A method, system, terminal, and storage medium for measuring urban three-dimensional greening features based on a human-centered perspective and integrating ground and space.

Abstract

This application discloses a method, system, terminal, and storage medium for measuring urban 3D greening features based on a human-centered perspective and ground-air fusion, relating to the field of data processing technology. The method includes: acquiring multi-source data corresponding to a target area, including oblique photogrammetry data acquired from aerial equipment and laser point cloud data acquired from ground-based equipment; performing color processing on the laser point cloud data according to preset point cloud coloring operations to obtain target point cloud data; constructing a 3D greening model corresponding to the target area based on the oblique photogrammetry data and the target point cloud data; determining the corresponding human-centered viewpoint point in the 3D greening model according to a preset viewpoint height; constructing a ray beam based on the human-centered viewpoint point and preset field-of-view parameters; and determining the value of the greening feature evaluation index corresponding to the target area based on the collision detection results between the rays in the ray beam and the 3D greening model. This improves the accuracy of urban greening feature measurement.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, system, terminal and storage medium for measuring urban three-dimensional greening features based on a human-centered perspective and the integration of ground and air. Background Technology

[0002] Currently, urban greening assessment is receiving increasing attention. Existing technologies typically employ satellite remote sensing-based planar greening measurement techniques to measure urban greening characteristics. This technology uses satellite imagery data to calculate two-dimensional indicators such as green coverage rate and vegetation index to assess urban greening.

[0003] The problem with existing technologies is that using only a single data source can easily lead to data gaps due to factors such as building obstruction, resulting in misjudgments of greening information and hindering the improvement of the accuracy of urban greening characteristic measurement.

[0004] Therefore, the relevant technologies still need to be improved and developed. Summary of the Invention

[0005] The main purpose of this application is to provide a method, system, terminal and storage medium for measuring urban three-dimensional greening characteristics based on a human-centered perspective and the integration of ground and air. It aims to solve the technical problem that the use of a single data source in related technologies is prone to data loss due to factors such as building obstruction, which leads to misjudgment of greening information and is not conducive to improving the accuracy of urban greening characteristic measurement.

[0006] To achieve the above objectives, the first aspect of this application provides a method for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space integration, wherein the aforementioned method for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space integration includes:

[0007] Acquire multi-source data corresponding to the target area, including oblique photogrammetry data acquired by aerial equipment and laser point cloud data acquired by ground acquisition equipment;

[0008] According to the preset point cloud coloring processing operation, the above laser point cloud data is colored to obtain the target point cloud data;

[0009] Based on the above oblique photogrammetry data and the above target point cloud data, a three-dimensional greening model corresponding to the above target area is constructed.

[0010] Based on the preset viewpoint height, determine the corresponding human-centered viewpoint in the above three-dimensional greening model;

[0011] A ray beam is constructed based on the aforementioned human-centered viewpoint and preset field of view parameters. Based on the collision detection results between the rays in the aforementioned ray beam and the three-dimensional greening model, the values ​​of the greening feature evaluation indicators corresponding to the aforementioned target area are determined. The aforementioned greening feature evaluation indicators include greening density, line-of-sight depth, and greening feature diversity. The aforementioned greening density is used to characterize the proportion of greening elements covered within the field of view corresponding to the aforementioned ray beam. The aforementioned line-of-sight depth is used to characterize the distance between the greening elements within the aforementioned field of view and the aforementioned human-centered viewpoint. The aforementioned greening feature diversity is used to characterize the diversity of greening elements within the aforementioned field of view. The aforementioned greening elements are the grids corresponding to the greening features in the aforementioned three-dimensional greening model.

[0012] Optionally, the laser point cloud data is colored according to a preset point cloud coloring operation to obtain target point cloud data, including:

[0013] Obtain the panoramic image data corresponding to the above laser point cloud data;

[0014] Based on the color information in the panoramic image data, the laser point cloud data is colored to obtain the target point cloud data.

[0015] Optionally, the above-mentioned construction of a three-dimensional greening model corresponding to the target area based on the oblique photogrammetry data and the target point cloud data includes:

[0016] A first 3D model is constructed based on the aforementioned oblique photogrammetry data;

[0017] Construct a second 3D model based on the aforementioned target point cloud data;

[0018] Point cloud registration and fusion processing are performed on the first 3D model and the second 3D model to obtain the 3D greening model corresponding to the target area.

[0019] Optionally, the point cloud registration and fusion processing of the first 3D model and the second 3D model to obtain the 3D greening model corresponding to the target area includes:

[0020] Obtain at least one marker point in the target area, and perform preliminary alignment processing on the first three-dimensional model and the second three-dimensional model based on the marker point;

[0021] Based on the preset model registration tool, the model after the above preliminary alignment process is precisely registered and the point cloud is stitched together to obtain a fused point cloud model.

[0022] The above-mentioned fused point cloud model is subjected to semantic segmentation processing to obtain the above-mentioned three-dimensional greening model, wherein each grid cell in the above-mentioned three-dimensional greening model is labeled with semantic category information.

[0023] Optionally, the aforementioned greening density is the ratio of the projected area of ​​the aforementioned greening elements to the total area of ​​the aforementioned visual range within the aforementioned field of view.

[0024] Optionally, the aforementioned line-of-sight depth is the average distance of the target viewpoint within the aforementioned field of view;

[0025] The aforementioned target viewpoint distance includes the distance from the greening element corresponding to the target ray to the aforementioned human-centric viewpoint within the aforementioned field of view. The aforementioned target ray is the ray in the aforementioned ray beam that intersects with the greening element in the aforementioned three-dimensional greening model.

