Point cloud data processing method and device, storage medium and electronic device

Abstract

The invention discloses a point cloud data processing method and device, a storage medium and an electronic device. The method comprises the following steps: acquiring point cloud data; according to adjacent points of at least part of point sets in the point cloud data, attribute data and connection data are obtained, the attribute data are used for adjusting the size attribute of each point in the at least part of point sets, and the connection data are used for describing the connection relation between each point in the at least part of point sets and the adjacent points; determining volume gradient information of the point cloud data based on the attribute data and the connection data; a target axis of the point cloud data is generated using the volume gradient information. The technical problems of low extraction efficiency and poor accuracy when the central axis of the point cloud data is extracted in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a point cloud data processing method, device, storage medium and electronic device. Background Art

[0002] Point cloud data is a three-dimensional data expression obtained by collecting surface geometric feature data of an object. When processing point cloud data, extracting the central axis of its geometric shape is of great significance for simplifying three-dimensional structures, performing morphological analysis, and realizing path planning. In related technologies, the central axis of point cloud data can be extracted by skeletonization-based methods and curve fitting-based methods. However, when processing complex point cloud structures, the central axis obtained by the central axis extraction method in related technologies has poor accuracy, discontinuity or roughness, which in turn affects the effect of the central axis in subsequent applications, and the extraction efficiency is low when the point cloud data is large in scale.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] At least some embodiments of the present application provide a point cloud data processing method, device, storage medium and electronic device to at least solve the technical problems in the related art of low extraction efficiency and poor accuracy when extracting the central axis of point cloud data.

[0005] According to one embodiment of the present application, a point cloud data processing method is provided, including: acquiring point cloud data; acquiring attribute data and connection data based on neighboring points of at least part of a point set in the point cloud data, wherein the attribute data is used to adjust the size attributes of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points; determining volume gradient information of the point cloud data based on the attribute data and the connection data; and generating a target axis of the point cloud data using the volume gradient information.

[0006] According to one embodiment of the present application, a point cloud data processing device is also provided, including: a first acquisition module, used to acquire point cloud data; a second acquisition module, used to acquire attribute data and connection data based on neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attributes of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points; a determination module, used to determine the volume gradient information of the point cloud data based on the attribute data and the connection data; and a generation module, used to generate the target axis of the point cloud data using the volume gradient information.

[0007] According to one embodiment of the present application, a computer-readable storage medium is further provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned point cloud data processing method in each embodiment of the present application when running.

[0008] According to one embodiment of the present application, an electronic device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the above-mentioned point cloud data processing method in each embodiment of the present application.

[0009] According to another aspect of the embodiments of the present application, a computer program product is also provided, including a computer program, which implements the above-mentioned point cloud data processing method in each embodiment of the present application when executed by a processor.

[0010] According to another aspect of an embodiment of the present application, a computer program product is also provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned point cloud data processing method in each embodiment of the present application is implemented.

[0011] According to another aspect of the embodiments of the present application, a computer program is also provided. When the computer program is executed by a processor, the point cloud data processing method described above in each embodiment of the present application is implemented.

[0012] In at least some embodiments of the present application, point cloud data is acquired, and then attribute data and connection data are acquired based on neighboring points of at least part of the point set in the point cloud data, so that the size attributes of each point in at least part of the point set are adjusted using the attribute data, and the connection data is used to describe the connection relationship between each point and the neighboring points in at least part of the point set. Subsequently, the volume gradient information of the point cloud data is determined based on the attribute data and the connection data, and the target axis of the point cloud data is generated using the volume gradient information, thereby achieving the purpose of efficiently and accurately extracting the central axis of the point cloud data, thereby achieving the technical effect of improving the extraction efficiency and accuracy of the central axis of the point cloud data, and thus solving the technical problems of low extraction efficiency and poor accuracy in extracting the central axis of point cloud data in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0014] Figure 1 It is a hardware structure block diagram of a mobile terminal of a point cloud data processing method according to one embodiment of the present application;

[0015] Figure 2 is a flow chart of a point cloud data processing method according to one embodiment of the present application;

[0016] Figure 3 is a schematic diagram of point cloud data according to one embodiment of the present application;

[0017] Figure 4 is a schematic diagram of connecting data according to one embodiment of the present application;

[0018] Figure 5 is a schematic diagram of volume data according to one embodiment of the present application;

[0019] Figure 6 is a schematic diagram of smoothed data according to one embodiment of the present application;

[0020] Figure 7 is a schematic diagram of an update result according to one embodiment of the present application;

[0021] Figure 8 is a schematic diagram of a central axis of point cloud data according to one embodiment of the present application;

[0022] Fig. 9 is a schematic diagram of another central axis of point cloud data according to one embodiment of the present application;

[0023] Fig.10 is a structural block diagram of a point cloud data processing device according to one embodiment of the present application;

[0024] Fig.11 is a schematic diagram of an electronic device according to one embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] 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 are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Common point cloud central axis extraction methods in related technologies include skeletonization-based methods and curve fitting-based methods. Specifically, the skeletonization-based method usually uses morphological operations or graph theory algorithms to gradually reduce the boundary of the point cloud data or extract the central axis through the centrality calculation of the graph. This method is widely used in two-dimensional image processing, but faces efficiency and accuracy issues in three-dimensional point cloud data. In complex point cloud structures, the central axis extracted based on the skeletonization method is often not accurate enough and is easily affected by noise and data integrity.

[0028] In the curve fitting method, the central axis is extracted by fitting the point cloud data with a curve. This method usually requires the pre-assumption that the point cloud data conforms to a certain mathematical model and is suitable for target objects with strong regularity. Although the curve fitting method can effectively extract the central axis of the point cloud in some scenarios, when dealing with complex and irregular point cloud structures, the extracted central axis is often not accurate enough and is easily affected by noise and data integrity. In addition, the calculation complexity is high in the curve fitting process, so it is inefficient when processing large-scale point cloud data, making it difficult to meet real-time application requirements, and the extracted central axis is discontinuous or not smooth, which further affects the effect of the central axis in subsequent applications.

