Noisy point post-processing method and device based on point cloud automatic classification, equipment and medium

Abstract

The invention provides a noisy point post-processing method and device based on point cloud automatic classification, equipment and a medium, and the method comprises the steps: classifying input point cloud data, building a KD tree for the point cloud data between adjacent towers, searching adjacent points, and carrying out the statistics of the average distance, the target distance mean value and the distance standard deviation of each point; determining different preset standard deviation multipliers according to categories of point cloud data classification, and further determining a distance threshold of each category; screening points of which the average distance exceeds a corresponding distance threshold, and regarding the points as potential noisy points; and dividing the point cloud data into an upper region and a lower region of the lead by taking the minimum height value of the lead as a boundary, and respectively processing the upper region and the lower region to determine a final target noisy point. The problems of low noise point classification efficiency and high dependence degree on training data of point cloud data in an electric power scene are solved, the accuracy of a noise point classification result and the automation degree of data production are improved, and the requirements for computer hardware and a large amount of manual annotation are reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of power data processing, and in particular to a noise post-processing method based on automatic point cloud classification, and a device, equipment, and medium. Background Art

[0002] When processing point cloud data in power scenarios, although many noise extraction algorithms have been proposed, due to the complexity, diversity and other interference of power scenarios, it is difficult to achieve good noise classification effects using a single rule or pure deep learning approach.

[0003] Existing noise classification schemes all have some limitations and defects. For example: the noise classification method based on clustering, which specifically uses manually set clustering radius and minimum number of points per cluster to perform clustering to screen outliers and classify them as noise points. This method has a big performance problem. When the number of point clouds is large, the clustering algorithm needs to consume a lot of memory, has high requirements on computer equipment hardware during parallel processing, and is quite time-consuming to process; in addition, this method requires a lot of manual experience and parameter adjustment, and is difficult to apply to complex and changeable actual scenes. The rules are difficult to cover all possible situations, and it is easy to have problems of missed detection and false detection. Another example: the classification method based on machine learning or deep learning, which directly learns features and models from the original point cloud data to automatically classify noise points. This method is highly dependent on training data, requires a large amount of well-labeled training data, and has poor robustness to noise point clouds. Summary of the invention

[0004] The present disclosure at least provides a noise post-processing method, device, equipment, and medium based on automatic point cloud classification to solve at least one of the above-mentioned technical defects.

[0005] According to one aspect of the present disclosure, a noise post-processing method based on automatic point cloud classification is provided, comprising:

[0006] Acquire original point cloud data obtained by scanning the target power line area with a three-dimensional laser radar, classify and process the original point cloud data, and extract point cloud data of each category respectively; the categories include wire category and noise category;

[0007] Determine the minimum height value of the wire according to the point cloud data corresponding to the wire category;

[0008] Extracting point cloud data between every two adjacent towers from the point cloud data of each category to obtain a plurality of inter-tower point cloud arrays;

[0009] For each tower point cloud array, perform the following operations:

[0010] Establish a KD tree of the point cloud array between the tower poles;

[0011] Traverse each point in the point cloud array between the tower poles, and for each point, use the KD tree to search for the N points closest to the point, and calculate the average distance between the N points and the point; wherein N is a positive integer;

[0012] Calculate the mean of the average distances corresponding to all points in the point cloud array between the tower poles to obtain the target distance mean; and calculate the distance standard deviation based on the average distances corresponding to all points;

[0013] Determine the distance threshold corresponding to each category according to the target distance mean, the distance standard deviation and the preset standard deviation multiplier corresponding to each category;

[0014] Traversing each point in the point cloud array between the tower poles, for each point, if the average distance corresponding to the point is greater than the distance threshold of the category corresponding to the point, the point is regarded as a potential noise point;

[0015] Traverse all potential noise points. If the height value of the potential noise point is less than the minimum height value of the wire, use the KD tree to search for points whose distance from the potential noise point is less than a preset distance. If the number of points searched is zero, determine that the potential noise point is a target noise point. If the height value of the potential noise point is greater than the minimum height value of the wire, obtain the N points closest to the potential noise point, and when the categories of the N points are all noise categories, determine that the potential noise point is a target noise point.