[0026] Optionally, the aforementioned greening feature diversity is determined by the Shannon diversity index based on the types of greening elements within the aforementioned field of view.

[0027] The second aspect of this application provides a three-dimensional urban greening feature measurement system based on a human-centered perspective and ground-space integration, wherein the aforementioned three-dimensional urban greening feature measurement system based on a human-centered perspective and ground-space integration includes:

[0028] The data acquisition module is used to acquire multi-source data corresponding to the target area. The multi-source data includes oblique photogrammetry data acquired by aerial equipment and laser point cloud data acquired by ground acquisition equipment.

[0029] The coloring processing module is used to perform coloring processing on the above laser point cloud data according to the preset point cloud coloring processing operation to obtain the target point cloud data.

[0030] The model building module is used to build a three-dimensional greening model corresponding to the target area based on the above oblique photography data and the above target point cloud data.

[0031] The viewpoint determination module is used to determine the corresponding human-centered viewpoint in the above-mentioned three-dimensional greening model based on the preset viewpoint height.

[0032] The measurement module is used to construct a ray beam based on the aforementioned human-centric viewpoint and preset field-of-view parameters. Based on the collision detection results between the rays in the ray beam and the three-dimensional greening model, the module determines the value of the greening feature evaluation index corresponding to the aforementioned target area. The aforementioned greening feature evaluation index includes greening density, line-of-sight depth, and greening feature diversity. The aforementioned greening density is used to characterize the proportion of greening elements covered within the field of view corresponding to the aforementioned ray beam. The aforementioned line-of-sight depth is used to characterize the distance between the greening elements within the aforementioned field of view and the aforementioned human-centric viewpoint. The aforementioned greening feature diversity is used to characterize the diversity of greening elements within the aforementioned field of view. The aforementioned greening elements are the grids corresponding to the greening features in the aforementioned three-dimensional greening model.

[0033] A third aspect of this application provides a terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements any of the steps of the above-mentioned method for measuring urban three-dimensional greening features based on a human-centered perspective and the integration of ground and space.

[0034] The fourth aspect of this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the steps of the above-described method for measuring urban three-dimensional greening features based on a human-centered perspective and the fusion of ground and space.

[0035] As can be seen from the above, in this application, multi-source data corresponding to the target area is acquired, including oblique photogrammetry data acquired by aerial equipment and laser point cloud data acquired by ground-based equipment. The laser point cloud data is then colored according to a preset point cloud coloring operation to obtain target point cloud data. A three-dimensional greening model corresponding to the target area is constructed based on the oblique photogrammetry data and the target point cloud data. A human-centric viewpoint is determined in the three-dimensional greening model based on a preset viewpoint height. Rays are constructed based on the human-centric viewpoint and preset field-of-view parameters. Based on the collision detection results between the rays in the aforementioned ray beam and the three-dimensional greening model, the values ​​of the greening feature evaluation indicators corresponding to the aforementioned target area are determined. The aforementioned greening feature evaluation indicators include greening density, line-of-sight depth, and greening feature diversity. The aforementioned greening density is used to characterize the proportion of greening elements covered within the field of view corresponding to the aforementioned ray beam. The aforementioned line-of-sight depth is used to characterize the distance between the greening elements within the aforementioned field of view and the aforementioned human-centric viewpoint. The aforementioned greening feature diversity is used to characterize the diversity of greening elements within the aforementioned field of view. The aforementioned greening elements are the grids corresponding to the greening features in the aforementioned three-dimensional greening model.

[0036] Compared with existing technologies, the urban 3D greening feature measurement method based on a human-centered perspective and ground-air fusion provided in this application acquires multi-source data corresponding to the target area to measure the urban 3D greening features. The multi-source data includes oblique photogrammetry data acquired by aerial equipment and laser point cloud data acquired by ground-based equipment. Based on the 3D greening model obtained after processing the multi-source data and the human-centered perspective point determined based on a preset viewpoint height, the evaluation indicators of greening features such as greening density, line-of-sight depth, and greening feature diversity are calculated to achieve the measurement of urban 3D greening features. Thus, using multi-source data instead of a single data source helps solve the problem of missing data, improves the accuracy of greening information judgment, and thereby improves the accuracy of urban greening feature measurement. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating a method for measuring urban three-dimensional greening features based on a human-centered perspective and the integration of ground and air, as provided in an embodiment of this application.

[0039] Figure 2 This is a schematic diagram of the components of a three-dimensional urban greening feature measurement system based on a human-centered perspective and the integration of ground and air, provided in an embodiment of this application.

[0040] Figure 3 This is a block diagram illustrating the internal structure of a terminal provided in an embodiment of this application. Detailed Implementation

[0041] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0042] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0043] It should also be understood that the terminology used in this application specification is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0044] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0045] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to classification." Similarly, the phrases "if determined" or "if classified to [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once classified to [the described condition or event]," or "in response to classification to [the described condition or event]."

[0046] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0047] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0048] Currently, urban greening assessment is receiving increasing attention. Existing technologies typically employ satellite remote sensing-based planar greening measurement techniques to acquire and analyze greening information. This technology calculates two-dimensional indicators such as green coverage and vegetation index using satellite imagery data, providing data support for urban greening measurement.

[0049] In one application scenario, a single aerial photogrammetry technique is used, specifically, traditional vertical aerial photography is employed to obtain spatial distribution information of urban green spaces, which improves the accuracy and efficiency of data acquisition to a certain extent.

