Three-dimensional point cloud processing method, device, electronic device and storage medium

Abstract

The present application discloses a method, device, electronic device and storage medium for processing three-dimensional point clouds, and relates to the fields of computer vision and three-dimensional data processing. The method includes: obtaining three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system; projecting the three-dimensional point cloud data into two-dimensional point cloud data and the first target point into a second target point in two-dimensional form according to the coordinate axis of the three-dimensional coordinate system; taking the point in the two-dimensional point cloud data that is closest to the second target point as the third target point; taking the point corresponding to the third target point in the three-dimensional point cloud data as the key point that has a mapping relationship with the first target point. The present application solves the technical problem that the prior art cannot ensure that the point selected by the user is a real point in the point cloud data, resulting in poor accuracy when processing the point cloud data based on the selected point.

Description

Technical Field

[0001] The present application relates to the fields of computer vision and three-dimensional data processing, and more specifically, to a three-dimensional point cloud processing method, device, electronic device and storage medium. Background Art

[0002] In the field of 3D modeling and computer vision, 3D point cloud data is an important representation of the shape and position of an object surface and is widely used in scenes such as object detection, recognition, modeling and measurement. 3D point cloud data consists of discrete points on the surface of an object and can accurately reflect the geometric structure of the object. However, in practical applications, users often need to specify a certain 3D point for operation, such as measuring distance, marking feature point registration, point measurement, point classification and other extended functions.

[0003] Due to the discrete nature of point cloud data and the subjective randomness of users when specifying points, directly using user-specified points as operation targets often leads to inaccurate and unreliable operation results. In the prior art, when processing three-dimensional point cloud data, the points specified by the user may not be at the point position of the point cloud data set, or even if they are at the point position, there may be a deviation between the user-specified points and the actual structure of the point cloud due to the uneven distribution of the point cloud data and the noise present. This deviation is particularly prominent in applications with extremely high precision requirements such as precision engineering, medical imaging, and virtual reality, and may seriously affect system performance and reliability of operation.

[0004] Specifically, when users need to perform extended functions such as point registration, point measurement, and point classification in 3D point cloud data, traditional methods often directly use the user-specified points or their nearest points for operations. However, this method ignores the inherent characteristics of point cloud data, especially the distribution differences and noise effects of point cloud data in different axes. These factors result in the point specified by the user not being the most ideal key point in the point cloud data that reflects the shape of the object, thus introducing unnecessary errors in subsequent operations.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The present application provides a three-dimensional point cloud processing method, device, electronic device and storage medium to at least solve the technical problem in the prior art that it is impossible to ensure that the points selected by the user are actually existing points in the point cloud data, resulting in poor accuracy when processing the point cloud data based on the selected points.

[0007] According to one aspect of the present application, a method for processing a three-dimensional point cloud is provided, including: acquiring three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system; projecting the three-dimensional point cloud data into two-dimensional point cloud data and projecting the first target point into a second target point in two-dimensional form according to the coordinate axes of the three-dimensional coordinate system; taking the point in the two-dimensional point cloud data that is closest to the second target point as a third target point; and taking the point corresponding to the third target point in the three-dimensional point cloud data as a key point that has a mapping relationship with the first target point.

[0008] Optionally, based on the coordinate axes of the three-dimensional coordinate system, the three-dimensional point cloud data is projected into two-dimensional point cloud data and the first target point is projected into a second target point, including: calculating statistical data of the three-dimensional point cloud data on each coordinate axis of the three-dimensional coordinate system, wherein the statistical data of the three-dimensional point cloud data on each coordinate axis is used to characterize data changes of the three-dimensional point cloud data on the coordinate axis; based on the statistical data of the three-dimensional point cloud data on each coordinate axis, the three-dimensional point cloud data is projected into two-dimensional point cloud data and the first target point is projected into the second target point.

[0009] Optionally, based on statistical data of the three-dimensional point cloud data on each coordinate axis, the three-dimensional point cloud data is projected into two-dimensional point cloud data, and the first target point is projected into a second target point, including: determining the amount of data change and the amount of information loss of the three-dimensional point cloud data on each coordinate axis based on the statistical data of the three-dimensional point cloud data on each coordinate axis; determining a projection method for the three-dimensional point cloud data and the first target point based on the amount of data change and the amount of information loss of the three-dimensional point cloud data on each coordinate axis; and according to the projection method, projecting the three-dimensional point cloud data into two-dimensional point cloud data, and projecting the first target point into the second target point.

[0010] Optionally, based on the statistical data of the three-dimensional point cloud data on each coordinate axis, the data change and information loss of the three-dimensional point cloud data on each coordinate axis are determined, including: calculating the standard deviation of the three-dimensional point cloud data on each coordinate axis; based on the standard deviation of the three-dimensional point cloud data on each coordinate axis, determining the data change and information loss of the three-dimensional point cloud data on each coordinate axis.

[0011] Optionally, the projection method for the three-dimensional point cloud data and the first target point is determined based on the data change amount and information loss amount of the three-dimensional point cloud data on each coordinate axis, including: determining a first score for each coordinate axis based on the data change amount of the three-dimensional point cloud data on each coordinate axis, wherein the data change amount of the three-dimensional point cloud data on each coordinate axis is negatively correlated with the first score of the coordinate axis; determining a second score for each coordinate axis based on the information loss amount of the three-dimensional point cloud data on each coordinate axis, wherein the information loss amount of the three-dimensional point cloud data on each coordinate axis is negatively correlated with the second score of the coordinate axis; performing a weighted sum calculation on the first score and the second score of each coordinate axis to obtain a target score for each coordinate axis; and determining the projection method for the three-dimensional point cloud data and the first target point based on the target score of each coordinate axis.

