High-precision Real Estate Surveying and Mapping Method in Complex Terrain Environments Based on Optimization Algorithms

Abstract

The present invention discloses a high-precision real estate surveying and mapping method in complex terrain environments based on an optimization algorithm, which includes the following steps: By integrating lidar and global navigation satellite system sensors, rich geographical information data is collected, the data is preprocessed to generate basic geographical information data, and a digital elevation model is constructed to represent the three-dimensional undulation changes of the terrain. Through the optimization algorithm, path planning and dynamic adjustment of the equipment operation trajectory are carried out to adapt to the complex terrain. The multi-source data is integrated into a unified geographical information model using the fusion algorithm, and error analysis and correction are performed to obtain an optimized geographical information model. Based on this model, a real estate surveying and mapping map is generated, and the real estate boundaries and terrain features are accurately marked. The present invention achieves the goal of high-precision surveying and mapping in complex terrains through a series of optimization techniques.

Description

Technical Field

[0001] The present invention relates to the technical field of real estate surveying and mapping, and particularly to a high-precision real estate surveying and mapping method in complex terrain environments based on an optimization algorithm. Background Art

[0002] In modern real estate surveying and mapping, especially in surveying and mapping work in complex terrain environments, traditional surveying and mapping methods often face many challenges. With the development of geographic information systems, remote sensing technology, unmanned aerial vehicle technology, and data processing technology, the accuracy and efficiency of surveying and mapping have improved to some extent. However, existing technologies still have significant deficiencies when meeting the high-precision surveying and mapping requirements in complex terrain environments.

[0003] Traditional surveying and mapping methods mainly rely on a single data source, such as the Global Navigation Satellite System (GNSS) or lidar. However, the use of a single data source is easily restricted by environmental conditions, equipment accuracy, and data processing algorithms. In complex terrains such as mountains and canyons, GNSS signals may be affected by occlusion or reflection, resulting in a decrease in positioning accuracy. Although LiDAR can provide high-precision three-dimensional point cloud data, in areas with dense vegetation or large terrain undulations, the integrity and accuracy of the data are still difficult to guarantee. Due to the lack of effective fusion of multi-source data, traditional methods often cannot achieve sufficient coverage and accuracy in complex terrains.

[0004] Existing path planning algorithms, such as the traditional Dijkstra algorithm or A* algorithm, although can solve the optimization problem of surveying and mapping paths to a certain extent, when facing complex terrains, they often cannot dynamically adapt to terrain changes, resulting in low surveying and mapping efficiency and even possibly missing key terrain features. These algorithms usually only consider the length of the path and simple terrain features, lacking a comprehensive understanding of the terrain and the optimization ability of multi-modal paths. Therefore, they often show deficiencies in practical applications.

[0005] Most traditional multi-source data fusion technologies are based on linear interpolation or simple weighted average methods. When processing data from different sensors, these methods often ignore the non-linear characteristics and spatial relationships of the data, resulting in insufficient accuracy and consistency of the fusion results. In addition, existing error correction methods, such as the least squares method and Kalman filtering, although can effectively reduce errors in some simple scenarios, in complex terrain environments, especially when involving multi-source data fusion and multi-modal path optimization, they cannot fully eliminate systematic errors, affecting the accuracy of the final surveying and mapping results.

[0006] Therefore, how to provide a high-precision real estate surveying and mapping method in complex terrain environments based on an optimization algorithm is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0007] An object of the present invention is to propose a high-precision real estate surveying and mapping method in complex terrain environments based on optimization algorithms. The present invention integrates multi-source data acquisition technologies, adopts an adaptive multi-modal evolutionary optimization algorithm and a high-dimensional non-linear dynamic optimization fusion algorithm, and details the whole process of achieving high-precision surveying and mapping under complex terrain conditions. It has the advantages of extensive data acquisition, accurate path planning, high data fusion consistency, and high error correction accuracy.

[0008] The high-precision real estate surveying and mapping method in complex terrain environments based on optimization algorithms according to an embodiment of the present invention includes the following steps:

[0009] S1. In a complex terrain environment, adopt multi-source data acquisition technology, integrate LiDAR and GNSS sensors, collect geographic information data, and achieve data diversity and wide coverage;

[0010] S2. Preprocess the collected multi-source data, including data cleaning and coordinate transformation, to generate basic geographic information data;

[0011] S3. Based on the processed geographic information data, construct a digital elevation model to represent the three-dimensional undulation changes of the complex terrain;

[0012] S4. Based on the generated three-dimensional terrain model, adopt an adaptive multi-modal evolutionary optimization algorithm for surveying and mapping path planning. By identifying and optimizing multiple path modes, dynamically adjust the optimization strategy, and select the optimal path in the complex terrain;

[0013] S5. During the surveying and mapping process, according to the path planning results, dynamically adjust the running trajectory of the surveying and mapping equipment to adapt to terrain changes and perform surveying and mapping;

[0014] S6. Integrate the processed multi-source data with the generated three-dimensional terrain model, adopt a high-dimensional non-linear dynamic optimization fusion algorithm, integrate the data of different sensors into a unified geographic information model, and perform data fusion and optimization processing;

[0015] S7. Conduct error analysis and correction on the generated geographic information model, apply the deep residual regression algorithm for error correction, correct the systematic error through a progressive regression method layer by layer, and finally obtain an optimized geographic information model;

[0016] S8. Based on the optimized geographic information model, generate a real estate surveying and mapping map, and mark the real estate boundaries and terrain features.

