Vegetation coverage area determination method and device based on point cloud, equipment and medium
By classifying and clustering the three-dimensional lidar scan data, the point cloud coverage area of vegetation categories is calculated, and the problems of low efficiency and insecurity of vegetation coverage area analysis in the existing technology are solved, and efficient and accurate analysis results are achieved.
Patent Information
- Application Number
- CN202411452158.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-17
- Publication Date
- 2025-02-11
AI Technical Summary
The lack of systematic solutions in the analysis of vegetation coverage area in the prior art has led to high degree of manual intervention, low degree of intelligence, low analysis efficiency and unsafe.
By obtaining the original point cloud data scanned by three-dimensional lidar, performing classification processing and clustering, the point cloud coverage area of vegetation categories is determined, and then vegetation coverage area is calculated.
Efficient and accurate vegetation coverage area analysis is achieved, which reduces the risk of manual intervention and improves the accuracy and automation of analysis results.
Smart Images
Figure CN119417884A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of data processing, in particular to the field of laser point cloud data processing technology, and discloses a method for determining vegetation coverage area based on point cloud, and a device, equipment, and medium. Background Art
[0002] At present, point cloud processing technology based on LiDAR scanning is widely used, and point cloud data is widely used in tasks such as 3D reconstruction, object recognition, and posture estimation. Among them, 3D reconstruction is an important application direction of point cloud processing technology. By processing the point cloud data in the scene, a 3D model of the scene can be obtained. In addition, point cloud processing technology is also used in the field of robotics. Robots can perceive the surrounding environment through point cloud data, thereby achieving autonomous navigation and obstacle avoidance.
[0003] However, point cloud processing technology is still in its infancy in traditional industries, and there is a lack of systematic solutions. Especially for vegetation coverage area analysis, the degree of manual intervention is high, the degree of intelligence is low, and the current situation is that conclusions are drawn based on understanding the situation and experience, lacking effective, scientific and fast processing methods; if high-precision vegetation coverage area is required, manual on-site inspections are required to sort out the coverage of various types of vegetation, which results in a very large workload and the safety of personnel cannot be guaranteed. Summary of the invention
[0004] The present disclosure at least provides a method, device, equipment, and medium for determining vegetation coverage area based on point cloud to solve at least one of the above-mentioned technical defects.
[0005] According to one aspect of the present disclosure, a method for determining vegetation coverage area based on point cloud is provided, comprising:
[0006] Obtaining original point cloud data obtained by scanning the target area with a 3D laser radar;
[0007] Classifying and processing the original point cloud data to obtain point cloud data of multiple categories;
[0008] Determine a category to be removed, and extract point cloud data to be removed corresponding to the category to be removed from the multiple categories of point cloud data; the category to be removed includes at least one category except the vegetation category;
[0009] For each category in the to-be-eliminated categories, cluster the to-be-eliminated point cloud data corresponding to the category according to a preset clustering radius to obtain N clustered point cloud arrays; wherein N is a positive integer;
[0010] Determine the convex polygon boundary points of each cluster point cloud array respectively, and determine the region boundary of each cluster point cloud array respectively according to the determined convex polygon boundary points;
[0011] According to the area boundaries of each clustered point cloud array, the point cloud coverage area corresponding to each clustered point cloud array is determined;
[0012] The point cloud coverage area corresponding to each clustered point cloud array is subtracted from the area of the target area to obtain the point cloud coverage area corresponding to the vegetation category.
[0013] In a possible implementation manner, determining the point cloud coverage area corresponding to each clustered point cloud array according to the region boundary of each clustered point cloud array includes:
[0014] For each clustered point cloud array, perform the following operations:
[0015] If the area corresponding to the clustered point cloud array is a slope, the area corresponding to the clustered point cloud array is divided into a plurality of grids according to the boundary of the area corresponding to the clustered point cloud array;
[0016] Fill the mesh without point cloud with low points;
[0017] Use each mesh to construct multiple triangulated networks;
[0018] The sum of the areas of all triangulated networks is taken as the point cloud coverage area corresponding to the clustered point cloud array.
