A method, system and related device for processing waveform point cloud data

Abstract

The present application provides a method for processing waveform point cloud data, including: acquiring waveform point cloud data; determining a reference dimension for performing data compensation on the waveform point cloud data; determining the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension; creating a multi-dimensional data space and establishing reference point cloud data in the multi-dimensional data space; in the multi-dimensional data space, assigning the waveform point cloud data to the nearest coordinate point to obtain measured data; according to the measured data and spare calibration parameters, traversing and calculating the measured values on blank coordinates to obtain the filled point cloud data. The present application can achieve the repair of missing data, thereby solving the information loss of waveform point cloud data as radar data and improving the information recognition accuracy of waveform point cloud data. The present application also provides a processing system, a computer-readable storage medium and an electronic device for waveform point cloud data, which have the above beneficial effects.

Description

Technical Field

[0001] This application relates to the field of point cloud data, and particularly to a method and system for processing waveform point cloud data and related devices. Background Art

[0002] Currently, most of the lidars commonly used in the market are multi-line lidars, among which 16-line, 32-line, 64-line, etc. are relatively common. With the increase in the number of laser scanning lines, the clarity and sensitivity of the radar recognition signal are stronger. However, no matter how many lines the lidar has, the characteristic it shows is that the recognition ability in the direction directly facing the radar is stronger, and the closer to the edge area, the sparser the radar lines are.

[0003] In the area where the radar signal is denser, its recognition ability for the target object is stronger. On the contrary, its recognition ability is weaker. Therefore, when it is necessary to recognize the target object at the edge of the radar, the relatively sparse radar lines may interfere with the recognition and even cause omission.

[0004] Therefore, how to improve the recognition ability of the radar signal is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for processing waveform point cloud data, a computer-readable storage medium, and an electronic device, which can effectively repair the missing data in the waveform point cloud data.

[0006] To solve the above technical problems, this application provides a method for processing waveform point cloud data, and the specific technical solution is as follows:

[0007] Obtain the waveform point cloud data;

[0008] Determine the reference dimension for data compensation of the waveform point cloud data;

[0009] Determine the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension;

[0010] Create a multi-dimensional data space and establish reference point cloud data in the multi-dimensional data space;

[0011] In the multi-dimensional data space, assign the waveform point cloud data to the nearest coordinate point according to the reference point cloud data to obtain measured data;

[0012] According to the measured data and the spare calibration parameters, traverse and calculate the measured values on the blank coordinates to obtain the filled point cloud data.

[0013] Optionally, obtaining the waveform point cloud data includes:

[0014] Identify the target object to be observed;

[0015] If the contour of the target observed object is visible and the missing area of the target observed object does not exceed a preset percentage of the overall area, generate and obtain the point cloud data corresponding to the target observed object in a preset coordinate system.

[0016] Optionally, if the waveform point cloud data is three-dimensional point cloud data, determining the reference dimension for performing data compensation on the waveform point cloud data includes:

[0017] Determine the data positioning dimensions of the waveform point cloud data corresponding to the X direction and the Y direction, so as to adjust the values of the Z-axis coordinates in the waveform point cloud data respectively based on the positioning matrix in the X direction and that in the Y direction;

[0018] Wherein, the plane corresponding to the X direction and the Y direction is the reference dimension for performing data compensation.

[0019] Optionally, when determining the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension, it further includes:

[0020] Determine the optimal reference dimension value for determining the coordinates of the waveform point cloud data; the optimal reference dimension value is used to determine the data density.

[0021] Optionally, traversing and measuring the measured values on blank coordinates includes:

[0022] Measure the measured value of the blank coordinate according to the adjacent value of the blank coordinate.

[0023] This application also provides a processing system for waveform point cloud data, including:

[0024] An acquisition module, configured to acquire the waveform point cloud data;

[0025] A dimension determination module, configured to determine the reference dimension for performing data compensation on the waveform point cloud data;

[0026] A density determination module, configured to determine the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension;

[0027] An environment construction module, configured to create a multi-dimensional data space and establish reference point cloud data in the multi-dimensional data space;

[0028] An assignment module, configured to assign the waveform point cloud data to the nearest coordinate point according to the reference point cloud data in the multi-dimensional data space to obtain measured data;

[0029] A measurement module, configured to traverse and measure the measured values on blank coordinates according to the measured data and spare calibration parameters to obtain the filled point cloud data.

[0030] Optionally, the obtaining module includes:

[0031] A target determination unit for confirming the target observed object;

[0032] A point cloud data generation unit for generating and obtaining point cloud data corresponding to the target observed object in a preset coordinate system if the contour of the target observed object is visible and the missing area of the target observed object does not exceed a preset percentage of the overall area.