[0029] The above method embodiments involved in this application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, the mobile terminal can be a smart phone, a tablet computer, a PDA, a mobile Internet device, a PAD, a game console and other terminal devices. Figure 1 1 is a hardware structure block diagram of a mobile terminal of a point cloud data processing method according to an embodiment of the present application. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microprocessor (MCU), a field-programmable logic device (FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, etc.) and a memory 104 for storing data. In one embodiment of the present application, it may also include: an input and output device 108 and a display device 110.

[0030] In some optional embodiments mainly based on game scenarios, the above-mentioned device can also provide a human-computer interaction interface with a touch-sensitive surface, which can sense finger contact and / or gestures to perform human-computer interaction with a graphical user interface (GUI). The human-computer interaction function may include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interface, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for executing the above-mentioned human-computer interaction functions are configured / stored in a computer program product or readable storage medium executable by one or more processors.

[0031] Those skilled in the art will understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0032] According to one embodiment of the present application, an embodiment of a point cloud data processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] Figure 2 is a flow chart of a point cloud data processing method according to one embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0034] Step S21, obtaining point cloud data;

[0035] Step S22, acquiring attribute data and connection data according to neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attribute of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points;

[0036] Step S23, determining volume gradient information of the point cloud data based on the attribute data and the connection data;

[0037] Step S24, generating a target axis of the point cloud data using the volume gradient information.

[0038] The above point cloud data is a form of expression of three-dimensional spatial data, consisting of a large number of discrete points. Figure 3 is a schematic diagram of point cloud data according to one embodiment of the present application, such as Figure 3 As shown in the figure, the discrete points in the point cloud data have specific positions (X, Y, Z) in the three-dimensional coordinate system. Point cloud data can be collected through three-dimensional scanning equipment, such as lidar, structured light scanners, etc., or image-based three-dimensional reconstruction technology, and can be used to accurately capture the three-dimensional shape and structure of real-world objects or environments. Each point in the point cloud data carries spatial position information and can also contain additional data such as color, intensity, texture, etc., making point cloud data an important tool for processing and analyzing three-dimensional information in fields such as computer vision, three-dimensional modeling, robot navigation, unmanned driving technology, augmented reality (AR), virtual reality (VR) and medical imaging.

[0039] After acquiring the point cloud data, attribute data and connection data are acquired based on the neighboring points of at least part of the point set in the point cloud data. The attribute data is used to adjust the size attribute (pscale) of each point in at least part of the point set. The more neighboring points there are around a point in the point cloud data, the larger the size attribute of the point. The connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points. The connection relationship can be used to connect each point in at least part of the point set with the neighboring points.

[0040] Furthermore, the volume gradient information of the point cloud data, the volume gradient vector of the point cloud data and the length of the volume gradient vector are determined based on the attribute data and the connection data. The volume gradient information can be used to understand the local geometric features of the point cloud data. By analyzing the gradient of each point in the point cloud data, the high-density area, low-density area of ​​the point cloud as well as the boundary and internal structure of the point cloud can be identified, thereby more accurately extracting the central axis of the point cloud data. In the process of extracting the central axis, the volume gradient information provides a directional guide, indicating the density change trend of the point cloud data. By calculating the volume gradient vector of the point and adjusting the position of the point according to the volume gradient vector, the point can be moved to the high-density area inside the point cloud, and finally approach the central axis of the point cloud, thereby improving the accuracy of extracting the central axis.

[0041] Based on the above steps S21 to S24, by acquiring point cloud data, and then acquiring attribute data and connection data based on neighboring points of at least part of the point set in the point cloud data, the size attributes of each point in at least part of the point set are adjusted using the attribute data, and the connection data is used to describe the connection relationship between each point and the neighboring points in at least part of the point set. Subsequently, the volume gradient information of the point cloud data is determined based on the attribute data and the connection data, and the target axis of the point cloud data is generated using the volume gradient information, thereby achieving the purpose of efficiently and accurately extracting the central axis of the point cloud data, thereby achieving the technical effect of improving the extraction efficiency and accuracy of the central axis of the point cloud data, and then solving the technical problems of low extraction efficiency and poor accuracy in extracting the central axis of the point cloud data in the related technology.

[0042] The point cloud data processing method in the embodiment of the present application is further introduced below.

[0043] Optionally, in step S22, acquiring attribute data according to neighboring points of at least part of the point set in the point cloud data includes:

[0044] Step S221, selecting a first current point from at least part of the point set;

[0045] Step S222, obtaining the number of neighboring points of the first current point within a first preset range of the first current point;

[0046] Step S223, in response to the number of neighboring points being less than a preset number threshold and the first preset range being less than a preset range threshold, the first preset range is expanded and adjusted to obtain an adjusted range;

[0047] Step S224, continue searching for neighboring points of the first current point within the adjusted range;

[0048] Step S225: Based on the first current point and the multiple found neighboring points, the size attribute of the point cloud data is adjusted to obtain attribute data.

[0049] Specifically, a first current point is selected from at least part of the point set, and an index of the first current point is obtained. A first preset range of the first current point is determined by initializing the search radius, and the number of neighboring points of the first current point is obtained within the first preset range. If the number of neighboring points of the first current point is less than a preset number threshold, and the first preset range is less than a preset range threshold, the first preset range is expanded and adjusted to obtain an adjusted range.