[0017] Optionally, the S1 specifically includes:

[0018] S11. In a complex terrain environment, adopt multi-source data acquisition technology, integrate a lidar sensor and a global navigation satellite system sensor, and collect three-dimensional point cloud data and geographical location information respectively;

[0019] S12. Transmit a laser beam through the LiDAR sensor and receive the echo signal, and calculate the distance based on the echo time t and the speed of light c Generate three-dimensional point cloud data of the target area, and the data includes the three-dimensional coordinates (x i , y i , z i )

[0020] S13. Use the GNSS sensor to receive satellite signals, calculate and record the geographical coordinates (x i , y i , z i ) of the survey point, and provide geographical location information

[0021] S14. Use the adaptive data synchronization algorithm based on topology preservation to synchronize the three-dimensional point cloud data collected by the LiDAR sensor and the geographical coordinate data obtained by the GNSS sensor. By maintaining the topological structure of the terrain data, automatically adjust the time and space synchronization of the data

[0022] S15. Integrate the synchronized data after topology preservation to form an initial geographical information dataset covering a wide range and having diversity. The dataset includes three-dimensional terrain undulations, coordinates, and topological structures

[0023] Optionally, the specific steps of S3 are as follows

[0024] S31. Based on the formed initial geographical information dataset, extract the three-dimensional point cloud data (x i , y i , z i ) and the corresponding geographical coordinate information

[0025] S32. Grid the extracted three-dimensional point cloud data according to the geographical coordinates to generate a preliminary elevation data model, and adjust the size and distribution of the grid cells according to the complexity of the terrain

[0026] S33. Apply the digital elevation model generation algorithm, and calculate the elevation value Z within each grid cell according to the three-dimensional point cloud data (x i , y i , z i ) after gridding DEM

[0027] S34. Introduce the sparse matrix interpolation algorithm, and use the calculated elevation value Z DEM to construct the sparse matrix M

[0028]

[0029] ​In the interpolation process, the sparse matrix M is processed through an optimization algorithm:

[0030]

[0031] where W is the interpolation weight matrix, λ is the regularization coefficient, and R(M) is the regularization term of the sparse matrix M;

[0032] S35. Combine the elevation value Z' processed by the sparse matrix interpolation algorithm DEM with the geographic coordinate information (x i , y i ) to construct a complete three-dimensional digital elevation model.

[0033] Optionally, the S5 specifically includes:

[0034] S41. Based on the constructed three-dimensional digital elevation model, extract terrain feature data, including the elevation value Z' DEM , terrain slope θ, and terrain curvature κ;

[0035] S42. Input the extracted terrain feature data into the adaptive multi-modal evolutionary optimization algorithm to preliminarily generate multiple candidate paths in complex terrain. Each candidate path consists of a series of path points P i composed of, and the data of each path point includes elevation Z' DEM (P i ), slope θ(P i ), curvature κ(P i ), and other possible terrain features;

[0036] S43. In the process of path optimization, introduce a path evaluation function f(P). This function not only considers traditional terrain features but also includes the evolutionary stability of the path and its adaptability under complex terrain:

[0037] f(P) = ∫ P [α·Z'(x, y) + β·θ(x, y) + γ·κ(x, y) + δ·S(x, y) + ∈·E(P)]ds; DEM where α, β, and γ are weight factors in path optimization, respectively controlling the influence of elevation, slope, and curvature on path selection. S(x, y) represents the evolutionary stability at the path point (x, y), E(P) represents the global evolutionary complexity of the path, and ds is the path element in path integration;

[0038] where α, β, and γ are weight factors in path optimization, respectively controlling the influence of elevation, slope, and curvature on path selection. S(x, y) represents the evolutionary stability at the path point (x, y), E(P) represents the global evolutionary complexity of the path, and ds is the path element in path integration;

[0039] S44. Based on the result of the path evaluation function f(P), identify and optimize the optimal path mode, and dynamically adjust the key parameters α, β, γ, δ, ∈ of the path through the adaptive multi-modal evolutionary strategy to adapt to different terrain features:

[0040]

[0041] S45. Project the optimized optimal path P opt onto the three-dimensional digital elevation model to generate three-dimensional path data for the navigation of surveying equipment.

[0042] Optionally, step S6 specifically includes:

[0043] S61. Extract geographic information data from different sensors based on the processed multi-source data and the generated three-dimensional path data, including three-dimensional point cloud data D LiDAR , geographic coordinate data D GNSS and elevation value Z'; DEM ;

[0044] S62. Fuse the extracted data with the three-dimensional terrain model M DEM . Apply the high-dimensional non-linear dynamic optimization fusion algorithm. By constructing a non-linear mapping function F in the high-dimensional space, map the feature spaces of different data sources to a unified high-dimensional feature space:

[0045] M fused = F(D aligned , M DEM );

[0046] where F represents the non-linear mapping function, and M fused represents the fused geographic information model;

[0047] S63. During the data fusion process, adopt a dynamic optimization mechanism to adjust the parameters of the non-linear mapping function F in real time, so that the fusion result can maintain both global consistency and adaptability to local terrain features:

[0048] min F {∑ i,j (Z' fused (x i , y j ) - Z target (x i , y j )) 2 + λR(F)};

[0049] where Z' fused is the fused elevation value, Z target is the target elevation value, λ is the regularization coefficient, and R(F) is the regularization term of the mapping function F;

[0050] S64. Combine the geographic information model M fused after high-dimensional non-linear dynamic optimization fusion processing with the geographic coordinate information (x i , yi ) and elevation value Z' fused , generate a comprehensive geographic information model M composite .