[0012] Optionally, the projection method for the three-dimensional point cloud data and the first target point is determined according to the target score of each coordinate axis, including: taking the coordinate axis with the smallest target score as the projection axis; taking the plane formed by the two coordinate axes other than the projection axis in the three-dimensional coordinate system as the projection plane; and projecting the three-dimensional point cloud data into two-dimensional point cloud data and projecting the first target point into the second target point according to the projection axis and the projection plane.

[0013] Optionally, the point in the two-dimensional point cloud data that is closest to the second target point is used as the third target point, including: constructing a point cloud tree based on the two-dimensional point cloud data, wherein the point cloud tree is a data structure in the form of a binary tree, which is used to represent the two-dimensional point cloud data in the form of a binary tree; by calculating the Euclidean distance between the points in the point cloud tree and the second target point, a nearest neighbor search algorithm is used to determine the point in the two-dimensional point cloud data that is closest to the second target point, so as to obtain the third target point.

[0014] Optionally, a point corresponding to the third target point in the three-dimensional point cloud data is used as a key point having a mapping relationship with the first target point, including: after determining the third target point, determining the point corresponding to the third target point in the three-dimensional point cloud data based on the projection mapping relationship that the three-dimensional point cloud data relies on when projecting into two-dimensional point cloud data, and establishing a corresponding relationship between the point and the third target point; setting a binding relationship between the corresponding relationship and the first target point; when querying the key point corresponding to the first target point in the three-dimensional point cloud data, indexing the point corresponding to the third target point in the three-dimensional point cloud data as the key point according to the binding relationship.

[0015] Optionally, after taking the point corresponding to the third target point in the three-dimensional point cloud data as the key point having a mapping relationship with the first target point, the three-dimensional point cloud processing method also includes: replacing the first target point with the key point in the three-dimensional point cloud data to obtain an updated first target point, and performing any one of the following operations: a first operation, which is used to perform point cloud registration on the three-dimensional point cloud data according to the updated first target point; a second operation, which is used to perform a neighborhood search on the three-dimensional point cloud data according to the updated first target point; a third operation, which is used to perform point cloud measurement on the three-dimensional point cloud data according to the updated first target point; a fourth operation, which is used to perform point cloud classification on the three-dimensional point cloud data according to the updated first target point.

[0016] According to another aspect of the present application, a three-dimensional point cloud processing device is also provided, including: a first acquisition unit, which acquires three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system; a first projection unit, which projects the three-dimensional point cloud data into two-dimensional point cloud data and projects the first target point into a second target point in two-dimensional form according to the coordinate axes of the three-dimensional coordinate system; a first processing unit, which takes the point in the two-dimensional point cloud data that is closest to the second target point as a third target point; and a second processing unit, which takes the point corresponding to the third target point in the three-dimensional point cloud data as a key point that has a mapping relationship with the first target point.

[0017] According to another aspect of the present application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the above-mentioned three-dimensional point cloud processing method.

[0018] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned three-dimensional point cloud processing method.

[0019] In the present application, three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system are first obtained. Secondly, according to the coordinate axes in the three-dimensional coordinate system, the three-dimensional point cloud data is projected into two-dimensional point cloud data, and the first target point is projected into a second target point in two-dimensional form. Then, the point in the two-dimensional point cloud data that is closest to the second target point is used as the third target point. Finally, the point corresponding to the third target point in the three-dimensional point cloud data is used as the key point that has a mapping relationship with the first target point. The purpose of adaptively mapping the input selected point to a real point or the real closest point in the three-dimensional point cloud data and replacing the input selected point as the key point for post-processing of the point cloud data is achieved, thereby solving the problem of deviation in point cloud preprocessing caused by directly using the input selected point as the key point, thereby achieving the technical effect of improving the accuracy of processing point cloud data based on selected points, and further solving the technical problem in the prior art that it is impossible to ensure that the point selected by the user is a real point in the point cloud data, resulting in poor accuracy in processing point cloud data based on selected points. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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:

[0021] Figure 1 is a flowchart of an optional three-dimensional point cloud processing method according to an embodiment of the present application;

[0022] Figure 2 is a structural diagram of an optional three-dimensional point cloud processing method according to an embodiment of the present application;

[0023] Figure 3 is a schematic diagram of an optional three-dimensional point cloud processing method according to an embodiment of the present application;

[0024] Figure 4 It is a schematic diagram of an optional three-dimensional point cloud processing device according to an 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] It should also be noted that the information and data collected by this application are authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation portals for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0028] According to an embodiment of the present application, an embodiment of a method for processing a three-dimensional point cloud 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 a 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.

[0029] It should be noted that a point cloud processing system is used as the execution subject of the three-dimensional point cloud processing method of the embodiment of the present application. It is understandable that the three-dimensional point cloud processing method provided in the embodiment of the present application can also be executed by other systems or devices, and the embodiment of the present application does not specifically limit this.

[0030] Figure 1 is a flowchart of an optional three-dimensional point cloud processing method according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0031] Step S101, obtaining three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system.

[0032] Optionally, 3D point cloud data is a commonly used data representation in computer vision, 3D modeling, scanning and measurement technology. It consists of a large number of points distributed in 3D space. Each point contains three coordinate values ​​(usually X, Y, Z), which describe the specific position of the point in space. In this embodiment, the 3D point cloud data is recorded as , which consists of multiple three-dimensional points.

[0033] Optionally, the first target point represents a three-dimensional point selected by the user in a random or specified manner in a three-dimensional coordinate system, denoted as .

[0034] Optionally, the first target point may be a point that does not belong to the three-dimensional point cloud data, that is, the first target point is a point that is outside the three-dimensional point cloud data.

[0035] Optionally, the point cloud processing system acquires a set of three-dimensional point cloud data and a first target point selected by a user in a three-dimensional coordinate system.