[0016] In a possible implementation, the category further includes at least one of the following:

[0017] Ground wire category; upper and lower crossing wire category; pole tower category; insulator drain wire category; vegetation category; ground category.

[0018] In a possible implementation, the preset standard deviation multiplier corresponding to the tower category is greater than the preset standard deviation multiplier corresponding to the vegetation category and the ground category; the preset standard deviation multiplier corresponding to the conductor category, the ground wire category, the upper and lower crossing wire category, and the insulator drainage wire category is greater than the preset standard deviation multiplier corresponding to the vegetation category and the ground category.

[0019] In a possible implementation, determining the distance threshold corresponding to each category according to the target distance mean, the distance standard deviation, and a preset standard deviation multiplier corresponding to each category includes:

[0020] For each category, a preset standard deviation multiplier corresponding to the category is multiplied by the distance standard deviation, and the multiplied value is added to the target distance mean to obtain a distance threshold corresponding to the category.

[0021] In a possible implementation, determining the minimum height value of the wire according to the point cloud data corresponding to the wire category includes:

[0022] Sort the points in the point cloud data corresponding to the wire category in order from low to high elevation values ​​to obtain a target point cloud sequence;

[0023] According to the preset elevation values, the target point cloud sequence is segmented to obtain target point cloud arrays corresponding to multiple elevation segments;

[0024] The average of the elevation values ​​of all points in the target point cloud array corresponding to the first M lowest elevation segments is calculated to obtain the lowest height value of the wire; wherein M is a positive integer.

[0025] In a possible implementation, the classifying and processing the original point cloud data includes:

[0026] The original point cloud data between every two adjacent towers are segmented to obtain multiple groups of original point cloud arrays;

[0027] Using deep learning methods, each group of original point cloud arrays is classified and processed separately.

[0028] In a possible implementation manner, obtaining the N points closest to the potential noise point includes:

[0029] The KD tree searches for the N points closest to the potential noise point.

[0030] According to another aspect of the present disclosure, a noise post-processing device based on automatic classification of point clouds is provided, comprising:

[0031] A point cloud acquisition processing module is used to acquire the original point cloud data obtained by scanning the target power line area by the three-dimensional laser radar, classify the original point cloud data, and extract point cloud data of each category respectively; the categories include wire category and noise category;

[0032] A conductive minimum height determination module, used to determine the minimum height value of the conductor according to the point cloud data corresponding to the conductor category;

[0033] A point cloud segmentation module is used to extract point cloud data between every two adjacent towers from the point cloud data of each category to obtain a plurality of point cloud arrays between towers;

[0034] The noise post-processing module is used to perform the following operations on each tower point cloud array:

[0035] Establish a KD tree of the point cloud array between the tower poles;

[0036] Traverse each point in the point cloud array between the tower poles, and for each point, use the KD tree to search for the N points closest to the point, and calculate the average distance between the N points and the point; wherein N is a positive integer;

[0037] Calculate the mean of the average distances corresponding to all points in the point cloud array between the tower poles to obtain the target distance mean; and calculate the distance standard deviation based on the average distances corresponding to all points;

[0038] Determine the distance threshold corresponding to each category according to the target distance mean, the distance standard deviation and the preset standard deviation multiplier corresponding to each category;

[0039] Traversing each point in the point cloud array between the tower poles, for each point, if the average distance corresponding to the point is greater than the distance threshold of the category corresponding to the point, the point is regarded as a potential noise point;

[0040] Traverse all potential noise points. If the height value of the potential noise point is less than the minimum height value of the wire, use the KD tree to search for points whose distance from the potential noise point is less than a preset distance. If the number of points searched is zero, determine that the potential noise point is a target noise point. If the height value of the potential noise point is greater than the minimum height value of the wire, obtain the N points closest to the potential noise point, and when the categories of the N points are all noise categories, determine that the potential noise point is a target noise point.

