Disconnector data cutting method, device, storage medium and processor

Abstract

The present invention discloses a method, device, storage medium and processor for cutting isolating switch data. The method comprises: obtaining an initial point cloud data set of an isolating switch; filtering and processing the ground data in the initial point cloud data set to obtain a target point cloud data set; segmenting the neighborhood data of the isolating switch data in the target point cloud data set to obtain multiple sub-region data sets of the neighborhood data; determining the feature information of the isolating switch data in the target point cloud data set based on the distance feature information and direction feature information of each data in the multiple sub-region data sets; cutting the target point cloud data set based on the feature information of the isolating switch data to obtain the isolating switch data. The present invention solves the technical problem that the point cloud data of the isolating switch cannot be effectively cut.

Description

Technical Field

[0001] The present invention relates to the technical field of point cloud data processing, and in particular to a method, device, storage medium and processor for cutting isolating switch data. Background Art

[0002] An isolating switch is a device that disconnects the no-load current in a circuit, making an obvious disconnection point between the maintenance equipment and the power supply, which can ensure the personal safety of the maintenance personnel. Since the isolating switch does not have a special arc extinguishing device, and thus cannot cut off the load current and short-circuit current, the isolating switch can only be operated when the circuit breaker is disconnected. In order to more accurately monitor the status of the isolating switch, it is necessary to cut out the point cloud data of the isolating switch from the point cloud data containing the isolating switch for further processing.

[0003] At present, the traditional process of cutting the point cloud data of the isolating switch usually requires people to manually set parameters and filter the point cloud data, which leads to the technical problem that the point cloud data of the isolating switch cannot be effectively cut.

[0004] With respect to the above-mentioned technical problem of being unable to effectively cut the point cloud data of the disconnector, no effective solution has been proposed so far. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, storage medium and processor for cutting isolating switch data, so as to at least solve the technical problem that the point cloud data of the isolating switch cannot be effectively cut.

[0006] According to one aspect of an embodiment of the invention, a method for cutting isolating switch data is provided, and the method may include: obtaining an initial point cloud data set of the isolating switch, wherein the initial point cloud data set includes isolating switch data to be cut out and ground data, the isolating switch data is used to indicate a disconnection point between a maintenance device and a power source in a circuit, and the ground data is used to characterize the point cloud data of the ground; filtering the ground data in the initial point cloud data set to obtain a target point cloud data set; in the target point cloud data set, segmenting the neighborhood data of the isolating switch data to obtain multiple sub-region data sets of the neighborhood data; determining the feature information of the isolating switch data in the target point cloud data set based on the distance feature information and the direction feature information of each data in the multiple sub-region data sets; and cutting the target point cloud data set based on the feature information of the isolating switch data to obtain the isolating switch data.

[0007] Optionally, based on the characteristic information of the isolating switch data, the target point cloud data set is cut to obtain the isolating switch data, including: based on the characteristic information of the isolating switch data, the isolating switch data in the target point cloud data set is labeled to obtain the labeled target point cloud data set; based on the labeled target point cloud data set, the isolating switch data is determined.

[0008] Optionally, in the target point cloud dataset, the neighborhood data of the isolating switch data is segmented to obtain multiple sub-regional datasets of the neighborhood data, including: in the target point cloud dataset, determining the neighborhood data of the isolating switch data; segmenting the neighborhood data to obtain multiple regional datasets of the neighborhood data; segmenting the regional dataset to obtain multiple sub-regional datasets of the neighborhood data.

[0009] Optionally, the regional data set is segmented to obtain multiple sub-regional data sets of neighborhood data, including: determining the location information of the disconnector data in the regional data set; determining the midpoint of the regional data set based on the mean of the location information, wherein the midpoint is used to divide the regional data set into multiple sub-regional data sets; and using the midpoint to divide the regional data set into multiple sub-regional data sets.

[0010] Optionally, the method further includes: determining distance feature information of the sub-region data set based on coordinate information of the sub-region data set.

[0011] Optionally, the method further includes: determining neighborhood data of the isolating switch data in the sub-region data set; determining matrix information of the isolating switch data using the neighborhood data; and determining directional feature information of the sub-region data set based on the matrix information.

[0012] Optionally, based on the matrix information, the directional characteristic information of the sub-region data set is determined, including: determining the characteristic vector of the isolation switch data through the matrix information; averaging the characteristic vectors of multiple isolation switch data to obtain the directional characteristic information of the sub-region data set.

[0013] Optionally, based on the distance feature information and direction feature information of each data in multiple sub-area data sets, the feature information of the isolating switch data in the target point cloud data set is determined, including: fusing the distance feature information and direction feature information of each data in the multiple sub-area data sets to obtain the feature information of the fused isolating switch data; normalizing the feature information of the fused isolating switch data to obtain the feature information of the normalized isolating switch data; and determining the feature information of the normalized isolating switch data as the feature information of the isolating switch data in the target point cloud data set.

[0014] According to one aspect of an embodiment of the present invention, a device for cutting isolating switch data is provided. The device may include: a first acquisition unit, used to acquire an initial point cloud data set of the isolating switch, wherein the initial point cloud data set includes isolating switch data to be cut out and ground data, the isolating switch data is used to indicate a disconnection point between a maintenance device and a power source in a circuit, and the ground data is used to characterize the point cloud data of the ground; a filtering unit, used to filter the ground data in the initial point cloud data set to obtain a target point cloud data set; a segmentation unit, used to segment the neighborhood data of the isolating switch data in the target point cloud data set to obtain multiple sub-region data sets of the neighborhood data; a first determination unit, used to determine the feature information of the isolating switch data in the target point cloud data set based on the distance feature information and direction feature information of each data in the multiple sub-region data sets; a second acquisition unit, used to cut the target point cloud data set based on the feature information of the isolating switch data to obtain the isolating switch data.

[0015] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method in the embodiment of the present invention.