[0036] Step S102 , projecting the three-dimensional point cloud data into two-dimensional point cloud data and projecting the first target point into a second target point in two-dimensional form according to the coordinate axes of the three-dimensional coordinate system.

[0037] Optionally, the point cloud processing system selects an axis as a projection axis based on the coordinate axes in the three-dimensional coordinate system by calculating the statistical characteristics of the point cloud data on each axis (such as standard deviation and variance), and projects the three-dimensional point cloud data into two-dimensional point cloud data, while also projecting the first target point into a second target point in two-dimensional form.

[0038] Optionally, the second target point is a projection representation of the three-dimensional point selected by the user in the corresponding two-dimensional space.

[0039] Step S103: taking the point in the two-dimensional point cloud data that is closest to the second target point as the third target point.

[0040] Optionally, the point cloud processing system uses an efficient algorithm to perform a nearest neighbor search in the two-dimensional point cloud data to find the point closest to the second target point as the third target point.

[0041] Step S104: taking the point corresponding to the third target point in the three-dimensional point cloud data as a key point having a mapping relationship with the first target point.

[0042] Optionally, the point cloud processing system determines the corresponding point of the third target point in the original three-dimensional point cloud data, and uses it as a key point that has a mapping relationship with the first target point, for subsequent extended function operations based on selected points, such as neighborhood search, point registration, point measurement, and point classification.

[0043] Optionally, Figure 2is a structural diagram of an optional three-dimensional point cloud processing method according to an embodiment of the present application, such as Figure 2 As shown, the point cloud processing system first obtains the three-dimensional point (i.e., the first target point mentioned above) and the three-dimensional point cloud data selected by the user through the data reading module, and then projects the three-dimensional point and the three-dimensional point cloud data to a two-dimensional plane through the data projection module. Then, according to the key point search module, the system searches on the two-dimensional plane for a two-dimensional point (i.e., the third target point) closest to the two-dimensional point (i.e., the second target point) corresponding to the projection of the three-dimensional point selected by the user, and then maps this closest two-dimensional point (i.e., the third target point) in the three-dimensional point cloud data as a key point through the key point acquisition module, and outputs the key point information through the output module.

[0044] It can be seen from the contents of steps S101 to S104 that in the present application, three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system are first obtained, and then the three-dimensional point cloud data is projected into two-dimensional point cloud data according to the coordinate axes in the three-dimensional coordinate system, and the first target point is projected into a second target point in two-dimensional form, and then the point in the two-dimensional point cloud data that is closest to the second target point is used as the third target point, and finally the point corresponding to the third target point in the three-dimensional point cloud data is used as the key point that has a mapping relationship with the first target point, so as to achieve the purpose of adaptively mapping the input selected point to a real point or the real closest point in the three-dimensional point cloud data, and replacing the input selected point as the key point for post-processing of the point cloud data, thereby solving the problem of deviation in point cloud preprocessing caused by directly using the input selected point as the key point, thereby achieving the technical effect of improving the accuracy of processing point cloud data based on selected points, and further solving the technical problem that the prior art cannot ensure that the point selected by the user is a real point in the point cloud data, resulting in poor accuracy when processing point cloud data based on selected points.

[0045] In an optional embodiment, the point cloud processing system first calculates statistical data of the three-dimensional point cloud data on each coordinate axis of the three-dimensional coordinate system, wherein the statistical data of the three-dimensional point cloud data on each coordinate axis is used to characterize data changes of the three-dimensional point cloud data on the coordinate axis, and then projects the three-dimensional point cloud data into two-dimensional point cloud data based on the statistical data of the three-dimensional point cloud data on each coordinate axis, and projects the first target point into the second target point.

[0046] Optionally, the point cloud processing system calculates the statistical data of the three-dimensional point cloud data on each coordinate axis of the three-dimensional coordinate system, that is, calculates the data changes of the three-dimensional point cloud data on each coordinate axis, and can clearly understand the changes of the three-dimensional point cloud data on each axis based on the data changes. Then, based on the statistical data of the three-dimensional point cloud data on each coordinate axis, the axis with the smallest data change can be selected as the projection axis, and the three-dimensional point cloud data can be projected into two-dimensional point cloud data, and the first target point can be projected into the second target point.

[0047] Optionally, the point cloud processing system can determine the data changes of the point cloud data in each axis direction by calculating the statistical data of the three-dimensional point cloud data on the three coordinate axes of X, Y, and Z, such as the standard deviation, thereby providing a basis for selecting the most appropriate projection axis. According to the statistical data of the three-dimensional point cloud data on each coordinate axis, the system intelligently selects the most appropriate projection axis, projects the three-dimensional point cloud data into two-dimensional point cloud data, and projects the first target point specified by the user into the second target point on the two-dimensional plane. This selection is based on the statistical characteristics of the data and can effectively deal with the non-uniform distribution and noise problems of the point cloud data, ensuring that the projected two-dimensional data can still accurately reflect the key information of the original three-dimensional data, and the relative position information of the second target point in the two-dimensional space after projection is retained with respect to the first target point in the three-dimensional space.

[0048] From the above content, it can be seen that the point cloud processing system uses the statistical characteristics of three-dimensional point cloud data to perform intelligent two-dimensional projection, which not only optimizes the data processing process and improves computing efficiency, but also ensures the accuracy and robustness of the operation, providing a basis for subsequently finding the actual point closest to the three-dimensional point selected by the user.

[0049] In an optional embodiment, the point cloud processing system determines the data change and information loss of the three-dimensional point cloud data on each coordinate axis based on the statistical data of the three-dimensional point cloud data on each coordinate axis, and then determines the projection method of the three-dimensional point cloud data and the first target point based on the data change and information loss of the three-dimensional point cloud data on each coordinate axis, and then projects the three-dimensional point cloud data into two-dimensional point cloud data and projects the first target point into the second target point based on the projection method.

