Real estate geographic information surveying and mapping data acquisition method

Abstract

The invention belongs to the technical field of geographic information surveying and mapping, and provides a real estate geographic information surveying and mapping data acquisition method, which comprises the following steps: S1, carrying out aerial photography or ground measurement on real estate by using an unmanned aerial vehicle or ground surveying and mapping equipment to obtain a point cloud data set of a real estate building; s2, screening feature points according to the corresponding Thiessen polygons of the data points in the acquisition images, the normal vectors of the data points in the acquisition images and the normal vectors of the key points in the acquisition images; s3, performing feature extraction on the screened feature points to obtain feature descriptors; the unmanned aerial vehicle or ground surveying and mapping equipment is combined with the image processing technology to perform feature point screening and feature extraction, so that compared with the prior art, the method has different technical effects of improving surveying and mapping precision, reducing data processing complexity, enhancing environmental adaptability, improving surveying and mapping efficiency and the like; therefore, large-scale and high-precision real estate geographic information surveying and mapping requirements are met.

Description

Technical Field

[0001] The invention belongs to the technical field of geographic information surveying and mapping, and specifically is a method for collecting real estate geographic information surveying and mapping data. Background Art

[0002] Real estate geographic information surveying and mapping data collection has important application value in the fields of land management, urban planning, real estate evaluation, etc. However, the existing surveying and mapping data collection methods have problems such as insufficient accuracy, high data processing complexity, and susceptibility to environmental interference. Especially when dealing with complex real estate buildings, how to accurately and efficiently collect and process geographic information data has become an urgent problem to be solved.

[0003] The existing surveying and mapping data collection methods mostly rely on traditional measuring instruments, such as total stations and GPS, which are not only complicated to operate, but also easily affected by environmental factors, resulting in limited accuracy of collected data. In addition, with the increasing richness and complexity of real estate geographic information data, traditional data processing methods can no longer meet the needs of efficiency and accuracy.

[0004] To this end, those skilled in the art have proposed a real estate geographic information surveying and mapping data collection method to solve the problems raised by the background technology. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a real estate geographic information surveying and mapping data collection method to solve the problem that the existing surveying and mapping data collection methods mostly rely on traditional measuring instruments, such as total stations, GPS, etc. These methods are not only complicated to operate, but also easily affected by environmental factors, resulting in limited accuracy of collected data. In addition, with the increasing richness and complexity of real estate geographic information data, traditional data processing methods have been unable to meet the needs of high efficiency and accuracy.

[0006] A real estate geographic information surveying and mapping data collection method, comprising:

[0007] S1. Use drones or ground surveying equipment to perform aerial photography or ground measurement of real estate to obtain a point cloud dataset of real estate buildings;

[0008] S2, screening feature points according to the Thiessen polygons corresponding to each data point in each acquisition graph, the normal vectors of each data point in each acquisition graph, and the normal vectors of key points in each acquisition graph;

[0009] S3, extracting features from the filtered feature points to obtain feature descriptors;

[0010] S4, matching the point cloud data set of the real estate building with the standard point cloud data set based on the feature descriptor to determine the location information of the point cloud data of the real estate building;

[0011] S5. Finally, the location information is sorted and stored to form a real estate geographic information data set.

[0012] Preferably, in step S2, the feature point screening is performed by preprocessing the acquired real estate building surface image through image processing technology, including denoising, correction, and registration; the steps specifically include:

[0013] 2.1. Image denoising using computer vision algorithms;

[0014] 2.2. Use camera calibration technology to perform image correction;

[0015] 2.3. Use the same-name point matching method to perform image registration.

[0016] Preferably, in step S3, the feature extraction includes obtaining a feature descriptor based on the HOG operator corresponding to each feature point in each acquisition image, the grayscale value of each feature point, the Euclidean distance between each feature point and the feature points in its preset neighborhood, and the structural similarity between the structure graph corresponding to each feature point and the structure graph corresponding to the feature points in the preset neighborhood of each feature point.

[0017] Preferably, the feature descriptor also includes coding information obtained by performing local feature coding processing on each feature point.

[0018] Preferably, in step S4, the matching step further includes optimizing the matching results to improve matching accuracy.