[0050] When adjusting the first preset range, the initialization search radius can be adjusted according to the preset multiple, for example, the initialization search radius can be expanded to 1.5 times the original value, thereby expanding the first preset range to obtain the adjusted range. After obtaining the adjusted range, continue to search for multiple neighboring points of the first current point within the adjusted range. By dynamically adjusting the first preset range, it is possible to adapt to different point cloud densities and structures, and automatically expand the search range until enough neighboring points are found, thereby avoiding the problems caused by a fixed search range, such as missing key information in sparse areas due to a small search range, or introducing redundant information in high-density areas due to a large search range.

[0051] Furthermore, based on the first current point and the multiple neighboring points found, the size attribute of the point cloud data is adjusted to obtain attribute data. By dynamically adjusting the size attribute according to the number of neighboring points of the first current point, the local density and structural characteristics of the point cloud data can be more accurately reflected. In high-density areas, the size attribute of the points is small, while in sparse areas, the size attribute of the points is large, which helps to better restore the true geometric characteristics of the point cloud in subsequent processing.

[0052] Based on the above optional embodiments, by selecting the first current point from at least part of the point set, the number of neighboring points of the first current point is obtained within a first preset range of the first current point, and then in response to the number of neighboring points being less than a preset number threshold and the first preset range being less than a preset range threshold, the first preset range is expanded and adjusted to obtain an adjusted range, and multiple neighboring points of the first current point are continued to be searched within the adjusted range. Finally, based on the first current point and the multiple neighboring points found, the size attribute of the point cloud data is adjusted to obtain attribute data. This not only makes it possible to dynamically adjust the size attribute of the point cloud data and improve the flexibility and efficiency of point cloud processing, but also effectively reduce the impact of noise and enhance the accuracy of subsequent processing.

[0053] Optionally, in step S225, based on the first current point and the multiple neighboring points found, the size attribute of the point cloud data is adjusted to obtain the attribute data including:

[0054] Step S2251, determining a target distance based on the first current point and the multiple found neighboring points;

[0055] Step S2252, adjusting the size attribute of the point cloud data according to the target distance and the preset scale factor to obtain attribute data.

[0056] The above target distance is the average distance, which is the average distance between the first current point and multiple neighboring points found. The average distance can be used to describe the distribution of the point cloud around the first current point, or for other further geometric processing or analysis, such as density estimation, feature detection, parameter adjustment and other application scenarios.

[0057] Furthermore, the size attribute of the point cloud data is adjusted according to the target distance and the preset scale factor to obtain attribute data. The preset scale factor can be flexibly adjusted according to user needs. For example, the preset scale factor can be set to 4.5.

[0058] Based on the above optional embodiments, by determining the target distance based on the first current point and the multiple neighboring points found, and then adjusting the size attributes of the point cloud data according to the target distance and the preset proportional coefficient, the attribute data is quickly obtained for adjusting the size attributes of each point in at least part of the point set, thereby further improving the processing efficiency of the point cloud data.

[0059] Optionally, in step S2251, determining the target distance based on the first current point and multiple neighboring points found includes: obtaining the number of neighboring points found; in response to the number of neighboring points found being non-empty, counting the distance between the first current point and each neighboring point to obtain a total distance value; and using the total distance value and the number of neighboring points to calculate the target distance.

[0060] Specifically, if the number of neighboring points found is not empty, that is, the number of neighboring points is not zero, then all the neighboring points found are traversed, and the distance between the first current point and each neighboring point is counted to obtain the total distance value, and then the total distance value and the number of neighboring points are used to calculate the target distance.

[0061] Based on the above optional embodiments, by obtaining the number of neighboring points, and then in response to the number of neighboring points being non-empty, the distance between the first current point and each neighboring point is counted to obtain the total distance value, and finally the total distance value and the number of neighboring points are used to quickly and accurately calculate the target distance, thereby further improving the processing efficiency of point cloud data.

[0062] Optionally, in step S2251, determining the target distance based on the first current point and the multiple found neighboring points includes: obtaining the number of found neighboring points; in response to the number of neighboring points being empty, determining the target distance according to the adjusted range where the first current point is located.

[0063] Specifically, if the number of neighboring points is empty, that is, the number of neighboring points is zero, the target distance is determined according to the search radius corresponding to the adjusted range where the first current point is located.

[0064] Optionally, in step S22, obtaining connection data according to neighboring points of at least part of the point set in the point cloud data includes:

[0065] Step S226, selecting a second current point from at least part of the point set;

[0066] Step S227, obtaining neighboring points of the second current point within a second preset range of the second current point;

[0067] Step S228, by traversing the neighboring points of the second current point, setting the second current point as the starting point, setting the neighboring points of the second current point as the end point, and connecting the starting point and the end point to obtain connection data.

[0068] Specifically, a second current point is selected from at least part of the point set, and then neighboring points of the second current point are obtained within a second preset range of the second current point. The second preset range may be the same as or different from the first preset range. Figure 4 is a schematic diagram of connecting data according to one embodiment of the present application, such as Figure 4 As shown, by traversing the neighboring points of the second current point, the second current point is set as the starting point, the neighboring points of the second current point are set as the end point, and a line is connected between the starting point and the end point to obtain connection data, which can be a line segment network.

[0069] Based on the above optional embodiments, by selecting the second current point from at least part of the point set, and then obtaining the neighboring points of the second current point within a second preset range of the second current point, and finally traversing the neighboring points of the second current point, the second current point is set as the starting point, the neighboring points of the second current point are set as the end point, and a line connection is performed between the starting point and the end point to quickly obtain connection data, thereby further improving the processing efficiency of point cloud data.

[0070] Optionally, in step S23, determining the volume gradient information based on the attribute data and the connection data includes:

[0071] Step S231, converting the attribute data into a data format to obtain volume data;

[0072] Step S232, performing data smoothing processing on the volume data to obtain smoothed data;

[0073] Step S233, determining volume gradient information based on the smoothed data and the connected data.

