A construction method, device and electronic device for three-dimensional visual landscape architecture

Abstract

A method, device, and electronic device for constructing a three-dimensional visualized landscape garden, which relate to the field of garden planning. In this method, multiple garden images captured by a drone are obtained. The garden images are captured from multiple preset angles when the drone flies along a preset route. Feature points of the garden images are determined. The shooting time points of each garden image and the pos data of the drone at the shooting time points are obtained. According to the pos data and the feature points, aerial triangulation is used to perform feature point matching on each garden image to obtain the three-dimensional point cloud data of each feature point. A three-dimensional point cloud model corresponding to the landscape garden is constructed. Texture information is mapped onto the three-dimensional point cloud model to obtain a three-dimensional real scene model of the landscape garden. By implementing the technical solution provided in this application, garden data in a large range and from multiple perspectives can be quickly and systematically collected by the drone along the preset route, improving work efficiency.

Description

Technical Field

[0001] This application relates to the field of landscape planning, and particularly to a method, device, and electronic device for constructing a three-dimensional visual landscape garden. Background Art

[0002] With the development of society and the enhancement of environmental protection awareness, landscape planning has become increasingly prominent in urban planning and environmental beautification. Landscape gardens not only provide places for people to relax and entertain, but also play a crucial role in improving the urban ecological environment and enhancing the urban image. Through carefully designed garden landscapes, the quality of life of urban residents can be effectively improved. At the same time, it also has an inestimable impact on enhancing the tourism attractiveness and economic development of the city.

[0003] Currently, there are still many deficiencies in the three-dimensional visualization technology commonly used in the process of landscape planning and design, mainly reflected in the work efficiency of model construction. In the process of landscape planning and design, the original information data of the site is the premise for guiding the planning and design. Currently, garden designers use professional instruments carried by manpower to measure the internal environment of the landscape garden, which consumes a large amount of manpower and material resources and has a long working cycle. This technical method will lead to the problem of low work efficiency in the early stage of design.

[0004] Therefore, there is an urgent need for a method, device, and electronic device for constructing a three-dimensional visual landscape garden. Summary of the Invention

[0005] This application provides a method, device, and electronic device for constructing a three-dimensional visual landscape garden. By using a drone to collect garden data according to a preset route, a large range of multi-perspective garden data can be quickly and systematically collected, improving work efficiency.

[0006] In the first aspect of the present application, a method for constructing a three-dimensional visual landscape garden is provided. The method includes: obtaining multiple garden images of the landscape garden captured by a drone, where the garden images are captured from multiple preset angles when the drone flies along a preset route; determining the feature points of the garden images, where the feature points include control points and connection points, the control points are preset coordinate points, and the connection points are coordinate points that are commonly recognizable in multiple garden images; obtaining the shooting time points of each garden image, and at the shooting time points, the pos data of the drone, where the pos data includes the longitude, latitude, and altitude of the drone; according to the pos data and the feature points, using aerial triangulation (space resection operation), performing feature point matching on each garden image to obtain the three-dimensional point cloud data of each feature point; constructing a three-dimensional point cloud model corresponding to the landscape garden according to the three-dimensional point cloud data; extracting the texture information of the garden images according to the garden images; mapping the texture information to the three-dimensional point cloud model to obtain the three-dimensional real scene model of the landscape garden.

[0007] By adopting the above technical solution, the garden images of the landscape garden are obtained from multiple preset angles by the drone, which can comprehensively collect the image information of the garden and obtain rich data sources. By extracting the feature points of the garden images, including the preset control points and the connection points common to multiple images, the geometric association between the garden images is established, laying a foundation for subsequent three-dimensional reconstruction. At the same time, the shooting time point of each garden image and the corresponding drone position and attitude information, that is, the POS data, are recorded, which can determine the spatial position and direction of the garden images. Using the POS data and the feature points, feature matching between the garden images is realized through aerial triangulation (space resection operation), and the three-dimensional coordinates of the feature points are calculated to generate accurate three-dimensional point cloud data. On the basis of the point cloud, a three-dimensional point cloud model of the garden scene is further constructed, and then the image texture is mapped to the surface of the three-dimensional point cloud model, and finally a realistic three-dimensional real scene model is obtained. By constructing a high-precision three-dimensional real scene model, various elements of the landscape garden can be digitally recorded and displayed, comprehensively reproducing the spatial form and landscape layout of the landscape garden; at the same time, the three-dimensional real scene model provides a scientific analysis tool and data support for the planning and design of the landscape garden. This method utilizes the flexible and efficient data acquisition ability of the drone, combines photogrammetry and computer vision technologies, realizes the high-precision three-dimensional visualization reconstruction of the landscape garden, provides an intuitive and interactive digital scene for garden planning, design, management, etc., and improves work efficiency.

[0008] Optionally, after constructing the three-dimensional point cloud model corresponding to the landscape architecture according to the three-dimensional point cloud data, the method further includes: determining whether there is a layering phenomenon or an intersection phenomenon of feature points in the three-dimensional point cloud model; if it is determined whether there is a layering phenomenon or an intersection phenomenon of feature points in the three-dimensional point cloud model, controlling the unmanned aerial vehicle to re-acquire the garden images.

[0009] By adopting the above technical solution, by analyzing the spatial distribution characteristics of the point cloud, it is determined whether there is a layering phenomenon or an intersection phenomenon of feature points. Both of these phenomena will affect the integrity and accuracy of the three-dimensional point cloud model. By detecting layering and intersection, the quality and reliability of the three-dimensional point cloud model can be evaluated. When it is found that there are the above problems, the method can adaptively control the unmanned aerial vehicle to re-collect data and correct and improve the three-dimensional point cloud model.