[0051] Optionally, the S7 specifically includes:

[0052] S71. Based on the generated comprehensive geographic information model M composite , extract the geographic coordinates (x i , y i ) and elevation value Z' fused and the corresponding target elevation value Z target ;

[0053] S72. Input the extracted data into a deep residual regression model, and calculate the initial residual value r res (x i , y i ) of each coordinate point (x i , y i ) through establishing an initial prediction model f i :

[0054] r i = Z target (x i , y i ) - Z' fused (x i , y i );

[0055] S73. In the deep residual regression model, use a progressive regression method to correct the systematic error, and fit the residual value r i layer by layer through a multi-layer neural network. The goal of each layer of the regression model is to minimize the residual value of the current layer The updated elevation value Z″ fused is expressed as:

[0056]

[0057] Among them, represents the residual regression function of the l-th layer. The progressive regression algorithm gradually reduces the systematic error through multiple iterations, and L is the number of regression layers;

[0058] S74. During the progressive regression process, dynamically adjust the learning rate and regression coefficient parameters of the model to adapt to the complexity and error characteristics of different terrain regions, including adaptively adjusting the number of layers of the neural network and the number of neurons in each layer, so that the regression of each layer can effectively capture the error characteristics at different scales, and finally gradually reduce the overall systematic error:

[0059] M opt = M composite+ΔM;

[0060] Among them, M opt is the finally optimized model, and ΔM represents the error correction matrix obtained by the deep residual regression algorithm. This matrix contains the correction values for all coordinate points (x i , y i );

[0061] S75. After obtaining the error correction matrix ΔM, apply it to the comprehensive geographic information model M composite to generate the final optimized geographic information model M opt . This optimized model not only corrects the initial system error but also significantly improves the overall accuracy of the model through layer-by-layer regression. The final high-precision geographic information model M opt will be applied to subsequent surveying and mapping, analysis, and other related application scenarios to provide an accurate geographic information basis for actual operations.

[0062] Optionally, the specific content of S8 includes:

[0063] S81. Based on the generated final optimized geographic information model M opt , extract the topographic feature data of geographic coordinates (x i , y i ), the finally optimized elevation value Z″ fused , slope θ(x i , y i ), and curvature κ(x i , y i ) in the model;

[0064] S82. According to the extracted geographic information data, use the real estate surveying and mapping map generation algorithm to preliminarily identify the real estate boundary in the topographic model. By analyzing the changes in the elevation value Z″ fused , slope θ(x i , y i ), and curvature κ(x i , y i ), determine the initial position B init of the real estate boundary:

[0065] B init = {(x i , y i )|f(B(x i , y i )) = 0};

[0066] Among them, f(B(x i , y i )) is the boundary determination function;

[0067] S83. Introduce a topology-sensitive boundary optimization algorithm to further precisely adjust the initial real estate boundary B init and dynamically adjust the position of the boundary line according to the extracted terrain feature data:

[0068] B opt = argmin B {∑ i,j [f(B(x i , y j ))·w(x i , y j ) + λ·T(x i , y j )]};

[0069] where B opt is the optimized real estate boundary line, w(x i , y j ) is the weight factor for local position adjustment of the boundary line, λ is the smoothing parameter, and T(x i , y j ) is the topology-sensitive function for reflecting the gradient change of terrain features to optimize the smoothness and adaptability of the boundary line in the terrain mutation area;

[0070] S84. Project the optimized real estate boundary line B opt onto the three-dimensional digital elevation model M opt and combine it with the optimized terrain feature data θ(x i , y i ) and κ(x i , y i ) to generate a real estate surveying and mapping map containing the real estate boundary and terrain features;

[0071] S85. In the generated surveying and mapping map, make detailed annotations on the real estate boundary B opt and the main terrain features. The annotation positions and attribute values are determined by the geographical coordinates (x i , y i ) and the corresponding elevation value Z″ fused and associated with the final optimized geographic information model M opt to ensure that each piece of data in the surveying and mapping map is derived from the optimized geographic information model;

[0072] S86. Save the generated real estate surveying and mapping map as a digital file in a specified format, which contains the complete geographic information model and detailed terrain feature annotations.

[0073] The beneficial effects of the present invention are:

[0074] In the process of multi-source data acquisition, the present invention realizes the efficient synchronization of LiDAR and GNSS sensor data. This algorithm automatically adjusts the temporal and spatial synchronization of data by maintaining the topological structure of terrain data, ensuring the consistency and accuracy of data from different sensors in complex terrain environments, and overcoming the problem of difficult integration of multi-source data in traditional methods. The adaptive multi-modal evolutionary optimization algorithm is adopted for path planning. This algorithm can identify and optimize multiple path modalities in complex terrains, dynamically adjust the path planning strategy, and thus select the optimal path for surveying and mapping. Compared with traditional path planning methods, the adaptive multi-modal evolutionary optimization algorithm can better adapt to terrain changes, significantly improving the efficiency of surveying and mapping and the accuracy of path planning, especially showing superiority in environments with complex and severely changing terrains.

[0075] The present invention introduces a sparse matrix interpolation algorithm for constructing a digital elevation model. By performing sparse matrix interpolation on three-dimensional point cloud data, this algorithm not only reduces the data volume but also significantly improves the detail accuracy of the terrain model. Compared with traditional linear interpolation methods, the sparse matrix interpolation algorithm can more accurately capture the subtle changes in the terrain, making the digital elevation model more refined and accurate in complex terrains. The high-dimensional non-linear dynamic optimization fusion algorithm is used. By constructing a non-linear mapping function in a high-dimensional space, this algorithm fuses the data features from different sensors and adopts a dynamic optimization mechanism to adjust the parameters of the mapping function in real time, ensuring the global consistency of the fusion result while being able to adapt to local terrain features. This innovation effectively solves the problem of insufficient non-linear data processing in traditional fusion algorithms and greatly improves the accuracy of the fusion model.