[0050] In another application scenario, ground-based laser scanning technology is used, which can obtain high-precision three-dimensional point cloud data, providing a technical foundation for the refined modeling of greening elements.

[0051] The problem with existing technologies is that they rely on a single data source, resulting in insufficient data accuracy and susceptibility to data gaps due to factors such as building obstruction. This can lead to misjudgments of greening information and hinder the accuracy of urban greening characteristic measurements. Furthermore, existing technologies cannot comprehensively reflect the vertical spatial distribution and three-dimensional morphology of urban greening, especially in high-density urban environments where the vertical layering and spatial hierarchy of greening cannot be accurately represented. Simultaneously, the indicator system is incomplete, lacking a three-dimensional quantitative indicator system for greening characteristics from a human-centered perspective, thus failing to accurately reflect the actual impact of greening on people's visual perception and spatial experience. Moreover, the low spatial matching accuracy makes it difficult for traditional methods to achieve a precise correspondence between greening characteristics and people's activity spaces, failing to provide accurate spatial positioning information for urban planning and landscape design.

[0052] To address at least one of the aforementioned technical problems, this application proposes a method for measuring urban three-dimensional greening features based on a human-centered perspective and ground-air fusion. This method constructs a high-precision urban three-dimensional greening model by integrating UAV oblique photography and ground mobile mapping technologies, and establishes a three-dimensional greening feature quantification index system based on a human-centered perspective, thereby achieving accurate extraction and calculation of key features such as greening density, line-of-sight depth, and greening feature diversity.

[0053] Specifically, in this application, multi-source data corresponding to the target area is acquired, including oblique photogrammetry data obtained from aerial equipment and laser point cloud data obtained from ground-based equipment. The laser point cloud data is then colored according to a preset point cloud coloring operation to obtain target point cloud data. A three-dimensional greening model corresponding to the target area is constructed based on the oblique photogrammetry data and the target point cloud data. A human-centric viewpoint is determined in the three-dimensional greening model based on a preset viewpoint height. Rays are constructed based on the human-centric viewpoint and preset field-of-view parameters. Based on the collision detection results between the rays in the aforementioned ray beam and the three-dimensional greening model, the values ​​of the greening feature evaluation indicators corresponding to the aforementioned target area are determined. The aforementioned greening feature evaluation indicators include greening density, line-of-sight depth, and greening feature diversity. The aforementioned greening density is used to characterize the proportion of greening elements covered within the field of view corresponding to the aforementioned ray beam. The aforementioned line-of-sight depth is used to characterize the distance between the greening elements within the aforementioned field of view and the aforementioned human-centric viewpoint. The aforementioned greening feature diversity is used to characterize the diversity of greening elements within the aforementioned field of view. The aforementioned greening elements are the grids corresponding to the greening features in the aforementioned three-dimensional greening model.

[0054] Compared with existing technologies, the urban 3D greening feature measurement method based on a human-centered perspective and ground-air fusion provided in this application acquires multi-source data corresponding to the target area to measure the urban 3D greening features. The multi-source data includes oblique photogrammetry data acquired by aerial equipment and laser point cloud data acquired by ground-based equipment. Based on the 3D greening model obtained after processing the multi-source data and the human-centered perspective point determined based on a preset viewpoint height, the evaluation indicators of greening features such as greening density, line-of-sight depth, and greening feature diversity are calculated to achieve the measurement of urban 3D greening features. Thus, using multi-source data instead of a single data source helps solve the problem of missing data, improves the accuracy of greening information judgment, and thereby improves the accuracy of urban greening feature measurement.

[0055] like Figure 1 As shown in the embodiments of this application, a method for measuring urban three-dimensional greening features based on a human-centered perspective and the integration of ground and air is provided. Specifically, the method includes the following steps:

[0056] Step S100: Obtain multi-source data corresponding to the target area, wherein the multi-source data includes oblique photography data acquired based on aerial equipment and laser point cloud data acquired based on ground acquisition equipment.

[0057] The target area mentioned above is the area where three-dimensional greening feature measurement is required. In this embodiment, it is specifically a pre-defined urban area, but this is not a specific limitation. In this embodiment, an integrated ground-air data acquisition scheme is adopted, with the aerial acquisition device being a drone and the ground acquisition device being a handheld laser scanning device.

[0058] Specifically, a collaborative data acquisition model combining UAV oblique photography and ground-based mobile mapping is adopted to address the limitations of single data sources in complex urban environments through multi-source data fusion. The UAV oblique photography system is equipped with a pre-set flight platform and camera, enabling vertical mapping at a flight altitude of 400 meters. Downward shooting and tilting four directions Multi-angle shooting. In this embodiment, high overlap parameters of 75% lateral overlap and 85% forward overlap are set. The 75% lateral overlap ensures sufficient overlap between adjacent flight strips for accurate image matching, while the 85% forward overlap provides sufficient baseline length for stereo mapping. This parameter configuration optimizes acquisition efficiency while ensuring data integrity, ensuring sufficient overlap between adjacent images for stereo matching and 3D reconstruction, and guaranteeing the accuracy and efficiency of data processing, ensuring full coverage of urban green areas. The flight path adopts a combination of parallel and intersecting strategies, with a shooting interval of 3.4 seconds / frame and a sampling speed controlled at 15 meters / second. High-resolution image data acquisition is achieved through precise control of flight parameters.