[0074] Specifically, Figure 5 is a schematic diagram of volume data according to one embodiment of the present application, such as Figure 5As shown, the attribute data is converted into a data format to obtain volume data (Volume Database, VDB). The characteristic of VDB data is that it can effectively represent and operate irregular three-dimensional volume data, such as fluid simulation results, smoke, flames, and density fields of point cloud data. When processing large-scale data sets, using VDB data can significantly reduce memory usage and calculation time, especially when processing scenes with complex geometric shapes or dynamic changes. The advantages are more obvious. VDB data supports a variety of operations, including but not limited to arithmetic operations, segmentation, smoothing, deformation, sampling, etc. of volume fields. These operations are crucial for three-dimensional graphics and simulation applications. By converting the attribute data of point cloud data into VDB data, efficient volume data processing and analysis can be performed.

[0075] Figure 6 is a schematic diagram of smoothed data according to one embodiment of the present application, such as Figure 6 As shown, the volume data is smoothed to obtain smoothed data. Through smoothing, the noise and irregularity in the volume data can be removed, making the data more continuous and smooth, thereby ensuring the accuracy and reliability of the volume gradient information and avoiding analysis errors caused by defects in the original data.

[0076] Furthermore, the volume gradient information is determined based on the smoothed data and the connected data. The volume gradient information is the key to point cloud structure analysis. It can reveal the distribution trend of data points in space and help the algorithm quickly and accurately identify the central axis, boundary and internal structure of the point cloud.

[0077] Based on the above optional embodiments, the volume data is obtained by converting the data format of the attribute data, and then the volume data is smoothed to obtain smoothed data. Finally, the volume gradient information is determined based on the smoothed data and the connection data, thereby further improving the efficiency and accuracy of the axis extraction of the point cloud data.

[0078] Optionally, the thickness attribute of the volume data is inversely proportional to the size attribute of the point cloud data.

[0079] Specifically, when the value of the size attribute of the point cloud data is larger, the number of surrounding neighboring points is larger, and the thickness radius of the volume data is smaller, that is, the volume data is thinner; when the value of the size attribute of the point cloud data is smaller, the number of surrounding neighboring points is larger, and the thickness radius of the volume data is larger, that is, the volume data is thicker.

[0080] Optionally, the volume gradient information includes: a volume gradient vector of the point cloud data and a length of the volume gradient vector. In step S24, generating a target axis of the point cloud data using the volume gradient information includes:

[0081] Step S241, updating the point position in the point cloud data according to the volume gradient vector of the point cloud data and the length of the volume gradient vector to obtain an update result;

[0082] Step S242, generating a target axis of the point cloud data based on the update result.

[0083] Specifically, the volume gradient vector is used to describe the rate of change of volume data in three-dimensional space. According to the volume gradient vector of the point cloud data and the length of the volume gradient vector, the point position in the point cloud data is updated to obtain an update result. During the update process, the difference between the point position vector in the point cloud data and the intermediate result is used to determine the update result. The intermediate result is the product of the volume gradient vector, the length of the volume gradient vector and the preset coefficient. The preset coefficient can adjust the amplitude of the update.

[0084] In the process of updating the point positions in the point cloud data, the purpose of the update is to make the points in the point cloud data gradually move closer to the central axis. Since the central axis usually corresponds to the local extreme value area of ​​the data value, subtracting the direction and magnitude of the volume gradient vector is actually moving the point in the direction where the value decreases fastest, that is, making the point move closer to the central axis. The above update process is usually performed multiple times, and the point position updated after each iteration is used as the starting point for the next update. Figure 7 is a schematic diagram of an update result according to one embodiment of the present application, such as Figure 7 As shown in the figure, as the iterative update proceeds, the point cloud structure is gradually simplified, and finally the points in the point cloud are densely distributed in the direction representing the main axis of the structure, thereby generating a more accurate target axis.

[0085] Based on the above optional embodiments, the point positions in the point cloud data are updated according to the volume gradient vector of the point cloud data and the length of the volume gradient vector to obtain an update result, and then the target axis of the point cloud data is generated based on the update result, thereby further improving the extraction efficiency and accuracy of the axis in the point cloud data.

[0086] Optionally, in step S242, generating a target axis of the point cloud data based on the update result includes: fusing multiple points in the update result that meet preset conditions to generate a central axis of the point cloud data, wherein the preset conditions are used to determine that the distance between two points located at different positions among the multiple points is less than a preset distance threshold.

[0087] Figure 8 is a schematic diagram of a central axis of point cloud data according to one embodiment of the present application, such as Figure 8As shown, if the distance between two points located at different positions in the multiple points in the update result is less than the preset distance threshold, it is determined that the multiple points meet the preset conditions, and the multiple points are fused to generate the central axis of the point cloud data. During the fusion process, a fuse operation can be performed. The fuse operation refers to merging points within a certain distance range into one point, thereby reducing the redundancy of the point cloud data, simplifying the data structure, and ensuring the integrity and accuracy of the geometric information. For example, the preset threshold is set to 5, that is, the points within 5 meters are fused together to obtain the central axis of the point cloud data.

[0088] Fig. 9 is a schematic diagram of another central axis of point cloud data according to one embodiment of the present application, such as Fig. 9 As shown, multiple points that meet the preset conditions in the update results are merged to generate Figure 3 The central axis of the point cloud data shown.

[0089] Based on the above optional embodiments, by fusing multiple points that meet preset conditions in the update results to generate the central axis of the point cloud data, not only can the visual and geometric quality of the central axis be significantly improved, but also the data processing flow can be optimized, the consumption of storage and computing resources can be reduced, and the stability and robustness of the algorithm can be improved, thereby providing more efficient and accurate central axis information for various point cloud data-based applications.

[0090] Optionally, the point cloud data processing method in the embodiment of the present application also includes: performing model segmentation processing on the virtual model corresponding to the point cloud data based on the target axis of the point cloud data, and / or performing path planning processing based on the target axis of the point cloud data.