[0041] According to another aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements any of the above methods when executing the computer program.

[0042] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any of the above-mentioned methods is implemented.

[0043] The noise point post-processing method based on point cloud automatic classification disclosed in the present invention first classifies the input point cloud data, then establishes a kd-tree for the point cloud data between adjacent poles and towers, searches for neighboring points and counts the average distance, target distance mean and distance standard deviation of each point; then determines different preset standard deviation multipliers according to the classification category of the point cloud data, and further determines the distance threshold of each category; then screens points whose average distance exceeds the corresponding distance threshold and regards them as potential noise points; then uses the minimum height value of the conductor as the boundary, divides them into two areas, the upper and lower areas of the conductor, and processes them separately to determine the final target noise point. It solves the problems of low efficiency and high dependence on training data in point cloud data noise classification in power scenarios, improves the accuracy of noise classification results and the degree of automation of data production, and reduces the demand for computer hardware and a large amount of manual annotation.

[0044] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0046] Figure 1 is a flow chart of a noise post-processing method based on automatic classification of point clouds according to the present disclosure;

[0047] Figure 2 is a structural schematic diagram of a noise point post-processing device based on automatic point cloud classification according to the present disclosure;

[0048] Figure 3 is a schematic structural diagram of an electronic device according to the present disclosure. DETAILED DESCRIPTION

[0049] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0050] In view of the defects of low efficiency, low accuracy, high labor cost and poor robustness in the current point cloud data noise classification, the present invention provides a noise post-processing method and device, equipment and medium based on point cloud automatic classification. The present invention solves the problems of low efficiency and high dependence on training data in point cloud data noise classification in power scenarios, improves the accuracy of noise classification results, the degree of automation of data production and scene adaptability, and reduces the demand for computer hardware and a large amount of manual annotation.

[0051] The technical solution of the present disclosure is described below through specific embodiments.

[0052] like Figure 1 As shown, it is a flowchart of the noise post-processing method based on point cloud automatic classification of this embodiment. The execution subject of this embodiment is a computing device or component with data processing capability. The specific method of this embodiment may include the following steps:

[0053] S110, obtaining original point cloud data obtained by scanning the target power line area with a three-dimensional laser radar, classifying and processing the original point cloud data, and extracting point cloud data of each category respectively; the categories include wire category and noise category.

[0054] The collected original point cloud data include power lines, poles, towers, ground, buildings, vegetation and other ground objects. Therefore, the above classification and processing of the original point cloud data can obtain the following categories of point cloud data: ground line category; upper and lower crossing line category; pole tower category; insulator drainage line category; vegetation category; ground category, building category.

[0055] The classification process of the original point cloud data can be implemented by the following steps:

[0056] The original point cloud data between every two adjacent towers are segmented to obtain multiple groups of original point cloud arrays; each group of original point cloud arrays is classified and processed separately using deep learning.

[0057] The original point cloud data between every two adjacent towers is divided into multiple groups of point cloud data, which reduces the amount of data and facilitates subsequent separate processing.

[0058] In addition, each group of original point cloud arrays can be automatically classified using methods such as clustering. Point cloud data classification helps to filter out useless points and obtain the required point cloud data. In the present invention, the point cloud data after initial classification is taken out during post-processing. For example, in step S120, the minimum height value of the wire is determined using the point cloud data of the wire category.

[0059] S120. Determine a minimum height value of the wire according to the point cloud data corresponding to the wire category.

[0060] It should be noted here that step S120 does not have to be executed before step S130, and the present disclosure does not limit the execution order of the steps by the sequence numbers of the steps.

[0061] Subsequently, the minimum height value of the wire will be used to divide the entire area into two areas: the area above the wire and the area below the wire to classify the noise points separately.

[0062] S130, extracting point cloud data between every two adjacent towers from the point cloud data of each category to obtain a plurality of inter-tower point cloud arrays.