[0059] The ground-based mobile mapping and data acquisition system utilizes handheld laser scanning equipment to collect comprehensive data across the entire target area, forming a complementary data acquisition system with UAV oblique photography. Operators move at a slow speed of approximately 2 meters per second, employing S-shaped or Z-shaped paths to ensure complete coverage of key areas such as building facades, plaza spaces, and underpasses. A closed-loop acquisition strategy ensures data integrity and continuity. This ground-based acquisition method can obtain detailed near-ground greening information that is difficult for UAVs to access, effectively compensating for blind spots in aerial photography and achieving integrated ground-air collaborative data acquisition.

[0060] Thus, the integrated ground-air acquisition scheme is conducive to improving the integrity of data coverage and significantly increases the effective data acquisition rate compared with the single aerial photography method; multi-angle oblique image data provides sufficient geometric constraints for subsequent 3D reconstruction, and the model reconstruction accuracy is significantly improved compared with traditional vertical photography; the integration of ground supplementary mapping data enables the effective preservation of greening information in building shadow areas and complex terrain areas, solving the problem of insufficient adaptability of a single data source in complex urban environments.

[0061] Step S200: According to the preset point cloud coloring processing operation, the laser point cloud data is colored to obtain the target point cloud data.

[0062] Specifically, the laser point cloud data can be colorized based on a preset coloring processing tool. In this embodiment, the above-mentioned coloring processing of the laser point cloud data according to the preset point cloud coloring processing operation to obtain the target point cloud data includes:

[0063] Obtain the panoramic image data corresponding to the above laser point cloud data;

[0064] Based on the color information in the panoramic image data, the laser point cloud data is colored to obtain the target point cloud data.

[0065] The aforementioned panoramic image data is acquired using a pre-set handheld laser scanning device to record the true colors of the scanned scene and can serve as the original data source for laser point cloud data coloring. In this embodiment, coloring processing is performed using pre-set processing software (e.g., Lixel Studio), but this is not intended as a specific limitation.

[0066] Step S300: Based on the above oblique photography data and the above target point cloud data, construct a three-dimensional greening model corresponding to the above target area.

[0067] In this embodiment of the application, the construction of the three-dimensional greening model corresponding to the target area based on the oblique photogrammetry data and the target point cloud data includes:

[0068] A first 3D model is constructed based on the aforementioned oblique photogrammetry data;

[0069] Construct a second 3D model based on the aforementioned target point cloud data;

[0070] Point cloud registration and fusion processing are performed on the first 3D model and the second 3D model to obtain the 3D greening model corresponding to the target area.

[0071] The first three-dimensional model is a city three-dimensional model generated from oblique photogrammetry data, and the second three-dimensional model is a city three-dimensional model generated from target point cloud data. In this embodiment, point cloud registration and fusion processing are performed on the two to obtain a more accurate three-dimensional greening model.

[0072] Specifically, the point cloud registration and fusion processing of the first 3D model and the second 3D model are performed to obtain the 3D greening model corresponding to the target area, including:

[0073] Obtain at least one marker point in the target area, and perform preliminary alignment processing on the first three-dimensional model and the second three-dimensional model based on the marker point;

[0074] Based on the preset model registration tool, the model after the above preliminary alignment process is precisely registered and the point cloud is stitched together to obtain a fused point cloud model.

[0075] The above-mentioned fused point cloud model is subjected to semantic segmentation processing to obtain the above-mentioned three-dimensional greening model, wherein each grid cell in the above-mentioned three-dimensional greening model is labeled with semantic category information.

[0076] In this embodiment, the processing procedure in a specific application scenario is used as an example for detailed explanation. Specifically, the 3D greening model reconstruction scheme is based on a processing flow that combines multi-source data fusion and deep learning semantic segmentation to achieve automated conversion from raw point cloud image data to a semantic 3D greening model.

[0077] In one application scenario, before generating the first and / or second 3D models, the corresponding data can be preprocessed to remove outliers and improve the quality of the generated models. Specifically, the data preprocessing stage uses the Reconstruct Master software platform to perform quality screening and aerial triangulation (i.e., aerial triangulation calculation) on the image data. Quality assessment indicators such as the number of key points, the number of connect points, and reprojection errors are analyzed to determine whether the data meets the modeling accuracy requirements. The denoising process employs outlier filtering algorithms based on statistical analysis and anomaly detection algorithms based on geometric constraints. Combined with the automated denoising function of DasViewer Beta software and the manual editing function of the point cloud comparison software (CloudCompare), invalid points introduced by non-environmental factors such as people and vehicles, as well as sensor errors, are systematically removed. Simultaneously, outliers caused by occlusion or positioning offsets are eliminated, ensuring the purity and reliability of the point cloud data.

[0078] Point cloud registration and fusion processing employs a combined approach based on control point alignment and global registration. First, preliminary alignment of the oblique photogrammetric point cloud and the handheld laser point cloud is achieved by manually selecting control points (i.e., marker points) with distinct ground features. Then, precise registration is performed using the Fine Registration module of the point cloud comparison software (CloudCompare). The iterative nearest point (ICP) algorithm automatically stitches together multiple point cloud segments, ultimately generating fused point cloud data (i.e., the fused point cloud model) in a unified coordinate system. This fused point cloud integrates the advantages of multi-source data. For repetitive data at the same location, a precision-first principle is adopted: high-rise objects such as buildings are primarily represented by aerial oblique photogrammetric data, while ground-based greening elements are primarily represented by ground-based laser scan data. Data quality is ensured through geometric accuracy evaluation and semantic consistency checks. The main purpose of the fusion processing is to integrate the respective advantages of the aerial and ground-based data sets, achieving data complementarity and improved accuracy. The fused point cloud density reaches 250-300 points / square meter, while retaining RGB color information and laser reflection intensity information, providing rich feature data for subsequent semantic segmentation.