[0019] In a possible implementation, after determining the region boundaries of each cluster point cloud array according to the determined convex polygon boundary points, the method further includes:
[0020] According to the area boundary of each cluster point cloud array, the distance of each cluster point cloud array relative to the starting side of the positive direction is determined, and the cluster point cloud arrays are sorted in order of distance from small to large.
[0021] In a possible implementation, the original point cloud data is classified to obtain multiple categories of point cloud data, including:
[0022] The original point cloud data is classified and processed according to the point cloud clustering mode or the point cloud block shape to obtain point cloud data of multiple categories.
[0023] In a possible implementation manner, the above-mentioned method for determining vegetation coverage area based on point cloud further includes:
[0024] Output the area boundary information of each cluster point cloud array, as well as the point cloud coverage area corresponding to the vegetation category.
[0025] In a possible implementation manner, the category to be eliminated includes at least one of the following:
[0026] Building category; Ground category; Power line category.
[0027] In a possible implementation, the original point cloud data is classified to obtain multiple categories of point cloud data, including:
[0028] Segmenting the original point cloud data to obtain multiple groups of original point cloud arrays;
[0029] By using deep learning methods, each group of original point cloud arrays is classified and processed separately to obtain point cloud data of multiple categories.
[0030] According to another aspect of the present disclosure, a device for determining vegetation coverage area based on point cloud is provided, comprising:
[0031] Point cloud acquisition module, used to obtain the original point cloud data obtained by scanning the target area by the 3D laser radar;
[0032] A point cloud classification module is used to classify the original point cloud data to obtain point cloud data of multiple categories;
[0033] A point cloud extraction module, used to determine the category to be eliminated, and extract the point cloud data to be eliminated corresponding to the category to be eliminated from the multiple categories of point cloud data; the category to be eliminated includes at least one category except the vegetation category;
[0034] A clustering module, for clustering the to-be-eliminated point cloud data corresponding to each category in the to-be-eliminated categories according to a preset clustering radius, to obtain N clustered point cloud arrays; wherein N is a positive integer;
[0035] A boundary determination module is used to respectively determine the convex polygon boundary points of each clustered point cloud array, and to respectively determine the region boundary of each clustered point cloud array according to the determined convex polygon boundary points;
[0036] The point cloud area determination module is used to determine the point cloud coverage area corresponding to each clustered point cloud array according to the area boundary of each clustered point cloud array;
[0037] The target area determination module is used to subtract the point cloud coverage area corresponding to each clustered point cloud array from the area of the target area to obtain the point cloud coverage area corresponding to the vegetation category.
[0038] 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.
[0039] 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.
[0040] The method for determining vegetation coverage area based on point cloud disclosed in the present invention first obtains original point cloud data obtained by scanning a target area with a three-dimensional laser radar; then, classifies and processes the original point cloud data to obtain point cloud data of multiple categories; then, determines the category to be eliminated, and extracts the point cloud data to be eliminated corresponding to the category to be eliminated from the point cloud data of multiple categories; the category to be eliminated includes at least one category other than the vegetation category; then, for each category in the category to be eliminated, the point cloud data to be eliminated corresponding to the category is clustered according to a preset clustering radius to obtain N clustered point cloud arrays; wherein N is a positive integer; then, respectively determine the convex polygon boundary points of each clustered point cloud array, and respectively determine the area boundary of each clustered point cloud array according to the determined convex polygon boundary points; then, respectively determine the point cloud coverage area corresponding to each clustered point cloud array according to the area boundary of each clustered point cloud array; finally, subtract the point cloud coverage area corresponding to each clustered point cloud array from the area of the target area to obtain the point cloud coverage area corresponding to the vegetation category. The above solution provides a complete set of vegetation coverage area analysis solutions based on point cloud data for various industries, which can obtain vegetation coverage area analysis data efficiently and accurately, and solves the problems of manual analysis of vegetation coverage, which requires highly unsafe on-site operations and inspections, and is inefficient. While improving the accuracy of the analysis results, it also improves the degree of automation of the operation.