[0010] Optionally, the determining whether there is a layering phenomenon of feature points in the three-dimensional point cloud model specifically includes: performing a layering process on the three-dimensional point cloud model, dividing the three-dimensional point cloud data into multiple layers according to height information; performing a clustering analysis on the point cloud data within each layer to obtain multiple point cloud clusters; determining a plurality of target point clouds included in the target point cloud cluster, where the target point cloud cluster is any one of the multiple point cloud clusters; calculating the height difference between a first target point cloud and a second target point cloud, where the first target point cloud is any one of the multiple target point clouds, and the second target point cloud is any one of the multiple target point clouds other than the first target point cloud; if it is determined that the height difference is greater than or equal to a preset height difference, determining that the first target point cloud and the second target point cloud are layered point clouds; determining whether the number of point clouds of the layered point clouds is greater than or equal to a preset number threshold; if it is determined whether the number of point clouds of the layered point clouds is greater than or equal to a preset number threshold, determining that there is the layering phenomenon in the three-dimensional point cloud model.

[0011] By adopting the above technical solution, the three-dimensional point cloud model is divided into multiple layers according to the height information of the point cloud, highlighting the distribution differences in the vertical direction. Then, a clustering analysis is performed within each layer, clustering the point clouds that are spatially adjacent and have similar attributes into clusters to form multiple point cloud clusters, depicting the agglomeration pattern in the horizontal direction. Select any one of the point cloud clusters as the target cluster and extract the point clouds contained therein as the target point clouds. By calculating the height difference between any two different target point clouds and setting a preset height difference, potential layered point clouds can be found. By counting the number of layered point clouds and setting a preset number threshold, it is determined whether there is a layering phenomenon in the entire three-dimensional point cloud model according to whether it exceeds the preset number threshold. This method makes full use of the elevation and neighborhood information of the point cloud, effectively analyzes the spatial differentiation characteristics of the point cloud through layering and clustering, and can quantitatively evaluate the layering phenomenon.

[0012] Optionally, determining whether there is an intersection phenomenon of feature points in the three-dimensional point cloud model specifically includes: calculating the spatial distance between the first target point cloud and the second target point cloud; if it is determined that the spatial distance is less than a preset distance threshold, determining that the intersection phenomenon exists in the three-dimensional point cloud model.

[0013] By adopting the above technical solution, by calculating the spatial distance between any two target point clouds and setting a preset distance threshold, abnormally close point clouds, that is, potential intersection point clouds, can be found. When the spatial distance is less than the preset distance threshold, it means that the point clouds of different landscape elements are interspersed with each other in the three-dimensional space, and an erroneous intersection phenomenon occurs. The accuracy of the three-dimensional point cloud model can be quantitatively evaluated by measuring the degree of intersection using spatial distance. This method cleverly utilizes the spatial topological relationship of the point cloud and realizes the rapid detection of intersection phenomena through distance calculation. This method can comprehensively evaluate the quality of the three-dimensional point cloud model, provide accurate feedback for the data supplement of the drone, and improve the reliability of the three-dimensional visualization of landscape gardens. At the same time, through intelligent quality control, the workload of manual inspection and correction is reduced, and the automation level of garden digitization is improved.

[0014] Optionally, based on the POS data and the feature points, aerial triangulation is used to match the feature points of each of the garden images to obtain three-dimensional point cloud data of each of the feature points, specifically including: matching the feature points of multiple garden images to obtain the correspondence between the same feature point in the multiple garden images; constructing the correspondence between the image coordinate system and the ground coordinate system using the control point coordinates of the control point on the ground and the feature point coordinates in the garden image; obtaining the three-dimensional coordinates of each of the feature points in the three-dimensional space based on the correspondence; and densely matching the three-dimensional coordinates to generate the three-dimensional point cloud data.

[0015] By adopting the above technical solution, the same feature points are identified in different garden images through feature point matching, and the corresponding relationship between garden images is established. This step achieves accurate registration between images by measuring the similarity of feature points. Then, the coordinates of the control points on the ground and in the image are used to build the corresponding relationship between the garden image coordinate system and the ground coordinate system. According to the established corresponding relationship, the coordinates of each feature point in three-dimensional space are calculated to obtain a discrete three-dimensional point cloud. The image information and spatial information of the feature points are fully utilized, and through rigorous mathematical models and coordinate transformation, high-precision reconstruction of two-dimensional images into three-dimensional point clouds is achieved.

[0016] Optionally, extracting the texture information of the garden image according to the garden image specifically includes: extracting pixel blocks corresponding to each feature point from the garden image; performing color correction on the pixel blocks to obtain corrected pixel blocks, and using the corrected pixel blocks as the texture information of the garden image.

[0017] By adopting the above technical solution, pixel blocks corresponding to each feature point are extracted from each garden image. Feature points not only contain position information, but the pixels around them also reflect local texture features. Extracting pixel blocks can obtain rich texture samples. Color correction is performed on the extracted pixel blocks. Due to differences in lighting, exposure and other conditions between images, the colors of pixel blocks may deviate. Through color correction, these deviations can be eliminated, making the colors of pixel blocks more consistent and natural. The corrected pixel blocks are used as the texture information of the garden image, which can reflect the true colors and material properties of the landscape. This method makes full use of the texture information contained in the garden image and obtains high-quality texture samples through feature point-driven pixel block extraction.