[0076] The present invention applies a deep residual regression algorithm for error correction. Through a progressive regression method, the present invention can gradually reduce systematic errors and finally generate an optimized high-precision geographic information model. Compared with traditional error correction methods, the deep residual regression algorithm can more effectively capture systematic errors in complex terrains and accurately correct them through a deep learning model, greatly improving the accuracy of the final surveying and mapping results. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0078] Figure 1 is a flowchart of the high-precision real estate surveying and mapping method in complex terrain environments based on the optimization algorithm proposed by the present invention;

[0079] Figure 2 is a schematic diagram of the adaptive multi-modal evolutionary optimization algorithm for path planning in the present invention;

[0080] Figure 3 This is a combined schematic diagram of the high-dimensional non-linear dynamic optimization fusion algorithm and the deep residual regression algorithm in the present invention. Specific Embodiment

[0081] Now, the present invention will be further described in detail with reference to the accompanying drawings. These drawings are all simplified schematic diagrams, only illustrating the basic structure of the present invention in a schematic manner, so they only show the components related to the present invention.

[0082] Reference Figures 1 - 3 , a high-precision real estate surveying and mapping method in a complex terrain environment based on an optimization algorithm, includes the following steps:

[0083] S1. In a complex terrain environment, adopt multi-source data acquisition technology, integrate LiDAR and GNSS sensors, collect geographic information data, and achieve data diversity and wide coverage;

[0084] S2. Preprocess the collected multi-source data, including data cleaning and coordinate transformation, to generate basic geographic information data;

[0085] S3. Based on the processed geographic information data, construct a digital elevation model to represent the three-dimensional undulation changes of the complex terrain;

[0086] S4. Based on the generated three-dimensional terrain model, adopt an adaptive multi-modal evolutionary optimization algorithm for surveying and mapping path planning. By identifying and optimizing multiple path modes, dynamically adjust the optimization strategy, and select the optimal path in the complex terrain;

[0087] S5. During the surveying and mapping process, dynamically adjust the running trajectory of the surveying and mapping equipment according to the path planning results, adapt to terrain changes and perform surveying and mapping;

[0088] S6. Integrate the processed multi-source data with the generated three-dimensional terrain model, adopt a high-dimensional non-linear dynamic optimization fusion algorithm, integrate the data of different sensors into a unified geographic information model, and perform data fusion and optimization processing;

[0089] S7. Conduct error analysis and correction on the generated geographic information model, apply the deep residual regression algorithm for error correction, correct the systematic error through a layer-by-layer progressive regression method, and finally obtain an optimized geographic information model;

[0090] S8. Based on the optimized geographic information model, generate a real estate surveying and mapping map, and mark the real estate boundaries and terrain features.

[0091] In this embodiment, the specific content of S1 includes:

[0092] S11. In a complex terrain environment, adopt multi-source data acquisition technology, integrate lidar sensors and global navigation satellite system sensors, and collect three-dimensional point cloud data and geographical location information respectively;

[0093] S12. The LiDAR sensor emits laser beams and receives echo signals, and calculates the distance based on the echo time t and the speed of light c to generate three-dimensional point cloud data of the target area, and the data includes the three-dimensional coordinates (x i , y i , z i ) of the target points;

[0094] S13. Use the GNSS sensor to receive satellite signals, calculate and record the geographical coordinates (x i , y i , z i ) of the survey points, and provide geographical location information;

[0095] S14. Use the adaptive data synchronization algorithm based on topology preservation to synchronize the three-dimensional point cloud data collected by the LiDAR sensor and the geographical coordinate data obtained by the GNSS sensor, and automatically adjust the time and space synchronization of the data by maintaining the topological structure of the terrain data;

[0096] S15. Integrate the synchronized data after topology preservation to form an initial geographical information data set with wide coverage and diversity, and the data set includes three-dimensional terrain undulation, coordinates and topological structure.

[0097] In this embodiment, the specific content of S3 includes:

[0098] S31. Based on the formed initial geographical information data set, extract the three-dimensional point cloud data (x i , y i , z i ) and the corresponding geographical coordinate information;

[0099] S32. Grid the extracted three-dimensional point cloud data according to the geographical coordinates to generate a preliminary elevation data model, and the size and distribution of the grid cells are adjusted according to the complexity of the terrain;

[0100] S33. Apply the digital elevation model generation algorithm, and calculate the elevation value Z i , y i , z i ) within each grid cell according to the three-dimensional point cloud data (x DEM ;

[0101] S34. Introduce the sparse matrix interpolation algorithm, and use the calculated elevation value Z DEM to construct a sparse matrix M:

[0102]

[0103] In the interpolation process, the sparse matrix M is processed by an optimization algorithm:

[0104]

[0105] where W is the interpolation weight matrix, λ is the regularization coefficient, and R(M) is the regularization term of the sparse matrix M;

[0106] S35. Combine the elevation value Z' processed by the sparse matrix interpolation algorithm DEM with the geographic coordinate information (x i , y i ) to construct a complete three-dimensional digital elevation model.

