Obstacle point cloud data processing methods, devices, equipment, media, and vehicles

Abstract

This disclosure relates to a method, apparatus, device, and computer-readable storage medium for processing obstacle point cloud data. The method includes: acquiring raw point cloud data; sorting the raw point cloud data to obtain sorted point cloud data; acquiring obstacle point cloud data; and determining the position information of the obstacle point cloud data within the raw point cloud data based on the obstacle point cloud data and the sorted point cloud data. This disclosure solves the problem of unordered point cloud data by sorting the raw point cloud data to obtain sorted point cloud data; and by determining the position information of the obstacle point cloud data within the raw point cloud data based on the obstacle point cloud data and the sorted point cloud data, it avoids multiple iterations of the raw point cloud data, improves the processing efficiency of obstacle point cloud data, and meets the need for rapid analysis of raw point cloud data.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and in particular to a method, apparatus, device, medium, and vehicle for processing obstacle point cloud data. Background Technology

[0002] Point cloud data contains data from multiple points. Regardless of the order in which these points appear in the point cloud, the information they represent remains unchanged. This is the unordered nature of point clouds.

[0003] Typically, obtaining the correspondence between obstacle point clouds and the global point cloud requires multiple iterations of the same point cloud data, which is highly inefficient. For example, a single frame of point cloud contains nearly 100,000 points. To match the point clouds corresponding to 50 obstacles, multiple loops are needed to obtain the matching relationship between local obstacles and the global point cloud. Furthermore, operational efficiency is extremely sensitive in vehicle-side perception, requiring hard real-time processing. If the perception time exceeds 100ms, the frequency of data acquisition downstream will decrease.

[0004] Therefore, how to efficiently obtain the correspondence between obstacle point clouds and global point clouds has become an urgent problem to be solved. Summary of the Invention

[0005] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides an obstacle point cloud data processing method, apparatus, device and computer-readable storage medium to improve the processing efficiency of obstacle point cloud data.

[0006] In a first aspect, embodiments of this disclosure provide a method for processing obstacle point cloud data, including:

[0007] Obtain raw point cloud data, sort the raw point cloud data, and obtain sorted point cloud data;

[0008] Acquire obstacle point cloud data;

[0009] Based on the obstacle point cloud data and the sorted point cloud data, determine the position information of the obstacle point cloud data in the original point cloud data.

[0010] In a second aspect, embodiments of this disclosure provide an obstacle point cloud data processing apparatus, comprising:

[0011] The sorting module is used to acquire raw point cloud data, sort the raw point cloud data, and obtain sorted point cloud data.

[0012] The acquisition module is used to acquire obstacle point cloud data;

[0013] The determination module is used to determine the position information of the obstacle point cloud data in the original point cloud data based on the obstacle point cloud data and the sorted point cloud data.

[0014] Thirdly, embodiments of this disclosure provide an electronic device, including:

[0015] Memory;

[0016] Processor; and

[0017] Computer programs;

[0018] The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in the first aspect.

[0019] Fourthly, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method described in the first aspect.

[0020] Fifthly, embodiments of this disclosure also provide a vehicle including the obstacle point cloud data processing device described above.

[0021] The obstacle point cloud data processing method, apparatus, device, medium, and vehicle provided in this disclosure solve the problem of unordered point cloud data by sorting the original point cloud data to obtain sorted point cloud data. Based on the obstacle point cloud data and the sorted point cloud data, the position information of the obstacle point cloud data in the original point cloud data is determined, thereby identifying the obstacle point cloud data in the original point cloud data. This avoids multiple iterations of the original point cloud data to obtain the obstacle point cloud data, improves the processing efficiency of obstacle point cloud data, and meets the need for rapid analysis of the original point cloud data. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0023] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart of an obstacle point cloud data processing method provided in this embodiment of the disclosure;

[0025] Figure 2 A schematic diagram of the raw point cloud data provided in the embodiments of this disclosure;

[0026] Figure 3 A flowchart of an obstacle point cloud data processing method provided in this embodiment of the disclosure;

[0027] Figure 4 A schematic diagram of an obstacle point cloud data sorting method provided in an embodiment of this disclosure;

[0028] Figure 5 A flowchart of an obstacle point cloud data processing method provided in this embodiment of the disclosure;

[0029] Figure 6 A flowchart of an obstacle point cloud data processing method provided in this embodiment of the disclosure;