[0016] According to another aspect of an embodiment of the present invention, a processor is provided. The processor is used to run a program, wherein the method in the embodiment of the present invention is executed when the program is run.

[0017] According to another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in the embodiments of the present invention is implemented.

[0018] In an embodiment of the present invention, an initial point cloud data set of an isolating switch is obtained, wherein the initial point cloud data set includes isolating switch data to be cut out and ground data, the isolating switch data is used to indicate a disconnection point between a maintenance device and a power source in a circuit, and the ground data is used to characterize ground point cloud data; the ground data in the initial point cloud data set is filtered to obtain a target point cloud data set; in the target point cloud data set, the neighborhood data of the isolating switch data is segmented to obtain multiple sub-region data sets of the neighborhood data; based on the distance feature information and direction feature information of each data in the multiple sub-region data sets, the feature information of the isolating switch data in the target point cloud data set is determined; based on the feature information of the isolating switch data, the target point cloud data set is cut to obtain the isolating switch data. That is to say, the embodiment of the present invention can first obtain the initial point cloud data set of the isolating switch, and then filter the ground data in the initial point cloud data set to achieve the purpose of obtaining the target point cloud data set. In the target point cloud data set obtained above, the neighborhood data of the isolating switch data can be segmented to obtain multiple sub-region data sets of the neighborhood data. Then, according to the distance feature information and direction feature information of each data in the multiple sub-region data sets, the feature information of the isolating switch data in the target point cloud data set can be determined. Finally, according to the feature information of the isolating switch data, the target point cloud data set is cut to obtain the isolating switch data, thereby solving the technical problem that the point cloud data of the isolating switch cannot be effectively cut, and achieving the technical effect of effectively cutting the point cloud data of the isolating switch. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1 is a flow chart of a method for cutting isolating switch data according to an embodiment of the present invention;

[0021] Figure 2 is a flow chart of cutting point cloud data of an isolating switch according to an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of dividing a neighborhood into regions according to an embodiment of the present invention;

[0023] Figure 4 is a schematic diagram of dividing a region into sub-regions according to an embodiment of the present invention;

[0024] Figure 5 Schematic diagram of a device for cutting isolating switch data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable people in the technical field to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Example 1

[0028] According to an embodiment of the present invention, a method for cutting isolating switch data is provided. It should be noted that in the flowchart of the accompanying drawings, the steps shown therein 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.

[0029] The following is an introduction to the disconnector data cutting method according to an embodiment of the present invention.

[0030] Figure 1 is a flow chart of a method for cutting isolating switch data according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0031] Step S101, obtaining an initial point cloud data set of the disconnector.

[0032] In the technical solution provided in the above step S101 of the present invention, the initial point cloud data set of the disconnector can be obtained by laser radar. The initial point cloud data set includes the disconnector data to be cut out and the ground data, the disconnector data is used to represent the disconnection point between the maintenance equipment and the power supply in the circuit, and the ground data is used to represent the point cloud data of the ground.

[0033] Optionally, an initial point cloud data set of the isolating switch and the annotated point cloud data of the isolating switch are obtained. The annotated point cloud data of the isolating switch can be obtained by manual annotation. For example, a frame of point cloud data containing the isolating switch can be selected and the point cloud data of the isolating switch can be manually annotated to achieve the purpose of obtaining the annotated point cloud data of the isolating switch.

[0034] Optionally, the isolating switch data may be isolating switch point data, and the isolating switch data data set may be composed of data of multiple isolating switch points, and the isolating switch data data set may be called isolating switch point cloud data. The initial point cloud data set may be called a point cloud data set containing an isolating switch to be cut. For example, a point cloud data set containing an isolating switch to be cut may be constructed.

[0035] Optionally, based on a target scene, an initial point cloud data set is obtained using a laser radar, wherein the target scene is used to characterize a scene containing an isolating switch.

[0036] It should be noted that this is only a preferred implementation method for obtaining the initial point cloud dataset of the disconnector, and does not specifically limit the process and method for obtaining the initial point cloud dataset of the disconnector.

[0037] For example, a laser radar is used in a high-voltage substation. The laser radar emits a laser beam to a scene containing a disconnector, and returns point cloud data containing the disconnector. This process can be repeated many times to obtain multiple frames of point cloud data, thereby forming a point cloud data set containing the disconnector to be cut. Select any frame of point cloud data containing a disconnector, and manually mark the point cloud data of the disconnector to achieve the purpose of obtaining the marked point cloud data of the disconnector.

[0038] Step S102 , filtering the ground data in the initial point cloud data set to obtain a target point cloud data set.

[0039] In the technical solution provided in the above step S102 of the present invention, after obtaining the initial point cloud data set of the disconnector, the ground data in the initial point cloud data set can be filtered to obtain the target point cloud data set, wherein the target point cloud data set can be a new point cloud data set containing the disconnector to be cut.

[0040] Optionally, the ground data in the initial point cloud data set is filtered by an iterative algorithm to obtain a target point cloud data set. For example, the ground point cloud data is filtered by an iterative algorithm (RANSAC algorithm) to obtain a new point cloud data set containing a disconnector to be cut.

[0041] Step S103: segmenting the neighborhood data of the disconnector data in the target point cloud data set to obtain a plurality of sub-region data sets of the neighborhood data.

[0042] In the technical solution provided in the above step S103 of the present invention, after obtaining the target point cloud data set, the neighborhood data of the disconnector data can be segmented in the target point cloud data set to achieve the purpose of obtaining multiple sub-region data sets of the neighborhood data. For example, eight sub-region data sets can be obtained.

[0043] Optionally, the neighborhood data of the isolating switch data may be referred to as the neighborhood of the isolating switch point. The sub-region data set may be referred to as the sub-region. Here, only examples are given for representing the neighborhood data and the sub-region data set, and no specific limitation is given to the representation of the neighborhood data and the sub-region data set.

[0044] Step S104: determining feature information of the disconnector data in the target point cloud data set based on the distance feature information and direction feature information of each data in the plurality of sub-region data sets.