[0018] Optionally, constructing a three-dimensional point cloud model corresponding to the landscape garden according to the three-dimensional point cloud data specifically includes: performing filtering processing and downsampling on the three-dimensional point cloud data to obtain target three-dimensional point cloud data; generating a triangular mesh surface according to the target three-dimensional point cloud data and constructing the three-dimensional point cloud model.

[0019] By adopting the above technical solution, through point cloud preprocessing and triangulation, an efficient conversion from discrete point cloud to continuous surface is realized, and a fine three-dimensional point cloud model of the landscape garden is constructed. Filtering and downsampling ensure the data quality and calculation efficiency of the three-dimensional point cloud model, which is beneficial to the rapid modeling of large-scale landscape gardens. The triangular mesh surface provides a compact and standard three-dimensional representation, which is convenient for visualization rendering and spatial analysis operations.

[0020] In a second aspect of the present application, there is provided a device for constructing a three-dimensional visualized landscape garden. The device includes an acquisition module and a processing module. The acquisition module is configured to acquire multiple garden images of the landscape garden captured by a drone. The garden images are captured from multiple preset angles when the drone flies along a preset flight path. The processing module is configured to determine feature points of the garden images. The feature points include control points and connection points. The control points are preset coordinate points, and the connection points are coordinate points that are commonly recognizable in multiple garden images. The acquisition module is further configured to acquire the shooting time points of each garden image and the pos data of the drone at the shooting time point. The pos data includes the longitude, latitude, and altitude of the drone. The processing module is further configured to perform feature point matching on each garden image by using aerial triangulation based on the pos data and the feature points to obtain three-dimensional point cloud data of each feature point. The processing module is further configured to construct a three-dimensional point cloud model corresponding to the landscape garden according to the three-dimensional point cloud data. The processing module is further configured to extract texture information of the garden images according to the garden images. The processing module is further configured to map the texture information to the three-dimensional point cloud model to obtain a three-dimensional real-scene model of the landscape garden.

[0021] In a third aspect of the present application, there is provided an electronic device, including a processor, a memory, a user interface, and a network interface. The memory is used for storing instructions. The user interface and the network interface are both used for communicating with other devices. The processor is used for executing the instructions stored in the memory so that the electronic device executes the method described in any one of the above.

[0022] In a fourth aspect of the present application, there is provided a computer-readable storage medium storing instructions that, when executed, execute the method described in any one of the above.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0024] 1. By using drones to obtain garden images of landscape gardens from multiple preset angles, the image information of the gardens can be comprehensively collected, obtaining rich data sources. By extracting the feature points of the garden images, including the preset control points and the connection points shared by multiple images, the geometric correlation between the garden images is established, laying a foundation for subsequent 3D reconstruction. At the same time, the shooting time points of each garden image and the corresponding drone position and attitude information, that is, POS data, are recorded, which can determine the spatial position and direction of the garden images. Using the POS data and feature points, feature matching between the garden images is achieved through aerial triangulation (aerial triangulation operation), and the 3D coordinates of the feature points are calculated to generate accurate 3D point cloud data. Based on the point cloud, a 3D point cloud model of the garden scene is further constructed, and then the image texture is mapped to the surface of the 3D point cloud model, and finally a realistic 3D virtual model is obtained. By constructing a high-precision 3D virtual model, various elements of the landscape garden can be digitally recorded and displayed, comprehensively reproducing the spatial form and landscape layout of the landscape garden; at the same time, the 3D virtual model provides a scientific analysis tool and data support for the planning and design of the landscape garden. This method utilizes the flexible and efficient data acquisition ability of drones, combined with photogrammetry and computer vision technologies, to achieve high-precision 3D visualization reconstruction of the landscape garden, providing an intuitive and interactive digital scene for garden planning, design, management, etc., and improving work efficiency.

[0025] 2. By analyzing the spatial distribution characteristics of the 3D point cloud model, it is judged whether there are stratification phenomena or intersection phenomena of the feature points. These two phenomena will affect the integrity and accuracy of the 3D point cloud model. By detecting stratification and intersection, the quality and reliability of the 3D point cloud model can be evaluated. When the above problems are found, this method can adaptively control the drone to re-collect data and correct and improve the 3D point cloud model.

[0026] 3. The point cloud is stratified according to the height information of the point cloud, and the 3D point cloud model is divided into multiple layers, highlighting the distribution differences in the vertical direction. Then, clustering analysis is performed within each layer, and the point clouds that are spatially adjacent and have similar attributes are clustered into clusters, forming multiple point cloud clusters, which depict the aggregation patterns in the horizontal direction. Select any one point cloud cluster as the target cluster, and extract the point cloud contained therein as the target point cloud. By calculating the height difference between any two different target point clouds and setting a preset height difference, potential stratified point clouds can be found. By counting the number of stratified point clouds and setting a preset number threshold, it is determined whether there is a stratification phenomenon in the entire 3D point cloud model according to the situation exceeding the preset number threshold. This method makes full use of the elevation and neighborhood information of the point cloud, and effectively analyzes the spatial differentiation characteristics of the point cloud through stratification and clustering, and can quantitatively evaluate the stratification phenomenon. Description of the Drawings

[0027] Figure 1It is a schematic flowchart of a method for constructing a three-dimensional visual landscape garden disclosed in an embodiment of the present application;

[0028] Figure 2 It is a schematic module diagram of a device for constructing a three-dimensional visual landscape garden disclosed in an embodiment of the present application;

[0029] Figure 3 It is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.