[0030] Figure 7 A schematic diagram of some points in the obstacle point cloud data provided in the embodiments of this disclosure;

[0031] Figure 8 A schematic diagram of the smallest polygon in the obstacle point cloud data provided in the embodiments of this disclosure;

[0032] Figure 9 A schematic diagram of 3D boxes in obstacle point cloud data provided in the embodiments of this disclosure;

[0033] Figure 10 A schematic diagram of the structure of the obstacle point cloud data processing device provided in the embodiments of this disclosure;

[0034] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0035] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0036] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0037] This disclosure provides a method for processing obstacle point cloud data, which will be described below with reference to specific embodiments.

[0038] Figure 1This is a flowchart illustrating an obstacle point cloud data processing method provided in an embodiment of this disclosure. The method can be executed by an obstacle point cloud data processing device, which can be implemented in software and / or hardware. This device can be configured in an electronic device, such as a server or terminal, where the terminal may specifically include a vehicle. Furthermore, this method can be applied to application scenarios involving matching obstacle point cloud data with original point cloud data. It is understood that the obstacle point cloud data processing method provided in this disclosure can also be applied to other scenarios.

[0039] The following is about Figure 1 The method for processing obstacle point cloud data is described below, and the specific steps of this method are as follows:

[0040] S101. Obtain the original point cloud data, sort the original point cloud data, and obtain sorted point cloud data.

[0041] In reverse engineering, a point cloud is a collection of point data on the surface of a product obtained through measuring instruments. Point clouds obtained using a 3D coordinate measuring machine typically have a smaller number of points and larger spacing between them, and are called sparse point clouds. Point clouds obtained using a 3D laser scanner or photogrammetric scanner have a larger number of points and are denser, and are called dense point clouds.

[0042] Laser point clouds are formed when a laser beam strikes the surface of an object, and the reflected laser light carries information such as orientation and distance. If the laser beam is scanned along a certain trajectory, the information of the reflected laser points will be recorded as it is scanned. Because the scanning is extremely precise, a large number of laser points can be obtained, thus forming a laser point cloud.

[0043] Point cloud data refers to a set of vectors in a three-dimensional coordinate system. Scanned data is recorded in the form of points, each containing three-dimensional coordinates, and some may contain information such as color and reflectivity.

[0044] Resolution, also known as image resolution or image sharpness, can be further divided into display resolution, image resolution, print resolution, and scan resolution. Resolution determines the level of detail in a bitmap image. Generally, the higher the image resolution, the more pixels it contains, and the clearer the image.

[0045] The obstacle point cloud data processing device can scan the actual area covering the obstacle using a laser emitter. It primarily acquires raw point cloud data, i.e., global point cloud data, through three methods: spaceborne, airborne, and ground-based. This raw point cloud data can be, for example,... Figure 2The image shown illustrates how sorting the original point cloud data yields sorted point cloud data. Furthermore, it establishes a one-to-one correspondence between the original and sorted point cloud data. Specifically, the points in the original point cloud data correspond one-to-one with the points in the sorted point cloud data. The obstacle point cloud processing device can be installed on a vehicle or in the cloud, depending on requirements and actual conditions.

[0046] It should be noted that the above method for obtaining raw point cloud data does not constitute a limitation on this embodiment. Those skilled in the art will realize that point cloud data can be obtained in other ways, such as by taking pictures with a three-dimensional imaging sensor, and then processing the images to obtain raw point cloud data. The three-dimensional imaging sensor can be a binocular camera, a three-dimensional scanner, an RGB-D camera, etc.

[0047] S102. Obtain obstacle point cloud data.

[0048] An obstacle is something that blocks progress.

[0049] Obstacle point cloud data processing devices can acquire obstacle point cloud data through model training detection methods or rule clustering detection methods.

[0050] For example, an obstacle could be a vehicle. In that case, the obstacle point cloud data would be the same as the vehicle's point cloud data.

[0051] S103. Based on the obstacle point cloud data and the sorted point cloud data, determine the position information of the obstacle point cloud data in the original point cloud data.

[0052] The obstacle point cloud data processing device can determine the position information of the obstacle point cloud data within the original point cloud data based on the obstacle point cloud data and the sorted point cloud data.