[0045] In the technical solution provided in the above step S104 of the present invention, based on the multiple sub-region data sets obtained in step S103, the characteristic information of the isolating switch data in the target point cloud data set can be determined according to the distance characteristic information and direction characteristic information of each data in the multiple sub-region data sets. The characteristic information of the isolating switch data can be referred to as the characteristic information of the isolating switch point.

[0046] Step S105 , based on the characteristic information of the disconnector data, the target point cloud data set is cut to obtain the disconnector data.

[0047] In the technical solution provided by the above step S105 of the present invention, the target point cloud data set can be cut according to the characteristic information of the disconnector data obtained in step S104 to obtain the disconnector data. For example, after cutting the target point cloud data set, point cloud data representing the disconnector can be obtained, thereby completing the automatic cutting of the point cloud data of the disconnector.

[0048] Optionally, based on the marked point cloud data of the disconnector and the feature information of the disconnector data, the target point cloud data set is cut to obtain the disconnector data.

[0049] It should be noted that this is only a preferred implementation method for determining the isolating switch data based on the characteristic information of the isolating switch data, and does not specifically limit the process and method for determining the isolating switch data based on the characteristic information of the isolating switch data. As long as the process and method for obtaining the isolating switch data are obtained through the characteristic information of the isolating switch data, they are within the protection scope of the present invention and are not listed one by one here.

[0050] In the above steps S101 to S105 of the present invention, an initial point cloud data set of the isolating switch can be first obtained, and then the ground data in the initial point cloud data set can be filtered to obtain the target point cloud data set. In the target point cloud data set obtained above, the neighborhood data of the isolating switch data can be segmented to obtain multiple sub-region data sets of the neighborhood data. Then, the characteristic information of the isolating switch data in the target point cloud data set can be determined based on the distance feature information and direction feature information of each data in the multiple sub-region data sets. Finally, based on the characteristic information of the isolating switch data, the target point cloud data set can be cut to obtain the isolating switch data, thereby solving the technical problem that the point cloud data of the isolating switch cannot be effectively cut, and achieving the technical effect that the point cloud data of the isolating switch can be effectively cut.

[0051] The above method of this embodiment is further introduced below.

[0052] As an optional implementation method, step S105, based on the characteristic information of the isolating switch data, cuts the target point cloud data set to obtain the isolating switch data, including: based on the characteristic information of the isolating switch data, annotates the isolating switch data in the target point cloud data set to obtain the annotated target point cloud data set; based on the annotated target point cloud data set, determines the isolating switch data.

[0053] In this embodiment, the isolating switch data in the target point cloud data set may be labeled according to the characteristic information of the isolating switch data to obtain a labeled target point cloud data set, and then the isolating switch data may be determined according to the labeled target point cloud data set.

[0054] Optionally, based on the feature information of each data in the target point cloud data set and the feature information of each data of the marked points in the point cloud data of the marked disconnector, the disconnector data in the target point cloud data set are labeled; in the labeled target point cloud data set, the labeled disconnector data are extracted to obtain the disconnector data.

[0055] Optionally, the disconnector data in the target point cloud data set are labeled based on the feature information of each data in the target point cloud data set and the related information and distance information between the feature information of each data of the labeled points in the point cloud data of the labeled disconnector. The related information is used to characterize the degree of correlation between the two feature information, which can be represented by ρ. The distance information is used to characterize the distance between the two feature information, which can be represented by γ.

[0056] For example, the feature information of the marked points in the point cloud data of the marked disconnector can be set as S n =(s1, s2, ..., s 256 ), the feature information of the points in the point cloud data containing the disconnector to be cut is R m =(r1, r2, ..., r 256 ). Wherein, n and m are used to represent the number of annotated points in the point cloud data of the annotated disconnector and the number of points in the point cloud data containing the disconnector to be cut, respectively.

[0057] Further, in the point cloud data containing the disconnector to be cut, according to the correlation ρ and distance γ between the feature information of each point and the feature information of each point marked in the point cloud data of the marked disconnector, when ρ>ρ0 and γ<γ0 (ρ0 and γ0 need to be adjusted by the automatic cutting effect, and ρ0=0.9 and γ0=0.1 can be preliminarily set), the points in the corresponding point cloud data containing the disconnector to be cut can be marked, and then the points marked in the above process can be extracted from the point cloud data containing the disconnector to be cut, so as to obtain the point cloud data representing the disconnector, thereby completing the automatic cutting of the point cloud data of the disconnector. Among them, the above-mentioned correlation and distance can be expressed by the following formula:

[0058]

[0059]

[0060] in, are all expressed as mean values, that is,

[0061] As an optional implementation method, in the target point cloud dataset, the neighborhood data of the isolating switch data is segmented to obtain multiple sub-regional datasets of the neighborhood data, including: in the target point cloud dataset, determining the neighborhood data of the isolating switch data; segmenting the neighborhood data to obtain multiple regional datasets of the neighborhood data; segmenting the regional dataset to obtain multiple sub-regional datasets of the neighborhood data.

[0062] In this embodiment, the neighborhood data of the isolating switch data can be first determined in the target point cloud data set, and then the neighborhood data obtained above can be segmented to obtain multiple regional data sets of the neighborhood data, and finally the regional data set can be segmented to obtain multiple sub-regional data sets of the neighborhood data. Among them, the neighborhood data of the isolating switch data can be called the neighborhood data of the isolating switch point, which can be referred to as the neighborhood of the point, and the regional data set can be referred to as the region.

[0063] Optionally, in the target point cloud dataset, set the neighborhood data of the disconnector data. For example, let the target point cloud dataset be A = {a1, a2,..., a N}, where a i is the vector form of the points in the target point cloud dataset, (x, y, z) are the three-dimensional coordinates of a i , and N is the number of points. For each point a i , assume there is a neighborhood N i = {a j |d(a i , a j ) < r}, where d(·) is the distance function between two points, and r is the radius of the neighborhood (this radius should be less than the distance between disconnector points).