[0030] Explanation of reference numerals: 201, acquisition module; 202, processing module; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed implementation manners

[0031] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0032] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0033] In the description of the embodiments of the present application, the meaning of the term "a plurality" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0034] The present application provides a method for constructing a three-dimensional visual landscape garden, referring to Figure 1 , Figure 1 It is a schematic flowchart of a method for constructing a three-dimensional visual landscape garden provided in an embodiment of the present application. This method is applied to a server and includes steps S101 to S107. The above steps are as follows:

[0035] Step S101: Obtain multiple garden images of the landscape garden captured by the drone. The garden images are captured from multiple preset angles when the drone flies along a preset route.

[0036] In step S101, the server plans a preset route for the drone through dedicated software (such as Altizure). According to the area, terrain complexity, and required image resolution of the landscape garden, route parameters are designed, including flight altitude, speed, forward overlap, and side overlap. The server controls the drone to fly along the preset route and capture garden images from multiple preset angles. In the embodiments of the present application, preferably, the multiple preset angles are five preset angles, namely one angle perpendicular to the ground and four angles inclined at 45 degrees to the ground. When planning the preset route, it is also necessary to ensure that the forward overlap rate is greater than or equal to 75% and the side overlap rate is greater than or equal to 65%. Capturing images at a vertical angle can obtain orthophotos, which are convenient for extracting the planar information of the landscape garden, such as roads and water systems. Capturing images at an inclined angle can obtain the side information of the garden, which helps to capture the facade features of trees, buildings, etc. By setting multiple shooting angles, the three-dimensional information of the landscape garden can be comprehensively recorded. For example, the server can instruct the drone to capture 1 set of images at a vertical angle and 4 sets of inclined images at 45-degree angles in the east, south, west, and north directions, for a total of 5 sets of multi-perspective garden image data. After the drone completes the shooting task, the image data is sent to the server in real time through a wireless transmission module (such as Wi-Fi, 4G), or stored in the on-board memory card and then transmitted to the server after the flight ends.

[0037] Step S102: Determine the feature points of the garden images. The feature points include control points and connection points. The control points are preset coordinate points, and the connection points are coordinate points that can be commonly recognized in multiple garden images.

[0038] In step S102, the server first determines the coordinate system of the garden images. The server selects the WGS84 coordinate system. WGS84 is a geodetic coordinate system that is directly compatible with GPS positioning results, which is convenient for subsequent spatial data fusion and applications. The control points are landmark points pre-laid on the garden site, with known high-precision three-dimensional coordinates. The control points are selected by using the image piercing points that are close to the center of the route, can map a large range, and have obvious ground object information as control points. On the selected control point images, the server marks at least 3 control points to form an effective control point set. Each control point should appear in at least 2 or more different preset-angle captured garden images. For example, in a three-dimensional modeling project of a landscape garden, the server determines 10 garden images located at the center of the route from 500 images as control point images, and a total of 5 control points are marked on these 10 control point images. Each control point is reflected in 3-4 different-angle control point images, and on average, each control point appears in 6 images.

[0039] Junction points are the same-named points that can be clearly identified on different garden images and are used to encrypt the geometric relationships between garden images. Different from control points, junction points do not have pre-determined three-dimensional coordinates, and their coordinates are obtained through aerial triangulation encryption calculation. The server automatically detects significant features on garden images, such as corner points and edges, using feature extraction algorithms (such as SIFT), to obtain a large number of candidate junction points. Then, feature matching algorithms (such as RANSAC) are used to match the same-named points between different images, and the incorrectly matched points are eliminated to obtain reliable junction points. To improve the accuracy and stability of aerial triangulation encryption, the server adds positioning constraint conditions to control points and junction points. The constraint conditions include origin constraint, scale constraint, direction constraint, and plane constraint. Origin constraint means fixing a certain control point as the coordinate origin to reduce the translational degree of freedom; scale constraint means fixing the distance between two control points to reduce the scale degree of freedom; direction constraint means fixing the connection direction of two control points to reduce the rotational degree of freedom; plane constraint means fixing the plane where three control points are located to reduce the tilt degree of freedom. By adding appropriate constraint conditions, the equivalent solutions in the process of aerial triangulation encryption can be eliminated, and the uniqueness and reliability of the solution results can be improved.

[0040] For example, in the above landscape gardening project, the server selects the control point at the park entrance as the origin, the connection line from the entrance to the visitor center as the direction constraint, and the three control points on the front square of the visitor center as the plane constraint, thus effectively constraining the spatial position and attitude of the entire park.

[0041] Step S103: Obtain the shooting time points of each garden image and the pos data of the drone at the shooting time points. The pos data includes the longitude, latitude, and altitude of the drone.

[0042] In step S103, when the drone flies according to the preset route, the shooting moment of each garden image is automatically recorded by the on-board control system, usually accurate to the millisecond level. The shooting moment will be written as metadata into the Exif (Exchangeable image file format) header of the garden image file. The server can obtain the shooting time point of each garden image by reading the Exif information of the garden image file. While shooting the garden images, the drone also continuously records its own POS data. The POS data is obtained through the on-board GPS / INS (Inertial Navigation System) integrated navigation system and includes the three-dimensional spatial position (longitude, latitude, altitude) and attitude (roll angle, pitch angle, yaw angle) information of the drone. The POS data can be stored separately from the garden image data to form an independent flight log file, or it can be directly written into the Exif header of the garden image. The server uses different methods for parsing and extraction according to the storage method of the data.