[0091] In an optional embodiment, performing model segmentation processing on the virtual model corresponding to the point cloud data based on the target axis of the point cloud data may include the following processing steps:

[0092] Step 1: preprocess the point cloud data, which may include but is not limited to: denoising, filtering, downsampling, etc., to improve the efficiency and accuracy of subsequent processing.

[0093] Step 2, determining the target axis is the key to segmentation, that is, determining the target axis of the point cloud data through the above implementation process, which will not be repeated here.

[0094] Step 3, segmenting the point cloud data using the target axis, can be achieved by the following methods:

[0095] 1) Distance-based segmentation divides the points in the point cloud within a certain distance from the target axis into a region.

[0096] 2) Angle-based segmentation: points in the point cloud that form a specific angle with the target axis are divided into a region.

[0097] Step 4: Convert the segmented point cloud data into a three-dimensional model, which usually involves surface reconstruction technology, such as Poisson reconstruction, Delaunay triangulation, etc.

[0098] Step 5: Verify the segmented model to ensure the accuracy of the segmentation, such as smoothing and removing artifacts.

[0099] In another optional embodiment, path planning processing based on the target axis of the point cloud data may include the following processing steps:

[0100] Step 1: Data preprocessing, for example: using filtering algorithms to remove noise points in point cloud data, improve data quality, and reduce the amount of point cloud data to improve processing efficiency while maintaining key information.

[0101] Step 2, feature extraction, for example: extracting the features of the target axis from the point cloud data, you can use straight line detection algorithms such as Hough transform, and identify key points in path planning, such as turning points, obstacle edges, etc.

[0102] Step 3: Select a suitable path planning algorithm according to the application scenario, such as A*, Dijkstra, RRT, etc.

[0103] Step 4: Initialize one or more possible paths based on the target axis and key points, and use an optimization algorithm (such as a genetic algorithm, an ant colony algorithm, etc.) to optimize the initial path to meet the requirements of the shortest path, the safest path, etc.

[0104] Step 5: Perform collision detection on the generated path to ensure that the path is safe and feasible, and adjust the path to avoid obstacles based on the collision detection results.

[0105] Step 6, use a smoothing algorithm (such as Bezier curve, spline curve, etc.) to smooth the path for practical application.

[0106] Step 7: Output the final path in an appropriate format for subsequent navigation and control.

[0107] Step 8: In actual application, the path is dynamically updated and adjusted according to the point cloud data obtained in real time.

[0108] Step 9: Perform safety and reliability assessment on the planned path to ensure the robustness of the path planning.

[0109] Step 10: Provide a user interaction interface to allow the user to manually adjust the path or set specific path planning parameters.

[0110] Specifically, the target axis provides a clear geometric reference that can be used as a benchmark for virtual model segmentation. With the target axis, complex models can be segmented accurately, which can significantly reduce the time and computing resources required for segmentation. The segmented model parts can be further simplified to remove unnecessary details, which is critical for real-time rendering, game development, and virtual reality applications, and can improve the loading speed and rendering efficiency of virtual models.

[0111] In complex and dense environments, the target axis can help the system quickly identify the key structures of obstacles and provide reliable path planning information even when the point cloud data is incomplete or noisy.

[0112] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0113] In this embodiment, a point cloud data processing device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0114] Fig.10 is a structural block diagram of a point cloud data processing device according to one embodiment of the present application, such as Fig.10 As shown, the device comprises:

[0115] The first acquisition module 1001 is used to acquire point cloud data;

[0116] A second acquisition module 1002 is used to acquire attribute data and connection data based on neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attribute of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points;

[0117] A determination module 1003, for determining volume gradient information of point cloud data based on attribute data and connection data;

[0118] The generating module 1004 is used to generate the target axis of the point cloud data by using the volume gradient information.

[0119] Optionally, the second acquisition module 1002 is also used to: select a first current point from at least part of the point set; obtain the number of neighboring points of the first current point within a first preset range of the first current point; in response to the number of neighboring points being less than a preset number threshold and the first preset range being less than a preset range threshold, expand and adjust the first preset range to obtain an adjusted range; continue to search for multiple neighboring points of the first current point within the adjusted range; based on the first current point and the multiple neighboring points found, adjust the size attributes of the point cloud data to obtain attribute data.

[0120] Optionally, the second acquisition module 1002 is further used to: determine the target distance based on the first current point and the multiple found neighboring points; and adjust the size attribute of the point cloud data according to the target distance and a preset scale factor to obtain attribute data.

[0121] Optionally, the second acquisition module 1002 is also used to: obtain the number of neighboring points found; in response to the number of neighboring points being non-empty, count the distance between the first current point and each neighboring point to obtain a total distance value; and use the total distance value and the number of neighboring points to calculate the target distance.

[0122] Optionally, the second acquisition module 1002 is further used to: acquire the number of found neighboring points; and in response to the number of neighboring points being empty, determine the target distance according to the adjusted range where the first current point is located.

[0123] Optionally, the second acquisition module 1002 is also used to: select a second current point from at least part of the point set; obtain neighboring points of the second current point within a second preset range of the second current point; traverse the neighboring points of the second current point, set the second current point as the starting point, set the neighboring points of the second current point as the end point, and perform line processing between the starting point and the end point to obtain connection data.

[0124] Optionally, the determination module 1003 is further used to: perform data format conversion on the attribute data to obtain volume data; perform data smoothing processing on the volume data to obtain smoothed data; and determine volume gradient information based on the smoothed data and the connection data.

[0125] Optionally, the thickness attribute of the volume data is inversely proportional to the size attribute of the point cloud data.

[0126] Optionally, the generation module 1004 is further used to: update the point position in the point cloud data according to the volume gradient vector of the point cloud data and the length of the volume gradient vector to obtain an update result; and generate a target axis of the point cloud data based on the update result.