[0064] As an alternative embodiment, segment the regional dataset to obtain multiple sub-regional datasets of the neighborhood data, including: in the regional dataset, determine the position information of the disconnector data; based on the mean of the position information, determine the midpoint of the regional dataset, where the midpoint is used to divide the regional dataset into multiple sub-regional datasets; use the midpoint to divide the regional dataset into multiple sub-regional datasets.

[0065] In this embodiment, in the regional dataset, the position information of the disconnector data can be determined, and then based on the mean of the position information, the midpoint of the regional dataset can be determined, and the regional dataset can be divided into multiple sub-regional datasets using the midpoint. Among them, the position information can be used to represent the three-dimensional coordinates of the disconnector data, such as the x-axis, y-axis, z-axis, etc. The midpoint can be represented by B.

[0066] Optionally, in the regional dataset, determine the position information of each data in the neighborhood data of the disconnector data. Based on the mean of the above position information, the midpoint in the neighborhood data can be determined, and based on the above midpoint, the regional dataset can be divided into multiple sub-regional datasets.

[0067] For example,[[]] Figure 3 is a schematic diagram of dividing a neighborhood into regions according to an embodiment of the present invention. As Figure 3 shown, according to the point a i assumed above, the neighborhood of the point a i is divided into eight regions of the same size along the x-axis, y-axis, and z-axis. In each region, the midpoint B is obtained by finding the mean of the coordinates of the points in the region. Among them, the midpoint B can be represented by the following formula:

[0068]

[0069]

[0070]

[0071] Among them, x0, y0, and z0 represent the x, y, and z coordinates of the middle point B, respectively. k ,y k 、z k They represent the x, y, and z coordinates of all points in the region (k=1, 2, ..., n), and n is the number of points in the region.

[0072] For example, Figure 4 is a schematic diagram of dividing a region into sub-regions according to an embodiment of the present invention, such as Figure 4 As shown, the region can be divided into eight sub-regions along the x-axis, y-axis, and z-axis with the middle point as the origin.

[0073] As an optional implementation manner, the method further includes: determining distance feature information of the sub-region data set based on coordinate information of the sub-region data set.

[0074] In this embodiment, the distance feature information of the sub-region dataset can be determined according to the coordinate information of the sub-region dataset, or the distance feature information of each sub-region dataset can be determined according to the coordinate information of the sub-region dataset.

[0075] Optionally, the distance feature information can be expressed by the following formula:

[0076]

[0077] Among them, x j ,y j 、z j They respectively represent the x, y, and z coordinates of all points in the sub-region (j=1, 2, ..., m), m is the number of points in the sub-region, and x0, y0, and z0 respectively represent the x, y, and z coordinates of the middle point B of the sub-region.

[0078] As an optional implementation mode, the method also includes: determining neighborhood data of the isolation switch data in the sub-region data set; determining matrix information of the isolation switch data using the neighborhood data; and determining directional feature information of the sub-region data set based on the matrix information.

[0079] In this embodiment, the neighborhood data of the isolation switch data can be determined in the sub-region data set, and then the matrix information of the isolation switch data can be determined based on the neighborhood data obtained above, and finally the purpose of determining the directional characteristic information of the sub-region data set can be achieved based on the matrix information.

[0080] Optionally, neighborhood data of each data in the sub-region data set is determined, and then matrix information of each data is determined using the neighborhood data, and directional feature information of the sub-region data set is determined based on the matrix information.

[0081] Optionally, the amount of data in the neighborhood data may be a preset value, for example, the number of points in the neighborhood may be set to k. The matrix information may be represented by a covariance matrix, and the covariance matrix may be represented by the following formula:

[0082]

[0083] Among them, C j represents the covariance matrix of the points in the sub-region, p i is the coordinates of the points in the neighborhood of the point (x i ,y i , z i ), (i=1, 2,...,k; j=1, 2,...,m), is the average coordinate of all points in the neighborhood of the point (including itself), and m is the number of points in the sub-region.

[0084] As an optional implementation method, based on matrix information, directional characteristic information of the sub-region data set is determined, including: determining the characteristic vector of the isolation switch data through the matrix information; averaging the characteristic vectors of multiple isolation switch data to obtain the directional characteristic information of the sub-region data set.

[0085] In this embodiment, the characteristic vector of the isolating switch data can be determined through the matrix information, and then the characteristic vectors of multiple isolating switch data can be averaged to obtain the directional characteristic information of the sub-region data set.

[0086] Optionally, the characteristic vector of each data in the sub-region data set is determined through the matrix information, and then the characteristic vector of each data in the sub-region data set is averaged to obtain the directional characteristic information of the sub-region data set.

[0087] Optionally, the matrix information is used to generate normal information, and based on the normal information, the characteristic vector of the disconnector data is determined. The normal information can be obtained through the matrix information.

[0088] Optionally, the matrix information is used to generate normal information; based on the normal information, the characteristic vector of each data in the sub-region data set is determined.

[0089] For example, the normal information is obtained by eigenvalue decomposition of the covariance matrix. The eigenvalues ​​can be represented by λ1, λ2 and λ3. The eigenvectors can be represented by v1, v2, and v3. Assuming that the eigenvalues ​​λ1≥λ2≥λ3, the corresponding eigenvectors are v1, v2, and v3 respectively. Then the normal direction (n) can be calculated by selecting the eigenvector corresponding to the minimum eigenvalue, that is, n=v3. By averaging the eigenvectors obtained for each point, the directional characteristics of the sub-region can be obtained.

[0090] As an optional implementation method, based on the distance feature information and direction feature information of each data in multiple sub-area data sets, the feature information of the isolating switch data in the target point cloud data set is determined, including: fusing the distance feature information and direction feature information of each data in the multiple sub-area data sets to obtain the feature information of the fused isolating switch data; normalizing the feature information of the fused isolating switch data to obtain the feature information of the normalized isolating switch data; and determining the feature information of the normalized isolating switch data as the feature information of the isolating switch data in the target point cloud data set.