[0053] This embodiment solves the problem of disordered point cloud data by sorting the original point cloud data to obtain sorted point cloud data; based on the obstacle point cloud data and the sorted point cloud data, the position information of the obstacle point cloud data in the original point cloud data is determined, avoiding multiple iterations of the original point cloud data, improving the processing efficiency of obstacle point cloud data, and meeting the need for rapid analysis of the original point cloud data.

[0054] Furthermore, since the embodiments disclosed herein do not change the original point cloud structure and point cloud quality, filter noise, and explicitly provide a scheme for determining the position of obstacle point cloud data in the original point cloud data, compared to the prior art which iterates the original point cloud data multiple times to obtain the matching relationship between obstacle point cloud data and original point cloud data, it is faster, more efficient, and more intuitive.

[0055] In some embodiments, S101 can be achieved through, for example... Figure 3 The method shown is implemented. Specifically, as... Figure 3 As shown, S101 can be implemented through the following steps:

[0056] S301. Based on the original point cloud data, determine a preset range to obtain the original point cloud data within the preset range and the original point cloud data outside the preset range.

[0057] like Figure 4 As shown, based on the original point cloud data 40, a preset range 41 is determined. For example, the original point cloud data within the preset range is obtained, i.e. Figure 4 The original point cloud data within the 41-inch range, and the original point cloud data outside the preset range, such as... Figure 4 The data shown includes all other point cloud data except for 41.

[0058] Specifically, the preset range corresponds to the actual range captured by the 3D imaging sensor. The length and width of the preset range can be the same or different. For ease of understanding and calculation, we will use the example of a preset range with the same length and width. For example, the actual range covering the obstacle is 120m*120m, the preset range is 10m*10m, and the resolution is 480*480.

[0059] S302. Sort the original point cloud data within the preset range to obtain the first point cloud data.

[0060] like Figure 4 As shown, the original point cloud data within the preset range 41 is sorted to obtain the first point cloud data.

[0061] Optionally, the original point cloud data within the preset range is divided according to the preset grid side length to obtain the divided point cloud data and point cloud grid number. The divided point cloud data is then sorted according to the point cloud grid number to obtain the first point cloud data.

[0062] It should be noted that the above-mentioned division of the preset range, as well as the values ​​of the preset range length and width, are only examples and do not constitute a limitation on this embodiment. Those skilled in the art can conceive of determining the optimal preset range division method and the values ​​of the preset range length and width through a limited number of experiments.

[0063] The actual range of the obstacle coverage is 120m*120m, with a resolution of 480*480. Each resolution represents an object within a 0.25m*0.25m grid. When the preset range is 10m*10m and the preset grid side length is 2.5m*2.5m, a reference point is first set on the acquired original point cloud data image, i.e., the position of point (0.0) is determined. Then, the data is extended by 2.5m perpendicular to the horizontal line (Y-axis) and parallel to the horizontal line (X-axis) to obtain the divided point cloud data, as shown below. Figure 4 The point cloud data shown is divided into 16 grids, with grid numbers (0,0), (0,1), (0,2), (0,3), (1,0), (1,1), (1,2), (1,3), (2,0), (2,1), (2,2), (2,3), (3,0), (3,1), (3,2), and (3,3). The divided point cloud data is then sorted according to these grid numbers to obtain the first point cloud data. This allows us to determine the number of points in each grid, the number of points in each point cloud, and the height information of the point clouds, including the maximum, minimum, and average values ​​of the z-axis.

[0064] S303. Sort the original point cloud data outside the preset range to obtain the second point cloud data.

[0065] The point cloud data outside the preset range is added sequentially to obtain the second point cloud data.

[0066] S304. The first point cloud data is placed before the second point cloud data to obtain sorted point cloud data.

[0067] The sorted point cloud data is obtained by placing the first point cloud data before the second point cloud data. It can be understood that the points in the sorted point cloud data correspond one-to-one with the points in the original point cloud data. At the same time, the correspondence between the points in each grid after sorting is consistent with the correspondence between the points in the first original data.

[0068] This disclosure describes the sorting of the original point cloud data in detail, making the correspondence between the sorted point cloud data and the original point cloud data clearer, and providing a data foundation for the retrieval of obstacle point cloud data.

[0069] In some embodiments, S102 can be performed as follows: Figure 5 The method shown is implemented. Specifically, as... Figure 5 As shown, S102 can be implemented through the following steps:

[0070] S501. Train the obstacle model based on the point cloud data to be trained to obtain the trained obstacle model.