[0019] A real estate geographic information surveying and mapping data collection system, such as the real estate geographic information surveying and mapping data collection method mentioned above, comprises:

[0020] A data acquisition module is used to use drones or ground surveying equipment to perform aerial photography or ground measurement of real estate to obtain a point cloud data set of real estate buildings;

[0021] The feature point screening module uses image processing technology to pre-process the corresponding Thiessen polygons of each data point in each acquisition image, the normal vectors of each data point in each acquisition image, and the normal vectors of the key points in each acquisition image, including denoising, correction, and registration, to screen feature points; denoising uses computer vision algorithms, correction uses camera calibration technology, and registration uses the same-name point matching method;

[0022] The feature extraction module extracts features from the selected feature points. The extracted features include the HOG operator corresponding to each feature point in each acquisition image, the gray value of each feature point, the Euclidean distance between each feature point and the feature points in its preset neighborhood, the structural similarity between the structure graph corresponding to each feature point and the structure graph corresponding to the feature points in the preset neighborhood of each feature point, and the encoding information obtained by performing local feature encoding processing on each feature point, thereby obtaining a feature descriptor;

[0023] The data matching module matches the point cloud data set of the real estate building with the standard point cloud data set based on the feature descriptor, determines the location information of the point cloud data of the real estate building, and optimizes the matching results to improve the matching accuracy;

[0024] The data sorting and storage module sorts and stores the location information to form a real estate geographic information data set.

[0025] A processor is configured to execute the real estate geographic information surveying and mapping data collection method described above.

[0026] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned real estate geographic information surveying and mapping data collection method.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The present invention adopts unmanned aerial vehicle (UAV) or ground surveying and mapping equipment combined with image processing technology to perform feature point screening and feature extraction. Compared with the current existing technology, the present invention has different technical effects such as improving surveying and mapping accuracy, reducing data processing complexity, enhancing environmental adaptability and improving surveying and mapping efficiency, thereby meeting the needs of large-scale, high-precision real estate geographic information surveying and mapping. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a flow chart of the real estate geographic information surveying and mapping data collection method of the present invention;

[0030] Figure 2 This is a framework diagram of the real estate geographic information surveying and mapping data acquisition system of the present invention. DETAILED DESCRIPTION

[0031] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0032] Embodiment: The present invention provides a method for collecting real estate geographic information surveying and mapping data, such as Figure 1 As shown, including:

[0033] S1. Use drones or ground surveying equipment to perform aerial photography or ground measurement of real estate to obtain a point cloud dataset of real estate buildings;

[0034] S2, screening feature points according to the Thiessen polygons corresponding to each data point in each acquisition graph, the normal vectors of each data point in each acquisition graph, and the normal vectors of key points in each acquisition graph;

[0035] S3, extracting features from the filtered feature points to obtain feature descriptors;

[0036] S4, matching the point cloud data set of the real estate building with the standard point cloud data set based on the feature descriptor to determine the location information of the point cloud data of the real estate building;

[0037] S5. Finally, the location information is sorted and stored to form a real estate geographic information data set.

[0038] As can be seen from the above, the present invention can quickly obtain a large-scale, high-precision real estate building point cloud data set by using drones or ground surveying equipment for data collection. This method not only improves the surveying efficiency, but also covers a wider geographical area and meets the needs of large-scale real estate surveying. In step S2, the feature points are screened by comprehensively considering the Thiessen polygons, normal vectors and normal vectors of key points of each data point in each acquisition graph. This method can accurately identify data points with significant features, providing a reliable basis for subsequent feature extraction and matching. In step S3, feature extraction is performed on the screened feature points, and the extracted features include HOG Operators, grayscale values, Euclidean distances, structural similarities, and local feature encoding information, etc., the above features can fully and accurately describe the point cloud data of real estate buildings, providing rich information for subsequent matching work; matching the point cloud data set of real estate buildings with the standard point cloud data set based on feature descriptors can determine the location information of the point cloud data of real estate buildings. This step not only improves the matching accuracy, but also ensures the reliability of surveying and mapping data; finally, the location information is sorted and stored to form a real estate geographic information data set. This step provides convenience for subsequent data applications and lays the foundation for the intelligent management and analysis of real estate geographic information.