[0091] In this embodiment, the distance feature information and direction feature information of each data in the multiple sub-region data sets can be fused to obtain the feature information of the fused isolating switch data, and then the feature information of the fused isolating switch data can be normalized to obtain the feature information of the normalized isolating switch data. Finally, the feature information of the normalized isolating switch data can be determined as the feature information of the isolating switch data in the target point cloud data set. The normalization process can be performed by a normalization operation. The feature information of the isolating switch data can be referred to as the feature information of the isolating switch point.

[0092] For example, since the directional feature is three-dimensional, the feature information of the sub-region includes one distance feature information and three directional feature information, a total of four pieces of information. i The neighborhood of is divided into eight regions, each region is divided into eight sub-regions, each sub-region has 4 information, a total of 256 information, and then point a can be obtained i Feature information: G i =(F1, F2, ..., F 256 ), through normalization operation, we get the normalized point a i Feature information: L i =(Q1, Q2, ..., Q 256 ),in,

[0093] In this embodiment, the initial point cloud data set of the isolating switch can be obtained first, and then the ground data in the initial point cloud data set can be filtered to achieve the purpose of obtaining the target point cloud data set. At the same time, any frame of point cloud data containing the isolating switch is selected, and the point cloud data of the isolating switch is manually marked to achieve the purpose of obtaining the marked point cloud data of the isolating switch. In the target point cloud data set obtained above, the neighborhood data of the isolating switch data can be segmented to obtain multiple sub-region data sets of the neighborhood data. Then, according to the distance feature information and direction feature information of each data in the multiple sub-region data sets, the feature information of the isolating switch data in the target point cloud data set can be determined. Finally, according to the feature information of the isolating switch data, the target point cloud data set is cut to obtain the isolating switch data, thereby solving the technical problem of not being able to effectively cut the point cloud data of the isolating switch and achieving the technical effect of effectively cutting the point cloud data of the isolating switch.

[0094] Example 2

[0095] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0096] An isolating switch is a device that disconnects the no-load current circuit, making a clear disconnection point between the maintenance equipment and the power supply, which can ensure the personal safety of the maintenance personnel. Since the isolating switch does not have a special arc extinguishing device, it cannot cut off the load current and short-circuit current, so the isolating switch can only be operated when the circuit breaker is disconnected.

[0097] In a substation, a laser radar is used to emit a laser beam to a power grid operation area (such as a substation, etc.) containing a disconnector, and point cloud data containing the disconnector can be obtained. In order to more accurately monitor the status of the disconnector, it is necessary to cut out the point cloud data of the disconnector from the point cloud data containing the disconnector for further processing. Among them, the laser radar is a sensor that can use a laser beam to measure the distance and shape of the surrounding environment. It obtains distance information by emitting a laser beam and recording the time and intensity of its reflection back from the target object. The collection of these data points is called point cloud data, which is a collection of a large number of three-dimensional points. The collection can be used to describe the position and shape of the object scanned by the laser radar in space.

[0098] The traditional process of cutting the point cloud data of the isolating switch usually requires people to manually set parameters and filter the point cloud data, which leads to the technical problem that the point cloud data of the isolating switch cannot be effectively cut.

[0099] Therefore, in order to solve the above problems, the present invention provides a method for cutting isolating switch data, which can first obtain an initial point cloud data set of the isolating switch, and then filter the ground data in the initial point cloud data set to achieve the purpose of obtaining a target point cloud data set. In the target point cloud data set obtained above, the neighborhood data of the isolating switch data can be segmented to obtain multiple sub-region data sets of the neighborhood data, and then the characteristic information of the isolating switch data in the target point cloud data set can be determined according to the distance feature information and direction feature information of each data in the multiple sub-region data sets. Finally, according to the characteristic information of the isolating switch data, the target point cloud data set is cut to obtain the isolating switch data, thereby solving the technical problem of being unable to effectively cut the point cloud data of the isolating switch and achieving the technical effect of effectively cutting the point cloud data of the isolating switch.

[0100] Figure 2 is a flow chart of cutting point cloud data of an isolating switch according to an embodiment of the present invention, such as Figure 2 As shown, the flowchart mainly includes the following steps:

[0101] Step S201, constructing a point cloud data set containing a disconnector to be cut.

[0102] In this embodiment, a point cloud data set containing a disconnector to be cut can be constructed. For example, a laser radar is used in a high-voltage substation. The laser radar emits a laser beam to a scene containing a disconnector, and returns point cloud data containing the disconnector. This process can be repeated many times to obtain multiple frames of point cloud data, thereby forming a point cloud data set containing a disconnector to be cut. Select any frame of point cloud data containing a disconnector, and manually cut out the point cloud data of the disconnector to achieve the purpose of obtaining the marked point cloud data of the disconnector.

[0103] Step S202: pre-processing the data in the point cloud data set.

[0104] In this embodiment, the data in the point cloud data set may be preprocessed, for example, using an iterative algorithm (RANSAC algorithm) to filter out the point cloud data on the ground, and after filtering, a new point cloud data set containing the disconnector to be cut may be obtained.

[0105] Step S203: extracting feature information of points in the point cloud data.

[0106] In this embodiment, feature information of points is obtained for each frame of point cloud data in the point cloud data set containing the isolating switch and the point cloud data set to be cut.

[0107] Step S2031, setting the neighborhood of the point.

[0108] In this embodiment, let the target point cloud data set be A = {a1, a2,..., a N}, where a i is the vector form of the points in the target point cloud data set, (x, y, z) are the three-dimensional coordinates of a i , and N is the number of points. For each point a i , assume there is a neighborhood N i = {a j | d(a i , a j ) < r}, where d(·) is the distance function between two points, and r is the radius of the neighborhood (this radius should be less than the distance between the disconnector points).

[0109] Step S2032, divide the neighborhood of the point.