[0071] The obstacle point cloud data processing device acquires point cloud data to be trained. This point cloud data contains basic obstacle information, and this basic obstacle information is labeled. The acquired point cloud data is used to train the obstacle model multiple times. That is, after inputting the point cloud data to be trained, the standard output that should be obtained is compared with the actual output and adjusted to obtain the trained obstacle model.

[0072] S502. Input the original point cloud data into the trained obstacle model to obtain the basic information of the obstacle point cloud data.

[0073] The raw point cloud data is input into the trained obstacle model to obtain the basic information of the obstacle point cloud data.

[0074] Optionally, the basic information of the obstacle point cloud data includes: the location of the obstacle point cloud data, the size of the obstacle point cloud data, and the orientation of the obstacle point cloud data.

[0075] Specifically, the location of obstacle point cloud data includes the location of the midpoint of the obstacle point cloud data, and the location information of the point includes the X value, Y value, and Z value of the point; the size of obstacle point cloud data includes the length, width, and height of the obstacle; the orientation of obstacle point cloud data can be a 360-degree direction, including the obstacle facing south, the obstacle facing east, the obstacle facing 30 degrees west of south, etc.

[0076] S503. Obtain obstacle point cloud data based on the basic information of the obstacle point cloud data.

[0077] Based on the basic information of the obstacle point cloud data, obstacle point cloud data is obtained. The obstacle point cloud data obtained here includes the data of all points in the obstacle point cloud data, as well as the relative positional relationships of all these points.

[0078] This disclosure describes in detail how to acquire obstacle point cloud data, providing a data foundation for obstacle point cloud data retrieval and improving the retrieval efficiency of obstacle point cloud data.

[0079] In some embodiments, S103 can be performed as follows: Figure 6 The method shown is implemented. Specifically, as... Figure 6 As shown, S103 can be implemented through the following steps.

[0080] S601. Obtain the position information of multiple points in the obstacle point cloud data based on the obstacle point cloud data.

[0081] Obtain the position information of multiple points in the obstacle point cloud data, and determine the relative positional relationship of the multiple points based on the position information of the multiple points.

[0082] For example, there are 5 points in total, such as... Figure 7 As shown, the location information of these 5 points are A(1,1,1), B(0,1,0), C(2,3,1), D(4,6,6), and E(5,6,7). The relative positional relationship of these 5 points can be determined based on these 5 points A, B, C, D, and E.

[0083] S602. Based on the position information of the multiple points, determine the smallest polygon containing the multiple points.

[0084] Based on the location information of multiple points, determine the smallest polygon containing these multiple points. That is, there are countless polygons containing these multiple points, but there is only one smallest polygon. Generally, the smallest polygon is the polygon obtained by connecting two adjacent points in sequence among these five points. It can be understood that some points may be exactly on the line segment connecting two other points. For example, (0,1,0) is the midpoint of the line connecting (0,0,0) and (0,2,0). Some points may overlap with another point on a different layer, such as the two points (1,1,0) and (1,1,1).

[0085] For example, the location information of these 5 points are A(1,1,1), B(0,1,0), C(2,3,1), D(4,6,6), and E(5,6,7), as follows: Figure 8 As shown, the smallest polygon is pentagon ABCDE, which can contain the five points A, B, C, D, and E.

[0086] S603. Based on the minimum polygon, determine the number of grids occupied by the minimum polygon and the grid number.

[0087] Based on the smallest polygon, determine the 3D box, and based on the 3D box, determine the number of grids occupied by the 3D box and the grid number.

[0088] For example, such as Figure 9 As shown, a 3D box is determined based on the smallest polygon ABCDE. The nearest grid regions are determined through the 3D box, thus obtaining the number of grids occupied by the 3D box and the grid number.

[0089] S604. Determine the correspondence between the obstacle point cloud data and the sorted point cloud data based on the number of grids occupied by the smallest polygon and the grid number.

[0090] Based on the number of grids occupied and the grid number, the position of the obstacle point cloud data in the sorted point cloud data is determined, that is, the correspondence between the obstacle point cloud data and the sorted point cloud data is determined.

[0091] S605. Based on the correspondence between the obstacle point cloud data and the sorted point cloud data, and the correspondence between the original point cloud data and the sorted point cloud data, determine the position information of the obstacle point cloud data in the original point cloud data.