[0127] Optionally, the generation module 1004 is also used to: fuse multiple points in the update results that meet preset conditions to generate a central axis of the point cloud data, wherein the preset conditions are used to determine that the distance between two points located at different positions among the multiple points is less than a preset distance threshold.

[0128] Optionally, the point cloud data processing device further includes: a processing module 1005, which is used to perform model segmentation processing on the virtual model corresponding to the point cloud data based on the target axis of the point cloud data, and / or perform path planning processing based on the target axis of the point cloud data.

[0129] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0130] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0131] Optionally, in this embodiment, the above-mentioned computer-readable storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0132] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the mobile terminals in a mobile terminal group.

[0133] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0134] S1, obtain point cloud data;

[0135] S2, acquiring attribute data and connection data according to neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attribute of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points;

[0136] S3, determining volume gradient information of the point cloud data based on the attribute data and the connection data;

[0137] S4, using volume gradient information to generate the target axis of the point cloud data.

[0138] Optionally, the computer-readable storage medium is also configured to store program codes for executing the following steps: selecting a first current point from at least a portion of the point set; obtaining the number of neighboring points of the first current point within a first preset range of the first current point; in response to the number of neighboring points being less than a preset number threshold and the first preset range being less than a preset range threshold, expanding and adjusting the first preset range to obtain an adjusted range; continuing to search for multiple neighboring points of the first current point within the adjusted range; and adjusting the size attributes of the point cloud data based on the first current point and the multiple neighboring points found to obtain attribute data.

[0139] Optionally, the computer-readable storage medium is also configured to store program codes for executing the following steps: determining a target distance based on a first current point and a plurality of neighboring points found; and adjusting a size attribute of the point cloud data according to the target distance and a preset proportional coefficient to obtain attribute data.

[0140] Optionally, the computer-readable storage medium is also configured to store program codes for executing the following steps: obtaining the number of neighboring points found; in response to the number of neighboring points being non-empty, counting the distance between the first current point and each neighboring point to obtain a total distance value; and using the total distance value and the number of neighboring points to calculate the target distance.

[0141] Optionally, the computer-readable storage medium is further configured to store program codes for executing the following steps: obtaining the number of found neighboring points; and in response to the number of neighboring points being empty, determining the target distance based on the adjusted range where the first current point is located.

[0142] Optionally, the computer-readable storage medium is also configured to store program codes for executing the following steps: selecting a second current point from at least part of the point set; obtaining neighboring points of the second current point within a second preset range of the second current point; setting the second current point as the starting point and the neighboring points of the second current point as the end point by traversing the neighboring points of the second current point, and performing line processing between the starting point and the end point to obtain connection data.

[0143] Optionally, the computer-readable storage medium is further configured to store program codes for executing the following steps: performing data format conversion on the attribute data to obtain volume data; performing data smoothing processing on the volume data to obtain smoothed data; and determining volume gradient information based on the smoothed data and the connection data.

[0144] Optionally, the thickness attribute of the volume data is inversely proportional to the size attribute of the point cloud data.

[0145] Optionally, the above-mentioned computer-readable storage medium is also configured to store program codes for executing the following steps: updating the point position in the point cloud data based on the volume gradient vector of the point cloud data and the length of the volume gradient vector to obtain an updated result; and generating a target axis of the point cloud data based on the updated result.

[0146] Optionally, the above-mentioned computer-readable storage medium is also configured to store program code for executing the following steps: fusing multiple points in the update results that meet preset conditions to generate a central axis of the point cloud data, wherein the preset conditions are used to determine that the distance between two points located at different positions among the multiple points is less than a preset distance threshold.

[0147] Optionally, the computer-readable storage medium is also configured to store program codes for executing the following steps: performing model segmentation processing on a virtual model corresponding to the point cloud data based on a target axis of the point cloud data, and / or performing path planning processing based on the target axis of the point cloud data.

[0148] In the computer-readable storage medium of this embodiment, point cloud data is acquired, and then attribute data and connection data are acquired based on neighboring points of at least part of the point set in the point cloud data, so that the size attributes of each point in at least part of the point set are adjusted using the attribute data, and the connection data is used to describe the connection relationship between each point and the neighboring points in at least part of the point set. Subsequently, the volume gradient information of the point cloud data is determined based on the attribute data and the connection data, and the target axis of the point cloud data is generated using the volume gradient information, thereby achieving the purpose of efficiently and accurately extracting the central axis of the point cloud data, thereby achieving the technical effect of improving the extraction efficiency and accuracy of the central axis of the point cloud data, and thus solving the technical problems of low extraction efficiency and poor accuracy when extracting the central axis of point cloud data in the related art.

[0149] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0150] In an exemplary embodiment of the present application, a program product capable of implementing the above method of the present embodiment is stored on a computer-readable storage medium. In some possible implementations, various aspects of the embodiments of the present application can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present application described in the above "Exemplary Method" section of the present embodiment.

[0151] According to the program product for implementing the above method in the embodiment of the present application, it can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the embodiment of the present application is not limited thereto. In the embodiment of the present application, the computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0152] The program product may be in any combination of one or more computer-readable media. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive) of computer-readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0153] It should be noted that the program code contained in the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0154] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0155] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0156] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0157] S1, obtain point cloud data;

[0158] S2, acquiring attribute data and connection data according to neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attribute of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points;

[0159] S3, determining volume gradient information of the point cloud data based on the attribute data and the connection data;

[0160] S4, using volume gradient information to generate the target axis of the point cloud data.

[0161] Optionally, the processor can also be configured to perform the following steps through a computer program: selecting a first current point from at least part of the point set; obtaining the number of neighboring points of the first current point within a first preset range of the first current point; in response to the number of neighboring points being less than a preset number threshold and the first preset range being less than a preset range threshold, expanding and adjusting the first preset range to obtain an adjusted range; continuing to search for multiple neighboring points of the first current point within the adjusted range; and adjusting the size attributes of the point cloud data based on the first current point and the multiple neighboring points found to obtain attribute data.