[0110] In this embodiment, the neighborhood of the point can be divided. For example, as Figure 3 shown, divide the neighborhood of point a i into eight regions of the same size along the x-axis, y-axis, and z-axis. In each region, by calculating the mean value of the coordinates of the points in this region, the middle point B is obtained. Among them, the middle point B can be represented by the following formula:

[0111]

[0112]

[0113]

[0114] where x0, y0, z0 respectively represent the x, y, z coordinates of the middle point B, and x k , y k , z k respectively represent the x, y, z coordinates of all points in this region (k = 1, 2,..., n), and n is the number of points in this region.

[0115] Taking another example, Figure 4 is a schematic diagram of dividing a region into sub-regions. As Figure 4 shown, this region can be divided into eight sub-regions with the middle point as the origin along the x-axis, y-axis, and z-axis.

[0116] Step S2033, obtain the feature information of the points in the point cloud data.

[0117] In this embodiment, the feature information of the points in the point cloud data can be obtained.

[0118] Optionally, the distance feature information and the direction feature information of each sub-region are first obtained, and then the feature information of the points in the point cloud data is obtained, wherein the distance feature information can be expressed by the following formula:

[0119]

[0120] Among them, x j ,y j 、z j They respectively represent the x, y, and z coordinates of all points in the sub-region (j=1, 2, ..., m), m is the number of points in the sub-region, and x0, y0, and z0 respectively represent the x, y, and z coordinates of the middle point B of the sub-region.

[0121] Optionally, the step of obtaining the directional feature information is as follows: the number of points in the neighborhood can be set to k, and then the covariance matrix is ​​calculated. The covariance matrix can be expressed by the following formula:

[0122]

[0123] Among them, C j represents the covariance matrix of the points in the sub-region, p i is the coordinates of the points in the neighborhood of the point (x i ,y i , z i ), (i=1, 2,...,k; j=1, 2,...,m), is the coordinate average of all points in the neighborhood of the point (including itself), and m is the number of points in the sub-region. The normal information is obtained by eigenvalue decomposition of the covariance matrix. Among them, the eigenvalues ​​can be represented by λ1, λ2 and λ3. The eigenvectors can be represented by v1, v2, v3. Assuming that the eigenvalue λ1≥λ2≥λ3, the corresponding eigenvectors are v1, v2, v3 respectively. Then the normal direction (n) can be calculated by selecting the eigenvector corresponding to the minimum eigenvalue, that is, n=v3. By averaging the eigenvectors obtained for each point, the directional characteristics of the sub-region can be obtained.

[0124] Optionally, since the directional feature is three-dimensional, the feature information of the sub-region includes one distance feature information and three directional feature information, a total of four pieces of information. i The neighborhood of is divided into eight regions, each region is divided into eight sub-regions, each sub-region has 4 information, a total of 256 information, and then point a can be obtained i Feature information: G i =(F1, F2, ..., F 256 ), through normalization operation, we get the normalized point a i Feature information: L i=(Q1, Q2, ..., Q 256 ),in,

[0125] Step S204: marking points representing the disconnector in the point cloud data to be cut that includes the disconnector.

[0126] In this embodiment, the characteristic information of the marked points in the point cloud data of the marked disconnector can be set as S n =(s1, s2, ..., s 256 ), the feature information of the points in the point cloud data containing the disconnector to be cut is R m =(r1, r2, ..., r 256 ). Wherein, n and m are respectively the number of annotated points in the point cloud data of the annotated disconnector and the number of points in the point cloud data containing the disconnector to be cut.

[0127] Optionally, in the point cloud data containing the disconnector to be cut, according to the correlation ρ and distance γ between the feature information of each point and the feature information of each point marked in the point cloud data of the marked disconnector, when ρ>ρ0 and γ<γ0 (ρ0 and γ0 need to be adjusted by the automatic cutting effect, and ρ0=0.9 and γ0=0.1 can be preliminarily set), the points in the corresponding point cloud data containing the disconnector to be cut can be marked, and then the points marked in the above process can be extracted from the point cloud data containing the disconnector to be cut, so as to obtain the point cloud data representing the disconnector, thereby completing the automatic cutting of the point cloud data of the disconnector. Among them, the above-mentioned correlation and distance can be expressed by the following formula:

[0128]

[0129]

[0130] in, are all expressed as mean values, that is,

[0131] Step S205, cutting out point cloud data representing the disconnector.

[0132] In this embodiment, the points marked in step S204 are extracted from the point cloud data containing the isolating switch to be cut, and the point cloud data representing the isolating switch is obtained, thereby completing the automatic cutting of the isolating switch point cloud data.

[0133] In this embodiment, the initial point cloud data set of the isolating switch can be obtained first, and then the ground data in the initial point cloud data set can be filtered to achieve the purpose of obtaining the target point cloud data set. In the target point cloud data set obtained above, the neighborhood data of the isolating switch data can be segmented to obtain multiple sub-region data sets of the neighborhood data. Then, based on the distance feature information and direction feature information of each data in the multiple sub-region data sets, the feature information of the isolating switch data in the target point cloud data set can be determined. Finally, based on the feature information of the isolating switch data, the target point cloud data set can be cut to obtain the isolating switch data, thereby solving the technical problem of being unable to effectively cut the point cloud data of the isolating switch and achieving the technical effect of effectively cutting the point cloud data of the isolating switch.

[0134] Example 3

[0135] According to an embodiment of the present invention, a device for cutting isolating switch data is provided. It should be noted that the device for cutting isolating switch data can be used to execute an isolating switch data cutting method in embodiment 1.

[0136] Figure 5 Schematic diagram of a device for cutting isolating switch data according to an embodiment of the present invention. Figure 5 As shown, a device 500 for cutting isolating switch data may include: a first acquiring unit 501 , a filtering unit 502 , a segmenting unit 503 , a first determining unit 504 and a second acquiring unit 505 .