[0092] Based on the correspondence between obstacle point cloud data and sorted point cloud data, and the correspondence between original point cloud data and sorted point cloud data, the location information of obstacle point cloud data in the original point cloud data is determined.

[0093] This disclosure describes in detail how to obtain the location information of obstacle point cloud data within the original point cloud data, from point to surface, and from surface to volume. During the continuous detection process of obstacle point cloud data, there is a matching and search process between obstacle point cloud data and original point cloud data. Compared with the prior art, firstly, the time for matching and searching between obstacle point cloud data and original point cloud data is superimposed with the time for detecting obstacle point cloud data, thus shortening the matching and search time; secondly, the matching and search is performed on obstacle point cloud data within sorted point cloud data, improving the matching and search speed. Therefore, the processing efficiency of obstacle point cloud data is improved, meeting the need for rapid analysis of original point cloud data.

[0094] Figure 10 This is a schematic diagram of the obstacle point cloud data processing device provided in an embodiment of this disclosure. The obstacle point cloud data processing device provided in this embodiment can execute the processing flow provided in the embodiment of the obstacle point cloud data processing method, such as... Figure 10 As shown, the obstacle point cloud data processing device 100 includes: a sorting module 101, an acquisition module 102, and a determination module 103; wherein, the sorting module 101 is used to acquire raw point cloud data and sort the raw point cloud data to obtain sorted point cloud data; the acquisition module 102 is used to acquire obstacle point cloud data; and the determination module 103 is used to determine the position information of the obstacle point cloud data in the raw point cloud data based on the obstacle point cloud data and the sorted point cloud data.

[0095] Optionally, the sorting module 101 is further configured to sort the original point cloud data to obtain sorted point cloud data, including: determining a preset range based on the original point cloud data to obtain original point cloud data within the preset range and original point cloud data outside the preset range; sorting the original point cloud data within the preset range to obtain first point cloud data; sorting the original point cloud data outside the preset range to obtain second point cloud data; and placing the first point cloud data before the second point cloud data to obtain sorted point cloud data.

[0096] Optionally, the sorting module 101 is further configured to sort the original point cloud data within the preset range to obtain the first point cloud data, including: dividing the original point cloud data within the preset range according to the preset grid side length to obtain the divided point cloud data and the point cloud grid number, and sorting the divided point cloud data according to the point cloud grid number to obtain the first point cloud data.

[0097] Optionally, the acquisition module 102 is further configured to acquire obstacle point cloud data, including: training the obstacle model based on the point cloud data to be trained to obtain the trained obstacle model; inputting the original point cloud data into the trained obstacle model to obtain basic information of the obstacle point cloud data; and acquiring the obstacle point cloud data based on the basic information of the obstacle point cloud data.

[0098] Optionally, the basic information of the obstacle point cloud data includes:

[0099] The location, size, and orientation of the obstacle point cloud data.

[0100] Optionally, the determining module 103 is further configured to determine the position information of the obstacle point cloud data in the original point cloud data based on the obstacle point cloud data and the sorted point cloud data, including: determining the correspondence between the obstacle point cloud data and the sorted point cloud data based on the obstacle point cloud data and the sorted point cloud data; and determining the position information of the obstacle point cloud data in the original point cloud data based on the correspondence between the obstacle point cloud data and the sorted point cloud data, and the correspondence between the original point cloud data and the sorted point cloud data.

[0101] Optionally, the determining module 103 is further configured to determine the correspondence between the obstacle point cloud data and the sorted point cloud data based on the obstacle point cloud data and the sorted point cloud data, including: obtaining position information of multiple points in the obstacle point cloud data based on the obstacle point cloud data; determining the smallest polygon containing the multiple points based on the position information of the multiple points; determining the number of grids occupied by the smallest polygon and the grid number based on the smallest polygon; and determining the correspondence between the obstacle point cloud data and the sorted point cloud data based on the number of grids occupied by the smallest polygon and the grid number.

[0102] Figure 10 The obstacle point cloud data processing device of the illustrated embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0103] Figure 11This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device can be a terminal as described in the above embodiments. The electronic device provided in this disclosure can execute the processing flow provided in the obstacle point cloud data processing method embodiments, such as… Figure 11 As shown, the electronic device 110 includes: a memory 111, a processor 112, a computer program, and a communication interface 113; wherein the computer program is stored in the memory 111 and is configured to be executed by the processor 112 as described above for the obstacle point cloud data processing method.