[0162] Optionally, the processor may also be configured to perform the following steps through a computer program: determining a target distance based on a first current point and a plurality of neighboring points found; and adjusting a size attribute of the point cloud data according to the target distance and a preset proportional coefficient to obtain attribute data.

[0163] Optionally, the processor can also be configured to perform the following steps through a computer program: obtaining the number of neighboring points found; in response to the number of neighboring points being non-empty, counting the distance between the first current point and each neighboring point to obtain a total distance value; and using the total distance value and the number of neighboring points to calculate the target distance.

[0164] Optionally, the processor may also be configured to execute the following steps through a computer program: obtaining the number of found neighboring points; and in response to the number of neighboring points being empty, determining the target distance based on the adjusted range where the first current point is located.

[0165] Optionally, the above-mentioned processor can also be configured to perform the following steps through a computer program: selecting a second current point from at least part of the point set; obtaining the neighboring points of the second current point within a second preset range of the second current point; traversing the neighboring points of the second current point, setting the second current point as the starting point, setting the neighboring points of the second current point as the end point, and performing line processing between the starting point and the end point to obtain connection data.

[0166] Optionally, the processor may also be configured to execute the following steps through a computer program: converting the attribute data into a data format to obtain volume data; performing data smoothing on the volume data to obtain smoothed data; and determining volume gradient information based on the smoothed data and the connection data.

[0167] Optionally, the thickness attribute of the volume data is inversely proportional to the size attribute of the point cloud data.

[0168] Optionally, the processor can also be configured to perform the following steps through a computer program: updating the point position in the point cloud data based on the volume gradient vector of the point cloud data and the length of the volume gradient vector to obtain an updated result; and generating a target axis of the point cloud data based on the updated result.

[0169] Optionally, the processor can also be configured to perform the following steps through a computer program: fusing multiple points in the update results that meet preset conditions to generate a central axis of the point cloud data, wherein the preset conditions are used to determine that the distance between two points at different positions among the multiple points is less than a preset distance threshold.

[0170] Optionally, the processor may also be configured to execute the following steps through a computer program: performing model segmentation processing on a virtual model corresponding to the point cloud data based on a target axis of the point cloud data, and / or performing path planning processing based on the target axis of the point cloud data.

[0171] In the electronic device of this embodiment, point cloud data is acquired, and then attribute data and connection data are acquired based on neighboring points of at least part of the point set in the point cloud data, so that the size attributes of each point in at least part of the point set are adjusted by using the attribute data, and the connection data is used to describe the connection relationship between each point and the neighboring points in at least part of the point set. Subsequently, the volume gradient information of the point cloud data is determined based on the attribute data and the connection data, and the target axis of the point cloud data is generated using the volume gradient information, thereby achieving the purpose of efficiently and accurately extracting the central axis of the point cloud data, thereby realizing the technical effect of improving the extraction efficiency and accuracy of the central axis of the point cloud data, and thus solving the technical problems of low extraction efficiency and poor accuracy in extracting the central axis of the point cloud data in the related art.

[0172] Fig.11 is a schematic diagram of an electronic device according to an embodiment of the present application. Fig.11 As shown, the electronic device 1100 is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0173] like Fig.11As shown, the electronic device 1100 is in the form of a general computing device. The components of the electronic device 1100 may include but are not limited to: the at least one processor 1110, the at least one memory 1120, a bus 1130 connecting different system components (including the memory 1120 and the processor 1110), and a display 1120.

[0174] The memory 1120 stores program codes, which can be executed by the processor 1110, so that the processor 1110 executes the steps described in the method part of the embodiment of the present application according to various exemplary embodiments of the present application.

[0175] The memory 1120 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 11201 and / or a cache memory unit 11202, and may further include a read-only memory unit (ROM) 11203, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0176] In some examples, the memory 1120 may also include a program / utility 11204 having a set (at least one) of program modules 11205, such program modules 11205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. The memory 1120 may further include a memory remotely disposed relative to the processor 1110, and these remote memories may be connected to the electronic device 1100 via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0177] The bus 1130 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a local bus of the processor 1110, or a bus using any of a variety of bus architectures.

[0178] The display 1120 may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 1100 .

[0179] Optionally, the electronic device 1100 may also communicate with one or more external devices 1200 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 1100, and / or any device that enables the electronic device 1100 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 1150. Furthermore, the electronic device 1100 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 1160. Fig.11 As shown, the network adapter 1160 communicates with other modules of the electronic device 1100 via the bus 1130. It should be understood that although Fig.11 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0180] The electronic device 1100 may further include: a keyboard, a cursor control device (such as a mouse), an input / output interface (I / O interface), a network interface, a power supply and / or a camera.

[0181] It can be understood by those skilled in the art that Fig.11 The structure shown is only for illustration and does not limit the structure of the above electronic device. Fig.11 More or fewer components as shown, or with Figure 1 The memory 1120 may be used to store computer programs and corresponding data, such as the computer programs and corresponding data corresponding to the point cloud data processing method in the embodiment of the present application. The processor 1110 executes various functional applications and data processing by running the computer programs stored in the memory 1120, that is, implementing the above-mentioned point cloud data processing method.

[0182] The embodiment of the present application further provides a computer program product. Optionally, in this embodiment, the computer program product may include a computer program, and the computer program implements the method provided in the embodiment when executed by a processor.

[0183] Optionally, the computer program included in the above-mentioned computer program product is executed by a processor to perform the following steps:

[0184] S1, obtain point cloud data;

[0185] S2, acquiring attribute data and connection data according to neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attribute of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points;

[0186] S3, determining volume gradient information of the point cloud data based on the attribute data and the connection data;

[0187] S4, using volume gradient information to generate the target axis of the point cloud data.