[0050] Optionally, the point cloud processing system determines the data change and information loss of the three-dimensional point cloud data on each coordinate axis based on the statistical data of the three-dimensional point cloud data on each coordinate axis, and then determines the projection method of the three-dimensional point cloud data and the first target point based on the data change and information loss of the three-dimensional point cloud data on each coordinate axis, and projects the three-dimensional point cloud data and the first target point according to the projection method.

[0051] Optionally, the point cloud processing system can identify the axis with the most uniform data distribution and the smallest change by calculating the data change amount of the three-dimensional point cloud data on each coordinate axis. Small data change means that the data distribution along the axis is more concentrated and less affected by noise, so selecting this axis for projection can reduce errors in the data processing process. In addition to the data change amount, the system also considers the evaluation of the amount of information loss during the projection process. The information loss amount refers to the fact that some information or details of the data may be ignored or simplified during the projection process from three-dimensional to two-dimensional. By quantifying this information loss, the system can select the projection direction that retains the most key information and has the least impact on the operation, thereby ensuring the integrity and validity of the projected data. Based on the comprehensive analysis of the data change amount and the information loss amount, the point cloud processing system automatically selects the optimal projection method to convert the three-dimensional point cloud data and the first target point specified by the user into a two-dimensional representation. This process ensures the accuracy of the projection result and the robustness of the operation through statistical analysis of the data. Finally, according to the intelligently selected projection method, the three-dimensional point cloud data is projected into two-dimensional point cloud data, and the first target point is accurately mapped to the second target point position in the two-dimensional point cloud data.

[0052] From the above content, it can be seen that the point cloud processing system determines the projection method of the three-dimensional point cloud data and the first target point through the data change and information loss of the three-dimensional point cloud data on each coordinate axis, thereby ensuring the reliability of the projection method.

[0053] In an optional embodiment, the point cloud processing system first calculates the standard deviation of the three-dimensional point cloud data on each coordinate axis, and then determines the data change and information loss of the three-dimensional point cloud data on each coordinate axis based on the standard deviation of the three-dimensional point cloud data on each coordinate axis.

[0054] Optionally, the standard deviation of the three-dimensional point cloud data along the axis distribution can usually represent the data variation and information loss of the three-dimensional point cloud data on each axis.

[0055] Optionally, 3D point cloud data From n points Composition, of which , calculate the average value of the coordinates on each axis, as shown in formula (1):

[0056]

[0057] in, represents the mean value on the x-axis, represents the mean value on the y-axis, Represents the average value on the z-axis.

[0058] Optionally, the point cloud processing system calculates the standard deviation of the coordinates of the three-dimensional point cloud data on each axis, as shown in formula (2):

[0059]

[0060] in, represents the standard value on the x-axis, represents the standard value on the y-axis, Indicates the standard value on the z-axis.

[0061] Optionally, the point cloud processing system determines the data change amount and information loss amount of the three-dimensional point cloud data on each coordinate axis based on the calculated standard deviation on each axis.

[0062] From the above content, it can be seen that the point cloud processing system determines the data change and information loss of the three-dimensional point cloud data on each coordinate axis by calculating the standard deviation, which improves the efficiency and accuracy of data processing, simplifies user operations, and improves work efficiency.

[0063] In an optional embodiment, the point cloud processing system determines a first score for each coordinate axis based on the amount of data change of the three-dimensional point cloud data on each coordinate axis, wherein the amount of data change of the three-dimensional point cloud data on each coordinate axis is negatively correlated with the first score of the coordinate axis; then determines a second score for each coordinate axis based on the amount of information loss of the three-dimensional point cloud data on each coordinate axis, wherein the amount of information loss of the three-dimensional point cloud data on each coordinate axis is negatively correlated with the second score of the coordinate axis; a weighted sum is performed on the first score and the second score of each coordinate axis to obtain a target score for each coordinate axis; finally, a projection method for the three-dimensional point cloud data and the first target point is determined based on the target score of each coordinate axis.

[0064] Optionally, the point cloud processing system determines a first score for each coordinate axis based on the amount of data change of the three-dimensional point cloud data on each coordinate axis, wherein a smaller change in the data amount has a higher first score, and a larger change in the data amount has a lower first score. Then, the second score for each coordinate axis is determined based on the amount of information loss of the three-dimensional point cloud data on each coordinate axis, wherein a smaller amount of information loss has a higher second score, and a larger amount of information loss has a lower second score. Then, the weight value of each score is obtained, and the weighted sum of the first score and the second score of each coordinate axis is calculated to obtain a target score for each coordinate axis. Finally, the projection method for the three-dimensional point cloud data and the first target point is determined based on the target score of each coordinate axis.

[0065] From the above content, it can be seen that the point cloud processing system comprehensively evaluates the amount of data change and information loss through a scoring mechanism, and automatically selects the optimal projection method based on the target score of each coordinate axis, thereby improving the efficiency and accuracy of three-dimensional point cloud data processing. At the same time, this process ensures that the projection method can effectively reduce the amount of data change and minimize information loss, providing a high-quality data foundation for subsequent two-dimensional point cloud operations.

[0066] In an optional embodiment, the point cloud processing system uses the coordinate axis with the smallest target score as the projection axis, and uses the plane formed by the two coordinate axes other than the projection axis in the three-dimensional coordinate system as the projection plane, and then projects the three-dimensional point cloud data into two-dimensional point cloud data based on the projection axis and the projection plane, and projects the first target point into the second target point.

[0067] Optionally, the point cloud processing system can directly use the coordinate axis with the smallest standard deviation as the projection axis, and then use the plane formed by the two coordinate axes other than the projection axis in the three-dimensional coordinate system as the projection plane, and finally project the three-dimensional point cloud data into two-dimensional point cloud data, and project the first target point into the second target point.