[0033] Optionally, if the waveform point cloud data is three-dimensional point cloud data, the dimension determination module is a module for determining the data positioning dimensions corresponding to the X direction and the Y direction of the waveform point cloud data, so as to adjust the values of the Z-axis coordinates in the waveform point cloud data based on the positioning matrix in the X direction and the Y direction respectively; wherein, the planes corresponding to the X direction and the Y direction are the reference dimensions for performing data compensation.

[0034] The present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described above are implemented.

[0035] The present application also provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the method described above are implemented.

[0036] The present application provides a method for processing waveform point cloud data, including: obtaining the waveform point cloud data; determining the reference dimension for performing data compensation of the waveform point cloud data; determining the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension; creating a multi-dimensional data space, and establishing reference point cloud data in the multi-dimensional data space; in the multi-dimensional data space, assigning the waveform point cloud data to the nearest coordinate point according to the reference point cloud data to obtain measured data; according to the measured data and spare calibration parameters, traversing and calculating the measured values on blank coordinates to obtain the filled point cloud data.

[0037] The present application aims at the waveform point cloud data to be repaired, converts it into data in a multi-dimensional data space for processing, and converts the waveform point cloud data in a ring state from the perspective of point cloud into dense lattice data through projection, and performs assignment calculation on the lattice data in the multi-dimensional data space, which can realize the repair of missing data, thereby solving the information loss of waveform point cloud data as radar data and improving the information recognition accuracy of waveform point cloud data.

[0038] The present application also provides a processing system for waveform point cloud data, a computer-readable storage medium, and an electronic device, which have the above beneficial effects and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on the provided drawings without creative efforts.

[0040] Figure 1 It is a flowchart of a method for processing waveform point cloud data provided by an embodiment of the present application;

[0041] Figure 2 It is a schematic diagram for processing waveform point cloud data provided by an embodiment of the present application;

[0042] Figure 3 It is a schematic structural diagram of a processing system for waveform point cloud data provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0044] Please refer to Figure 1 , Figure 1 It is a flowchart of a method for processing waveform point cloud data provided by an embodiment of the present application. The method includes:

[0045] S101: Obtain the waveform point cloud data;

[0046] This step aims to obtain waveform point cloud data, which can be directly obtained from a radar. Or perform point cloud processing on the data output by the radar to obtain waveform point cloud data. In a feasible implementation, if it is for waveform point cloud data, the waveform point cloud data can be directly obtained from a lidar.

[0047] In addition, for the target observed object monitored by the radar, the outline of the target observed object should be visible, and the missing area of the target observed object does not exceed a preset percentage of the overall area, and the point cloud data corresponding to the target observed object is generated and obtained in a preset coordinate system. The preset percentage is not limited here and can usually be set to 40% or 50%.

[0048] S102: Determine the reference dimension for performing data compensation on the waveform point cloud data;

[0049] This step aims to determine the reference dimension for data compensation. Since waveform point cloud data is usually two-dimensional or three-dimensional data, the reference dimension for performing compensation is usually one dimension or two dimensions. Taking ordinary three-dimensional point cloud as an example, two dimensions need to be determined for data positioning, let them be x and y, and then the value of the z coordinate is adjusted based on the positioning matrices of x and y. At this time, the plane determined by x and y is the reference dimension for this test.

[0050] S103: Determine the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension;

[0051] This step needs to measure the data density of the reference dimension according to the projection of the waveform point cloud data on the determined reference dimension. For example, let the projection density of the point cloud on the z-axis be ρ, then from ρ at the center of the circle 0 to ρ at the outermost edge n , its density change usually decreases gradually.

[0052] Then the principle for establishing the reference density at this time is to be able to accurately locate as many original data as possible. Assuming the coordinates of the original data on x are 0, 1, and 1.5 respectively, then it is best to take 0.5 as the data density of the reference dimension, and 1 or 1.5 as alternatives, but compared with the data density of 0.5, some accuracy will be lost.

[0053] The so-called data density, that is, the interval distance between data. In order to accurately locate the original data as much as possible, its data density should be moderate. Too large is likely to lose data accuracy, and too small is likely to increase the calculation amount.

[0054] Then a preferred execution method for this step can be as follows:

[0055] Determine the data positioning dimensions in the X direction and Y direction corresponding to the waveform point cloud data, so as to adjust the values of the z-axis coordinates in the waveform point cloud data based on the positioning matrices in the X direction and Y direction respectively. The planes corresponding to the X direction and Y direction are the reference dimensions for performing data compensation.

