Extraction of irrigation water conservancy element information based on LiDAR point cloud data and system

Abstract

The application discloses a kind of based on LiDAR point cloud data's irrigation area water conservancy element information extraction method and system.Based on LiDAR point cloud data generation irrigation area orthographic image and give spatial coordinate information;Identify the object of different water conservancy element categories in irrigation area and determine its coordinate range;According to coordinate range, point cloud data is segmented to establish the point cloud data block corresponding to different categories of objects;According to the geometric characteristics of irrigation area water conservancy element, in different scanning surface, the point cloud data obtained by scanning is preprocessed;According to water conservancy element category characteristics, complete the scanning in horizontal direction of water conservancy element point cloud data according to growth direction;According to water conservancy element geometric shape characteristics and point cloud data information, extract the geometric shape data of water conservancy element fine;According to point cloud data and water conservancy element geometric characteristics, establish attribute database.The application relies on the point cloud data and corresponding image data obtained by LiDAR system, realizes the extraction of irrigation area water conservancy element.

Description

Technical Field

[0001] This invention belongs to the field of smart irrigation district construction technology, specifically relating to a system for extracting irrigation district water conservancy element information based on LiDAR point cloud data. Background Technology

[0002] Smart irrigation districts represent a major direction and key characteristic of modern irrigation district development. The realization of smart irrigation districts requires the rapid and accurate acquisition and updating of spatial information on water resources elements, providing fundamental data support and ensuring the timeliness of this information. Airborne LiDAR technology can quickly and accurately acquire water resources element information, providing technical support for the intelligentization of irrigation districts.

[0003] LiDAR technology can quickly, comprehensively, and accurately acquire spatial coordinates, spectral data, and laser echo information of irrigation area elements. Spectral information is used to generate point cloud orthophotos, providing conditions for artificial intelligence applications. The development of convolutional neural networks has led to revolutionary breakthroughs in target recognition and image segmentation. A large amount of digital image data was collected for irrigation area water conservancy elements to establish a target recognition training library. The main categories of irrigation area water conservancy elements are five: fields, canals, ditches, sluice gates, and pumping stations, corresponding to three geometric types: planar, linear, and point, respectively, exhibiting strong planar distribution characteristics. Simultaneously, water conservancy element target images from the orthophotos generated from point clouds were used in the training to improve the convolutional neural network's ability to recognize water conservancy element targets, achieving accurate identification and segmentation of water conservancy element objects and obtaining the boundary coordinate range of the segmented water conservancy element objects.

[0004] In the construction of smart irrigation districts, it is necessary to quickly and accurately acquire information on the spatial distribution and internal geometric structure of different water conservancy elements. While artificial intelligence technology can identify and segment water conservancy elements, it only provides the category and coordinate range of the element objects, lacking information on their internal structure. The internal structural information of water conservancy elements is contained within the spatial coordinate information of the point cloud. Directly extracting this information from the entire point cloud data of the irrigation district presents challenges due to high algorithm complexity and computational burden.

[0005] Currently, the production methods for the data foundation of intelligent irrigation district construction mainly include three types: total station, RTK, and UAV photogrammetry. Total station and RTK digital mapping struggle to obtain comprehensive topographic maps, while photogrammetry methods are technically complex, computationally intensive, and suffer from inconsistent solution accuracy. Airborne LiDAR technology can obtain comprehensive information about the irrigation district with high data accuracy and consistency, effectively compensating for the shortcomings of traditional mapping methods. Point cloud data offers a rich variety of information categories, enabling detailed 3D modeling. Currently, the mainstream application of this technology is in urban real-scene 3D modeling; however, there are few reports on its application and research in smart irrigation district construction, and substantial applications are still lacking. Summary of the Invention

[0006] To address the current technical challenges in constructing a refined data foundation for smart irrigation districts based on point cloud data, this invention proposes a method and system for extracting irrigation district water conservancy element information based on LiDAR point cloud data. This method can solve a series of technical problems in the process of extracting water conservancy element information. By performing image recognition through convolutional neural networks, the spatial location of water conservancy elements is obtained. The point cloud data is further segmented to obtain water conservancy element point cloud data blocks, and then the internal structural information of the water conservancy element objects is extracted using a scanning surface algorithm.