[0137] The first acquisition unit 501 is used to acquire an initial point cloud data set of the disconnector, wherein the initial point cloud data set includes disconnector data to be cut out and ground data, the disconnector data is used to represent the disconnection point between the maintenance equipment and the power supply in the circuit, and the ground data is used to represent the point cloud data of the ground.

[0138] The filtering unit 502 is used to filter the ground data in the initial point cloud data set to obtain a target point cloud data set.

[0139] The segmentation unit 503 is used to segment the neighborhood data of the disconnector data in the target point cloud data set to obtain a plurality of sub-region data sets of the neighborhood data.

[0140] The first determining unit 504 is used to determine the characteristic information of the disconnector data in the target point cloud data set based on the distance characteristic information and the direction characteristic information of each data in the multiple sub-region data sets.

[0141] The second acquisition unit 505 is used to cut the target point cloud data set based on the feature information of the disconnector data to obtain the disconnector data.

[0142] Optionally, the second acquisition unit 505 includes: a first acquisition module, used to label the isolating switch data in the target point cloud data set based on the feature information of the isolating switch data to obtain the labeled target point cloud data set; a first determination module, used to determine the isolating switch data based on the labeled target point cloud data set.

[0143] Optionally, the segmentation unit 503 may include: a second determination module, used to determine the neighborhood data of the disconnector data in the target point cloud data set; a first segmentation module, used to segment the neighborhood data to obtain multiple regional data sets of the neighborhood data; and a second segmentation module, used to segment the regional data set to obtain multiple sub-regional data sets of the neighborhood data.

[0144] Optionally, the second segmentation module may include: a first determination submodule, used to determine the location information of the disconnector data in the regional data set; a second determination submodule, used to determine the midpoint of the regional data set based on the mean of the location information, wherein the midpoint is used to divide the regional data set into multiple sub-regional data sets; and a division submodule, used to divide the regional data set into multiple sub-regional data sets using the midpoint.

[0145] Optionally, the device may further include: a second determining unit, configured to determine distance feature information of the sub-region data set based on coordinate information of the sub-region data set.

[0146] Optionally, the device may also include: a third determination unit, used to determine the neighborhood data of the isolation switch data in the sub-area data set; a fourth determination unit, used to determine the matrix information of the isolation switch data using the neighborhood data; and a fifth determination unit, used to determine the directional feature information of the sub-area data set based on the matrix information.

[0147] Optionally, the fifth determination unit may further include: a third determination module, used to determine the characteristic vector of the isolation switch data through matrix information; a second acquisition module, used to average the characteristic vectors of multiple isolation switch data to obtain the directional characteristic information of the sub-region data set.

[0148] Optionally, the first determination unit 504 may also include: a fusion module, used to fuse the distance feature information and direction feature information of each data in multiple sub-area data sets to obtain the feature information of the fused isolating switch data; a processing module, used to normalize the feature information of the fused isolating switch data to obtain the feature information of the normalized isolating switch data; a fourth determination module, used to determine the feature information of the normalized isolating switch data as the feature information of the isolating switch data in the target point cloud data set.

[0149] In this embodiment, an initial point cloud data set of the isolating switch is acquired by a first acquisition unit, wherein the initial point cloud data set includes isolating switch data to be cut out and ground data, the isolating switch data is used to indicate a disconnection point between the maintenance equipment and the power supply in the circuit, and the ground data is used to characterize the point cloud data of the ground; the ground data in the initial point cloud data set is filtered by a filtering unit to obtain a target point cloud data set; the neighborhood data of the isolating switch data is segmented in the target point cloud data set by a segmentation unit to obtain a plurality of sub-region data sets of the neighborhood data; the feature information of the isolating switch data in the target point cloud data set is determined by a first determination unit based on the distance feature information and direction feature information of each data in the plurality of sub-region data sets; the target point cloud data set is segmented by a second acquisition unit based on the feature information of the isolating switch data to obtain the isolating switch data, thereby solving the technical problem that the point cloud data of the isolating switch cannot be effectively cut, and achieving the technical effect that the point cloud data of the isolating switch can be effectively cut.

[0150] Example 4

[0151] According to an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored program, wherein when the program is executed by a processor, the device where the computer-readable storage medium is located is controlled to execute the isolating switch data cutting method in Example 1.

[0152] Example 5

[0153] According to an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein the isolating switch data cutting method in embodiment 1 is executed when the program is run.

[0154] Example 6

[0155] According to an embodiment of the present invention, a computer program product is further provided, including a computer program, and when the computer program is executed by a processor, the disconnector data cutting method in Embodiment 1 of the present invention is implemented.

[0156] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0157] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0158] In the several embodiments provided by the present invention, 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 units can be a logical function division, and there can be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, 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.

[0159] 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 over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0160] In addition, each functional unit in each embodiment of the present invention 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.

[0161] 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 invention, 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 for 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 methods of each embodiment of the present invention. 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.