[0107] In this embodiment, the S5 specifically includes:

[0108] S41. Based on the constructed three-dimensional digital elevation model, extract terrain feature data, including the elevation value Z' DEM , the terrain slope θ, and the terrain curvature κ;

[0109] S42. Input the extracted terrain feature data into the adaptive multimodal evolutionary optimization algorithm to preliminarily generate multiple candidate paths in complex terrain. Each candidate path consists of a series of path points P i . The data of each path point includes the elevation Z' DEM (P i ), the slope θ(P i ), the curvature κ(P i ), and other possible terrain features;

[0110] S43. In the process of path optimization, introduce a path evaluation function f(P). This function not only considers traditional terrain features but also includes the evolutionary stability of the path and its adaptability under complex terrain:

[0111] f(P) = ∫ P [α·Z'(x,y) + β·θ(x,y) + γ·κ(x,y) + δ·S(x,y)· + ∈·E(P)]ds; DEM where α, β, and γ are weight factors in path optimization, which respectively control the influence of elevation, slope, and curvature on path selection. S(x,y) represents the evolutionary stability at the path point (x,y), E(P) represents the global evolutionary complexity of the path, and ds is the path element in path integration;

[0112]

[0113] ​S44. Based on the results of the path evaluation function f(P), identify and optimize the optimal path mode, and dynamically adjust the key parameters α, β, γ, δ, ∈ of the path through the adaptive multi-modal evolution strategy to adapt to different terrain features:

[0114]

[0115] S45. Project the optimized optimal path P opt onto the three-dimensional digital elevation model to generate three-dimensional path data for the navigation of the surveying equipment.

[0116] In this embodiment, the specific steps of S6 are as follows:

[0117] S61. Based on the processed multi-source data and the generated three-dimensional path data, extract the geographic information data from different sensors, including the three-dimensional point cloud data D LiDAR , the geographic coordinate data D GNSS and the elevation value Z'; DEM ;

[0118] S62. Integrate the extracted data with the three-dimensional terrain model M DEM using the high-dimensional non-linear dynamic optimization integration algorithm. By constructing a non-linear mapping function F in the high-dimensional space, map the feature spaces of different data sources to a unified high-dimensional feature space:

[0119] M fused = F(D aligned , M DEM );

[0120] where F represents the non-linear mapping function, and M fused represents the integrated geographic information model;

[0121] S63. During the data integration process, adopt a dynamic optimization mechanism to adjust the parameters of the non-linear mapping function F in real time, and the integration result should maintain both global consistency and adaptability to local terrain features:

[0122] min F {∑ i,j (Z' fused (x i , y j ) - Z target (x i , y j )) 2 + λR(F)};

[0123] where Z' fused is the integrated elevation value, Z target is the target elevation value, λ is the regularization coefficient, and R(F) is the regularization term of the mapping function F;

[0124] S64. Combine the geographical information model M that has undergone high-dimensional non-linear dynamic optimization and fusion processing fused with geographical coordinate information (x i , y i ) and elevation value Z' fused to generate a comprehensive geographical information model M composite .

[0125] In this embodiment, S7 specifically includes:

[0126] S71. Based on the generated comprehensive geographical information model M composite , extract the geographical coordinates (x i , y i ), elevation value Z' fused and the corresponding target elevation value Z target ;

[0127] S72. Input the extracted data into a deep residual regression model, and calculate the initial residual value r res (x i , y i ) of each coordinate point (x i , y i ) through the established initial prediction model f i :

[0128] r i = Z target (x i , y i ) - Z' fused (x i , y i );

[0129] S73. In the deep residual regression model, use a progressive regression method to correct the systematic error, and fit the residual value r i layer by layer through a multi-layer neural network. The goal of each layer of the regression model is to minimize the residual value of the current layer , and the updated elevation value Z″ fused is expressed as:

[0130]

[0131] where represents the residual regression function of the l-th layer. The progressive regression algorithm gradually reduces the systematic error through multiple iterations, and L is the number of regression layers;

[0132] S74. During the step-by-step regression process, dynamically adjust the learning rate and regression coefficient parameters of the model to adapt to the complexity and error characteristics of different terrain regions, including adaptively adjusting the number of layers of the neural network and the number of neurons in each layer, so that the regression of each layer can effectively capture the error characteristics at different scales, and finally gradually reduce the overall system error:

[0133] M opt = M composite + ΔM;

[0134] where M opt is the finally optimized model, and ΔM represents the error correction matrix obtained through the deep residual regression algorithm. This matrix contains the correction values for all coordinate points (x i , y i );

[0135] S75. After obtaining the error correction matrix ΔM, apply it to the comprehensive geographic information model M composite to generate the final optimized geographic information model M opt . This optimized model not only corrects the initial system error but also significantly improves the overall accuracy of the model through step-by-step regression. The final high-precision geographic information model M opt will be applied to subsequent surveying and mapping, analysis, and other related application scenarios to provide an accurate geographic information basis for actual operations.

[0136] In this embodiment, the specific content of S8 includes:

[0137] S81. Based on the generated final optimized geographic information model M opt , extract the terrain feature data of geographic coordinates (x i , y i ), the finally optimized elevation value Z″ fused , slope θ(x i , y i ) and curvature κ(x i , y i ) in the model;

[0138] S82. According to the extracted geographic information data, use the real estate surveying and mapping map generation algorithm to preliminarily identify the real estate boundaries in the terrain model. By analyzing the changes in the elevation value Z″ fused , slope θ(x i , y i ) and curvature κ(x i , y i ), determine the initial position B init of the real estate boundary:

[0139] B init = {(x i , yi ) | f(B(x i , y i )) = 0};

[0140] Wherein, f(B(x i , y i )) is a boundary determination function;

[0141] S83. Introduce a topology-sensitive boundary optimization algorithm to further precisely adjust the initial real estate boundary B init According to the extracted terrain feature data, dynamically adjust the position of the boundary line:

