Land expropriation red line early warning management method based on oblique photography model comparative analysis

Abstract

This invention provides a method for early warning of land acquisition boundaries using UAV oblique photography technology, comprising: S1 using a UAV to photograph the area within the project scope; S2 processing the UAV aerial data into model data, outputting an oblique photography model, and matching it with the scope of the land acquisition boundary data; S3 importing the confirmed version of the land acquisition boundary boundary and overlaying it onto the oblique photography model to visually display the land acquisition scope and current status at the project site; S4 using image recognition technology to identify the cleared area and the land acquisition boundary in the oblique photography model; S5 analyzing and comparing the data to identify instances of under-acquisition or over-occupation, and generating early warning records to notify the land acquisition and resettlement department. This method improves the accuracy and efficiency of land acquisition boundary management, ensures the smooth implementation of projects, and achieves effective monitoring and management of land acquisition boundaries.

Description

Technical Field

[0001] This invention relates to the fields of land resource management and engineering project monitoring, and in particular to a land acquisition red line early warning management method based on oblique photography model comparative analysis. Background Technology

[0002] With the acceleration of urbanization, land acquisition has become a common requirement in urban construction and infrastructure projects. Traditional land acquisition boundary management relies on manual inspections and ground surveys, which is time-consuming, labor-intensive, difficult to update in real time, and prone to errors. Therefore, an efficient and accurate technical means is needed to improve the existing land acquisition boundary management methods. Summary of the Invention

[0003] The purpose of this invention is to provide a land acquisition boundary early warning method based on oblique photogrammetry model comparative analysis, to solve the problems of traditional methods being time-consuming, labor-intensive, difficult to update in real time, and prone to errors. The method includes the following steps:

[0004] Step S1: Use a drone equipped with a high-resolution camera to take oblique photographs of the engineering site, acquire image data from multiple angles, and ensure that the spatial range of the data acquisition meets the preset requirements and covers the required target area;

[0005] Step S2: Process the acquired image data, generate an oblique photogrammetry model using 3D reconstruction technology, and spatially align the model with the land acquisition boundary data using a spatial registration algorithm;

[0006] Step S3: Import the confirmed version of the land acquisition boundary data into the generated oblique photogrammetry model for precise overlay, so as to intuitively display the land acquisition scope and current status of the project site;

[0007] Step S4: Identify the intersection of the cleared area and the land acquisition boundary in the oblique photogrammetry model with superimposed red line data, and extract the matching situation between the cleared area and the red line boundary;

[0008] Step S5: Compare and analyze the differences between the cleared area and the land acquisition boundary, identify areas where land acquisition is insufficient or excessive, generate early warning records, and notify the land acquisition and relocation department for further processing.

[0009] Further, step S2 includes the following steps:

[0010] Step S201: Preprocess the acquired image data, including noise reduction, color correction, and image registration;

[0011] Step S202: Using a 3D reconstruction algorithm, image data from multiple angles are fused to generate a high-precision oblique photogrammetry 3D model. The accuracy of the generated 3D model is then verified to ensure that it is highly consistent with the spatial information of the actual site.

[0012] Step S203: Spatially align the generated 3D oblique photography model with the land acquisition boundary data, and use a spatial registration algorithm to accurately match the spatial position of the boundary data and the model.

[0013] Further, step S4 includes the following steps:

[0014] Step S401: Using the oblique photography model with superimposed red line data, identify the intersection of the cleared area and the land acquisition red line in the oblique photography model, and use the intersection area as the target area for subsequent analysis;

[0015] Step S402: Use a feature extraction algorithm to extract stable feature points from the cleared area and the red line area, and calculate the descriptors of the feature points;

[0016] Step S403: Classify the extracted features, identify the feature point categories of the clear area and the red line area, and mark and distinguish them;

[0017] Step S404: Based on the classified feature points, use a feature matching algorithm to refine the matching relationship between the cleared area and the red line boundary.

[0018] Further, step S5 includes the following steps:

[0019] Step S501: Based on the matching results in step S4, analyze the relationship between the cleared area and the land acquisition boundary line, calculate the intersection area between the cleared area and the boundary line, and determine whether the cleared area completely overlaps with the boundary line, does not reach the boundary line range, or exceeds the boundary line range.