[0007] To achieve the above-mentioned technical features, the present invention includes the following technical solutions:

[0008] A method for extracting irrigation district water conservancy element information based on LiDAR point cloud data includes the following steps:

[0009] Step S1: Generate an orthophoto of the irrigation area based on LiDAR point cloud data, and assign spatial coordinate information to the orthophoto to determine the spatial plane coordinates corresponding to each pixel;

[0010] Step S2: Based on orthophotos, use artificial intelligence methods to identify objects of different water conservancy element categories in the irrigation area and determine the coordinate range of different water conservancy element objects;

[0011] Step S3: Based on the coordinate range of the water conservancy element objects, segment the point cloud data and establish point cloud data blocks corresponding to different categories of objects;

[0012] Step S4: Based on the geometric characteristics of the irrigation area's water conservancy elements, set the initial scanning surface parameters, and perform preprocessing operations on the point cloud data obtained from scanning on different scanning surfaces;

[0013] Step S5: Based on the characteristics of water conservancy element categories, identify and determine the growth direction of the scanning surface, and complete the horizontal scanning of the water conservancy element point cloud data according to the growth direction;

[0014] Step S6: While scanning, extract detailed geometric data of the water conservancy elements based on their geometric features and point cloud data.

[0015] Step S7: Establish an attribute database based on the acquired point cloud data and the geometric features of water conservancy elements to uniformly manage the water conservancy element data of the irrigation area.

[0016] Furthermore, in step S1, the rich spatial point information and spectral information of LiDAR point cloud data are used to generate an orthophoto, set the corresponding image resolution and size, calculate and determine the coverage area of ​​the orthophoto, and calculate the pixel coordinates and spatial coordinates corresponding to any pixel based on the image resolution and the boundary of the image coverage area.

[0017] Further, step S2 includes the following sub-steps:

[0018] S21: Establish a training library of water conservancy element images of different categories in the irrigation area, and use artificial intelligence methods to identify and segment water conservancy element objects of different categories distributed in the orthophotos of the irrigation area, so as to obtain water conservancy element category information and the coordinate range corresponding to the element objects.

[0019] S22: Establish a corresponding database structure according to the categories of irrigation area water conservancy elements, and store data of various types, such as category, boundary and internal geometric shape of water conservancy element objects, according to category.

[0020] Furthermore, in step S3, the point cloud data of the water conservancy element objects is segmented using the coordinate range of the water conservancy element objects to obtain the point cloud data of the water conservancy element objects. Then, the scan line algorithm is used to perform feature recognition and information extraction on the point cloud data of the element objects.

[0021] Furthermore, in step S4, the feature point cloud data is scanned along a preset direction using a scanning surface algorithm. Before scanning, the initial parameters of the scanning surface are set, the cross-section aggregation parameters are set, the spacing between the point cloud data aggregated onto the scanning surface and the front and back of the scanning surface is set, and the cross-section point cloud data filtering parameters are set to preprocess the cross-section point cloud data.

[0022] Furthermore, the initial global parameters of the scanning surface are first set, and then the scanning surface parameters are adaptively optimized based on the point cloud features to determine the scanning direction and scanning step size for scanning.

[0023] Furthermore, step S6 specifically includes:

[0024] S61: Obtain point cloud slice data of water conservancy element objects in the vertical direction from the current scanning surface, and generate cross-section graphics after preprocessing. Combine the water conservancy element category information and call the corresponding cross-section internal structure information recognition method. One type of water conservancy element corresponds to one pattern recognition method. Analyze the cross-section information of water conservancy elements to obtain the feature point information of the current cross-section as the vertical feature of water conservancy element objects.