[0041] 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
[0042] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.
[0043] Figure 1 is a flow chart of a method for determining vegetation coverage area based on point cloud according to the present disclosure;
[0044] Figure 2 is a structural schematic diagram of a device for determining vegetation coverage area based on point cloud according to the present disclosure;
[0045] Figure 3 is a schematic structural diagram of an electronic device according to the present disclosure. DETAILED DESCRIPTION
[0046] 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.
[0047] The existing solutions for vegetation coverage area analysis have the following problems: the degree of manual intervention is high, the degree of intelligence is low, and the conclusion is drawn based on understanding the situation and experience, lacking effective, scientific and fast processing methods; if a high-precision vegetation coverage area is required, it is necessary to manually conduct on-site field investigations and sort out the coverage of various types of vegetation, which results in a very large workload and the safety of personnel cannot be guaranteed. In order to solve the above technical problems, the present disclosure proposes a method and device, equipment and medium for determining vegetation coverage area based on point cloud. The present disclosure scans and obtains point cloud data of the target area, classifies the point cloud data, extracts point cloud data of various categories, selects the categories to be excluded, analyzes the coverage area of the categories to be excluded, and finally calculates the coverage area of vegetation based on the coverage area of the categories to be excluded. The present disclosure provides a complete set of vegetation coverage area analysis solutions based on point cloud data for various industries, which can efficiently and accurately obtain vegetation coverage area analysis data, solves the problem that manual analysis of vegetation coverage requires highly unsafe on-site operations and investigations, and is inefficient, while improving the accuracy of the analysis results, and improving the degree of automation of the operation.
[0048] The technical solution of the present disclosure is described below through specific embodiments.
[0049] like Figure 1 As shown, it is a flowchart of determining vegetation coverage area based on point cloud in this embodiment. The execution subject of this embodiment is a computing device or component with data processing capability. Specifically, the method of this embodiment may include the following steps:
[0050] S110, obtaining original point cloud data obtained by scanning the target area with a three-dimensional laser radar.
[0051] Laser point cloud technology refers to the use of points distributed in space to describe actual objects, that is, using laser point cloud data to describe the absolute spatial position of objects on the earth.
[0052] Specifically, the target area can be scanned by a drone equipped with a laser radar scanning system to collect original point cloud data in the target area; the target area here is the area where vegetation area analysis is required.
[0053] S120: Classify the original point cloud data to obtain point cloud data of multiple categories.
[0054] Point cloud data is used to describe the absolute spatial position of objects on the earth. These points include all objects in the scanned area, including usable and unusable parts, as well as noise points. Therefore, after obtaining the original point cloud data, the point cloud data needs to be classified, that is, the content represented by the point cloud block or area is marked. According to the classification results, useless points can be filtered out, and useful parts can be extracted and segmented to obtain usable point cloud data. For example, in the point cloud classification of power transmission lines in the power industry, the pole towers can be extracted separately, and the route design can be further carried out based on the point cloud of the pole towers.
[0055] The classification method may be manual classification, or automatic classification according to the point cloud clustering pattern or the point cloud block shape, and manual repair may be performed after classification.
[0056] For example, point cloud data can be classified in the following way:
[0057] The original point cloud data is segmented to obtain multiple groups of original point cloud arrays; and each group of original point cloud arrays is classified and processed by deep learning to obtain point cloud data of multiple categories.
[0058] The original point cloud data may be segmented into multiple groups of original point cloud arrays according to the predetermined area size. The purpose of segmentation is to reduce the amount of data processed at a time, improve processing efficiency and accuracy, and reduce the requirements on the computing power of hardware devices.