[0020] Step S502: If the cleared area completely coincides with the red line, record the area as a compliant area; if the cleared area does not reach the red line range, record it as an under-collected area; if the cleared area exceeds the red line range, record it as an over-occupied area.

[0021] Step S503: Based on the judgment result, generate an early warning record, including the specific location and area of ​​the under-requisitioned and over-occupied areas, and notify the relocation department of the early warning information to facilitate subsequent processing.

[0022] The beneficial effects of this invention are: the method of this invention can greatly improve the automation level and accuracy of land acquisition boundary management, reduce human error, save labor costs, and provide a guarantee for the smooth progress of engineering projects. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating the method of the present invention. Detailed Implementation

[0024] This embodiment describes, as follows: Figure 1This paper presents a land acquisition boundary warning method based on oblique photogrammetry model comparative analysis. It utilizes unmanned aerial vehicles (UAVs), 3D reconstruction technology, feature matching algorithms, and spatial alignment technology to accurately analyze and issue warnings at engineering sites. The method mainly includes steps such as image data acquisition, data processing, spatial registration, matching analysis of cleared areas with the boundary line, and generating warning records.

[0025] Step S1: Aerial photography by drone

[0026] First, a drone equipped with a high-resolution camera is used to conduct oblique photography of the construction site. The drone's flight path and shooting angle are pre-set to ensure that image data of the target area is acquired from multiple perspectives. The drone adjusts its flight altitude and shooting angle according to the actual situation on site to ensure that the spatial range of image data acquisition meets the preset requirements and fully covers the required target area. After image acquisition, the image data is transmitted in real time to the data processing system for further processing via wireless transmission technology.

[0027] Step S2: Output of the oblique photogrammetry model

[0028] Step S201: First, the acquired image data is preprocessed. Preprocessing includes removing noise from the image using common denoising algorithms such as median filtering and mean filtering to improve image clarity. Then, color correction is performed to ensure accurate color reproduction in the image. Finally, multiple images are registered using image registration techniques to ensure spatial consistency and accuracy between the images.

[0029] Step S202: Perform 3D reconstruction on the processed image data. Using 3D reconstruction algorithms, such as structured light, stereo vision, or multi-view reconstruction methods, image data from multiple angles are fused to generate a high-precision 3D oblique photogrammetry model. The generated 3D model will undergo accuracy verification by comparing it with the spatial information of the actual site to ensure that the spatial data of the model is highly consistent with the actual situation.

[0030] Step S203: Spatially align the generated 3D oblique photogrammetry model with the land acquisition boundary data. Use spatial registration algorithms, such as feature point-based registration or iterative nearest-point algorithm, to perform accurate matching. This step ensures that the boundary data and the generated 3D model are spatially aligned so that subsequent comparative analysis can be performed accurately.

[0031] Step S3: Import the project land acquisition boundary.

[0032] The confirmed land acquisition boundary data is imported into the generated 3D oblique photogrammetry model and precisely overlaid using spatial alignment technology. This allows for a visual representation of the land acquisition area and the actual terrain at the project site, providing an intuitive basis for subsequent comparative analysis of the cleared area and the boundary line.

[0033] Step S4: Automatic detection using image recognition algorithm

[0034] Step S401: Using a 3D oblique photogrammetry model overlaid with red line data, identify the intersection between the cleared area and the red line. This intersection is clearly marked in the image as the target area for subsequent analysis, preparing for the following matching and comparison analysis.

[0035] Step S402: Extract stable feature points from the cleared and red-lined regions in the image. Use feature extraction algorithms such as scale-invariant feature transform or accelerated robust feature extraction to extract key feature points from the cleared and red-lined regions. These feature points represent key parts of the image and can help accurately match corresponding regions in different images.

[0036] Step S403: Classify the extracted features, identify the feature point categories between the cleared area and the red line area, and mark and distinguish them. Classification further distinguishes which feature points belong to the cleared area and which belong to the red line area, providing a basis for subsequent matching.

[0037] Step S404: Based on the classified feature points, use feature matching algorithms, such as brute-force matching and fast nearest neighbor search library matching, to refine the matching relationship between the cleared area and the red line boundary. Through precise matching algorithms, ensure that the spatial relationships between feature points are accurately matched, thus improving matching accuracy.