[0043] Step S104: According to the pos data and feature points, use aerial triangulation operation to perform feature point matching on each garden image, and obtain the three-dimensional point cloud data of each feature point.

[0044] In step S104, perform feature point matching on multiple garden images to obtain the corresponding relationship of the same feature point in multiple garden images; use the control point coordinates on the ground and the feature point coordinates in the garden image to construct the corresponding relationship between the image coordinate system and the ground coordinate system; according to the corresponding relationship, obtain the three-dimensional coordinates of each feature point in three-dimensional space; perform dense matching on the three-dimensional coordinates to generate three-dimensional point cloud data.

[0045] Specifically, the server first performs feature point matching on multiple garden images to find the corresponding relationship of the same feature point on different garden images. The server uses the SIFT (Scale-Invariant Feature Transform) feature point matching algorithm to achieve feature point matching. The control points are landmark points pre-laid in the garden site and have known high-precision three-dimensional coordinates (X, Y, Z). At the same time, these control points are also accurately marked on the garden image to obtain their image coordinates (x, y). The server constructs the conversion relationship from the image coordinate system to the ground coordinate system according to the image coordinates and ground coordinates of the control points. The conversion relationship includes the internal orientation elements (principal point, focal length, distortion parameters) and external orientation elements (position, attitude angle) of the garden image. By combining multiple control points and multiple garden images, the server calculates these parameters through adjustment to achieve accurate coordinate conversion. After obtaining the conversion relationship from the image coordinate system to the ground coordinate system, the server converts the image coordinates of the feature points into ground coordinates to obtain the three-dimensional space coordinates (X, Y, Z) of each feature point. The server further performs dense matching according to the three-dimensional coordinates of the feature points. Specifically, the server can use a dense matching algorithm based on belief propagation to perform pixel matching on multiple garden images to generate high-density three-dimensional point cloud data. Dense matching is to match all pixels of the garden image on the basis of feature point matching to obtain the three-dimensional coordinates of each pixel.

[0046] Step S105: Construct a three-dimensional point cloud model corresponding to the landscape garden according to the three-dimensional point cloud data.

[0047] In step S105, perform filtering processing and downsampling on the three-dimensional point cloud data to obtain the target three-dimensional point cloud data; generate a triangular mesh surface according to the target three-dimensional point cloud data to construct a three-dimensional point cloud model.

[0048] Specifically, the server first filters the three-dimensional point cloud data to remove noise points and outliers, improving the quality and accuracy of the point cloud. After filtering, the server downsamples the point cloud data to reduce data redundancy and improve the efficiency of modeling and rendering. Specifically, the server uses a statistical filtering algorithm to filter the three-dimensional point cloud data and a voxel downsampling algorithm to downsample the three-dimensional point cloud data. After filtering and downsampling, the three-dimensional point cloud data becomes more concise and regular, but it is still composed of discrete points and lacks topological structure and surface information. To better represent the geometric shape of the landscape object, the server generates a triangular mesh surface based on the optimized three-dimensional point cloud data and constructs a three-dimensional point cloud model of the landscape architecture according to the generated triangular mesh surface.

[0049] After step S105, the method further includes: determining whether there is a stratification phenomenon or a crossing phenomenon of feature points in the three-dimensional point cloud model; if it is determined that there is a stratification phenomenon or a crossing phenomenon of feature points in the three-dimensional point cloud model, then controlling the drone to re-acquire the garden images.

[0050] Specifically, after constructing the three-dimensional point cloud model, the server performs quality inspection and acceptance on the three-dimensional point cloud model to ensure the integrity, accuracy, and usability of the three-dimensional point cloud model. Among them, the server mainly checks for two types of point cloud model defects: the stratification phenomenon and the crossing phenomenon of feature points.

[0051] In a possible implementation, determining whether there is a stratification phenomenon of feature points in the three-dimensional point cloud model specifically includes: performing a stratification process on the three-dimensional point cloud model, dividing the three-dimensional point cloud data into multiple layers according to height information; performing clustering analysis on the point cloud data within each layer to obtain multiple point cloud clusters; determining multiple target point clouds included in the target point cloud cluster, where the target point cloud cluster is any one of the multiple point cloud clusters; calculating the height difference between the first target point cloud and the second target point cloud, where the first target point cloud is any one of the multiple target point clouds and the second target point cloud is any one of the multiple target point clouds other than the first target point cloud; if it is determined that the height difference is greater than or equal to a preset height difference, then determining the first target point cloud and the second target point cloud as stratified point clouds; determining whether the number of points in the stratified point cloud is greater than or equal to a preset number threshold; if it is determined that the number of points in the stratified point cloud is greater than or equal to the preset number threshold, then determining that there is a stratification phenomenon in the three-dimensional point cloud model.

[0052] Specifically, the server performs a stratification process on the entire three-dimensional point cloud model. The stratification process divides the point cloud data into multiple levels according to height information, and the height values of the point clouds within each level are within a certain range. The server implements the stratification process based on the Z coordinate histogram method of the point cloud.

[0053] For example, in a 3D reconstruction project of a large park, the 3D point cloud model generated by the server contains 100 million points, with a height range of 0 - 50 meters. The server first performs a histogram statistics on the Z coordinates of the point cloud and finds that the height distribution presents multiple obvious peaks, corresponding to different height levels of the ground, tree canopies, and buildings respectively. According to the peak-valley characteristics of the histogram, the server divides the point cloud into 5 height layers, such as 0 - 1 meter, 1 - 5 meters, 5 - 15 meters, and 15 - 50 meters. The number of point clouds and the height range within each layer are relatively uniform.