[0142] B opt = argmin B {∑ i,j [f(B(x i , y j )) · w(x i , y j ) + λ · T(x i , y j )};

[0143] Wherein, B opt is the optimized real estate boundary line, w(x i , y j ) is a weight factor for local position adjustment of the boundary line, λ is a smoothing parameter, and T(x i , y j ) is a topology-sensitive function for reflecting the gradient change of terrain features to optimize the smoothness and adaptability of the boundary line in terrain mutation areas;

[0144] S84. Project the optimized real estate boundary line B opt onto the three-dimensional digital elevation model M opt , and combine the optimized terrain feature data θ(x i , y i ) and κ(x i , y i ) to generate a real estate surveying and mapping map including the real estate boundary and terrain features;

[0145] S85. In the generated surveying and mapping map, make detailed annotations on the real estate boundary B opt and the main terrain features. The annotation positions and attribute values are determined by the geographical coordinates (x i , y i ) and the corresponding elevation value Z″ fused , and are associated with the final optimized geographical information model M opt to ensure that each data item in the surveying and mapping map is derived from the optimized geographical information model;

[0146] S86. Save the generated real estate surveying and mapping map as a digital file in a specified format, which contains a complete geographical information model and detailed topographic feature annotations.

[0147] Example 1:

[0148] To verify the feasibility of the present invention in implementation, the present invention is applied to a mountainous area in the south, where the terrain is complex, the mountains undulate, the vegetation is dense, and there are a large number of gullies and canyons. High-precision real estate surveying and mapping is required in this area to determine the real estate boundaries and provide data support for subsequent land management and resource planning. However, due to the complexity of the terrain, it is difficult for traditional surveying and mapping methods to achieve high-precision and high-efficiency surveying and mapping work in this area. In particular, GNSS signals are easily blocked in mountainous areas, LiDAR data may be incomplete in vegetation-covered areas, and conventional path planning algorithms are also difficult to find the optimal path in such complex terrain.

[0149] In the data acquisition stage, the present invention adopts a multi-source data acquisition technology, integrating lidar and global navigation satellite system sensors. In early July 2024, the surveying and mapping team selected a typical area in the southern mountainous area, with an area of about 100 square kilometers, and used a drone-mounted LiDAR sensor and a ground GNSS receiver to synchronously collect data. In this process, the lidar collected three-dimensional point cloud data in the area by emitting laser beams and receiving echo signals, while the GNSS receiver recorded the geographical coordinates of each surveying point by receiving satellite signals. Through an adaptive data synchronization algorithm based on topology preservation, the surveying and mapping team precisely synchronized the data collected by the lidar and GNSS in terms of time and space, generating a complete and accurate initial geographical information dataset.

[0150] In the data processing stage, the surveying and mapping team first cleaned and transformed the coordinates of the collected data, and constructed a digital elevation model of the area. Due to the complex terrain and large undulations in the mountainous area, the surveying and mapping team used a sparse matrix interpolation algorithm to interpolate the gridded three-dimensional point cloud data and constructed a refined elevation model. Compared with traditional methods, this model shows higher accuracy in areas with drastic height changes. According to the actual test data of the surveying and mapping team, using the method of the present invention, the average error between the interpolated elevation model and the measured data is reduced by 15%, especially in areas with high slopes and uneven surfaces, the error is reduced by nearly 20%.

[0151] The surveying and mapping team planned the surveying and mapping path. Due to the complex and variable paths in mountainous areas, conventional path planning algorithms are difficult to adapt to. Through the adaptive multi-modal evolutionary optimization algorithm, the surveying and mapping team selected the path with the best performance in terms of terrain adaptability and surveying and mapping efficiency among multiple candidate paths. During the path planning process, the algorithm considered multiple features of the terrain, such as elevation, slope, and curvature, and adjusted the optimization strategy in real time to adapt to complex terrain changes. In actual surveying and mapping, the optimization algorithm enabled the surveying and mapping equipment to avoid multiple signal interference areas and obstacle areas while still covering the key terrain features of the surveying and mapping area. Compared with traditional path planning algorithms, the path planning time of the present invention was reduced by approximately 30%, and the path coverage rate was increased by approximately 25%.

[0152] In the data fusion and error correction stage, the surveying and mapping team fused the data collected by LiDAR and GNSS with the three-dimensional terrain model, and used the high-dimensional non-linear dynamic optimization fusion algorithm to integrate the data of different sensors into a unified geographic information model. By dynamically adjusting the parameters of the mapping function, the algorithm ensured the balance between global consistency and local feature adaptability of the fusion result. After data fusion, the surveying and mapping team adopted the deep residual regression algorithm to correct the errors of the fused geographic information model. The test results showed that after multi-layer regression processing, the overall error of the model was reduced by more than 40%, and the surveying and mapping accuracy of the final generated geographic information model was significantly improved in multiple key terrain areas.

[0153] Based on the optimized geographic information model, the surveying and mapping team generated the real estate surveying and mapping map of the area. Through the topology-sensitive boundary optimization algorithm, the real estate boundary was further accurately delimited to ensure the rationality and accuracy of the boundary line in complex terrain. The actual data showed that using the method of the present invention, the deviation between the generated boundary line and the actual ground measurement result was less than 10 cm, and the accuracy was improved by approximately 50% compared with the traditional method.

[0154] During the entire test process, the present invention demonstrated great superiority. Compared with traditional surveying and mapping methods, the present invention not only greatly improved the accuracy and efficiency of surveying and mapping, but also effectively solved common problems such as signal interference, incomplete data, and difficult path planning in complex terrain. Under the condition of the same surveying and mapping area, the surveying and mapping time was shortened by approximately 40%, and the overall data processing and image generation time was reduced by nearly half. These results fully proved the feasibility and advantages of the present invention in the application of complex terrain environments, providing a new high-precision solution for the field of real estate surveying and mapping.