[0068] Optionally, the point cloud processing system finds the minimum standard deviation, as shown in formula (3):

[0069]

[0070] in, is the smallest standard deviation among the three coordinate axes.

[0071] Optionally, the point cloud processing system determines the corresponding projection axis according to the standard deviation , if the standard deviation of the x-axis is the smallest, select the x-axis as the projection axis; if the standard deviation of the y-axis is the smallest, select the y-axis as the projection axis; if the standard deviation of the z-axis is the smallest, select the z-axis as the projection axis, as shown in formula (4):

[0072]

[0073] Optionally, the point cloud processing system converts the three-dimensional selected points and 3D point cloud data Along the projection axis Projected into the other two dimensions to form a two-dimensional selection point and 2D point cloud data , as shown in formula (5) and formula (6):

[0074]

[0075]

[0076] If the projection axis is the x-axis, then the two-dimensional selection point Mapped on the surface composed of the y-axis and the z-axis, that is , 2D point cloud data It is also mapped on the surface composed of the y-axis and the z-axis, that is , if the projection axis is the y-axis, then the two-dimensional selection point and 2D point cloud data Both are mapped onto the surface composed of the x-axis and the z-axis. is the z-axis, and the same can be said for .

[0077] From the above content, it can be seen that the point cloud processing system realizes the accurate mapping of three-dimensional point cloud data to two-dimensional representation by intelligently selecting the projection axis and projection plane, thereby improving the accuracy of subsequent processing.

[0078] In an optional embodiment, the point cloud processing system constructs a point cloud tree based on the two-dimensional point cloud data, wherein the point cloud tree is a data structure in the form of a binary tree, which is used to represent the two-dimensional point cloud data in the form of a binary tree, and obtains the third target point by calculating the Euclidean distance between a point in the point cloud tree and a second target point, and using a nearest neighbor search algorithm to determine the point in the two-dimensional point cloud data that is closest to the second target point.

[0079] Optionally, the point cloud processing system uses a KD tree (K-dimensional tree) to perform Euclidean distance calculation on a two-dimensional plane to find the closest actual point. The KD tree is a data structure for storing and searching points in a multi-dimensional space, and is particularly suitable for operations such as fast nearest neighbor search and range search. Its main purpose is to efficiently search and compare points in a high-dimensional space, avoiding the high complexity of direct linear search on a large data set. In three-dimensional point cloud data processing, the application of the KD tree can greatly improve the efficiency of searching for nearest neighbor points.

[0080] Alternatively, Euclidean distance is a common method for measuring the distance between two points in a multidimensional space. Euclidean distance is based on the distance definition in a rectangular coordinate system. It determines the straight-line distance between two points by calculating the square root of the sum of the difference in the coordinate values ​​of the two points, reflecting the direct interval between the two points in space.

[0081] Optionally, the point cloud processing system selects points based on two dimensions In 2D point cloud data Finding and selecting points in 2D The closest point (Third target point).

[0082] Optionally, the point cloud processing system constructs a KD (point cloud tree) based on the two-dimensional point cloud data, and then uses a nearest neighbor search algorithm based on Euclidean distance to search for points in the two-dimensional point cloud data. Searching and selecting points in 2D The closest point .

[0083] From the above content, it can be seen that by constructing a point cloud tree, the point cloud processing system can organize huge two-dimensional point cloud data sets into a tree structure, which greatly improves the efficiency of searching for the nearest neighbor points. The Euclidean distance is used to calculate the distance between each point in the point cloud tree and the second target point. This method is intuitive and geometrically intuitive, ensuring the accuracy of the search results. Combined with the nearest neighbor search algorithm, it can accurately identify the point closest to the user-specified point (the second target point), that is, the third target point, which significantly improves the calculation efficiency of matching, reduces the complexity of manual adjustment, simplifies the data processing process, and improves work efficiency.

[0084] In an optional embodiment, after determining the third target point, the point cloud processing system determines the point corresponding to the third target point in the three-dimensional point cloud data based on the projection mapping relationship that the three-dimensional point cloud data relies on when projecting it into two-dimensional point cloud data, and establishes a corresponding relationship between the point and the third target point, sets a binding relationship between the corresponding relationship and the first target point, and when querying the key point corresponding to the first target point in the three-dimensional point cloud data, indexes the point corresponding to the third target point in the three-dimensional point cloud data as the key point according to the binding relationship.

[0085] Optionally, after determining the third target point, that is, determining the closest point corresponding to the three-dimensional point selected by the user in the two-dimensional point cloud data, the point cloud processing system determines the point corresponding to the third target point in the three-dimensional point cloud data based on the projection mapping relationship that the three-dimensional point cloud data relies on when projecting it into two-dimensional point cloud data, and establishes a corresponding relationship between the point and the third target point, and sets a binding relationship between the corresponding relationship and the first target point. The form of this binding relationship can be an index. Finally, when querying the key point corresponding to the first target point in the three-dimensional point cloud data, the point corresponding to the third target point in the three-dimensional point cloud data, that is, the key point, can be obtained according to this binding relationship.

[0086] Optionally, the point cloud processing system can determine in the two-dimensional point cloud data Select points in 2D The closest point Index , and based on this index, you can get the two-dimensional selection point In 3D point cloud data The key points of the mapping , as shown in formula (7):

[0087]

[0088] Optionally, Figure 3 is a schematic diagram of an optional three-dimensional point cloud processing method according to an embodiment of the present application, such as Figure 3 As shown, first input the points selected by the user and the 3D point cloud data, then calculate the standard deviation of the 3D point cloud data on each coordinate axis, select the optimal projection axis based on the calculation result of the standard deviation, and then map the points selected by the user and the 3D point cloud data into 2D points and 2D point cloud data according to the selected projection axis, then search for the point closest to the 2D point selected by the user based on the KD tree nearest neighbor algorithm, restore the searched nearest point to a real 3D point in the 3D point cloud data, and output the 3D point as a key point.