[0056] S104: Create a multi-dimensional data space and establish reference point cloud data in the multi-dimensional data space;

[0057] This step aims to create a multi-dimensional data space and establish reference point cloud data. The multi-dimensional data space is used to perform data measurement in a specified dimension using its unique spatial data, and the reference point cloud data is used to assist in the execution of data measurement. Of course, when establishing the reference point cloud data, the data density determined in the previous step should be referred to.

[0058] In addition, this step can also include the initialization process of the multi-dimensional data space, such as specifying the size of the multi-dimensional data space, configuring the relevant features of the target object to be observed, and setting the measurement method in the multi-dimensional data space, etc. Generally, the size of the multi-dimensional data space should at least include the entire size of the target object to be observed. Configuring the relevant features of the target object to be observed helps to quickly perform measurement. For example, if the target object to be observed is a symmetric figure, after obtaining the data on one side of the symmetry line through measurement, the coordinate data on the other side of the symmetry line can be directly obtained through coordinate transformation. The measurement method in the multi-dimensional data space can be measured according to the point density. Of course, other measurement methods can also be used, and no specific examples are listed here for limitation.

[0059] S105: In the multi-dimensional data space, assign the waveform point cloud data to the nearest coordinate point according to the reference point cloud data to obtain the measured data;

[0060] This step aims to perform assignment. Specifically, assign each data included in the waveform point cloud data to the multi-dimensional data space. For those with measured values, directly assign them. For those without measured values, they can be not assigned, or set to null or 0.

[0061] In addition, for the waveform point cloud data not on the reference data, it can be assigned to the nearest coordinate point. For example, if the data density is set to 0.5 in the previous step, then for the point (1.1, 1.1), obviously its exact position cannot be determined. At this time, it can be assigned to the nearest coordinate point, that is, (1, 1). Of course, it can also be selected to generate spare parameters for measurement correction according to the measurement rules included in the multi-dimensional data space, and then perform correction after obtaining the measured value.

[0062] S106: According to the measured data and the spare correction parameters, traverse and measure the measured values on the blank coordinates to obtain the filled point cloud data.

[0063] This step aims to perform measurement on the blank coordinates based on the measured data. When measuring, it can be measured in a certain measurement order, and the measurement order is not limited here and can be set by those skilled in the art. It should be noted that the spare correction parameters can be calculated by those skilled in the art according to historical measured data to correct the filled point cloud data. Of course, the spare correction parameters can also be null or zero.

[0064] When measuring the measured values on the blank coordinates, the measured values of the blank coordinates can be calculated according to the adjacent values of the blank coordinates. If there are multiple adjacent blank coordinates, the blank coordinates with adjacent values are preferentially calculated.

[0065] See Figure 2 , Figure 2 For the waveform point cloud data processed by the processing method disclosed in this application, the waveform point cloud data to be repaired before processing on the left side, such as Figure 2 can be repaired and filled into the dot matrix data on the right side, such as Figure 2 .

[0066] In the embodiment of the present application, for the waveform point cloud data to be repaired, it is converted into data in a multi-dimensional data space for processing. Through projection, the waveform point cloud data in a circular state from the point cloud perspective is converted into dense dot matrix data. The dot matrix data is assigned and measured in the multi-dimensional data space, which can realize the repair of missing data, thereby solving the information loss of the waveform point cloud data as radar data and improving the information recognition accuracy of the waveform point cloud data.

[0067] Next, the processing system for waveform point cloud data provided by the embodiment of the present application will be introduced. The processing system described below can be mutually corresponding and referred to the processing method of the waveform point cloud data described above.

[0068] See Figure 3 , Figure 3 which is a schematic structural diagram of a processing system for waveform point cloud data provided by an embodiment of the present application. The present application also provides a processing system for waveform point cloud data, including:

[0069] An acquisition module, configured to acquire the waveform point cloud data;

[0070] A dimension determination module, configured to determine the reference dimension for performing data compensation on the waveform point cloud data;

[0071] A density determination module, configured to determine the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension;

[0072] An environment construction module, configured to create a multi-dimensional data space and establish reference point cloud data in the multi-dimensional data space;

[0073] An assignment module, configured to assign the waveform point cloud data to the nearest coordinate point according to the reference point cloud data in the multi-dimensional data space to obtain measured data;

[0074] A measurement module, configured to traverse and measure the measured values on the blank coordinates according to the measured data and spare calibration parameters to obtain the filled point cloud data.

[0075] Optionally, the obtaining module includes:

[0076] A target determination unit for confirming the target observed object;

[0077] A point cloud data generation unit for generating and obtaining point cloud data corresponding to the target observed object in a preset coordinate system if the contour of the target observed object is visible and the missing area of the target observed object does not exceed a preset percentage of the overall area.