[0155] Table 1 Comparison of surveying and mapping accuracy and path planning effect

[0156]

[0157] Comparison of Data Fusion, Error Correction and Map Generation Effects in Table 2

[0158]

[0159] By comparing the test results of the traditional method and the method of the present invention on multiple key performance indicators, the present invention demonstrates significant technical advantages, especially in the application performance in complex terrain environments. In terms of data acquisition, the multi-source data acquisition and synchronous processing technology of the present invention has increased the data acquisition coverage rate by 11.8%. This means that under complex terrain conditions, the present invention can collect geographical information data more comprehensively, ensuring the integrity of the surveyed area. At the same time, the data synchronization error has been reduced by 40%, reflecting that the present invention effectively improves the data consistency and synchronization accuracy during the multi-source data fusion process. In the construction of the digital elevation model, by introducing the sparse matrix interpolation algorithm, the present invention reduces the average error between the elevation model and the measured data by 16.7%. Especially in areas with large terrain undulations, the accuracy of the model has been significantly improved. This lays a more reliable basic data for subsequent surveying and mapping work.

[0160] During the path planning process, the adaptive multi-modal evolutionary optimization algorithm adopted by the present invention greatly improves the efficiency and accuracy of path planning. Compared with the traditional method, the path planning time is shortened by 30%, while the path coverage rate is increased by 25.7%. This shows that the present invention can not only formulate the optimal surveying and mapping path faster, but also cover important areas more comprehensively in complex terrains. At the same time, the obstacle avoidance success rate of the surveying and mapping equipment has also been increased by 41.7%, further enhancing the adaptability and safety of the equipment in complex terrains.

[0161] In terms of data fusion and error correction, through the application of the high-dimensional non-linear dynamic optimization fusion algorithm and the deep residual regression algorithm, the present invention reduces the error of the fused geographical information model by 40%, and improves the model accuracy after system error correction by 15%. This ensures that the finally generated real estate surveying and mapping map has higher accuracy. The boundary line deviation is reduced by 50%, and the accuracy of terrain feature annotation is increased by 11.8%, further reflecting the excellent performance of the present invention in surveying and mapping accuracy.

[0162] In summary, in the real estate surveying and mapping work in complex terrain environments, the present invention significantly improves the comprehensiveness of data acquisition, the accuracy of path planning, the consistency of data fusion, as well as the accuracy and efficiency of the final surveying and mapping results. Compared with the traditional method, the present invention not only overcomes many limitations in the existing technology, but also provides a more reliable and efficient solution for practical applications, with broad application prospects and significant technical advantages.

[0163] As described above, it is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered within the protection scope of the present invention.

Claims

1. A high-precision real estate surveying and mapping method in complex terrain environments based on an optimization algorithm, characterized in that, It includes the following steps: S1. In a complex terrain environment, adopt multi-source data acquisition technology, integrate LiDAR and GNSS sensors to collect geographic information data, and achieve data diversity and wide coverage; S2. Preprocess the collected multi-source data, including data cleaning and coordinate transformation, to generate basic geographic information data; S3. Based on the processed geographic information data, construct a digital elevation model to represent the three-dimensional undulation changes of the complex terrain; S4. Based on the generated three-dimensional terrain model, adopt an adaptive multi-modal evolutionary optimization algorithm for surveying path planning. By identifying and optimizing multiple path modes, dynamically adjust the optimization strategy, and select the optimal path in the complex terrain; S5. During the surveying process, dynamically adjust the running trajectory of the surveying equipment according to the path planning results, adapt to terrain changes and perform surveying; S6. Integrate the processed multi-source data with the generated three-dimensional terrain model, adopt a high-dimensional non-linear dynamic optimization fusion algorithm to integrate the data of different sensors into a unified geographic information model, and perform data fusion and optimization processing; S7. Conduct error analysis and correction on the generated geographic information model, apply the deep residual regression algorithm for error correction, and correct the systematic error through a progressive regression method layer by layer, and finally obtain an optimized geographic information model; S8. Based on the optimized geographic information model, generate an immovable property surveying map, and mark the immovable property boundaries and terrain features.

2. The high-precision real estate mapping method in a complex terrain environment based on an optimization algorithm according to claim 1, wherein The specific content of S1 includes: S11. In a complex terrain environment, adopt multi-source data acquisition technology, integrate a lidar sensor and a global navigation satellite system sensor to collect three-dimensional point cloud data and geographical location information respectively; S12. Transmit a laser beam through the LiDAR sensor and receive the echo signal, and calculate the distance based on the echo time t and the speed of light c Generate three-dimensional point cloud data for the target area, and the data includes the three-dimensional coordinates (x i , y i , z i ) S13. Use the GNSS sensor to receive satellite signals, calculate and record the geographical coordinates (x i , y i , z i ) of the survey point, and provide geographical location information; S14. Use a topology-preserving adaptive data synchronization algorithm to synchronize the three-dimensional point cloud data collected by the LiDAR sensor with the geographic coordinate data obtained by the GNSS sensor. By maintaining the topological structure of the terrain data, automatically adjust the time and space synchronization of the data; S15. Integrate the synchronized data after topology preservation to form an initial geographic information data set with wide coverage and diversity. This data set includes three-dimensional terrain undulation, coordinates, and topological structure.

