group of points.

[0093] In an exemplary embodiment, the data processing unit is further configured to, when all the differences of a group of points of the first group of points on the z-axis are less than the first preset threshold and the variances of the differences of the first group of points on the x-axis and y-axis are both less than the second preset threshold, determine that the differences of the first group of points satisfy the first preset condition; when there is a difference greater than or equal to the first preset threshold among the differences of a group of points of the first group of points on the z-axis and / or the variances of the differences of the first group of points on the x-axis and y-axis are greater than or equal to the second preset threshold, determine that the differences of the first group of points do not satisfy the first preset condition.

[0094] In an exemplary embodiment, the data processing unit is further configured to perform a clustering operation on the edge points of the lane to obtain two sets of target edge points, wherein, in each set of target edge points of the two sets of target edge points, the distance between each target edge point and an adjacent target edge point is less than a third preset threshold; and determine the direction of the lane according to the two sets of target edge points.

[0095] In an exemplary embodiment, the data processing unit is further configured to respectively fit two edge lines according to the coordinate positions of each target edge point in the two sets of target edge points, wherein both of the fitted two edge lines are straight lines; determine the directions of the two edge lines in a three-dimensional coordinate system as the direction of the lane, and use the two edge lines as the edge lines of the lane.

[0096] It should be noted here that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above system can run in a hardware environment as shown in Figure 1 and can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0097] According to another aspect of the embodiments of the present application, a storage medium is further provided. Optionally, in this embodiment, the above storage medium can be used to execute the program code of any one of the above point cloud coordinate system calibration methods in the embodiments of the present application.

[0098] Optionally, in this embodiment, the above storage medium can be located on at least one of multiple network devices in the network shown in the above embodiment.

[0099] Optionally, in this embodiment, the storage medium is set to store program code for performing the following steps:

[0100] S1, obtaining target point cloud data within at least one scanning period through a multi-line lidar;

[0101] S2, determining the edge points of the lane according to the point cloud data;

[0102] S3, determining the direction of the lane according to the edge points of the lane;

[0103] S4, calibrating the point cloud coordinate system of the multi-line lidar according to the direction of the lane.

[0104] Optionally, the specific examples in this embodiment can refer to the examples described in the above embodiments, and details are not described herein again.

[0105] Optionally, in this embodiment, the above storage medium may include, but is not limited to: various media capable of storing program codes such as USB flash drives, ROMs, RAMs, mobile hard disks, magnetic disks, or optical discs.

[0106] According to another aspect of the embodiments of the present application, there is also provided an electronic device for implementing the above calibration method of the point cloud coordinate system. The electronic device may be a server, a terminal, or a combination thereof.

[0107] Figure 5 is a structural block diagram of an optional electronic device according to the embodiments of the present application. As Figure 5 shown, it includes a processor 502, a communication interface 504, a memory 506, and a communication bus 508. Among them, the processor 502, the communication interface 504, and the memory 506 complete mutual communication through the communication bus 508. Among them,

[0108] The memory 506 is used to store a computer program;

[0109] The processor 502, when executing the computer program stored on the memory 506, implements the following steps:

[0110] S1, obtaining target point cloud data within at least one scanning period through a multi-line lidar;

[0111] S2, determining the edge points of the lane according to the point cloud data;

[0112] S3, determining the direction of the lane according to the edge points of the lane;

[0113] S4, calibrating the point cloud coordinate system of the multi-line lidar according to the direction of the lane.

[0114] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the above electronic device and other devices.

[0115] The memory may include a RAM, and may also include a non-volatile memory, for example, at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0116] The above-mentioned processor can be a general-purpose processor, including but not limited to: CPU (Central Processing Unit, central processing unit), NP (Network Processor, network processor), etc.; it can also be a DSP (Digital Signal Processing, digital signal processor), ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), FPGA (Field-Programmable Gate Array, field-programmable gate array), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0117] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments, and will not be elaborated here.

[0118] Those of ordinary skill in the art can understand that Figure 5 The structure shown is only schematic. The device for implementing the calibration method of the point cloud coordinate system can be a terminal device, which can be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, and a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. Figure 5 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device may further include more or fewer components (such as a network interface, a display device, etc.) than those shown in Figure 5 or have a different configuration from that shown in Figure 5 shown.

[0119] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware of the terminal device through a program, and the program can be stored in a computer-readable storage medium. The storage medium may include: a flash drive, a ROM, a RAM, a magnetic disk, or an optical disc, etc.

[0120] The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0121] If the integrated units in the above embodiments are implemented in the form of software function units and sold or used as independent products, they can be stored in the above computer-readable storage media. Based on such understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable one or more computer devices (which can be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the above methods in various embodiments of this application.