[0079] Furthermore, semantic segmentation is performed on the fused point cloud model to obtain a 3D greening model. Specifically, the Planarity-sensible Semantic Segmentation (PSSNet) algorithm is used to automatically identify and classify urban scene elements. This algorithm can effectively identify different element categories such as ground, buildings, vegetation, and roads. To ensure segmentation accuracy, a 3D urban mesh annotator is used for interactive label correction, and a semi-automated processing method guided by expert knowledge ensures the accuracy of semantic information. The processed 3D model is output in standard formats such as obj, b3dm, and las. Each grid cell in the model is labeled with clear semantic category information, providing a precise data foundation for subsequent human-centered feature extraction.

[0080] It should be noted that in practical applications, other methods can also be used, such as semantic annotation through other platforms or manual annotation, to add semantic category information to the 3D model. No specific limitations are made here. The aforementioned semantic category information is used to indicate the type of element corresponding to each grid cell, for example, to indicate whether the grid cell represents a tree, grassland, or other greening feature.

[0081] Thus, semantic segmentation accuracy is significantly improved, showing a clear improvement compared to traditional color feature-based classification methods; the geometric accuracy of the 3D model reaches the centimeter level, meeting the requirements for refined analysis of urban greening; and the automated processing flow greatly improves the efficiency of model reconstruction in large-scale urban areas, significantly reducing the workload and time cost of manual processing.

[0082] Step S400: Determine the corresponding human-centered viewpoint in the above three-dimensional greening model based on the preset viewpoint height.

[0083] Specifically, the human-centered viewpoint in the aforementioned 3D greening model is determined based on a preset viewpoint height, including:

[0084] Obtain multiple candidate coordinate points within the target area mentioned above;

[0085] Adjust the height of the candidate coordinate points according to the above viewpoint height to obtain multiple human-centric viewpoints.

[0086] The viewpoint height can be preset according to actual needs. In this embodiment, the preset viewpoint height is 1.6 meters, but it is not a specific limitation.

[0087] In one application scenario, multiple human-centric viewpoints can be randomly generated in the aforementioned 3D greening model based on the preset viewpoint height and the number of pre-selected viewpoints. This is not considered a specific limitation. These human-centric viewpoints are used to simulate a person's perspective for further analysis and processing.

[0088] Step S500: Construct a ray beam based on the aforementioned human-centered viewpoint and preset field of view parameters. Based on the collision detection results between the rays in the ray beam and the three-dimensional greening model, determine the value of the greening feature evaluation index corresponding to the aforementioned target area. The aforementioned greening feature evaluation index includes greening density, line-of-sight depth, and greening feature diversity. The aforementioned greening density is used to characterize the proportion of greening elements covered within the field of view corresponding to the aforementioned ray beam. The aforementioned line-of-sight depth is used to characterize the distance between the greening elements within the aforementioned field of view and the aforementioned human-centered viewpoint. The aforementioned greening feature diversity is used to characterize the diversity of greening elements within the aforementioned field of view. The aforementioned greening elements are the grids corresponding to the greening features in the aforementioned three-dimensional greening model.

[0089] Specifically, in this embodiment, based on a human visual field geometric model and a reverse ray tracing algorithm, spatial localization and quantitative analysis of urban greening features from the perspective of human visual perception are achieved. This technical solution constructs a ray beam simulating the human eye's line of sight, and determines the spatial attributes and geometric features of visible greening elements based on the collision detection results between the ray beam and the three-dimensional greening model. In some application scenarios, voxel traversal algorithms or ray casting algorithms can be used to replace reverse ray tracing, achieving spatial localization of greening features through different spatial traversal methods; no specific limitations are made here.

[0090] Visual field geometry modeling uses the collected coordinates of the target object (e.g., an operator) as the analysis reference point, employing a standard human eye height of 1.6 meters to construct a three-dimensional visual field analysis framework that conforms to human visual characteristics. The setting of visual field parameters is based on research findings in ergonomics and visual physiology; the vertical visual field angle range is set from the horizontal plane of the line of sight upwards. Towards downwards ( This parameter range covers the effective visual area of ​​the human eye in its natural state; the horizontal visual field angle extends to the left and right of the line of sight. ( This conforms to the physiological characteristics of human binocular fusion vision; the maximum radius of the visual field is set at 50 meters, and green elements beyond this distance are considered to have no significant impact on human visual perception.

[0091] The reverse ray tracing algorithm emits dense visual rays from the human-centric viewpoint across the entire field of view, with the ray spacing set in both the vertical and horizontal directions. A regular ray mesh is formed for spatial sampling. Each ray undergoes collision detection with the 3D greening model, and the spatial distribution information of greening elements within the viewport is obtained by calculating the intersection points of the ray and the model surface. The collision detection algorithm adopts a hierarchical bounding box acceleration structure, which significantly improves the computational efficiency of ray tracing and can complete the viewport analysis of complex urban scenes within a reasonable time. The ray tracing results include the spatial coordinates, distance information, surface normal vector, and semantic category information (i.e., semantic labels) of each sampling point, providing complete geometric and semantic data for subsequent feature quantization calculations.

[0092] Thus, by introducing ray tracing technology from computer graphics into the field of urban greening analysis, visual perception simulation based on real physical optics principles has been achieved. The accuracy of the view domain analysis is significantly improved compared to traditional planar projection-based methods, accurately reflecting the occlusion relationship of greening elements on human vision in three-dimensional space. The algorithm is highly automated, capable of batch processing view domain analysis tasks for a large number of observation points, significantly improving processing efficiency compared to manual surveys. The analysis results show good consistency with actual human visual perception, which is conducive to realizing human-centered urban greening assessment.