[0025] S62: Enter the next scan, obtain the next cross-sectional data of the current water conservancy element object with the scan surface, identify the feature point information corresponding to the cross-section after preprocessing, and then use the similarity matching algorithm to match the feature points in the front and rear cross-sections in the horizontal direction to extract and express the internal feature information of the water conservancy element in the forward direction of the scan surface.

[0026] S63: Repeat the above steps to complete the extraction of spatial information of the current water conservancy element object.

[0027] Furthermore, in step S7, different types of water conservancy elements are replaced, and water conservancy element information is extracted from the point cloud data to obtain accurate boundary and geometric shape data of the water conservancy element objects, which are then stored in the database.

[0028] On the other hand, the present invention also provides a system for extracting irrigation district water conservancy element information based on LiDAR point cloud data, comprising:

[0029] Module 1: It is used to generate orthophotos of irrigation areas based on LiDAR point cloud data, and to assign spatial coordinate information to the orthophotos to determine the spatial plane coordinates corresponding to each pixel;

[0030] Module 2: It is used to identify objects of different water conservancy element categories in the irrigation area based on orthophotos and using artificial intelligence methods, and to determine the coordinate range of different water conservancy element objects;

[0031] Module 3: It is used to segment point cloud data according to the coordinate range of water conservancy element objects and establish point cloud data blocks corresponding to different categories of objects;

[0032] Module 4: It is used to set the initial scanning surface parameters based on the geometric characteristics of the irrigation area's water conservancy elements, and to perform preprocessing operations on the point cloud data obtained from scanning in different scanning surfaces;

[0033] Module 5: It is used to identify and determine the growth direction of the scanning surface based on the characteristics of water conservancy element categories, and complete the horizontal scanning of water conservancy element point cloud data according to the growth direction;

[0034] Module Six: It is used to extract detailed geometric data of water conservancy elements based on their geometric features and point cloud data while scanning.

[0035] Module 7: It is used to establish an attribute database based on the acquired point cloud data and the geometric features of water conservancy elements, and to uniformly manage the water conservancy element data of the irrigation area;

[0036] The system for extracting irrigation area water conservancy element information based on LiDAR point cloud data is used to perform the steps in the above-mentioned method for extracting irrigation area water conservancy element information based on LiDAR point cloud data.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] (1) This invention promotes the application of airborne LiDAR point cloud technology in the field of smart irrigation district construction. It integrates multiple high-tech technologies such as artificial intelligence, computational geometry and spatial database. It uses point cloud data that can cover all elements of the irrigation district to perform accurate information extraction, and can quickly and efficiently complete the construction of a precise full-element irrigation district data base.

[0039] (2) This invention is based on a thorough analysis of the characteristics of point cloud data in irrigation areas and the features of water conservancy elements in irrigation areas. It is an intelligent algorithm for extracting spatial and internal structural information of water conservancy elements. Compared with traditional manual data acquisition and modeling and UAV oblique photogrammetry calculation, the method of this invention for intelligently extracting water conservancy element information based on LiDAR technology to acquire point cloud data can provide more refined spatial information for the construction of smart irrigation areas and has a wider range of application potential.

[0040] (3) The method provided by the present invention has been verified by experiments to have stable solution results and high solution efficiency, demonstrating the applicability and superiority of extracting irrigation water conservancy elements based on LiDAR point cloud technology. Attached Figure Description

[0041] Figure 1 This is a flowchart of the present invention;

[0042] Figure 2 This is an orthophoto image of the irrigation area in Embodiment 1 of the present invention;

[0043] Figure 3 This is a field point cloud map of Embodiment 1 of the present invention;