[0039] Furthermore, in step S2, the feature point screening is to pre-process the acquired real estate building surface image by image processing technology, including denoising, correction, and registration; the steps specifically include:

[0040] 2.1. Image denoising is performed using a computer vision algorithm. The denoising uses a non-local mean denoising algorithm, which removes noise by calculating the weighted average of each pixel in the image and its similar pixels. The formula of the non-local mean denoising algorithm is as follows:

[0041]

[0042] Where x is the pixel position in the image, I(y) is the grayscale value of pixel y, and w(x,y) is the weight between pixels x and y, which is usually calculated based on the similarity between them;

[0043] 2.2. Image correction is performed using camera calibration technology. The camera calibration technology is a method for determining the internal parameters (such as focal length, principal point coordinates, distortion coefficient, etc.) and external parameters (such as the position and direction of the camera) of the camera through the relationship between known three-dimensional space points and corresponding two-dimensional image points. The camera calibration technology includes radial distortion of the distortion coefficient. The radial distortion is expressed as a polynomial function, and its formula is as follows:

[0044] r d =r(1+k1r 2 +k2r 4 +k3r 6 );

[0045] Among them, r is the distance from the image point to the principal point, k1, k2, k3 are radial distortion coefficients;

[0046] 2.3. Use the same-name point matching method to perform image registration. The same-name point matching method is a technology that realizes image registration by finding common feature points (i.e., same-name points) in two or more images and calculating the transformation relationship between these points. In real estate geographic information surveying and mapping, the same-name point matching method is used to further align the images that have been preliminarily corrected to ensure that images taken from different perspectives or at different times can be accurately superimposed. The same-name point matching method includes the Harris corner detection algorithm. The Harris corner detection algorithm detects feature points by calculating the gradient, scale space and other characteristics of the image. The formula of the Harris corner detection algorithm is as follows:

[0047] R = det(T) - k·trace 2 (T);

[0048] Where T is the second-order matrix of the image, det(T) is the determinant of the matrix, trace(T) is the trace of the matrix, and k is an empirical constant.

[0049] From the above, it can be seen that by introducing more specific denoising algorithms, camera calibration methods and feature point matching algorithm formulas, the creativity and accuracy of feature point screening technology can be significantly improved, thereby providing more accurate and reliable data support for real estate geographic information surveying and mapping data collection.

[0050] Furthermore, in step S3, the feature extraction includes obtaining a feature descriptor based on the HOG operator corresponding to each feature point in each acquired image, the grayscale value of each feature point, the Euclidean distance between each feature point and the feature points in its preset neighborhood, and the structural similarity between the structure graph corresponding to each feature point and the structure graph corresponding to the feature points in the preset neighborhood of each feature point.

[0051] From the above, it can be seen that by comprehensively considering the HOG operator corresponding to each feature point, the grayscale value, the Euclidean distance between the feature points in its preset neighborhood, and the structural similarity between the structure graph corresponding to each feature point and the structure graph corresponding to the feature points in its preset neighborhood, the point cloud data features of real estate buildings can be extracted more comprehensively and accurately, thereby obtaining a feature descriptor with rich information; this multi-dimensional feature extraction method improves the accuracy and reliability of data matching, and provides a solid foundation for subsequent real estate geographic information surveying and mapping data processing and analysis.

[0052] Furthermore, the feature descriptor also includes coding information obtained by performing local feature coding processing on each feature point.

[0053] From the above, we can see that through local feature encoding, each feature point is converted into a series of binary or numerical codes. These codes not only retain the key information of the feature points, but also reduce data redundancy and improve the efficiency and accuracy of subsequent matching and recognition processes; at the same time, the encoding information makes the feature descriptor more robust and can better cope with complex situations such as image transformation and noise interference, providing strong support for high-precision matching and analysis of real estate geographic information surveying and mapping data.

[0054] Furthermore, in step S4, the matching step further includes optimizing the matching result, and the optimization process adopts a Gaussian algorithm, and the formula of the Gaussian algorithm is as follows:

[0055] (H+λD T D) Δx = -g;

[0056] Among them, H represents the matrix approximation, D represents the Jacobian matrix, g is the gradient vector, and Δx is the damping factor used to control the behavior of the algorithm.

[0057] From the above, it can be seen that by introducing the Gaussian algorithm, the matching results can be optimized in step S4 to improve the accuracy and robustness of the matching, thereby improving the overall performance of the real estate geographic information surveying and mapping data acquisition method.