[0063] Processing the point cloud data between every two adjacent towers separately can reduce the amount of data processed at a time and improve processing efficiency.

[0064] S140, performing noise classification operations on each point cloud array between tower poles to determine the target noise point of each point cloud array between tower poles:

[0065] Step 1: Create a KD tree of the point cloud array between tower poles.

[0066] The KD tree is used for subsequent searches of neighboring points.

[0067] Step 2: traverse each point in the point cloud array between the tower poles, and for each point, use the KD tree to search for the N points closest to the point, and calculate the average distance between the N points and the point; where N is a positive integer.

[0068] Here, N can be determined according to the requirements of the actual scenario, for example, N is set to 5.

[0069] Step 3: Calculate the mean of the average distances corresponding to all points in the point cloud array between the tower poles to obtain the target distance mean; and calculate the distance standard deviation based on the average distances corresponding to all points.

[0070] Step 4: Determine the distance threshold corresponding to each category based on the target distance mean, the distance standard deviation, and the preset standard deviation multiplier corresponding to each category.

[0071] Different categories of point cloud data use different preset standard deviation multipliers. In order to avoid important targets such as power lines and poles being misclassified as noise points, the preset standard deviation multipliers corresponding to these categories are set larger. At the same time, targets such as vegetation and ground categories contain a large number of noise points, so the preset standard deviation multipliers corresponding to these categories are set smaller.

[0072] Specifically, the preset standard deviation multiplier corresponding to the tower category is greater than the preset standard deviation multiplier corresponding to the vegetation category and the ground category; the preset standard deviation multiplier corresponding to the conductor category, the ground wire category, the upper and lower crossing wire category, and the insulator drainage wire category is greater than the preset standard deviation multiplier corresponding to the vegetation category and the ground category.

[0073] Step 5: traverse each point in the point cloud array between the tower poles. For each point, if the average distance corresponding to the point is greater than the distance threshold of the category corresponding to the point, the point is regarded as a potential noise point.

[0074] Step 6, traverse all potential noise points. If the height value of the potential noise point is less than the minimum height value of the wire, use the KD tree to search for points whose distance from the potential noise point is less than a preset distance. If the number of points searched is zero, the potential noise point is determined to be a target noise point; accordingly, if the number of points searched is not zero, that is, other points are searched, it is determined that the potential noise point is not a target noise point; if the height value of the potential noise point is greater than the minimum height value of the wire, the N points closest to the potential noise point are obtained, and when the categories of the N points are all noise categories, the potential noise point is determined to be a target noise point, that is, if the categories of the N points do not have other categories except the noise category, the potential noise point is determined to be a target noise point.

[0075] Here we can directly use the N points searched in step 2, or we can use the KD tree to re-search the N points closest to the potential noise point.

[0076] In some embodiments, the distance threshold corresponding to each category is determined according to the target distance mean, the distance standard deviation, and the preset standard deviation multiplier corresponding to each category, which can be specifically implemented by the following steps:

[0077] For each category, a preset standard deviation multiplier corresponding to the category is multiplied by the distance standard deviation, and the multiplied value is added to the target distance mean to obtain a distance threshold corresponding to the category.

[0078] In some embodiments, the minimum height value of the wire is determined according to the point cloud data corresponding to the wire category, which can be specifically implemented by the following steps:

[0079] Step 1: Sort the points in the point cloud data corresponding to the wire category in order from low to high elevation values ​​to obtain the target point cloud sequence.

[0080] Step 2: Segment the target point cloud sequence according to the preset elevation value to obtain target point cloud arrays corresponding to multiple elevation segments.

[0081] Step 3: Calculate the average of the elevation values ​​of all points in the target point cloud array corresponding to the first M lowest elevation segments to obtain the lowest height value of the wire; wherein M is a positive integer.