[0059] S130, determining a category to be eliminated, and extracting point cloud data to be eliminated corresponding to the category to be eliminated from the multiple categories of point cloud data; the category to be eliminated includes at least one category except the vegetation category.
[0060] The categories to be eliminated include at least one of the following: building category; ground category; power line category.
[0061] S140. For each category in the to-be-eliminated categories, cluster the to-be-eliminated point cloud data corresponding to the category according to a preset clustering radius to obtain N clustered point cloud arrays; wherein N is a positive integer.
[0062] The above clustering radius can be set to be different according to different categories through the interface. Of course, the clustering radius of point cloud data of all categories can also be set to be the same through the interface, and the present disclosure does not limit this.
[0063] S150 , respectively determining the convex polygon boundary points of each clustered point cloud array, and respectively determining the region boundary of each clustered point cloud array according to the determined convex polygon boundary points.
[0064] The convex polygon boundary points of each group of clustered point cloud arrays are obtained through an algorithm, and then the region boundary of each group of clustered point cloud arrays is determined according to the determined boundary points.
[0065] After respectively determining the region boundaries of each cluster point cloud array according to the determined convex polygon boundary points, the following may also be included:
[0066] According to the regional boundaries of each cluster point cloud array, the distance of each cluster point cloud array relative to the starting side of the positive direction is determined through spatial analysis, and each cluster point cloud array is sorted in order from small to large distance, so that it can be displayed and output in the order of arrangement in subsequent needs, which is convenient for users to view.
[0067] S160 , determining the point cloud coverage area corresponding to each clustered point cloud array according to the region boundary of each clustered point cloud array.
[0068] Calculation of point cloud coverage area supports the options of calculating plane area and calculating slope area. You can select the appropriate calculation method based on the type of plane where the point cloud data is located.
[0069] S170. Subtract the point cloud coverage area corresponding to each clustered point cloud array from the area of the target area to obtain the point cloud coverage area corresponding to the vegetation category.
[0070] The area of the target area also supports the option of calculating the plane area and calculating the slope area. Select the appropriate calculation method based on the type of plane in the target area.
[0071] The target area can be set to scan the entire range or a certain area therein according to the needs, and the business end realizes the intersection of each group of area boundaries and the target area as a new area boundary.
[0072] After determining the point cloud coverage area corresponding to the vegetation category and the region boundaries of each clustered point cloud array, the above-mentioned method for determining the vegetation coverage area based on point cloud may further include the following steps:
[0073] Output the regional boundary information of each clustered point cloud array and the point cloud coverage area corresponding to the vegetation category; the regional boundary information of each clustered point cloud array can be output in the form of a KML file so as to be presented in major 3D software, systems, and scenes.
[0074] In some embodiments, the above-mentioned determination of the point cloud coverage area corresponding to each clustered point cloud array according to the region boundary of each clustered point cloud array can be specifically implemented by the following steps:
[0075] The following operations are performed for each clustered point cloud array: if the area corresponding to the clustered point cloud array is a slope, then the area corresponding to the clustered point cloud array is divided into multiple grids according to the area boundary corresponding to the clustered point cloud array; the grids without point clouds are filled with low points; multiple triangulated networks are constructed using each grid; the sum of the areas of all triangulated networks is used as the point cloud coverage area corresponding to the clustered point cloud array. If the area corresponding to the clustered point cloud array is a plane, the area of the convex polygon of the area is calculated using the conventional plane calculation method.
[0076] The above embodiments provide a complete set of vegetation coverage area analysis solutions based on point cloud data for various industries, which can efficiently and accurately obtain vegetation coverage area analysis data, solve the problem that manual analysis of vegetation coverage requires highly unsafe on-site operations and inspections, and is inefficient, while improving the accuracy of the analysis results and the degree of automation of the operation. In addition, the above embodiments can provide clear analysis results, a universal analysis result output method, support the presentation of analysis results on multiple platforms, and can be more widely used.