[0089] From the above content, it can be seen that the point cloud processing system optimizes the processing flow of 3D point cloud data by establishing a precise mapping between 3D points and 2D representations through automated projection and matching processes, reduces the complexity of manual adjustments, simplifies the data processing process, improves the accuracy and efficiency of operations, simplifies the data processing process, and enhances the stability and consistency of the system.

[0090] In an optional embodiment, the point cloud processing system replaces the first target point with a key point in the three-dimensional point cloud data to obtain an updated first target point, and performs any one of the following operations:

[0091] A first operation is used to perform point cloud registration on the three-dimensional point cloud data according to the updated first target point;

[0092] A second operation is used to perform a neighborhood search on the three-dimensional point cloud data according to the updated first target point;

[0093] A third operation is used to perform point cloud measurement on the three-dimensional point cloud data according to the updated first target point;

[0094] The fourth operation is used to perform point cloud classification on the three-dimensional point cloud data according to the updated first target point.

[0095] Optionally, the point cloud processing system receives the three-dimensional point cloud data and the first target point selected by the user, and determines the precise mapping point of the first target point in the point cloud, i.e., the key point, through the aforementioned statistical characteristic projection and matching technology. Then, the key point is used to replace the first target point to obtain the updated first target point. The three-dimensional point cloud data is processed using the updated first target point, which can more accurately reflect the user's intention and can be used to perform a variety of extended function operations based on the selected point, including but not limited to: point cloud registration, neighborhood search, point cloud measurement, and point cloud classification. Each operation uses the updated first target point as a reference point. Through its mapping relationship, the system can more accurately implement the corresponding function and improve the accuracy and efficiency of the operation.

[0096] From the above content, it can be seen that the point cloud processing system ensures the accuracy of subsequent operations by replacing the first target point specified by the user with the key point in the point cloud data. The replacement reduces the error caused by point selection deviation and improves the accuracy of operations such as point cloud registration, neighborhood search, point cloud measurement and point cloud classification. It not only solves common problems in point cloud data processing, such as point selection deviation, low operation accuracy and slow processing efficiency, but also provides a more accurate and efficient operation basis for the extended functions based on three-dimensional point cloud data, significantly enhancing the application performance of the point cloud processing system in the field of three-dimensional data processing.

[0097] In an optional embodiment, an application scenario of the three-dimensional point cloud processing method in the embodiment of the present application may be applied to an optical surface scanning system, wherein the optical surface scanning system is an important auxiliary tool in the field of radiotherapy, which uses optical technologies such as lasers and structured light to accurately detect and monitor the patient's body surface information, and combines with the registration algorithm to complete real-time monitoring of the patient's position, respiratory synchronization monitoring, and non-invasive positioning, thereby achieving the purpose of improving the treatment effect and patient comfort. In the actual application process, the user often needs to specify a certain three-dimensional point in the three-dimensional point cloud data of the human body surface to perform related operations. However, due to the discreteness of the point cloud data and the fact that the selected points are randomly and subjectively selected, the points specified by the user may not be exactly the points in the point cloud data, which affects the robustness and stability of the extended functions based on the selected points, and further affects the patient's treatment effect.

[0098] However, if the technical solution of the present application is adopted, by replacing the first target point specified by the user with the key point in the point cloud data, the accuracy of subsequent operations can be ensured, the error caused by point selection deviation can be reduced, the accuracy of operations such as point cloud registration, neighborhood search, point cloud measurement and point cloud classification can be improved, and the robustness and stability of the extended functions based on the selected points can be improved, ensuring that patients can obtain higher treatment effects.

[0099] It should be noted that the application of the above-mentioned optical surface scanning system is only an example. Those skilled in the art can understand that, except for the field of radiotherapy technology, any other scenario that requires point cloud processing or point cloud registration is applicable to the technical solution of the embodiment of the present application.

[0100] According to an embodiment of the present application, an embodiment of a three-dimensional point cloud processing device is also provided. Figure 4 is a schematic diagram of an optional three-dimensional point cloud processing device according to an embodiment of the present application, such as Figure 4 As shown, the three-dimensional point cloud processing device includes: a first acquisition unit 401, a first projection unit 402, a first processing unit 403 and a second processing unit 404.

[0101] Optionally, the first acquisition unit 401 is used to acquire three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system; the first projection unit 402 is used to project the three-dimensional point cloud data into two-dimensional point cloud data and the first target point into a second target point in two-dimensional form based on the coordinate axes of the three-dimensional coordinate system; the first processing unit 403 is used to take the point in the two-dimensional point cloud data that is closest to the second target point as the third target point; and the second processing unit 404 is used to take the point corresponding to the third target point in the three-dimensional point cloud data as the key point that has a mapping relationship with the first target point.

[0102] Optionally, the first projection unit 402 includes: a first calculation subunit and a first projection subunit. The first calculation subunit is used to calculate the statistical data of the three-dimensional point cloud data on each coordinate axis of the three-dimensional coordinate system, wherein the statistical data of the three-dimensional point cloud data on each coordinate axis is used to characterize the data change of the three-dimensional point cloud data on the coordinate axis; the first projection subunit is used to project the three-dimensional point cloud data into two-dimensional point cloud data and project the first target point into the second target point according to the statistical data of the three-dimensional point cloud data on each coordinate axis.