[0038] Step S5: Early warning of under-collection or over-collection, and information push.

[0039] Step S501: Based on the matching results in Step S4, analyze the relationship between the cleared area and the land acquisition boundary line. Calculate the intersection area between the cleared area and the boundary line, and determine the three main relationships between the cleared area and the boundary line: whether they completely overlap, whether they do not reach the boundary line range, or whether they exceed the boundary line range.

[0040] Step S502: If the cleared area completely overlaps with the red line, record the area as compliant; if the cleared area does not reach the red line, record it as an under-requisitioned area; if the cleared area exceeds the red line, record it as an over-occupied area. These classifications allow for accurate assessment of land acquisition and identification of problematic areas.

[0041] Step S503: Based on the judgment results, generate an early warning record, recording the specific location, area, and other information of the under-requisitioned areas, over-occupied areas, and areas that meet the requirements. The early warning information is then sent to the land acquisition and relocation department through the system. The early warning record may also include other key information, such as the areas involved, relevant responsible persons, and rectification suggestions, to provide a reference for subsequent processing.

[0042] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be determined by the claims.

Claims

1. A method for early warning of land acquisition red lines based on oblique photogrammetry model comparative analysis, characterized in that, The method includes the following steps: Step S1: Use a drone equipped with a high-resolution camera to take oblique photographs of the engineering site, acquire image data from multiple angles, and ensure that the spatial range of the data acquisition meets the preset requirements and covers the required target area; Step S2: Process the acquired image data, generate an oblique photogrammetry model using 3D reconstruction technology, and spatially align the model with the land acquisition boundary data using a spatial registration algorithm; Step S3: Import the confirmed version of the land acquisition boundary data into the generated oblique photogrammetry model for precise overlay, so as to intuitively display the land acquisition scope and current status of the project site; Step S4: Identify the intersection of the cleared area and the land acquisition boundary in the oblique photogrammetry model with superimposed red line data, and extract the matching situation between the cleared area and the red line boundary; Step S5: Compare and analyze the differences between the cleared area and the land acquisition boundary, identify areas where land acquisition is insufficient or excessive, generate early warning records, and notify the land acquisition and relocation department for further processing.

2. The land acquisition red line early warning method based on oblique photography model comparative analysis as described in claim 2, characterized in that, Step S2 includes the following steps: Step S201: Preprocess the acquired image data, including noise reduction, color correction, and image registration; Step S202: Using a 3D reconstruction algorithm, image data from multiple angles are fused to generate a high-precision oblique photogrammetry 3D model. The accuracy of the generated 3D model is then verified to ensure that it is highly consistent with the spatial information of the actual site. Step S203: Spatially align the generated 3D oblique photography model with the land acquisition boundary data, and use a spatial registration algorithm to accurately match the spatial position of the boundary data and the model.

3. The land acquisition red line early warning method based on oblique photography model comparative analysis as described in claim 1, characterized in that, Step S4 includes the following steps: Step S401: Using the oblique photography model with superimposed red line data, identify the intersection of the cleared area and the land acquisition red line in the oblique photography model, and use the intersection area as the target area for subsequent analysis; Step S402: Use a feature extraction algorithm to extract stable feature points from the cleared area and the red line area, and calculate the descriptors of the feature points; Step S403: Classify the extracted features, identify the feature point categories of the clear area and the red line area, and mark and distinguish them; Step S404: Based on the classified feature points, use a feature matching algorithm to refine the matching relationship between the cleared area and the red line boundary.

4. The land acquisition red line early warning method based on oblique photography model comparative analysis as described in claim 1, characterized in that, Step S5 includes the following steps: Step S501: Based on the matching results in step S4, analyze the relationship between the cleared area and the land acquisition boundary line, calculate the intersection area between the cleared area and the boundary line, and determine whether the cleared area completely overlaps with the boundary line, does not reach the boundary line range, or exceeds the boundary line range. Step S502: If the cleared area completely coincides with the red line, record the area as a compliant area; if the cleared area does not reach the red line range, record it as an under-collected area; if the cleared area exceeds the red line range, record it as an over-occupied area. Step S503: Based on the judgment result, generate an early warning record, including the specific location and area of ​​the under-requisitioned and over-occupied areas, and notify the relocation department of the early warning information to facilitate subsequent processing.

Images