[0058] The effects of the embodiment (real estate geographic information surveying and mapping data acquisition method) and the control example (existing surveying and mapping data acquisition method, including total station measurement, GPS measurement, ground photogrammetry or laser scanning measurement) are compared to obtain the following table:

[0059]

[0060] It can be seen from the above table that the real estate geographic information surveying and mapping data collection method of this embodiment shows significant advantages in data collection efficiency, accuracy, data processing complexity, etc. compared with existing surveying and mapping data collection methods (such as total station measurement, GPS measurement, ground photogrammetry or laser scanning measurement); these advantages make the method of the embodiment more suitable for the needs of modern real estate geographic information surveying and mapping, help to improve the efficiency and accuracy of surveying and mapping work, and promote technological progress and application development in related fields.

[0061] In summary, the present invention has the following beneficial effects:

[0062] 1) The present invention uses drones or ground surveying equipment to collect data, and can quickly obtain a large-scale, high-precision real estate building point cloud data set, covering a wider geographical area, and meeting the needs of large-scale real estate surveying and mapping; at the same time, it comprehensively utilizes geometric features such as Thiessen polygons and normal vectors to screen feature points, ensuring the accuracy and representativeness of feature points, and laying a solid foundation for subsequent feature extraction and matching;

[0063] 2) In the feature extraction stage, the present invention combines multi-dimensional features such as HOG operator, gray value, Euclidean distance, structural similarity and local feature encoding information to comprehensively and accurately describe the point cloud data of real estate buildings and improve the accuracy and reliability of data matching; at the same time, the matching results are optimized and advanced technologies such as Gaussian algorithm are used to further improve the accuracy and robustness of the matching results;

[0064] 3) Compared with traditional total stations, GPS and other measuring instruments, the method of the present invention is less affected by environmental factors and can maintain high data acquisition accuracy in complex environments; at the same time, the real estate building surface image is pre-processed through image processing technology (such as denoising, correction, and registration), effectively reducing noise interference, improving image quality, and providing strong support for subsequent feature point screening and feature extraction;

[0065] 4) The real estate geographic information data set formed by the present invention provides convenience for subsequent data applications, such as land management, urban planning, real estate evaluation and other fields, which helps to improve the scientificity and accuracy of decision-making; at the same time, by efficiently and accurately collecting and processing real estate geographic information data, it lays the foundation for the intelligent management and analysis of real estate geographic information, and helps to promote the digitalization and intelligent transformation of related fields;

[0066] 5) The present invention uses drones or ground surveying and mapping equipment to collect data, which can significantly reduce surveying and mapping costs and improve the economic benefits of surveying and mapping work compared to traditional manual surveying and mapping methods;

[0067] 6) The method of the present invention is applicable to real estate surveying and mapping projects of different types and scales, has strong flexibility and scalability, and can meet diverse surveying and mapping needs;

[0068] 7) The present invention proposes a new method for collecting real estate geographic information surveying and mapping data, which provides new ideas and new directions for technological innovation and industry development in the field of geographic information surveying and mapping technology.

[0069] A real estate geographic information surveying and mapping data acquisition system, such as Figure 2 As shown, the real estate geographic information surveying and mapping data collection method mentioned above includes:

[0070] A data acquisition module is used to use drones or ground surveying equipment to perform aerial photography or ground measurement of real estate to obtain a point cloud data set of real estate buildings;

[0071] The feature point screening module uses image processing technology to pre-process the corresponding Thiessen polygons of each data point in each acquisition image, the normal vectors of each data point in each acquisition image, and the normal vectors of the key points in each acquisition image, including denoising, correction, and registration, to screen feature points; denoising uses computer vision algorithms, correction uses camera calibration technology, and registration uses the same-name point matching method;

[0072] The feature extraction module extracts features from the selected feature points. The extracted features include the HOG operator corresponding to each feature point in each acquisition image, the gray value of each feature point, the Euclidean distance between each feature point and the feature points in its preset neighborhood, the structural similarity between the structure graph corresponding to each feature point and the structure graph corresponding to the feature points in the preset neighborhood of each feature point, and the encoding information obtained by performing local feature encoding processing on each feature point, thereby obtaining a feature descriptor;

[0073] The data matching module matches the point cloud data set of the real estate building with the standard point cloud data set based on the feature descriptor, determines the location information of the point cloud data of the real estate building, and optimizes the matching results to improve the matching accuracy;

[0074] The data sorting and storage module sorts and stores the location information to form a real estate geographic information data set.