[0044] Figure 4 This is a cross-sectional feature of a field in Embodiment 1 of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0046] In the construction of smart irrigation districts, it is necessary to quickly and accurately acquire information on the spatial distribution and internal geometric structure of different water conservancy elements. While artificial intelligence technology can identify and segment water conservancy elements, it only provides the category and coordinate range of the elements, lacking information on their internal structure. This internal structural information is contained within the spatial coordinates of the point cloud. Extracting this information directly from all point cloud data of the irrigation district presents challenges due to high algorithm complexity and computational burden. To address these issues, this paper first uses a convolutional neural network system to identify water conservancy elements in orthophotos of the irrigation district generated from LiDAR point clouds, obtaining element boundary information. Then, the extracted boundary information is used to segment the point cloud data. Within point cloud data blocks containing single water conservancy elements, a computational geometry scanning surface algorithm is used to obtain cross-sectional data and extract cross-sectional feature information. During the iterative scanning process, the internal structural features of the water conservancy elements in the scanning direction are fully generated.

[0047] The scanning surface algorithm is a fundamental method for exploring and mining spatial information in computational geometry. The method for mining the internal structural information of water conservancy element point cloud data blocks involved in this invention is an adaptive scanning surface algorithm guided by the internal structural information features of different categories of water conservancy elements. Based on the high matching result of the prior features of water conservancy element categories and the cross-sectional features obtained by the scanning surface, the scanning surface automatically judges and adjusts the scanning direction and step size.

[0048] Therefore, this invention, based on the characteristics of airborne LiDAR point cloud data and irrigation area water conservancy elements, utilizes artificial intelligence and computational geometry methods to provide a method for extracting irrigation area water conservancy element information based on LiDAR point cloud data. Under the premise that the irrigation area point cloud data acquired using the airborne LiDAR system, the artificial intelligence image recognition model, the computational geometry method, and the water conservancy element information storage database are all established and implemented as required, an orthophoto is generated from the point cloud data, and the spatial range of the water conservancy elements is identified using artificial intelligence. The point cloud data is then segmented according to the spatial range, and the internal structural information of the water conservancy elements is extracted from the segmented point cloud data blocks using computational geometry. The method described in this invention has clear algorithmic logic and a high level of automation, which can greatly improve the efficiency of irrigation area point cloud data modeling and has good application value. It can not only quickly and accurately identify the categories and spatial structure information of water conservancy elements, but also simultaneously manage the corresponding data by constructing a spatial database, providing a refined data foundation for the construction of smart irrigation areas.

[0049] Example 1:

[0050] Driven by artificial intelligence and spatial analysis technologies, this invention provides a method for extracting irrigation water conservancy element information based on LiDAR point cloud data. Artificial intelligence and computational geometric spatial analysis provide fundamental technical support for point cloud data information extraction. Based on this, point cloud spatial information and image texture information are combined to achieve efficient and automated extraction of irrigation water conservancy element information based on LiDAR point cloud data, providing a reliable data foundation for the intelligent construction of irrigation areas.

[0051] The following details the specific implementation process of the method for extracting irrigation area water conservancy element information based on LiDAR point cloud data provided by this invention:

[0052] like Figure 1 As shown, it includes the following steps:

[0053] Step S1: Generate an orthophoto of the irrigation area using point cloud data, and assign spatial coordinate information to the orthophoto to determine the spatial plane coordinates corresponding to each pixel.

[0054] Specifically, the data for each point in a LiDAR point cloud includes its spatial coordinates (x, y, z), color information (R, G, B), and echo intensity information (ratio). The size range of the orthophoto is set according to the boundary of the point cloud. min y max x max x min According to the accuracy requirements of the data base, the image pixel size Δd is set, and the spatial range corresponding to each pixel is calculated, as shown in formula (1). The coordinates of the lower left corner point (x i ,y i ), the coordinates of the upper right corner (x i+1 ,y i+1 ).

[0055]

[0056] The corresponding point cloud data is retrieved in this way. Assuming that n point cloud data points fall within the pixel range, the formula for calculating the RGB components of the current pixel is formula (2).

[0057]

[0058] Step S2: Based on orthophotos, use artificial intelligence methods to identify objects of different water conservancy element categories in the irrigation area and determine the coordinate range of different water conservancy element objects.