[0162] The above are only preferred embodiments of the present invention. It should be pointed out that ordinary technicians in this technical field can make several improvements and modifications without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for cutting isolating switch data, characterized in that: include: Acquire an initial point cloud data set of the disconnector, wherein the initial point cloud data set includes disconnector data to be cut out and ground data, the disconnector data is used to represent a disconnection point between the maintenance equipment and the power supply in the circuit, and the ground data is used to represent point cloud data of the ground; Filtering the ground data in the initial point cloud data set to obtain a target point cloud data set; In the target point cloud data set, segmenting the neighborhood data of the isolating switch data to obtain a plurality of sub-region data sets of the neighborhood data; Determine the characteristic information of the isolating switch data in the target point cloud data set based on the distance characteristic information and the direction characteristic information of each data in the plurality of sub-region data sets; Based on the characteristic information of the isolating switch data, the target point cloud data set is cut to obtain the isolating switch data; Wherein, in the target point cloud data set, the neighborhood data of the isolating switch data are segmented to obtain a plurality of sub-regional data sets of the neighborhood data, including: determining the neighborhood data of the isolating switch data in the target point cloud data set; segmenting the neighborhood data to obtain a plurality of regional data sets of the neighborhood data; segmenting the regional data set to obtain a plurality of sub-regional data sets of the neighborhood data; Segmenting the regional data set to obtain a plurality of sub-regional data sets of the neighborhood data, comprising: determining the location information of the disconnector data in the regional data set; determining the middle point of the regional data set based on the mean value of the location information, wherein the middle point is used to divide the regional data set into a plurality of the sub-regional data sets; and using the middle point to divide the regional data set into a plurality of the sub-regional data sets; The method further includes: determining the distance feature information of the sub-region data set based on the coordinate information of the sub-region data set; the method further includes: determining the neighborhood data of the isolating switch data in the sub-region data set; determining the matrix information of the isolating switch data using the neighborhood data; and determining the direction feature information of the sub-region data set based on the matrix information, wherein the matrix information is used to be expressed by the following formula: In the above formula, C j The covariance matrix of the points in the sub-region of the sub-region dataset, p i The coordinates (x) of the points in the neighborhood of the points in the sub-region are used to represent i ,y i ,z i ), (i=1,2,…,k; j=1,2,…,m), is used to represent the average coordinates of all points in the neighborhood of the point in the sub-region, m is used to represent the number of points in the sub-region, and k is used to represent the number of points in the neighborhood; Based on the distance feature information and direction feature information of each data in the plurality of sub-region data sets, determining the feature information of the isolating switch data in the target point cloud data set includes: fusing the distance feature information and direction feature information of each data in the plurality of sub-region data sets to obtain the fused feature information of the isolating switch data; normalizing the fused feature information of the isolating switch data to obtain the normalized feature information of the isolating switch data; determining the normalized feature information of the isolating switch data as the feature information of the isolating switch data in the target point cloud data set, wherein the distance feature information is used to be represented by the following formula: In the above formula, x j ,y j 、z j They are used to represent the x, y, and z coordinates (j=1, 2, ..., m) of all points in the sub-region, and x0, y0, and z0 are used to represent the x, y, and z coordinates of the middle point in the sub-region.

2. The method according to claim 1, characterized in that Based on the characteristic information of the isolating switch data, the target point cloud data set is cut to obtain the isolating switch data, including: Based on the feature information of the isolating switch data, the isolating switch data in the target point cloud data set are labeled to obtain the labeled target point cloud data set; The isolating switch data is determined based on the labeled target point cloud data set.

3. The method according to claim 1, characterized in that Determining directional feature information of the sub-region data set based on the matrix information includes: Determine the characteristic vector of the isolating switch data by using the matrix information; The characteristic vectors of the plurality of isolating switch data are averaged to obtain the directional characteristic information of the sub-region data set.

4. A device for cutting isolating switch data, characterized in that: include: A first acquisition unit is used to acquire an initial point cloud data set of the disconnector, wherein the initial point cloud data set includes disconnector data to be cut out and ground data, the disconnector data is used to represent a disconnection point between the maintenance equipment and the power supply in the circuit, and the ground data is used to represent point cloud data of the ground; A filtering unit, configured to filter the ground data in the initial point cloud data set to obtain a target point cloud data set; A segmentation unit, used for segmenting the neighborhood data of the disconnector data in the target point cloud data set to obtain a plurality of sub-region data sets of the neighborhood data; A first determining unit, configured to determine feature information of the disconnector data in the target point cloud data set based on distance feature information and direction feature information of each data in the plurality of sub-region data sets; A second acquisition unit, configured to cut the target point cloud data set based on the feature information of the disconnector data to obtain the disconnector data; The segmentation unit is further used to segment the neighborhood data of the isolating switch data in the target point cloud data set to obtain a plurality of sub-regional data sets of the neighborhood data by the following steps: determining the neighborhood data of the isolating switch data in the target point cloud data set; segmenting the neighborhood data to obtain a plurality of regional data sets of the neighborhood data; segmenting the regional data set to obtain a plurality of sub-regional data sets of the neighborhood data; Segmenting the regional data set to obtain a plurality of sub-regional data sets of the neighborhood data, comprising: determining the location information of the disconnector data in the regional data set; determining the middle point of the regional data set based on the mean value of the location information, wherein the middle point is used to divide the regional data set into a plurality of the sub-regional data sets; and using the middle point to divide the regional data set into a plurality of the sub-regional data sets; The device is further used to determine the distance feature information of the sub-region data set based on the coordinate information of the sub-region data set; the device is further used to determine the neighborhood data of the isolating switch data in the sub-region data set; determine the matrix information of the isolating switch data using the neighborhood data; determine the direction feature information of the sub-region data set based on the matrix information, wherein the matrix information is used to be expressed by the following formula: In the above formula, C j The covariance matrix of the points in the sub-region of the sub-region dataset, p i The coordinates (x) of the points in the neighborhood of the points in the sub-region are used to represent i ,y i ,z i ), (i=1,2,…,k; j=1,2,…,m), is used to represent the average coordinates of all points in the neighborhood of the point in the sub-region, m is used to represent the number of points in the sub-region, and k is used to represent the number of points in the neighborhood; The first determination unit is further used to determine the feature information of the isolating switch data in the target point cloud data set based on the distance feature information and the direction feature information of each data in the multiple sub-area data sets through the following steps: fusing the distance feature information and the direction feature information of each data in the multiple sub-area data sets to obtain the fused feature information of the isolating switch data; normalizing the fused feature information of the isolating switch data to obtain the normalized feature information of the isolating switch data; determining the normalized feature information of the isolating switch data as the feature information of the isolating switch data in the target point cloud data set, wherein the distance feature information is used to be represented by the following formula: In the above formula, x j ,y j 、z j They are used to represent the x, y, and z coordinates (j=1, 2, ..., m) of all points in the sub-region, and x0, y0, and z0 are used to represent the x, y, and z coordinates of the middle point in the sub-region.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 3.

6. A processor, characterized in that: The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 3 when running.

7. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images