[0075] From the above, it can be seen that the real estate geographic information surveying and mapping data acquisition system provided by the present invention can quickly and accurately collect real estate geographic information data, and efficiently process and store it, which provides convenience for subsequent applications and has broad application prospects and economic benefits.

[0076] The embodiment of the present application provides an electronic device applicable to the above-mentioned real estate geographic information surveying and mapping data collection method, including:

[0077] Memory, used to protect computer programs and data;

[0078] Processor, used to run system programs.

[0079] The embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned real estate geographic information surveying and mapping data collection method, and performs hierarchical confidentiality management on the above-mentioned system and data in accordance with confidentiality management requirements.

[0080] Those skilled in the art will appreciate that the embodiments of the present application may be provided as a system or a computer program product. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0081] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0082] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0084] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0085] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0086] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0088] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A real estate geographic information surveying and mapping data collection method, characterized in that: include: S1. Use drones or ground surveying equipment to perform aerial photography or ground measurement of real estate to obtain a point cloud dataset of real estate buildings; S2, screening feature points according to the Thiessen polygons corresponding to each data point in each acquisition graph, the normal vectors of each data point in each acquisition graph, and the normal vectors of key points in each acquisition graph; S3, extracting features from the filtered feature points to obtain feature descriptors; S4, matching the point cloud data set of the real estate building with the standard point cloud data set based on the feature descriptor to determine the location information of the point cloud data of the real estate building; S5. Finally, the location information is sorted and stored to form a real estate geographic information data set.

2. A real estate geographic information surveying and mapping data collection method as claimed in claim 1, characterized in that: In step S2, the feature point screening is to pre-process the acquired real estate building surface image by image processing technology, including denoising, correction, and registration; The specific steps include: 2.

1. Image denoising using computer vision algorithms; 2.

2. Use camera calibration technology to perform image correction; 2.

3. Use the same-name point matching method to perform image registration.

3. A real estate geographic information surveying and mapping data collection method as claimed in claim 1, characterized in that: In step S3, the feature extraction includes obtaining a feature descriptor based on the HOG operator corresponding to each feature point in each acquisition image, the grayscale value of each feature point, the Euclidean distance between each feature point and the feature points in its preset neighborhood, and the structural similarity between the structure graph corresponding to each feature point and the structure graph corresponding to the feature points in the preset neighborhood of each feature point.

4. A real estate geographic information surveying and mapping data collection method as claimed in claim 3, characterized in that: The feature descriptor also includes coding information obtained by performing local feature coding processing on each feature point.

5. The real estate geographic information surveying and mapping data collection method according to claim 1, characterized in that: In step S4, the matching step also includes optimizing the matching results.

6. A real estate geographic information surveying and mapping data collection system, characterized by: The real estate geographic information surveying and mapping data collection method according to any one of claims 1 to 5 comprises: A data acquisition module is used to use drones or ground surveying equipment to perform aerial photography or ground measurement of real estate to obtain a point cloud data set of real estate buildings; The feature point screening module performs preprocessing through image processing technology, including denoising, correction, and registration, based on the Thiessen polygons corresponding to each data point in each acquisition image, the normal vectors of each data point in each acquisition image, and the normal vectors of the key points in each acquisition image. Among them, denoising uses computer vision algorithms, correction uses camera calibration technology, and registration uses the same-name point matching method; The feature extraction module extracts features from the selected feature points. The extracted features include the HOG operator corresponding to each feature point in each acquisition image, the gray value of each feature point, the Euclidean distance between each feature point and the feature points in its preset neighborhood, the structural similarity between the structure graph corresponding to each feature point and the structure graph corresponding to the feature points in the preset neighborhood of each feature point, and the encoding information obtained by performing local feature encoding processing on each feature point, thereby obtaining a feature descriptor; The data matching module matches the point cloud data set of the real estate building with the standard point cloud data set based on the feature descriptor, determines the location information of the point cloud data of the real estate building, and optimizes the matching results; The data sorting and storage module sorts and stores the location information to form a real estate geographic information data set.

7. A processor, characterized in that: The method is configured to execute the real estate geographic information surveying and mapping data collection method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the real estate geographic information surveying and mapping data collection method described in any one of claims 1 to 5 is implemented.

Images