[0082] Specifically, the point cloud data corresponding to the wire category in step S120 is taken out, and the point cloud data is sorted from low to high according to the elevation; starting from the lowest point, all points are segmented at every 0.5 meter elevation value (i.e., the preset elevation value), and the points of the first three (i.e., M) lowest elevation segments are taken out, and the elevation average of these points is calculated, and this average is used as the demarcation standard, i.e., the above-mentioned wire minimum height value. The purpose of using the wire minimum height value to process the noise point classification in different regions is to overcome the following problems: the number of ground points and vegetation points with lower elevation values ​​is large, and although some points are outliers and are under the vegetation layer or the ground, they are still vegetation points or ground points. In order to avoid such points from being classified as noise points, the wire minimum height value is used as the demarcation and processed separately.

[0083] The scheme in the above embodiment improves the accuracy of automatic classification of noise points in power scenarios, and more effectively supports other business needs based on the automatic classification results; and, compared with methods such as clustering denoising, the scheme in the above embodiment consumes less running memory, has higher execution efficiency, and has lower requirements for computer hardware. In addition, the scheme in the above embodiment does not rely on a large amount of training data, does not require a lot of manpower to mark good samples, and has high robustness to noise points in various scenarios.

[0084] Based on the same inventive concept, the present disclosure provides a noise post-processing device based on point cloud automatic classification. The steps performed by the components of the device are the same or similar to those of the above method, so similar parts are not repeated. Figure 2 As shown, the noise post-processing device based on point cloud automatic classification of this embodiment includes:

[0085] The point cloud acquisition processing module 210 is used to obtain the original point cloud data obtained by the three-dimensional laser radar scanning the target power line area, classify the original point cloud data, and extract point cloud data of each category respectively; the categories include wire category and noise category.

[0086] The conductive minimum height determination module 220 is used to determine the minimum height value of the conductor according to the point cloud data corresponding to the conductor category.

[0087] The point cloud segmentation module 230 is used to extract the point cloud data between every two adjacent towers from the point cloud data of each category to obtain a plurality of inter-tower point cloud arrays.

[0088] The noise post-processing module 240 is used to perform the following operations on each inter-tower point cloud array:

[0089] Establish a KD tree of the point cloud array between the tower poles;

[0090] Traverse each point in the point cloud array between the tower poles, and for each point, use the KD tree to search for the N points closest to the point, and calculate the average distance between the N points and the point; wherein N is a positive integer;

[0091] Calculate the mean of the average distances corresponding to all points in the point cloud array between the tower poles to obtain the target distance mean; and calculate the distance standard deviation based on the average distances corresponding to all points;

[0092] Determine the distance threshold corresponding to each category according to the target distance mean, the distance standard deviation and the preset standard deviation multiplier corresponding to each category;

[0093] Traversing each point in the point cloud array between the tower poles, for each point, if the average distance corresponding to the point is greater than the distance threshold of the category corresponding to the point, the point is regarded as a potential noise point;

[0094] Traverse all potential noise points. If the height value of the potential noise point is less than the minimum height value of the wire, use the KD tree to search for points whose distance from the potential noise point is less than a preset distance. If the number of points searched is zero, determine that the potential noise point is a target noise point. If the height value of the potential noise point is greater than the minimum height value of the wire, obtain the N points closest to the potential noise point, and when the categories of the N points are all noise categories, determine that the potential noise point is a target noise point.

[0095] In some embodiments, the category of point cloud data further includes at least one of the following:

[0096] Ground wire category; upper and lower crossing wire category; pole tower category; insulator drain wire category; vegetation category; ground category.

[0097] In some embodiments, the preset standard deviation multiplier corresponding to the pole tower category is greater than the preset standard deviation multiplier corresponding to the vegetation category and the ground category; the preset standard deviation multiplier corresponding to the conductor category, the ground wire category, the upper and lower crossing wire category, and the insulator drainage wire category is greater than the preset standard deviation multiplier corresponding to the vegetation category and the ground category.