[0103] Optionally, the first projection subunit includes: a first determination module, a second determination module and a first projection module. The first determination module is used to determine the data change amount and information loss amount of the three-dimensional point cloud data on each coordinate axis according to the statistical data of the three-dimensional point cloud data on each coordinate axis; the second determination module is used to determine the projection method of the three-dimensional point cloud data and the first target point according to the data change amount and information loss amount of the three-dimensional point cloud data on each coordinate axis; the first projection module is used to project the three-dimensional point cloud data into two-dimensional point cloud data and project the first target point into the second target point according to the projection method.

[0104] Optionally, the first determination module includes: a first calculation submodule and a first determination submodule. The first calculation submodule is used to calculate the standard deviation of the three-dimensional point cloud data on each coordinate axis; the first determination submodule is used to determine the data change amount and information loss amount of the three-dimensional point cloud data on each coordinate axis according to the standard deviation of the three-dimensional point cloud data on each coordinate axis.

[0105] Optionally, the second determination module includes: a second determination submodule, a third determination submodule, a second calculation submodule and a fourth determination submodule. The second determination submodule is used to determine the first score of each coordinate axis according to the data change amount of the three-dimensional point cloud data on each coordinate axis, wherein the data change amount of the three-dimensional point cloud data on each coordinate axis is negatively correlated with the first score of the coordinate axis; the third determination submodule is used to determine the second score of each coordinate axis according to the information loss amount of the three-dimensional point cloud data on each coordinate axis, wherein the information loss amount of the three-dimensional point cloud data on each coordinate axis is negatively correlated with the second score of the coordinate axis; the second calculation submodule is used to perform weighted sum calculation on the first score and the second score of each coordinate axis to obtain the target score of each coordinate axis; the fourth determination submodule is used to determine the projection method of the three-dimensional point cloud data and the first target point according to the target score of each coordinate axis.

[0106] Optionally, the fourth determination submodule includes: a first processing component, a second processing component and a third processing component. The first processing component is used to use the coordinate axis with the smallest target score as the projection axis; the second processing component is used to use the plane formed by two coordinate axes other than the projection axis in the three-dimensional coordinate system as the projection plane; the third processing component is used to project the three-dimensional point cloud data into two-dimensional point cloud data and project the first target point into the second target point according to the projection axis and the projection plane.

[0107] Optionally, the first processing unit 403 includes: a first construction subunit and a first processing subunit. The first construction subunit is used to construct a point cloud tree based on the two-dimensional point cloud data, wherein the point cloud tree is a data structure in the form of a binary tree, and is used to represent the two-dimensional point cloud data in the form of a binary tree; the first processing subunit is used to determine the point closest to the second target point in the two-dimensional point cloud data by calculating the Euclidean distance between the point in the point cloud tree and the second target point, and using the nearest neighbor search algorithm to obtain the third target point.

[0108] Optionally, the second processing unit 404 includes: a second processing subunit, a first setting subunit, and a third processing subunit. The second processing subunit is used to determine the point corresponding to the third target point in the three-dimensional point cloud data after determining the third target point, based on the projection mapping relationship that the three-dimensional point cloud data depends on when projecting into two-dimensional point cloud data, and establish a corresponding relationship between the point and the third target point; the first setting subunit is used to set a binding relationship between the corresponding relationship and the first target point; the third processing subunit is used to index the point corresponding to the third target point in the three-dimensional point cloud data as the key point according to the binding relationship when querying the key point corresponding to the first target point in the three-dimensional point cloud data.

[0109] Optionally, the second processing unit 404 includes: a first execution subunit, used to replace the first target point with a key point in the three-dimensional point cloud data, obtain an updated first target point, and perform any one of the following operations: a first operation, used to perform point cloud registration on the three-dimensional point cloud data according to the updated first target point; a second operation, used to perform a neighborhood search on the three-dimensional point cloud data according to the updated first target point; a third operation, used to perform point cloud measurement on the three-dimensional point cloud data according to the updated first target point; a fourth operation, used to perform point cloud classification on the three-dimensional point cloud data according to the updated first target point.

[0110] According to another aspect of the present application, a three-dimensional point cloud processing device is also provided, including: a first acquisition unit, which acquires three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system; a first projection unit, which projects the three-dimensional point cloud data into two-dimensional point cloud data and projects the first target point into a second target point in two-dimensional form according to the coordinate axes of the three-dimensional coordinate system; a first processing unit, which takes the point in the two-dimensional point cloud data that is closest to the second target point as a third target point; and a second processing unit, which takes the point corresponding to the third target point in the three-dimensional point cloud data as a key point that has a mapping relationship with the first target point.

[0111] According to another aspect of the present application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the above-mentioned three-dimensional point cloud processing method.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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, 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. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute 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, etc., which can store program code.

[0118] 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 method for processing a three-dimensional point cloud, characterized in that: include: Acquire three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system; According to the coordinate axes of the three-dimensional coordinate system, the three-dimensional point cloud data is projected into two-dimensional point cloud data, and the first target point is projected into a second target point in two-dimensional form; Taking the point in the two-dimensional point cloud data that is closest to the second target point as the third target point; Using the point corresponding to the third target point in the three-dimensional point cloud data as a key point having a mapping relationship with the first target point; According to the coordinate axes of the three-dimensional coordinate system, the three-dimensional point cloud data is projected into two-dimensional point cloud data, and the first target point is projected into a second target point, including: calculating statistical data of the three-dimensional point cloud data on each coordinate axis of the three-dimensional coordinate system, wherein the statistical data of the three-dimensional point cloud data on each coordinate axis is used to characterize data changes of the three-dimensional point cloud data on the coordinate axis; according to the statistical data of the three-dimensional point cloud data on each coordinate axis, the three-dimensional point cloud data is projected into two-dimensional point cloud data, and the first target point is projected into a second target point.