[0077] Based on the same inventive concept, the present disclosure provides a device for determining vegetation coverage area based on point cloud, and 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 vegetation coverage area determination device based on point cloud of this embodiment includes:
[0078] The point cloud acquisition module 210 is used to obtain the original point cloud data obtained by scanning the target area by the three-dimensional laser radar.
[0079] The point cloud classification module 220 is used to classify the original point cloud data to obtain point cloud data of multiple categories.
[0080] The point cloud extraction module 230 is used to determine the category to be removed, and extract the point cloud data to be removed corresponding to the category to be removed from the multiple categories of point cloud data; the category to be removed includes at least one category except the vegetation category.
[0081] The clustering module 240 is used to cluster the to-be-eliminated point cloud data corresponding to each category in the to-be-eliminated categories according to a preset clustering radius to obtain N clustered point cloud arrays; wherein N is a positive integer.
[0082] The boundary determination module 250 is used to respectively determine the convex polygon boundary points of each clustered point cloud array, and respectively determine the region boundary of each clustered point cloud array according to the determined convex polygon boundary points.
[0083] The point cloud area determination module 260 is used to determine the point cloud coverage area corresponding to each clustered point cloud array according to the area boundary of each clustered point cloud array.
[0084] The target area determination module 270 is used to subtract the point cloud coverage area corresponding to each clustered point cloud array from the area of the target area to obtain the point cloud coverage area corresponding to the vegetation category.
[0085] In some embodiments, when the point cloud area determination module 260 determines the point cloud coverage area corresponding to each clustered point cloud array according to the area boundary of each clustered point cloud array, it is specifically used to:
[0086] For each clustered point cloud array, perform the following operations:
[0087] If the area corresponding to the clustered point cloud array is a slope, the area corresponding to the clustered point cloud array is divided into a plurality of grids according to the boundary of the area corresponding to the clustered point cloud array;
[0088] Fill the mesh without point cloud with low points;
[0089] Use each mesh to construct multiple triangulated networks;
[0090] The sum of the areas of all triangulated networks is taken as the point cloud coverage area corresponding to the clustered point cloud array.
[0091] In some embodiments, after determining the region boundaries of each cluster point cloud array according to the determined convex polygon boundary points, the boundary determination module 250 is further configured to:
[0092] According to the area boundary of each cluster point cloud array, the distance of each cluster point cloud array relative to the starting side of the positive direction is determined, and the cluster point cloud arrays are sorted in order of distance from small to large.
[0093] In some embodiments, when the point cloud classification module 220 classifies the original point cloud data to obtain multiple types of point cloud data, it is specifically used to:
[0094] The original point cloud data is classified and processed according to the point cloud clustering mode or the point cloud block shape to obtain point cloud data of multiple categories.
[0095] In some embodiments, the target area determination module 270 is further configured to:
[0096] Output the area boundary information of each cluster point cloud array, as well as the point cloud coverage area corresponding to the vegetation category.
[0097] In some embodiments, the category to be eliminated includes at least one of the following:
[0098] Building category; Ground category; Power line category.
[0099] In some embodiments, when the point cloud classification module 220 classifies the original point cloud data to obtain multiple categories of point cloud data, it is specifically used to:
[0100] Segmenting the original point cloud data to obtain multiple groups of original point cloud arrays;
[0101] By using deep learning methods, each group of original point cloud arrays is classified and processed separately to obtain point cloud data of multiple categories.
[0102] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a computer-readable storage medium.
[0103] 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.
[0104] like Figure 3 As 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.
[0105] 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.
[0106] 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).
[0107] 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.
[0108] 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.
[0109] 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.
[0110] 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).
[0111] 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.
[0112] 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.
[0113] 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.