[0122] In the above embodiments of this application, the descriptions of various embodiments have their own focuses. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0123] In the several embodiments provided by this application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of units or modules can be in electrical or other forms.

[0124] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0125] In addition, the functional units in various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or at least two units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software function units.

[0126] The above are only the preferred embodiments of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A calibration method for a point cloud coordinate system, characterized in that, Including: Obtaining target point cloud data within at least one scanning period through a multi-line lidar; Determining the edge points of the lane according to the point cloud data; Determining the direction of the lane according to the edge points of the lane; Calibrating the point cloud coordinate system of the multi-line lidar according to the direction of the lane.

2. The method according to claim 1, characterized in that, The target point cloud data is N×M point cloud data scanned by N laser lines in the multi-line lidar at M moments. The at least one scanning period includes the M moments. The determining the edge points of the lane according to the target point cloud data includes: Dividing the N×M point cloud data into N groups of point cloud data, where each group of point cloud data in the N groups of point cloud data includes M point cloud data scanned by one of the N laser lines at the M moments; Determining the edge points of the lane according to the positions of the M points in each group of point cloud data to obtain N groups of edge points.

3. The method according to claim 2, characterized in that, The dividing the N×M point cloud data into N groups of point cloud data includes: Dividing the N×M point cloud data according to the line sequence of the multi-line lidar to obtain N groups of point cloud data, where the line sequence is the sequence of multiple laser lines of the multi-line lidar.

4. The method according to claim 2, characterized in that, The determining the edge points of the lane according to the positions of the M points in each group of point cloud data to obtain N groups of edge points includes: According to the i-th group of point cloud data in the N groups of point cloud data, determining the difference between the coordinates of every two adjacent points in the i-th group of points corresponding to the i-th group of point cloud data to obtain the i-th group of differences, where the i-th group of point cloud data includes the coordinates of each point in the i-th group of points, and i is a positive integer greater than or equal to 1; According to the i-th group of differences, searching for the edge points on the edge of the lane in the i-th group of points, where the N groups of edge points include the edge points on the edge of the lane found in the i-th group of points, and the coordinates of every two adjacent points are the coordinates of points scanned by the same laser line at two adjacent moments among the M moments.

5. The method according to claim 4, characterized in that, The searching for the edge points on the edge of the lane in the i-th group of points according to the i-th group of differences includes: When the differences of the first group of points before the p-th point in the i-th group of points satisfy the first preset condition and the differences of the second group of points after the p-th point do not satisfy the first preset condition, determining the p-th point as the edge point in the i-th group of points, where p is a positive integer greater than or equal to 1; or, When the differences of the first group of points before the p-th point in the i-th group of points do not satisfy the first preset condition and the differences of the second group of points after the p-th point satisfy the first preset condition, determining the p-th point as the edge point in the i-th group of points.

6. The method according to claim 5, characterized in that, The method further includes: When the differences of a group of points of the first group of points on the z-axis are all less than the first preset threshold and the variances of the differences of the first group of points on the x-axis and y-axis are both less than the second preset threshold, determining that the differences of the first group of points satisfy the first preset condition; When there is a difference greater than or equal to the first preset threshold among a set of differences of the first set of points on the z-axis, and / or the variance of the differences of the first set of points on the x-axis and y-axis is greater than or equal to the second preset threshold, it is determined that the differences of the first set of points do not meet the first preset condition.

7. The method according to claim 1, wherein The determining the direction of the lane according to the edge points of the lane includes: Performing a clustering operation on the edge points of the lane to obtain two sets of target edge points, where, in each set of target edge points of the two sets of target edge points, the distance between each target edge point and its adjacent target edge point is less than a third preset threshold; Determining the direction of the lane according to the two sets of target edge points.

8. The method according to claim 7, wherein The determining the direction of the lane according to the two sets of target edge points includes: Respectively fitting two edge lines according to the coordinate positions of each target edge point in the two sets of target edge points, where the two edge lines obtained by fitting are both straight lines; Determining the direction of the two edge lines in the three-dimensional coordinate system as the direction of the lane, and using the two edge lines as the edge lines of the lane.

9. A calibration system for a point cloud coordinate system, characterized in that, including: A multi-line lidar for scanning the lane and the area around the lane, where the multi-line lidar includes N laser lines; A data processing unit for obtaining target point cloud data within at least one scanning period through the multi-line lidar; determining the edge points of the lane according to the point cloud data; determining the direction of the lane according to the edge points of the lane; calibrating the point cloud coordinate system of the multi-line lidar according to the direction of the lane.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, where the program, when running, executes the method according to any one of claims 1 to 8.

11. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 8 through the computer program.

Images