[0054] Within each height layer, the server performs a clustering analysis on the point cloud data. Clustering analysis is to divide the point clouds with similar spatial distributions into one cluster, and the point clouds between different clusters are relatively separated in space. The server can use algorithms such as K-Means and DBSCAN, or can also use a fast clustering algorithm based on octree and KD tree data structures. For example, within the 5 - 15 meter height layer of the above park point cloud model, the server uses the DBSCAN algorithm to cluster the point cloud, sets the clustering radius to 1 meter, and the minimum number of points to 100. The clustering result shows that there are 120 point cloud clusters in this layer, corresponding to different landscape elements such as tree canopies, lamp posts, and pavilions respectively. The point clouds within each point cloud cluster are relatively compactly distributed, and the distance between different point cloud clusters is greater than 1 meter, which conforms to the spatial distribution characteristics of the actual landscape. From the multiple point cloud clusters obtained in the previous step, the server randomly selects one as the target point cloud cluster, and selects two point clouds from within this point cloud cluster as the first target point cloud and the second target point cloud. These two target point clouds are any two point clouds within the point cloud cluster. The server calculates the height difference between the two target point clouds A and B, that is, ΔZ = |Z a -Z b |. The height difference reflects the distance between the target point clouds in the vertical direction and is an important indicator for judging whether there is a layering phenomenon. The server compares the height difference ΔZ between the target point clouds A and B with a preset height difference. If ΔZ is greater than or equal to the threshold, it is considered that the target point clouds A and B belong to different height levels and are layered point clouds; otherwise, it is considered that the target point clouds A and B belong to the same height level and are not layered point clouds. The setting of the preset height difference can be adjusted according to factors such as the density of the point cloud and the scene characteristics, and usually takes 2 - 5 times the average spacing of the point cloud. This application does not make a limitation on this.

[0055] The server counts all the number of point clouds determined to be stratified point clouds and compares it with a preset number threshold. If the number of stratified point clouds is greater than or equal to the preset number threshold, it is considered that there is a stratification phenomenon in the entire three-dimensional point cloud model and further repair processing is required; otherwise, it is considered that there is no significant stratification defect in the point cloud model and it can directly enter the subsequent application link. The setting of the preset number threshold needs to be weighed according to factors such as the total amount of point clouds and the allowable defect ratio, and usually takes 0.1%-1% of the total number of point clouds. This application does not limit this. Through the above steps, the server realizes the automatic judgment and estimation of the stratification phenomenon of the three-dimensional point cloud model.

[0056] In a possible implementation manner, determining whether there is an intersection phenomenon of feature points in the three-dimensional point cloud model specifically includes: calculating the spatial distance between the first target point cloud and the second target point cloud; if it is determined that the spatial distance is less than the preset distance threshold, it is determined that there is an intersection phenomenon in the three-dimensional point cloud model.

[0057] Specifically, the server calculates the spatial distance between the first target point cloud and the second target point cloud. The spatial distance refers to the closest distance between two point clouds in three-dimensional space and can be calculated using the Euclidean distance. The server compares the calculated spatial distance with the preset distance threshold. If the spatial distance is less than the preset distance threshold, it is considered that there is an intersection phenomenon between the first target point cloud and the second target point cloud, that is, the first target point cloud and the second target point cloud interpenetrate or mix; otherwise, it is considered that there is no intersection phenomenon between the first target point cloud and the second target point cloud, and they are relatively independent and separated in space. The setting of the preset distance threshold needs to be adjusted according to factors such as the density, scale, and scene characteristics of the point cloud, and usually takes 0.5-2 times the average spacing of the point cloud. This application does not limit this.

[0058] Step S106: Extract the texture information of the garden image according to the garden image.

[0059] In step S106, pixel blocks corresponding to each feature point are extracted from the garden image; the pixel blocks are color-corrected to obtain corrected pixel blocks, and the corrected pixel blocks are used as the texture information of the garden image.

[0060] Specifically, for each feature point, the server extracts a pixel block of a fixed size centered on that point. A pixel block refers to a square or rectangular area centered on the feature point, which contains the pixel information around the feature point and can express the local texture features of the feature point. The size of the pixel block needs to be set according to the resolution of the image and the detail level of the texture, taking values from 16×16 to 64×64 pixels. Since garden images may be affected by factors such as lighting, weather, and shooting angle, there may be differences in color between different images, which affects the consistency and authenticity of the texture. Therefore, the server performs color correction on the extracted pixel blocks to make their colors match a standard color card or a reference image. The color correction methods adopted by the server include correction algorithms such as white balance, color mapping, and histogram matching. After color correction, the server obtains the corrected pixel blocks corresponding to each feature point as the texture information of the feature point. The server summarizes the texture information of all feature points to generate a complete dataset of the texture information of the garden image.

[0061] Step S107: Map the texture information to the 3D point cloud model to obtain the 3D real scene model of the landscape garden.

[0062] In step S107, the server maps the extracted texture information of the garden image to the 3D point cloud model, attaches the corresponding texture block to each point cloud, and generates a 3D real scene model with real textures.