[0114] 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 method for determining vegetation coverage area based on point cloud, characterized in that: include: Obtaining original point cloud data obtained by scanning the target area with a 3D laser radar; Classifying and processing the original point cloud data to obtain point cloud data of multiple categories; Determine a category to be eliminated, and extract point cloud data to be eliminated corresponding to the category to be eliminated from the multiple categories of point cloud data; The category to be removed includes at least one category other than the vegetation category; For each category in the to-be-eliminated categories, cluster the to-be-eliminated point cloud data corresponding to the category according to a preset clustering radius to obtain N clustered point cloud arrays; wherein N is a positive integer; Determine the convex polygon boundary points of each cluster point cloud array respectively, and determine the region boundary of each cluster point cloud array respectively according to the determined convex polygon boundary points; According to the area boundaries of each clustered point cloud array, the point cloud coverage area corresponding to each clustered point cloud array is determined; The point cloud coverage area corresponding to each clustered point cloud array is subtracted from the area of the target area to obtain the point cloud coverage area corresponding to the vegetation category.
2. The method according to claim 1, characterized in that The step of determining the point cloud coverage area corresponding to each clustered point cloud array according to the region boundary of each clustered point cloud array comprises: For each clustered point cloud array, perform the following operations: If the area corresponding to the clustered point cloud array is a slope, the area corresponding to the clustered point cloud array is divided into a plurality of grids according to the boundary of the area corresponding to the clustered point cloud array; Fill the mesh without point cloud with low points; Use each mesh to construct multiple triangulated networks; The sum of the areas of all triangulated networks is taken as the point cloud coverage area corresponding to the clustered point cloud array.
3. The method according to claim 1, characterized in that After respectively determining the area boundaries of each cluster point cloud array according to the determined convex polygon boundary points, the method further includes: According to the area boundary of each cluster point cloud array, the distance of each cluster point cloud array relative to the starting side of the positive direction is determined, and the cluster point cloud arrays are sorted in order of distance from small to large.
4. The method according to claim 1, characterized in that The original point cloud data is classified and processed to obtain point cloud data of various categories, including: The original point cloud data is classified and processed according to the point cloud clustering mode or the point cloud block shape to obtain point cloud data of multiple categories.
5. The method according to claim 1, characterized in that Also includes: Output the area boundary information of each cluster point cloud array, as well as the point cloud coverage area corresponding to the vegetation category.
6. The method according to claim 1, characterized in that The categories to be eliminated include at least one of the following: Building category; Ground category; Power line category.
7. The method according to claim 1, characterized in that The original point cloud data is classified and processed to obtain point cloud data of various categories, including: Segmenting the original point cloud data to obtain multiple groups of original point cloud arrays; By using deep learning methods, each group of original point cloud arrays is classified and processed separately to obtain point cloud data of multiple categories.
8. A device for determining vegetation coverage area based on point cloud, characterized in that: include: Point cloud acquisition module, used to obtain the original point cloud data obtained by scanning the target area by the 3D laser radar; A point cloud classification module is used to classify the original point cloud data to obtain point cloud data of multiple categories; A point cloud extraction module, used for determining a category to be removed, and extracting point cloud data to be removed corresponding to the category to be removed from the multiple categories of point cloud data; The category to be removed includes at least one category other than the vegetation category; A clustering module, for clustering the to-be-eliminated point cloud data corresponding to each category in the to-be-eliminated categories according to a preset clustering radius, to obtain N clustered point cloud arrays; wherein N is a positive integer; A boundary determination module is used to respectively determine the convex polygon boundary points of each clustered point cloud array, and to respectively determine the region boundary of each clustered point cloud array according to the determined convex polygon boundary points; The point cloud area determination module is used to determine the point cloud coverage area corresponding to each clustered point cloud array according to the area boundary of each clustered point cloud array; The target area determination module is used to subtract the point cloud coverage area corresponding to each clustered point cloud array from the area of the target area to obtain the point cloud coverage area corresponding to the vegetation category.
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.