[0098] In some embodiments, when the noise post-processing module 240 determines the distance threshold corresponding to each category according to the target distance mean, the distance standard deviation, and the preset standard deviation multiplier corresponding to each category, it is specifically used to:

[0099] For each category, a preset standard deviation multiplier corresponding to the category is multiplied by the distance standard deviation, and the multiplied value is added to the target distance mean to obtain a distance threshold corresponding to the category.

[0100] In some embodiments, when determining the minimum height value of a conductor according to the point cloud data corresponding to the conductor category, the conductive minimum height determination module 220 is specifically used to:

[0101] Sort the points in the point cloud data corresponding to the wire category in order from low to high elevation values ​​to obtain a target point cloud sequence;

[0102] According to the preset elevation values, the target point cloud sequence is segmented to obtain target point cloud arrays corresponding to multiple elevation segments;

[0103] The average of the elevation values ​​of all points in the target point cloud array corresponding to the first M lowest elevation segments is calculated to obtain the lowest height value of the wire; wherein M is a positive integer.

[0104] In some embodiments, when the point cloud acquisition processing module 210 performs classification processing on the original point cloud data, it is specifically used to:

[0105] The original point cloud data between every two adjacent towers are segmented to obtain multiple groups of original point cloud arrays;

[0106] Using deep learning methods, each group of original point cloud arrays is classified and processed separately.

[0107] In some embodiments, when the noise point post-processing module 240 obtains the N points closest to the potential noise point, it is specifically used to:

[0108] The KD tree searches for the N points closest to the potential noise point.

[0109] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a computer-readable storage medium.

[0110] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0111] like Figure 3As shown, the device 300 includes a computing unit 310, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 320 or a computer program loaded from a storage unit 380 into a random access memory (RAM) 330. In the RAM 330, various programs and data required for the operation of the device 300 can also be stored. The computing unit 310, the ROM 320, and the RAM 330 are connected to each other via a bus 340. An input / output (I / O) interface 350 is also connected to the bus 340.

[0112] A number of components in the device 300 are connected to the I / O interface 350, including: an input unit 360, such as a keyboard, a mouse, etc.; an output unit 370, such as various types of displays, speakers, etc.; a storage unit 380, such as a disk, an optical disk, etc.; and a communication unit 390, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 390 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0113] The computing unit 310 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 310 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 310 performs the various methods and processes described above. For example, in some embodiments, any of the above methods may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 380. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via the ROM 320 and / or the communication unit 390. When the computer program is loaded into the RAM 330 and executed by the computing unit 310, one or more steps of any of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 310 may be configured to perform any of the methods described above in any other appropriate manner (e.g., by means of firmware).

[0114] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0116] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0118] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0119] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0120] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0121] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A noise post-processing method based on automatic classification of point clouds, characterized in that: include: Acquire original point cloud data obtained by scanning the target power line area with a three-dimensional laser radar, classify and process the original point cloud data, and extract point cloud data of each category respectively; the categories include wire category and noise category; Determine the minimum height value of the wire according to the point cloud data corresponding to the wire category; Extracting point cloud data between every two adjacent towers from the point cloud data of each category to obtain a plurality of inter-tower point cloud arrays; For each tower point cloud array, perform the following operations: Establish a KD tree of the point cloud array between the tower poles; Traverse each point in the point cloud array between the tower poles, and for each point, use the KD tree to search for the N points closest to the point, and calculate the average distance between the N points and the point; wherein N is a positive integer; Calculate the mean of the average distances corresponding to all points in the point cloud array between the tower poles to obtain the target distance mean; and calculate the distance standard deviation based on the average distances corresponding to all points; Determine the distance threshold corresponding to each category according to the target distance mean, the distance standard deviation and the preset standard deviation multiplier corresponding to each category; Traverse each point in the point cloud array between the tower poles. For each point, if the average distance corresponding to the point is greater than the distance threshold of the category corresponding to the point, the point is regarded as a potential noise point. Traverse all potential noise points. If the height value of the potential noise point is less than the minimum height value of the wire, use the KD tree to search for points whose distance from the potential noise point is less than a preset distance. If the number of points searched is zero, determine that the potential noise point is a target noise point. If the height value of the potential noise point is greater than the minimum height value of the wire, obtain the N points closest to the potential noise point, and when the categories of the N points are all noise categories, determine that the potential noise point is a target noise point.