[0059] Specifically, in the early stage, it is necessary to collect images of various water conservancy elements in the irrigation area to build an element object recognition training library. After completing the training, the orthophoto generated by the point cloud is used as the input data of the recognition model to identify the water conservancy element categories and their corresponding coordinate ranges. The coordinate range line is a series of coordinates that can form a closed curve. Based on the coordinates, a Polygon object is constructed, and the data is stored in the common file Shape file of the geographic information system.

[0060] Step S3: Based on the coordinate range of the water conservancy element objects, the point cloud data is segmented to establish point cloud data blocks corresponding to different categories of objects.

[0061] Specifically, based on the identified object category and the corresponding Polygon data, spatial analysis methods are used to segment the point cloud data within the closed area of ​​the Polygon, forming a complete point cloud data object corresponding to the water conservancy element object of that category. This point cloud data block contains only one complete water conservancy element object, and the amount of point cloud data is significantly reduced.

[0062] Step S4: Based on the geometric characteristics of the irrigation area's water conservancy elements, set the initial scanning surface parameters, and perform preprocessing operations on the point cloud data obtained from scanning in different scanning surfaces.

[0063] Specifically, each type of water conservancy element within the irrigation area possesses specific geometric characteristics, which exhibit a certain regular distribution. For example, canals, based on their classification, each level has a distinct cross-section. High-level canals often have trapezoidal cross-sections, while low-level canals have trapezoidal, U-shaped, or V-shaped cross-sections. Therefore, a scanning surface algorithm can be used to scan the element point cloud data along a specific direction. Before scanning, initial parameters for the scanning surface and cross-section aggregation parameters are set, specifying the spacing between point cloud data points before and after the scanning surface. Cross-section point cloud data filtering parameters are also set to preprocess the cross-section point cloud data, preparing it for further feature extraction.

[0064] Step S5: Based on the characteristics of water conservancy element categories, identify and determine the growth direction of the scanning surface, and complete the horizontal scanning of the water conservancy element point cloud data according to the growth direction.

[0065] Specifically, to ensure that the cross-sectional information obtained from the scanning surface can correctly and completely express the internal structural information of the water conservancy element object, the growth direction of the scanning surface should be parallel or orthogonal to the variation law of the water conservancy element characteristics. Before conducting a full scan, the relationship between the growth direction of the scanning surface and the variation direction of the water conservancy element point cloud data characteristics should be adaptively identified to ensure the quality of the cross-sectional information obtained from the scanning surface.

[0066] Step S6: While scanning, extract detailed geometric data of the water conservancy elements based on their geometric features and point cloud data.

[0067] Specifically, after determining the accurate growth direction of the scanning surface, the hydraulic element object is scanned as a whole according to the set scanning method and corresponding parameters. The vertical changes in the internal structural morphology of the hydraulic element object will be reflected in the scanning section. The horizontal internal structural morphology information is analyzed in the horizontal direction using feature data within the vertical section, and finally, a three-dimensional model is established. For example, a field has clear boundaries; whether it is dry land or paddy field, it is surrounded by field ridges that form an independent, closed space. Figure 3 , Figure 4 When analyzing point cloud data of field objects using scanning cross-sections, the scanning plane direction can be adaptively adjusted to extract internal geometric structure information along the horizontal or vertical direction of the field. The point cloud slices within the first and last feature cross-sections of the field are basically straight, such as... Figure 4 As shown in sections 1 and 3, the scanned sections within the field exhibit undulations near the field ridges. When there are no crops, the point cloud within the field is generally concave; when there are crops, some point clouds will protrude beyond the field ridges, making the morphological features very obvious. By processing the information revealed by the section data, the internal structural information of the field object can be extracted.

[0068] Step S7: Establish an attribute database based on the acquired point cloud data and the geometric features of water conservancy elements to uniformly manage the water conservancy element data of the irrigation area;

[0069] Specifically, it is necessary to pre-construct a spatial information database of irrigation area water conservancy elements. Different categories of water conservancy elements have different spatial data structures. The spatial database structure should be designed so that when extracting information for different categories of water conservancy elements, the acquired data can be stored in the corresponding database to realize the management of spatial information and internal structure of irrigation area water conservancy elements.