[0063] Referring to Figure 2 , this application also provides a device for constructing a 3D visual landscape garden. The device is a server, and the server includes an acquisition module 201 and a processing module 202. The acquisition module 201 is used to acquire multiple garden images of the landscape garden taken by a drone. The garden images are taken from multiple preset angles when the drone flies along a preset route. The processing module 202 is used to determine the feature points of the garden images. The feature points include control points and connection points. The control points are preset coordinate points, and the connection points are coordinate points that can be commonly recognized in multiple garden images. The acquisition module 201 is also used to acquire the shooting time points of each garden image and the pos data of the drone at the shooting time point. The pos data includes the longitude, latitude, and altitude of the drone. The processing module 202 is also used to perform feature point matching on each garden image according to the pos data and the feature points by using aerial triangulation to obtain the 3D point cloud data of each feature point. The processing module 202 is also used to construct a 3D point cloud model corresponding to the landscape garden according to the 3D point cloud data. The processing module 202 is also used to extract the texture information of the garden image according to the garden image. The processing module 202 is also used to map the texture information to the 3D point cloud model to obtain the 3D real scene model of the landscape garden.

[0064] In a possible implementation, after the processing module 202 constructs a three-dimensional point cloud model corresponding to the landscape garden based on the three-dimensional point cloud data, the method further includes: the processing module 202 determines whether there is a stratification phenomenon or an intersection phenomenon of feature points in the three-dimensional point cloud model; if the processing module 202 determines whether there is a stratification phenomenon or an intersection phenomenon of feature points in the three-dimensional point cloud model, it controls the drone to re-acquire garden images.

[0065] In a possible implementation, the processing module 202 determines whether there is a stratification phenomenon of feature points in the three-dimensional point cloud model, specifically including: the processing module 202 performs a stratification process on the three-dimensional point cloud model, divides the three-dimensional point cloud data into multiple layers according to the height information; the processing module 202 performs a clustering analysis on the point cloud data within each layer to obtain multiple point cloud clusters; the processing module 202 determines a plurality of target point clouds included in the target point cloud cluster, and the target point cloud cluster is any one of the multiple point cloud clusters; the processing module 202 calculates the height difference between the first target point cloud and the second target point cloud, where the first target point cloud is any one of the multiple target point clouds, and the second target point cloud is any one of the multiple target point clouds other than the first target point cloud; if the processing module 202 determines that the height difference is greater than or equal to a preset height difference, it determines that the first target point cloud and the second target point cloud are stratified point clouds; the processing module 202 determines whether the number of point clouds of the stratified point clouds is greater than or equal to a preset number threshold; if the processing module 202 determines whether the number of point clouds of the stratified point clouds is greater than or equal to a preset number threshold, it determines that there is a stratification phenomenon in the three-dimensional point cloud model.

[0066] In a possible implementation, the processing module 202 determines whether there is an intersection phenomenon of feature points in the three-dimensional point cloud model, specifically including: the processing module 202 calculates the spatial distance between the first target point cloud and the second target point cloud; if the processing module 202 determines that the spatial distance is less than a preset distance threshold, it determines that there is an intersection phenomenon in the three-dimensional point cloud model.

[0067] In a possible implementation, the processing module 202 performs feature point matching on each garden image by using aerial triangulation based on the pos data and feature points to obtain the three-dimensional point cloud data of each feature point, specifically including: the processing module 202 performs feature point matching on multiple garden images to obtain the corresponding relationship of the same feature point in the multiple garden images; the processing module 202 constructs the corresponding relationship between the image coordinate system and the ground coordinate system by using the control point coordinates on the ground and the feature point coordinates in the garden image; the processing module 202 obtains the three-dimensional coordinates of each feature point in the three-dimensional space according to the corresponding relationship; the processing module 202 performs dense matching on the three-dimensional coordinates to generate three-dimensional point cloud data.

[0068] In a possible implementation, the processing module 202 extracts the texture information of the garden image according to the garden image, specifically including: the processing module 202 extracts the pixel blocks corresponding to each feature point from the garden image; the processing module 202 performs color correction on the pixel blocks to obtain the corrected pixel blocks, and uses the corrected pixel blocks as the texture information of the garden image.

[0069] In a possible implementation, the processing module 202 constructs a three-dimensional point cloud model corresponding to the landscape garden according to the three-dimensional point cloud data, specifically including: the processing module 202 performs filtering processing and downsampling on the three-dimensional point cloud data to obtain the target three-dimensional point cloud data; the processing module 202 generates a triangular mesh surface according to the target three-dimensional point cloud data and constructs a three-dimensional point cloud model.

[0070] It should be noted that: when the device provided in the above embodiments realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be seen in the method embodiments, which will not be elaborated here.

[0071] This application also provides an electronic device. Refer to Figure 3 , Figure 3 is a schematic structural diagram of an electronic device provided in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0072] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0073] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0074] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0075] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines, and executes various functions of the server and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling the data stored in the memory 305. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a chip.

[0076] Among them, the memory 305 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above method embodiments, etc.; the data storage area may store the data involved in the above method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , the memory 305, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a method of constructing a three-dimensional visual landscape garden.

[0077] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input and obtain the data input by the user; while the processor 301 can be used to call the application program stored in the memory 305 for a method of constructing a three-dimensional visual landscape garden. When executed by one or more processors 301, the electronic device 300 is caused to execute one or more of the methods as described in the foregoing embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0078] This application also provides a computer-readable storage medium storing instructions. When executed by one or more processors 301, the electronic device 300 is caused to execute one or more of the methods as described in the foregoing embodiments.

[0079] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0080] In several implementation manners provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0081] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] In addition, in each embodiment of this application, the functional units can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0083] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, mobile hard disks, magnetic disks, or optical discs.

[0084] The foregoing are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will readily think of other implementation manners of the present disclosure after considering the specification and the practice of the present disclosure.