[0093] In this embodiment, a complete mathematical calculation framework is also established to realize the specific calculation of multiple greening characteristic evaluation indicators, thereby achieving accurate quantification of greening characteristics. Specifically, a reverse ray tracing algorithm is used to generate visual rays emanating from the center of the line of sight into the field of view, with the interval between each ray set to be [number missing] in both the vertical and horizontal directions. This forms a view area grid. Within this grid, collision detection with the 3D greening model is used to obtain the greening features within the view area, and the evaluation index values ​​of the greening features are calculated.

[0094] It should be noted that, in this embodiment, the greening element is the mesh corresponding to the greening feature in the three-dimensional greening model. The greening feature in the above-mentioned three-dimensional greening model can be determined based on the semantic category information obtained after semantic segmentation, or obtained based on a preset greening feature recognition platform or manual recognition, and is not specifically limited here.

[0095] The aforementioned greening density is the ratio of the projected area of ​​the aforementioned greening elements within the aforementioned field of view to the total area of ​​the aforementioned field of view. It is calculated by statistically analyzing the proportion of the field of view covered by greening elements.

[0096] ;

[0097] in, Represents green density. This represents the total projected area of ​​the greening elements within the view grid. This refers to the total area within the field of vision. This indicator accurately reflects the spatial proportion of green elements within the human eye's field of vision, providing technical support for the precise quantification of green coverage.

[0098] The aforementioned line-of-sight depth is the average distance of the target viewpoint within the aforementioned field of view;

[0099] The aforementioned target viewpoint distance includes the distance from the greening element corresponding to the target ray to the aforementioned human-centric viewpoint within the aforementioned field of view. The aforementioned target ray is the ray in the aforementioned ray beam that intersects with the greening element in the aforementioned three-dimensional greening model.

[0100] Specifically, line of sight depth This is used to indicate the average distance to green elements within the field of view, achieved by calculating the average distance of all rays from the center of the line of sight to the green element:

[0101] ;

[0102] in, This represents the total number of rays involved in depth calculation within the field of view. For the first The distance of a ray from the human-centric viewpoint to a green element is obtained through collision detection between the ray and the 3D greening model. Rays that do not collide with green elements are not included in the depth calculation to ensure the accuracy of the indicator. This represents the total number of rays within the field of view that collide with the primary green color. This is the average of all ray depth results. This index reflects the spatial distance relationship between green elements and the observer, providing a quantitative basis for the depth analysis of green spaces.

[0103] The aforementioned diversity of greening features is determined by the Shannon diversity index, which is based on the types of greening elements within the aforementioned field of view.

[0104] Diverse characteristics of greening The Shannon diversity index was used for quantification, which considers the proportion of different plant species within the total number of species in the field of view. It should be noted that the semantic category information mentioned above can also be used to indicate the plant species to which a corresponding greening feature belongs. The formula for calculating the diversity of greening features is as follows:

[0105] ;

[0106] in, The number of different plant species within the field of view. For the first The proportion of plant species to the total number of greening elements in the visual field. This indicator reflects the species diversity of greening elements.

[0107] Thus, in this embodiment of the application, a three-dimensional greening feature quantification standard based on a human-centered perspective is established, filling the gap in the three-dimensional spatial expression of traditional planar greening indicators; the calculation results have a good positive correlation with the subjective perception evaluation of the population, verifying the scientificity and practicality of the indicator system; the automated calculation process can quickly process the greening feature analysis task of large-scale urban areas, providing an efficient technical tool for urban greening planning and evaluation.

[0108] As can be seen, the urban 3D greening feature measurement method based on a human-centered perspective and ground-air fusion provided in this application acquires multi-source data corresponding to the target area to achieve the measurement of urban 3D greening features. The multi-source data includes oblique photogrammetry data acquired by aerial equipment and laser point cloud data acquired by ground-based equipment. Based on the 3D greening model obtained after processing the multi-source data, and the human-centered perspective point determined based on a preset viewpoint height, the evaluation index values ​​of greening features such as greening density, line-of-sight depth, and greening feature diversity are calculated to achieve the measurement of urban 3D greening features. Thus, using multi-source data instead of a single data source helps solve the problem of data gaps, improves the accuracy of greening information judgment, and thereby improves the accuracy of urban greening feature measurement.

[0109] Specifically, this application describes four key steps in its method for measuring urban 3D greening features based on a human-centered perspective and ground-air fusion: establishing a ground-air integrated data acquisition mechanism, acquiring multi-angle urban greening image data through UAV oblique photography, and simultaneously using ground-based mobile mapping equipment to supplement the data collection of obscured areas, thus achieving organic integration of data sources; constructing a 3D semantic segmentation and model reconstruction process, using deep learning algorithms to fuse multi-source point clouds and image data to generate a high-precision 3D greening model with semantic labels; designing a human-centered perspective feature extraction algorithm, based on the geometric model of the human eye's field of vision and inverse ray tracing technology, to achieve spatial positioning of greening features from the perspective of human visual perception; and establishing a 3D feature quantification calculation framework, using mathematical modeling methods to accurately calculate key indicators such as greening density, line-of-sight depth, and vegetation diversity. Through the above technical solutions, this application can significantly improve the accuracy and completeness of urban greening feature extraction, achieving centimeter-level spatial positioning accuracy and significantly improving data coverage completeness; processing efficiency is significantly improved, automation is greatly enhanced, and the processing efficiency of large-scale areas is significantly improved compared to traditional methods. Establish a three-dimensional greening evaluation system based on a human-centered perspective. The characteristic indicators based on the human-centered perspective have good consistency with actual visual perception, providing data support and decision-making basis for urban planning, landscape design and greening management.