[0070] Example 2:

[0071] This embodiment provides a system for extracting irrigation district water conservancy element information based on LiDAR point cloud data, including:

[0072] Module 1: It is used to generate orthophotos of irrigation areas based on LiDAR point cloud data, and to assign spatial coordinate information to the orthophotos to determine the spatial plane coordinates corresponding to each pixel;

[0073] Module 2: It is used to identify objects of different water conservancy element categories in the irrigation area based on orthophotos and using artificial intelligence methods, and to determine the coordinate range of different water conservancy element objects;

[0074] Module 3: It is used to segment point cloud data according to the coordinate range of water conservancy element objects and establish point cloud data blocks corresponding to different categories of objects;

[0075] Module 4: It is used to set the initial scanning surface parameters based on the geometric characteristics of the irrigation area's water conservancy elements, and to perform preprocessing operations on the point cloud data obtained from scanning in different scanning surfaces;

[0076] Module 5: It is used to identify and determine the growth direction of the scanning surface based on the characteristics of water conservancy element categories, and complete the horizontal scanning of water conservancy element point cloud data according to the growth direction;

[0077] Module Six: It is used to extract detailed geometric data of water conservancy elements based on their geometric features and point cloud data while scanning.

[0078] Module 7: It is used to establish an attribute database based on the acquired point cloud data and the geometric features of water conservancy elements, and to uniformly manage the water conservancy element data of the irrigation area.

[0079] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0080] Obviously, those skilled in the art can make various modifications and variations to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, if these modifications and variations to the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention also intends to include these modifications and variations.

[0081] All other parts not described in detail are existing technologies.

Claims

1. A method for extracting irrigation district water conservancy element information based on LiDAR point cloud data, characterized in that: Includes the following steps: Step S1: Generate an orthophoto of the irrigation area based on LiDAR point cloud data, and assign spatial coordinate information to the orthophoto to determine the spatial plane coordinates corresponding to each pixel; Step S2: Based on orthophotos, use artificial intelligence methods to identify objects of different water conservancy element categories in the irrigation area and determine the coordinate range of different water conservancy element objects; Step S3: Based on the coordinate range of the water conservancy element objects, segment the point cloud data and establish point cloud data blocks corresponding to different categories of objects; Step S4: Based on the geometric characteristics of the irrigation area's water conservancy elements, set the initial scanning surface parameters, and perform preprocessing operations on the point cloud data obtained from scanning on different scanning surfaces; Step S5: Based on the characteristics of water conservancy element categories, identify and determine the growth direction of the scanning surface, and complete the horizontal scanning of the water conservancy element point cloud data according to the growth direction; Step S6: While scanning, extract detailed geometric morphological data of the water conservancy elements based on their geometric features and point cloud data; specifically: S61: Obtain point cloud slice data of water conservancy element objects in the vertical direction from the current scanning surface, and generate cross-section graphics after preprocessing. Combine the water conservancy element category information and call the corresponding cross-section internal structure information recognition method. One type of water conservancy element corresponds to one pattern recognition method. Analyze the cross-section information of water conservancy elements to obtain the feature point information of the current cross-section as the vertical feature of water conservancy element objects. S62: Enter the next scan, obtain the next cross-sectional data of the current water conservancy element object with the scan surface, identify the feature point information corresponding to the cross-section after preprocessing, and then use the similarity matching algorithm to match the feature points in the front and rear cross-sections in the horizontal direction to extract and express the internal feature information of the water conservancy element in the forward direction of the scan surface. S63: Repeat the above steps to complete the spatial information extraction of the current water conservancy element object; Step S7: Establish an attribute database based on the acquired point cloud data and the geometric features of water conservancy elements to uniformly manage the water conservancy element data of the irrigation area.