2. The method according to claim 1, characterized in that The categories also include at least one of the following: Ground wire category; upper and lower crossing wire category; pole tower category; insulator drain wire category; vegetation category; ground category.

3. The method according to claim 2, characterized in that The preset standard deviation multiplier corresponding to the tower category is greater than the preset standard deviation multiplier corresponding to the vegetation category and the ground category; the preset standard deviation multiplier corresponding to the conductor category, the ground wire category, the upper and lower crossing wire category, and the insulator drainage wire category is greater than the preset standard deviation multiplier corresponding to the vegetation category and the ground category.

4. The method according to claim 1, characterized in that: The determining of the distance threshold corresponding to each category according to the target distance mean, the distance standard deviation and the preset standard deviation multiplier corresponding to each category includes: For each category, a preset standard deviation multiplier corresponding to the category is multiplied by the distance standard deviation, and the multiplied value is added to the target distance mean to obtain a distance threshold corresponding to the category.

5. The method according to claim 1, characterized in that Determining the minimum height value of the wire according to the point cloud data corresponding to the wire category includes: Sort the points in the point cloud data corresponding to the wire category in order from low to high elevation values ​​to obtain a target point cloud sequence; According to the preset elevation values, the target point cloud sequence is segmented to obtain target point cloud arrays corresponding to multiple elevation segments; The average of the elevation values ​​of all points in the target point cloud array corresponding to the first M lowest elevation segments is calculated to obtain the lowest height value of the wire; wherein M is a positive integer.

6. The method according to claim 1, characterized in that The classifying and processing the original point cloud data includes: The original point cloud data between every two adjacent towers are segmented to obtain multiple groups of original point cloud arrays; Using deep learning methods, each group of original point cloud arrays is classified and processed separately.

7. The method according to claim 1, characterized in that The obtaining of the N points closest to the potential noise point includes: The KD tree searches for the N points closest to the potential noise point.

8. A noise post-processing device based on automatic classification of point clouds, characterized in that: include: A point cloud acquisition and processing module is used to acquire the original point cloud data obtained by scanning the target power line area by the three-dimensional laser radar, classify the original point cloud data, and extract point cloud data of each category respectively; the categories include wire category and noise category; A conductive minimum height determination module, used to determine the minimum height value of the conductor according to the point cloud data corresponding to the conductor category; A point cloud segmentation module is used to extract point cloud data between every two adjacent towers from the point cloud data of each category to obtain a plurality of point cloud arrays between towers; The noise post-processing module is used to perform the following operations on each tower point cloud array: Establish a KD tree of the point cloud array between the tower poles; Traverse each point in the point cloud array between the tower poles, and for each point, use the KD tree to search for the N points closest to the point, and calculate the average distance between the N points and the point; wherein N is a positive integer; Calculate the mean of the average distances corresponding to all points in the point cloud array between the tower poles to obtain the target distance mean; and calculate the distance standard deviation based on the average distances corresponding to all points; Determine the distance threshold corresponding to each category according to the target distance mean, the distance standard deviation and the preset standard deviation multiplier corresponding to each category; Traverse each point in the point cloud array between the tower poles. For each point, if the average distance corresponding to the point is greater than the distance threshold of the category corresponding to the point, the point is regarded as a potential noise point. Traverse all potential noise points. If the height value of the potential noise point is less than the minimum height value of the wire, use the KD tree to search for points whose distance from the potential noise point is less than a preset distance. If the number of points searched is zero, determine that the potential noise point is a target noise point. If the height value of the potential noise point is greater than the minimum height value of the wire, obtain the N points closest to the potential noise point, and when the categories of the N points are all noise categories, determine that the potential noise point is a target noise point.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images