[0078] Optionally, if the waveform point cloud data is three-dimensional point cloud data, the dimension determination module is a module for determining the data positioning dimensions corresponding to the X direction and the Y direction of the waveform point cloud data, so as to adjust the values of the Z-axis coordinates in the waveform point cloud data based on the positioning matrix in the X direction and the Y direction respectively; wherein, the planes corresponding to the X direction and the Y direction are the reference dimensions for performing data compensation.

[0079] This application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the steps provided in the above embodiments can be implemented. The storage medium may include: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0080] This application also provides an electronic device, which may include a memory and a processor. When the processor calls the computer program stored in the memory, the steps provided in the above embodiments can be implemented. Of course, the electronic device may also include various network interfaces, power supplies and other components.

[0081] The various embodiments in the specification are described in a progressive manner. The key points of each embodiment are the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the system provided in the embodiment, since it corresponds to the method provided in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0082] Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of this application, several improvements and modifications can still be made to this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0083] It should also be noted that in this specification, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the said element.

Claims

1. A method for processing waveform point cloud data, characterized in that, it includes: Obtain the waveform point cloud data; Determine the reference dimension for performing data compensation on the waveform point cloud data; Determine the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension; Create a multi-dimensional data space and establish reference point cloud data in the multi-dimensional data space; In the multi-dimensional data space, assign the waveform point cloud data to the nearest coordinate point according to the reference point cloud data to obtain measured data; According to the measured data and the spare calibration parameters, traverse and calculate the measured values on the blank coordinates to obtain the filled point cloud data; Wherein, if the waveform point cloud data is three-dimensional point cloud data, determining the reference dimension for performing data compensation on the waveform point cloud data includes: Determine the data positioning dimensions corresponding to the X direction and the Y direction of the waveform point cloud data, so as to adjust the Z-axis coordinate values in the waveform point cloud data based on the positioning matrix in the X direction and the positioning matrix in the Y direction respectively; Wherein, the planes corresponding to the X direction and the Y direction are the reference dimensions for performing data compensation.

2. The processing method according to claim 1, characterized in that, Obtaining the waveform point cloud data includes: Identify the target observed object; If the contour of the target observed object is visible and the missing area of the target observed object does not exceed a preset percentage of the overall area, generate and obtain the point cloud data corresponding to the target observed object in a preset coordinate system.

3. The processing method according to claim 1, characterized in that, When determining the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension, it further includes: Determine the coordinate of the waveform point cloud data to determine the optimal reference dimension value; the optimal reference dimension value is used to determine the data density.

4. The processing method according to claim 1, characterized in that, Traversing and calculating the measured values on the blank coordinates includes: Calculate the measured value of the blank coordinate according to the adjacent value of the blank coordinate.

5. A processing system for waveform point cloud data, characterized in that, it includes: An acquisition module for acquiring the waveform point cloud data; A dimension determination module for determining the reference dimension for performing data compensation on the waveform point cloud data; A density determination module for determining the data density of the reference dimension according to the projection of the waveform point cloud data on the reference dimension; An environment construction module for creating a multi-dimensional data space and establishing reference point cloud data in the multi-dimensional data space; An assignment module for assigning the waveform point cloud data to the nearest coordinate point in the multi-dimensional data space according to the reference point cloud data to obtain measured data; A measurement module for traversing and calculating the measured values on the blank coordinates according to the measured data and the spare calibration parameters to obtain the filled point cloud data; Wherein, if the waveform point cloud data is three-dimensional point cloud data, the dimension determination module is a module for determining the data positioning dimensions corresponding to the X direction and the Y direction of the waveform point cloud data, so as to adjust the values of the Z-axis coordinates in the waveform point cloud data based on the positioning matrix in the X direction and the positioning matrix in the Y direction respectively; wherein, the planes corresponding to the X direction and the Y direction are the reference dimensions for performing data compensation.

6. The processing system according to claim 5, wherein, the obtaining module includes: a target determination unit for confirming the target observed object; a point cloud data generation unit for generating and obtaining the point cloud data corresponding to the target observed object in a preset coordinate system if the contour of the target observed object is visible and the missing area of the target observed object does not exceed a preset percentage of the overall area.

7. A computer-readable storage medium, on which a computer program is stored, wherein, the steps of the method according to any one of claims 1-4 are implemented when the computer program is executed by a processor.

8. An electronic device, wherein, it includes a memory and a processor, a computer program is stored in the memory, and the steps of the method according to any one of claims 1-4 are implemented when the processor calls the computer program in the memory.

Images