[0188] The embodiments of the present application also provide a computer program product. Optionally, the computer program product may include a non-volatile computer-readable storage medium, which may be used to store a computer program, and when the computer program is executed by a processor, the method provided in the embodiments is implemented.

[0189] Optionally, the computer program stored in the non-volatile computer-readable storage medium is used by the processor to execute the following steps:

[0190] S1, obtain point cloud data;

[0191] S2, acquiring attribute data and connection data according to neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attribute of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points;

[0192] S3, determining volume gradient information of the point cloud data based on the attribute data and the connection data;

[0193] S4, using volume gradient information to generate the target axis of the point cloud data.

[0194] The embodiment of the present application further provides a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, the method provided in the above embodiment is implemented.

[0195] Optionally, the computer program is executed by a processor to perform the following steps:

[0196] S1, obtain point cloud data;

[0197] S2, acquiring attribute data and connection data according to neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attribute of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points;

[0198] S3, determining volume gradient information of the point cloud data based on the attribute data and the connection data;

[0199] S4, using volume gradient information to generate the target axis of the point cloud data.

[0200] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0201] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0202] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0203] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0204] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0205] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0206] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A point cloud data processing method, characterized in that: include: Get point cloud data; Acquire attribute data and connection data according to neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attribute of each point in at least part of the point set, and the connection data is used to describe the connection relationship between each point in at least part of the point set and the neighboring points; Determine volume gradient information of the point cloud data based on the attribute data and the connection data; The target axis of the point cloud data is generated using the volume gradient information.

2. The point cloud data processing method according to claim 1, characterized in that: Acquiring the attribute data according to the neighboring points of at least part of the point set in the point cloud data includes: Selecting a first current point from at least a portion of the point set; Acquire the number of neighboring points of the first current point within a first preset range of the first current point; In response to the number of neighboring points being less than a preset number threshold and the first preset range being less than a preset range threshold, expanding and adjusting the first preset range to obtain an adjusted range; Continue searching for a plurality of neighboring points of the first current point within the adjusted range; Based on the first current point and the plurality of found neighboring points, the size attribute of the point cloud data is adjusted to obtain the attribute data.

3. The point cloud data processing method according to claim 2, characterized in that: Based on the first current point and the plurality of found neighboring points, the size attribute of the point cloud data is adjusted to obtain the attribute data including: Determine a target distance based on the first current point and the plurality of found neighboring points; The size attribute of the point cloud data is adjusted according to the target distance and a preset scale factor to obtain the attribute data.

4. The point cloud data processing method according to claim 3, characterized in that: Determining the target distance based on the first current point and the plurality of found neighboring points includes: Get the number of neighboring points found; In response to the number of neighboring points being non-empty, counting the distances between the first current point and each of the found neighboring points to obtain a total distance value; The target distance is calculated using the total distance value and the number of neighboring points.

5. The point cloud data processing method according to claim 3, characterized in that: Determining the target distance based on the first current point and the plurality of found neighboring points includes: Get the number of neighboring points found; In response to the number of neighboring points being empty, determining the target distance according to the adjusted range where the first current point is located.

6. The point cloud data processing method according to claim 1, characterized in that: Acquiring the connection data according to the neighboring points of at least part of the point set in the point cloud data includes: Selecting a second current point from the at least partial point set; Acquire neighboring points of the second current point within a second preset range of the second current point; The connection data is obtained by traversing the neighboring points of the second current point, setting the second current point as the starting point, setting the neighboring points of the second current point as the end point, and performing a line connection process between the starting point and the end point.

7. The point cloud data processing method according to claim 1, characterized in that: Determining the volume gradient information based on the attribute data and the connection data includes: Convert the attribute data into a data format to obtain volume data; Performing data smoothing processing on the volume data to obtain smoothed data; The volume gradient information is determined based on the smoothed data and the connected data.

8. The point cloud data processing method according to claim 7, characterized in that: The thickness attribute of the volume data is in inverse proportion to the size attribute of the point cloud data.

9. The point cloud data processing method according to claim 1, characterized in that: The volume gradient information includes: a volume gradient vector of the point cloud data and a length of the volume gradient vector, and generating a target axis of the point cloud data using the volume gradient information includes: According to the volume gradient vector of the point cloud data and the length of the volume gradient vector, updating the point position in the point cloud data to obtain an update result; A target axis of the point cloud data is generated based on the update result.

10. The point cloud data processing method according to claim 9, characterized in that: Generating the target axis of the point cloud data based on the update result includes: A plurality of points in the update result that meet a preset condition are merged to generate a central axis of the point cloud data, wherein the preset condition is used to determine that a distance between two points in different positions among the plurality of points is less than a preset distance threshold.

11. The point cloud data processing method according to claim 1, characterized in that: The point cloud data processing method further includes: Model segmentation processing is performed on the virtual model corresponding to the point cloud data based on the target axis of the point cloud data, and / or path planning processing is performed based on the target axis of the point cloud data.

12. A point cloud data processing device, characterized in that: include: A first acquisition module, used for acquiring point cloud data; A second acquisition module is used to acquire attribute data and connection data according to neighboring points of at least part of the point set in the point cloud data, wherein the attribute data is used to adjust the size attribute of each point in the at least part of the point set, and the connection data is used to describe the connection relationship between each point in the at least part of the point set and the neighboring points; A determination module, configured to determine volume gradient information of the point cloud data based on the attribute data and the connection data; A generating module is used to generate a target axis of the point cloud data using the volume gradient information.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the point cloud data processing method described in any one of claims 1 to 11 when executed by a processor.

14. 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 run the computer program to execute the point cloud data processing method described in any one of claims 1 to 11.

15. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the point cloud data processing method described in any one of claims 1 to 11.

Images