[0110] In some application scenarios, a data acquisition scheme based on LiDAR can be used, employing airborne laser scanners and ground-based mobile laser scanners as the main data sources, with oblique photogrammetry images as auxiliary data. This is mainly used to provide RGB color information and texture features, making up for the inability of LiDAR to directly obtain color information. This scheme is suitable for application scenarios with extremely high geometric accuracy requirements.

[0111] In other application scenarios, a multi-temporal dynamic monitoring scheme can be adopted. By regularly and repeatedly collecting data to establish a time series database, dynamic changes in urban greening characteristics can be monitored and trend analysis can be performed. This scheme is suitable for long-term greening effect evaluation and management.

[0112] Furthermore, a multi-scale analysis scheme can be adopted, which adjusts the field parameters and the spatial scale of feature calculation according to different application needs, enabling greening analysis at different levels, from individual buildings to urban areas.

[0113] like Figure 2 As shown, corresponding to the above-mentioned method for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space integration, this application embodiment also provides a system for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space integration. The above-mentioned system for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space integration includes:

[0114] The data acquisition module 210 is used to acquire multi-source data corresponding to the target area, wherein the multi-source data includes oblique photography data acquired based on aerial equipment and laser point cloud data acquired based on ground acquisition equipment.

[0115] The coloring processing module 220 is used to perform coloring processing on the above laser point cloud data according to the preset point cloud coloring processing operation to obtain target point cloud data.

[0116] The model building module 230 is used to build a three-dimensional greening model corresponding to the target area based on the above oblique photography data and the above target point cloud data.

[0117] The viewpoint determination module 240 is used to determine the corresponding human-centered viewpoint in the above-mentioned three-dimensional greening model based on the preset viewpoint height.

[0118] The measurement module 250 is used to construct a ray beam based on the aforementioned human-centric viewpoint and preset field of view parameters. Based on the collision detection results between the rays in the aforementioned ray beam and the three-dimensional greening model, the module determines the value of the greening feature evaluation index corresponding to the aforementioned target area. The aforementioned greening feature evaluation index includes greening density, line-of-sight depth, and greening feature diversity. The aforementioned greening density is used to characterize the proportion of greening elements covered within the field of view corresponding to the aforementioned ray beam. The aforementioned line-of-sight depth is used to characterize the distance between the greening elements within the aforementioned field of view and the aforementioned human-centric viewpoint. The aforementioned greening feature diversity is used to characterize the diversity of greening elements within the aforementioned field of view. The aforementioned greening elements are the grids corresponding to the greening features in the aforementioned three-dimensional greening model.

[0119] Thus, multi-source data corresponding to the target area is acquired to measure the three-dimensional greening characteristics of the city. This multi-source data includes oblique photogrammetry data acquired by aerial equipment and laser point cloud data acquired by ground-based equipment. Based on the three-dimensional greening model obtained after processing the multi-source data, and the human-centered viewpoint determined based on a preset viewpoint height, evaluation indicators for greening characteristics such as greening density, line-of-sight depth, and diversity of greening features are calculated to achieve the measurement of the city's three-dimensional greening characteristics. Using multi-source data instead of a single data source helps address the problem of missing data, improves the accuracy of greening information assessment, and thus enhances the accuracy of urban greening characteristic measurement.

[0120] It should be noted that the specific structure and implementation of the above-mentioned urban three-dimensional greening feature measurement system based on human-centered perspective and ground-space integration, as well as its various modules or units, can be referred to the corresponding descriptions in the above method embodiments, and will not be repeated here.

[0121] It should be noted that the division of the various modules of the above-mentioned urban three-dimensional greening feature measurement system based on human-centered perspective and ground-space integration is not unique and is not intended as a specific limitation.

[0122] Based on the above embodiments, this application also provides a terminal, the principle block diagram of which can be as follows: Figure 3 As shown. The terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps of any of the above-mentioned methods for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space fusion. The display screen can be a liquid crystal display (LCD) or an e-ink display.

[0123] Those skilled in the art will understand that Figure 3 The block diagram shown is only a partial structural diagram related to the solution of this application and does not constitute a limitation on the terminal on which the solution of this application is applied. The specific terminal may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0124] In one embodiment, a terminal is provided, the terminal including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of any of the urban three-dimensional greening feature measurement methods based on human-centered perspective and ground-space fusion provided in the embodiments of this application.

[0125] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of any of the urban three-dimensional greening feature measurement methods based on a human-centered perspective and ground-space fusion provided in this application.