2. The three-dimensional point cloud processing method according to claim 1, characterized in that: According to the statistical data of the three-dimensional point cloud data on each coordinate axis, projecting the three-dimensional point cloud data into two-dimensional point cloud data, and projecting the first target point into a second target point, comprising: Determine, according to statistical data of the three-dimensional point cloud data on each coordinate axis, a data change amount and an information loss amount of the three-dimensional point cloud data on each coordinate axis; Determining a projection method for the three-dimensional point cloud data and the first target point according to a data change amount and an information loss amount of the three-dimensional point cloud data on each coordinate axis; According to the projection method, the three-dimensional point cloud data is projected into two-dimensional point cloud data, and the first target point is projected into a second target point.

3. The three-dimensional point cloud processing method according to claim 2, characterized in that: Determining the data change amount and information loss amount of the three-dimensional point cloud data on each coordinate axis according to the statistical data of the three-dimensional point cloud data on each coordinate axis includes: Calculating the standard deviation of the three-dimensional point cloud data on each coordinate axis; According to the standard deviation of the three-dimensional point cloud data on each coordinate axis, the data change amount and the information loss amount of the three-dimensional point cloud data on each coordinate axis are determined.

4. The three-dimensional point cloud processing method according to claim 2, characterized in that: Determining a projection method for the three-dimensional point cloud data and the first target point according to a data change amount and an information loss amount of the three-dimensional point cloud data on each coordinate axis includes: Determine a first score for each coordinate axis according to a data change amount of the three-dimensional point cloud data on each coordinate axis, wherein the data change amount of the three-dimensional point cloud data on each coordinate axis is negatively correlated with the first score of the coordinate axis; Determine a second score for each coordinate axis according to the information loss amount of the three-dimensional point cloud data on each coordinate axis, wherein there is a negative correlation between the information loss amount of the three-dimensional point cloud data on each coordinate axis and the second score of the coordinate axis; Performing a weighted sum calculation on the first score and the second score of each coordinate axis to obtain a target score of each coordinate axis; A projection method for the three-dimensional point cloud data and the first target point is determined according to the target score of each coordinate axis.

5. The three-dimensional point cloud processing method according to claim 4, characterized in that: Determining a projection method for the three-dimensional point cloud data and the first target point according to the target score of each coordinate axis includes: The coordinate axis with the smallest target score is used as the projection axis; Taking a plane formed by two coordinate axes other than the projection axis in the three-dimensional coordinate system as a projection plane; According to the projection axis and the projection plane, the three-dimensional point cloud data is projected into two-dimensional point cloud data, and the first target point is projected into a second target point.

6. The three-dimensional point cloud processing method according to claim 1, characterized in that: Taking the point in the two-dimensional point cloud data that is closest to the second target point as the third target point, comprising: Constructing a point cloud tree based on the two-dimensional point cloud data, wherein the point cloud tree is a data structure in the form of a binary tree, and is used to represent the two-dimensional point cloud data in the form of the binary tree; The third target point is obtained by calculating the Euclidean distance between the points in the point cloud tree and the second target point and using a nearest neighbor search algorithm to determine the point in the two-dimensional point cloud data that is closest to the second target point.

7. The three-dimensional point cloud processing method according to claim 1, characterized in that: The point corresponding to the third target point in the three-dimensional point cloud data is used as a key point having a mapping relationship with the first target point, including: After determining the third target point, determining a point corresponding to the third target point in the three-dimensional point cloud data according to a projection mapping relationship on which the three-dimensional point cloud data depends when projecting the two-dimensional point cloud data, and establishing a corresponding relationship between the point and the third target point; Setting a binding relationship between the corresponding relationship and the first target point; When querying the key point corresponding to the first target point in the three-dimensional point cloud data, the point corresponding to the third target point in the three-dimensional point cloud data is indexed according to the binding relationship as the key point.

8. The three-dimensional point cloud processing method according to claim 1, characterized in that: After taking the point corresponding to the third target point in the three-dimensional point cloud data as a key point having a mapping relationship with the first target point, the three-dimensional point cloud processing method further includes: The first target point is replaced with a key point in the three-dimensional point cloud data to obtain an updated first target point, and any one of the following operations is performed: A first operation is used to perform point cloud registration on the three-dimensional point cloud data according to the updated first target point; A second operation is used to perform a neighborhood search on the three-dimensional point cloud data according to the updated first target point; A third operation is used to perform point cloud measurement on the three-dimensional point cloud data according to the updated first target point; The fourth operation is used to perform point cloud classification on the three-dimensional point cloud data according to the updated first target point.

9. A three-dimensional point cloud processing device, characterized in that: include: A first acquisition unit, which acquires three-dimensional point cloud data and a first target point selected in a three-dimensional coordinate system; A first projection unit, projecting the three-dimensional point cloud data into two-dimensional point cloud data and projecting the first target point into a second target point in two-dimensional form according to the coordinate axes of the three-dimensional coordinate system; A first processing unit, taking the point in the two-dimensional point cloud data that is closest to the second target point as a third target point; A second processing unit uses a point corresponding to the third target point in the three-dimensional point cloud data as a key point having a mapping relationship with the first target point; Among them, the first projection unit includes: a first calculation subunit, used to calculate the statistical data of the three-dimensional point cloud data on each coordinate axis of the three-dimensional coordinate system, wherein the statistical data of the three-dimensional point cloud data on each coordinate axis is used to characterize the data change of the three-dimensional point cloud data on the coordinate axis; a first projection subunit, used to project the three-dimensional point cloud data into two-dimensional point cloud data and project the first target point into a second target point according to the statistical data of the three-dimensional point cloud data on each coordinate axis.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the three-dimensional point cloud processing method according to any one of claims 1 to 8.

11. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the three-dimensional point cloud processing method described in any one of claims 1 to 8.

Images