2. The method for extracting irrigation district water conservancy element information based on LiDAR point cloud data according to claim 1, characterized in that: In step S1, the rich spatial point information and spectral information of LiDAR point cloud data are used to generate an orthophoto, set the corresponding image resolution and size, calculate and determine the coverage area of ​​the orthophoto, and calculate the pixel coordinates and spatial coordinates corresponding to any pixel based on the image resolution and the boundary of the image coverage area.

3. The method for extracting irrigation area water conservancy element information based on LiDAR point cloud data according to claim 1, characterized in that, Step S2 includes the following sub-steps: S21: Establish a training library of water conservancy element images of different categories in the irrigation area, and use artificial intelligence methods to identify and segment water conservancy element objects of different categories distributed in the orthophotos of the irrigation area, so as to obtain water conservancy element category information and the coordinate range corresponding to the element objects. S22: Establish a corresponding database structure according to the categories of irrigation area water conservancy elements, and store data of various types, such as category, boundary and internal geometric shape of water conservancy element objects, according to category.

4. The method for extracting irrigation district water conservancy element information based on LiDAR point cloud data according to claim 1, characterized in that: In step S3, the point cloud data of the water conservancy element objects is segmented by the coordinate range of the water conservancy element objects to obtain the point cloud data of the water conservancy element objects. Then, the scan line algorithm is used to perform feature recognition and information extraction on the point cloud data of the element objects.

5. The method for extracting irrigation area water conservancy element information based on LiDAR point cloud data according to claim 1, characterized in that: In step S4, the feature point cloud data is scanned along a preset direction using a scanning surface algorithm. Before scanning, the initial parameters of the scanning surface are set, the cross-section aggregation parameters are set, the spacing between the point cloud data aggregated onto the scanning surface and the front and back of the scanning surface is set, and the cross-section point cloud data filtering parameters are set to preprocess the cross-section point cloud data.

6. The method for extracting irrigation area water conservancy element information based on LiDAR point cloud data according to claim 5, characterized in that: First, set the global initial parameters of the scanning surface, and then adaptively optimize the scanning surface parameters based on the point cloud features to determine the scanning direction and scanning step size to carry out the scanning work.

7. The method for extracting irrigation area water conservancy element information based on LiDAR point cloud data according to claim 1, characterized in that: In step S7, different types of water conservancy elements are replaced, and water conservancy element information is extracted from the point cloud data to obtain accurate boundary and geometric shape data of the water conservancy element objects, which are then stored in the database.

8. A system for extracting irrigation district water conservancy element information based on LiDAR point cloud data, characterized in that: include: Module 1: It is used to generate orthophotos of irrigation areas based on LiDAR point cloud data, and to assign spatial coordinate information to the orthophotos to determine the spatial plane coordinates corresponding to each pixel; Module 2: It is used to identify objects of different water conservancy element categories in the irrigation area based on orthophotos and using artificial intelligence methods, and to determine the coordinate range of different water conservancy element objects; Module 3: It is used to segment point cloud data according to the coordinate range of water conservancy element objects and establish point cloud data blocks corresponding to different categories of objects; Module 4: It is used to set the initial scanning surface parameters based on the geometric characteristics of the irrigation area's water conservancy elements, and to perform preprocessing operations on the point cloud data obtained from scanning in different scanning surfaces; Module 5: It is used to identify and determine the growth direction of the scanning surface based on the characteristics of water conservancy element categories, and complete the horizontal scanning of water conservancy element point cloud data according to the growth direction; Module Six: It is used to extract detailed geometric data of water conservancy elements based on their geometric features and point cloud data while scanning. Module 7: It is used to establish an attribute database based on the acquired point cloud data and the geometric features of water conservancy elements, and to uniformly manage the water conservancy element data of the irrigation area; The system for extracting irrigation area water conservancy element information based on LiDAR point cloud data is used to perform the steps in the method for extracting irrigation area water conservancy element information based on LiDAR point cloud data as described in any one of claims 1-6.

Images