[0126] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0127] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0128] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0129] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0130] In the embodiments provided in this application, it should be understood that the disclosed systems / terminal devices and methods can be implemented in other ways. For example, the system / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units described above is merely a logical functional division, and in actual implementation, it can be divided in other ways. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0131] If the integrated modules / units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, and software distribution media, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0132] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions are not in essence a departure from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space integration, characterized in that, The method includes: Acquire multi-source data corresponding to the target area, wherein the multi-source data includes oblique photography data acquired based on aerial equipment and laser point cloud data acquired based on ground acquisition equipment; According to the preset point cloud coloring processing operation, the laser point cloud data is colored to obtain the target point cloud data; Based on the oblique photography data and the target point cloud data, a three-dimensional greening model corresponding to the target area is constructed; Based on the preset viewpoint height, determine the corresponding human-centered viewpoint in the three-dimensional greening model; A ray beam is constructed based on the human-centric viewpoint and preset field of view parameters. Based on the collision detection results between the rays in the ray beam and the three-dimensional greening model, the value of the greening feature evaluation index corresponding to the target area is determined. The greening feature evaluation index includes greening density, line-of-sight depth, and greening feature diversity. The greening density is used to characterize the proportion of greening elements covered within the field of view corresponding to the ray beam. The line-of-sight depth is used to characterize the distance between the greening elements within the field of view and the human-centric viewpoint. The greening feature diversity is used to characterize the diversity of greening elements within the field of view. The greening elements are the grids corresponding to the greening features in the three-dimensional greening model. Wherein, the line-of-sight depth is used to indicate the average distance of green elements within the field of view, and the line-of-sight depth is the average distance of the target viewpoint within the field of view; the target viewpoint distance includes the distance from the green element corresponding to the target ray to the human-centric viewpoint within the field of view, and the target ray is the ray in the ray beam that intersects with the green elements in the three-dimensional greening model. The formula for calculating the line-of-sight depth is: , The depth of sight, The total number of target rays participating in depth calculation within the field of view. For the first The distance from the human-centric perspective point to the greening element. Obtained through collision detection between the target ray and the 3D greening model; The greening feature diversity is determined by the Shannon diversity index based on the types of greening elements within the field of view. The formula for calculating the greening feature diversity is as follows: , For the diversity of the aforementioned greening characteristics, The number of different plant species within the field of view. For the first The proportion of plant species in the total number of green elements in the visual field.

2. The method for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space integration as described in claim 1, characterized in that, The step of performing color processing on the laser point cloud data according to a preset point cloud coloring processing operation to obtain target point cloud data includes: Obtain the panoramic image data corresponding to the laser point cloud data; Based on the color information in the panoramic image data, the laser point cloud data is colored to obtain the target point cloud data.

3. The method for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space integration as described in claim 1, characterized in that, The step of constructing a three-dimensional greening model corresponding to the target area based on the oblique photography data and the target point cloud data includes: A first three-dimensional model is constructed based on the oblique photogrammetry data; Construct a second three-dimensional model based on the target point cloud data; Point cloud registration and fusion processing are performed on the first 3D model and the second 3D model to obtain the 3D greening model corresponding to the target area.

4. The method for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space fusion as described in claim 3, is characterized in that... The step of performing point cloud registration and fusion processing on the first 3D model and the second 3D model to obtain a 3D greening model corresponding to the target area includes: Obtain at least one marker point in the target area, and perform preliminary alignment processing on the first 3D model and the second 3D model based on the marker point; According to the preset model registration tool, the model after the initial alignment process is precisely registered and the point cloud is stitched together to obtain a fused point cloud model; The fused point cloud model is subjected to semantic segmentation to obtain the three-dimensional greening model, wherein each grid cell in the three-dimensional greening model is labeled with semantic category information.

5. The method for measuring urban three-dimensional greening features based on a human-centered perspective and ground-space integration as described in claim 1, characterized in that, The greening density is the ratio of the projected area of ​​the greening elements to the total area of ​​the visual field.

6. A three-dimensional urban greening feature measurement system based on a human-centered perspective and ground-space integration, characterized in that, The system includes: The data acquisition module is used to acquire multi-source data corresponding to the target area, wherein the multi-source data includes oblique photography data acquired based on aerial equipment and laser point cloud data acquired based on ground acquisition equipment. The coloring processing module is used to perform coloring processing on the laser point cloud data according to the preset point cloud coloring processing operation to obtain target point cloud data; The model building module is used to build a three-dimensional greening model corresponding to the target area based on the oblique photography data and the target point cloud data. The viewpoint determination module is used to determine the corresponding human-centered viewpoint in the three-dimensional greening model based on the preset viewpoint height. The measurement module is used to construct a ray beam based on the human-centric viewpoint and preset field of view parameters. Based on the collision detection results between the rays in the ray beam and the three-dimensional greening model, the module determines the value of the greening feature evaluation index corresponding to the target area. The greening feature evaluation index includes greening density, line-of-sight depth, and greening feature diversity. The greening density is used to characterize the proportion of greening elements covered within the field of view corresponding to the ray beam. The line-of-sight depth is used to characterize the distance between the greening elements within the field of view and the human-centric viewpoint. The greening feature diversity is used to characterize the diversity of greening elements within the field of view. The greening elements are the grids corresponding to the greening features in the three-dimensional greening model. Wherein, the line-of-sight depth is used to indicate the average distance of green elements within the field of view, and the line-of-sight depth is the average distance of the target viewpoint within the field of view; the target viewpoint distance includes the distance from the green element corresponding to the target ray to the human-centric viewpoint within the field of view, and the target ray is the ray in the ray beam that intersects with the green elements in the three-dimensional greening model. The formula for calculating the line-of-sight depth is: , The depth of sight, The total number of target rays participating in depth calculation within the field of view. For the first The distance from the human-centric perspective point to the greening element. Obtained through collision detection between the target ray and the 3D greening model; The greening feature diversity is determined by the Shannon diversity index based on the types of greening elements within the field of view. The formula for calculating the greening feature diversity is as follows: , For the diversity of the aforementioned greening characteristics, The number of different plant species within the field of view. For the first The proportion of plant species in the total number of green elements in the visual field.

7. A terminal, characterized in that, The terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the urban three-dimensional greening feature measurement method based on human perspective and ground-space fusion as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the urban three-dimensional greening feature measurement method based on human-centered perspective and ground-space fusion as described in any one of claims 1 to 5.

Images