[0104] In addition, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the obstacle point cloud data processing method described in the above embodiments.

[0105] Furthermore, this disclosure also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement the obstacle point cloud data processing method described above.

[0106] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0107] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0108] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0109] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0110] Obtain raw point cloud data, sort the raw point cloud data, and obtain sorted point cloud data;

[0111] Acquire obstacle point cloud data;

[0112] Based on the obstacle point cloud data and the sorted point cloud data, determine the position information of the obstacle point cloud data in the original point cloud data.

[0113] In addition, the electronic device can also perform other steps in the obstacle point cloud data processing method described above.

[0114] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0115] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0116] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0117] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0118] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0119] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0120] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An obstacle point cloud data processing method, characterized by, The method comprises: obtaining original point cloud data, sorting the original point cloud data to obtain sorted point cloud data; obtaining obstacle point cloud data; determining position information of the obstacle point cloud data in the original point cloud data according to the obstacle point cloud data and the sorted point cloud data; sorting the original point cloud data to obtain sorted point cloud data comprises: determining a preset range according to the original point cloud data to obtain original point cloud data within the preset range and original point cloud data outside the preset range; sorting the original point cloud data within the preset range to obtain first point cloud data; sorting the original point cloud data outside the preset range to obtain second point cloud data; arranging the first point cloud data in front of the second point cloud data to obtain sorted point cloud data.

2. The method of claim 1, wherein, sorting the original point cloud data within the preset range to obtain first point cloud data comprises: dividing the original point cloud data within the preset range according to a preset grid length to obtain divided point cloud data and point cloud grid numbers, and sorting the divided point cloud data according to the point cloud grid numbers to obtain first point cloud data.

3. The method of claim 1, wherein, obtaining obstacle point cloud data comprises: training an obstacle model according to to-be-trained point cloud data to obtain a trained obstacle model; inputting the original point cloud data into the trained obstacle model to obtain basic information of the obstacle point cloud data; obtaining the obstacle point cloud data according to the basic information of the obstacle point cloud data.

4. The method of claim 3, wherein, The basic information of the obstacle point cloud data comprises: position of the obstacle point cloud data, size of the obstacle point cloud data, and orientation of the obstacle point cloud data.

5. The method of claim 1, wherein, Determining position information of the obstacle point cloud data in the original point cloud data according to the obstacle point cloud data and the sorted point cloud data comprises: determining a correspondence between the obstacle point cloud data and the sorted point cloud data according to the obstacle point cloud data and the sorted point cloud data; determining position information of the obstacle point cloud data in the original point cloud data according to the correspondence between the obstacle point cloud data and the sorted point cloud data, and a correspondence between the original point cloud data and the sorted point cloud data.

6. The method of claim 5, wherein, Determining a correspondence between the obstacle point cloud data and the sorted point cloud data according to the obstacle point cloud data and the sorted point cloud data comprises: obtaining position information of multiple points in the obstacle point cloud data according to the obstacle point cloud data; determining a minimum polygon containing the multiple points according to the position information of the multiple points; determining a grid number and a grid number occupied by the minimum polygon according to the minimum polygon; determining the correspondence between the obstacle point cloud data and the sorted point cloud data according to the grid number and the grid number occupied by the minimum polygon.

7. An obstacle point cloud data processing apparatus characterized by comprising: The device comprises: a sorting module configured to obtain original point cloud data, sort the original point cloud data to obtain sorted point cloud data; an obtaining module configured to obtain obstacle point cloud data; determining a position information of the obstacle point cloud data in the original point cloud data according to the obstacle point cloud data and the sorted point cloud data; the sorting module is further configured to determine a preset range according to the original point cloud data, to obtain original point cloud data within the preset range and original point cloud data outside the preset range; sorting the original point cloud data within the preset range to obtain first point cloud data; sorting the original point cloud data outside the preset range to obtain second point cloud data; arranging the first point cloud data in front of the second point cloud data to obtain sorted point cloud data.

8. An electronic device, comprising: comprise: a memory; a processor; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-6.

10. A vehicle comprising: The obstacle point cloud data processing apparatus of claim 7.

Images