[0085] The present application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A construction method for three-dimensional visualized landscape gardening, characterized in that The method includes: Obtaining multiple garden images of the landscape garden captured by a drone, where the garden images are captured from multiple preset angles when the drone flies along a preset route; Determining the feature points of the garden images, where the feature points include control points and connection points, the control points are preset coordinate points, and the connection points are coordinate points that can be commonly recognized in multiple garden images; Obtaining the shooting time points of each garden image, and at the shooting time points, the pos data of the drone, where the pos data includes the longitude, latitude, and altitude of the drone; According to the pos data and the feature points, using aerial triangulation operation to perform feature point matching on each garden image to obtain the three-dimensional point cloud data of each feature point; Constructing a three-dimensional point cloud model corresponding to the landscape garden according to the three-dimensional point cloud data; Extracting the texture information of the garden image according to the garden image; Mapping the texture information to the three-dimensional point cloud model to obtain a three-dimensional real scene model of the landscape garden; After constructing the three-dimensional point cloud model corresponding to the landscape garden according to the three-dimensional point cloud data, the method further includes: Judging whether there is a stratification phenomenon or an intersection phenomenon of feature points in the three-dimensional point cloud model; If it is determined whether there is a stratification phenomenon or an intersection phenomenon of feature points in the three-dimensional point cloud model, then controlling the drone to re-obtain the garden image; The judging whether there is a stratification phenomenon of feature points in the three-dimensional point cloud model specifically includes: Performing a stratification process on the three-dimensional point cloud model, and dividing the three-dimensional point cloud data into multiple layers according to height information; Performing clustering analysis on the point cloud data within each layer to obtain multiple point cloud clusters; Determining multiple target point clouds included in a target point cloud cluster, where the target point cloud cluster is any one of the multiple point cloud clusters; Calculating the height difference between a first target point cloud and a second target point cloud, where the first target point cloud is any one of the multiple target point clouds, and the second target point cloud is any one of the multiple target point clouds except the first target point cloud; If it is determined that the height difference is greater than or equal to a preset height difference, then determining the first target point cloud and the second target point cloud as stratified point clouds; Judging whether the number of point clouds of the stratified point clouds is greater than or equal to a preset number threshold; If it is determined whether the number of point clouds of the stratified point clouds is greater than or equal to a preset number threshold, then determining that there is a stratification phenomenon in the three-dimensional point cloud model; The judging whether there is an intersection phenomenon of feature points in the three-dimensional point cloud model specifically includes: Calculating the spatial distance between a first target point cloud and a second target point cloud; If it is determined that the spatial distance is less than a preset distance threshold, then determining that there is an intersection phenomenon in the three-dimensional point cloud model.

2. The method according to claim 1, characterized in that, The specifically including of using aerial triangulation operation to perform feature point matching on each garden image according to the pos data and the feature points to obtain the three-dimensional point cloud data of each feature point: Perform feature point matching on multiple pieces of the garden images to obtain the corresponding relationships of the same feature points in multiple pieces of the garden images; Utilize the control point coordinates on the ground of the control points and the feature point coordinates in the garden images to construct the corresponding relationship between the image coordinate system and the ground coordinate system; According to the corresponding relationship, obtain the three-dimensional coordinates of each of the feature points in three-dimensional space; Perform dense matching on the three-dimensional coordinates to generate the three-dimensional point cloud data.

3. The method according to claim 1, characterized in that The extracting the texture information of the garden images according to the garden images specifically includes: Extract the pixel blocks corresponding to each feature point from the garden images; Perform color correction on the pixel blocks to obtain the corrected pixel blocks, and use the corrected pixel blocks as the texture information of the garden images.

4. The method according to claim 1, wherein The constructing the three-dimensional point cloud model corresponding to the landscape garden according to the three-dimensional point cloud data specifically includes: Perform filtering processing and downsampling on the three-dimensional point cloud data to obtain the target three-dimensional point cloud data; Generate a triangular mesh surface according to the target three-dimensional point cloud data to construct the three-dimensional point cloud model.

5. A construction device for three-dimensional visual landscape architecture, characterized in that, The device is used to execute the method according to any one of claims 1-4. The device includes an acquisition module (201) and a processing module (202), wherein: The acquisition module (201) is used to acquire multiple garden images of the landscape garden captured by a drone. The garden images are captured from multiple preset angles when the drone flies along a preset flight path; The processing module (202) is used to determine the feature points of the garden images. The feature points include control points and connection points. The control points are preset coordinate points, and the connection points are coordinate points that are commonly recognizable in multiple pieces of the garden images; The acquisition module (201) is further used to acquire the shooting time points of each of the garden images, and at the shooting time points, the pos data of the drone. The pos data includes the longitude, latitude and altitude of the drone; The processing module (202) is further used to perform feature point matching on each of the garden images according to the pos data and the feature points by using aerotriangulation to obtain the three-dimensional point cloud data of each of the feature points; The processing module (202) is further used to construct the three-dimensional point cloud model corresponding to the landscape garden according to the three-dimensional point cloud data; The processing module (202) is further used to extract the texture information of the garden images according to the garden images; The processing module (202) is further used to map the texture information to the three-dimensional point cloud model to obtain the three-dimensional real scene model of the landscape garden.

6. An electronic device, characterized in that, It includes a processor (301), a memory (305), a user interface (303) and a network interface (304). The memory (305) is used to store instructions. The user interface (303) and the network interface (304) are used to communicate with other devices. The processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method according to any one of claims 1-4.

Images