3. The high-precision real estate mapping method in a complex terrain environment based on an optimization algorithm according to claim 1, characterized in that, The specific content of S3 includes: S31. Based on the formed initial geographic information dataset, extract the three-dimensional point cloud data (x i , y i , z i ) and the corresponding geographic coordinate information; S32. Grid the extracted three-dimensional point cloud data according to geographic coordinates to generate a preliminary elevation data model. The size and distribution of the grid cells are adjusted according to the complexity of the terrain; S33. Apply the digital elevation model generation algorithm to calculate the elevation value Z within each grid cell based on the three-dimensional point cloud data (x i , y i , z i ) after grid processing; DEM ; S34. Introduce the sparse matrix interpolation algorithm and use the calculated elevation value Z DEM Construct a sparse matrix M: In the interpolation process, process the sparse matrix M through an optimization algorithm: where W is the interpolation weight matrix, λ is the regularization coefficient, and R(M) is the regularization term of the sparse matrix M; S35. Combine the elevation value Z processed by the sparse matrix interpolation algorithm ′ DEM with the geographic coordinate information (x i , y i ) to construct a complete three-dimensional digital elevation model.

4. The high-precision real estate surveying and mapping method in a complex terrain environment based on an optimization algorithm according to claim 1, wherein The specific content of S5 includes: S41. Extract terrain feature data based on the constructed three-dimensional digital elevation model, including elevation value Z ′ DEM , terrain slope θ, and terrain curvature κ; S42. Input the extracted terrain feature data into the adaptive multi-modal evolutionary optimization algorithm to preliminarily generate multiple candidate paths in complex terrains. Each candidate path consists of a series of path points P i and the data of each path point includes elevation Z' DEM (P i ), slope θ(P i ), curvature κ(P i ), and other terrain features; S43. During the path optimization process, introduce a path evaluation function f(P): f(P) = ∫ P [α·Z' DEM (x, y) + β·θ(x, y) + γ·κ(x, y) + δ·S(x, y) + ∈·E(P)]ds; where α, β, and γ are weight factors in path optimization, which respectively control the influence of elevation, slope, and curvature on path selection. S(x,y) represents the evolution stability at the path point (x,y), E(P) represents the global evolution complexity of the path, and ds is the path element in the path integral; S44. Based on the result of the path evaluation function f(P), identify and optimize the optimal path mode, and dynamically adjust the key parameters α, β, γ, δ, ∈ of the path through an adaptive multi-modal evolution strategy to adapt to different terrain features: S45. Project the optimized optimal path P opt onto the three-dimensional digital elevation model to generate three-dimensional path data for the navigation of the surveying and mapping equipment.

5. The high-precision real estate surveying and mapping method in a complex terrain environment based on an optimization algorithm according to claim 1, wherein The specific content of S6 includes: S61. Extract the geographic information data from different sensors, including 3D point cloud data D, based on the processed multi-source data and the generated 3D path data. LiDAR , geographic coordinate data D GNSS and elevation value Z ′ DEM ; S62. Integrate the extracted data with the three-dimensional terrain model M DEM Perform fusion using a high-dimensional non-linear dynamic optimization fusion algorithm. By constructing a non-linear mapping function F in the high-dimensional space, map the feature spaces of different data sources to a unified high-dimensional feature space: M fused = F(D aligned , M DEM ); Among them, F represents the non-linear mapping function, and M fused represents the fused geographic information model; S63. During the data fusion process, adopt a dynamic optimization mechanism to adjust the parameters of the non-linear mapping function F in real time, and the fusion result simultaneously maintains global consistency and adaptability to local terrain features: min F {∑ i,j (Z' fused (x i ,y j )-Z target (x i ,y j )) 2 +λR(F)}; Among them, Z' fused is the fused elevation value, Z target is the target elevation value, λ is the regularization coefficient, and R(F) is the regularization term of the mapping function F; S64. Combine the geographic information model M that has undergone high-dimensional non-linear dynamic optimization and fusion processing fused with the geographic coordinate information (x i , y i ) and the elevation value Z ′ fused to generate the comprehensive geographic information model M composite .

6. The high-precision real estate surveying and mapping method in complex terrain environment based on the optimization algorithm according to claim 1, characterized in that, The specific content of S7 includes: S71. Based on the generated comprehensive geographic information model M composite , extract the geographic coordinates (x i , y i ) and elevation value Z ′ fused in the model, as well as the corresponding target elevation value Z target ; S72. Input the extracted data into the deep residual regression model, and calculate the initial residual value r res (x i ,y i ) for each coordinate point (x i ,y i ) by establishing the initial prediction model f i : r i = Z target (x i , y i ) - Z′ fused (x i , y i ); S73. In the deep residual regression model, a progressive regression method is used to correct the systematic error, and the residual value r is fitted layer by layer through a multi-layer neural network i , and the goal of each layer of the regression model is to minimize the residual value of the current layer The updated elevation value Z ″ fused is expressed as: Among them, represents the residual regression function of the l-th layer, and L is the number of regression layers; S74. During the step-by-step regression process, dynamically adjust the learning rate and regression coefficient parameters of the model to adapt to the complexity and error characteristics of different terrain regions, including adaptively adjusting the number of layers of the neural network and the number of neurons in each layer, so that the regression of each layer can effectively capture error characteristics at different scales: Mopt = Mcomposite + ΔM; Among them, M opt is the finally optimized model, and ΔM represents the error correction matrix obtained by the deep residual regression algorithm; S75. After obtaining the error correction matrix ΔM, apply it to the comprehensive geographic information model M composite to generate the final optimized geographic information model M opt .

7. The high-precision real estate surveying and mapping method in complex terrain environment based on optimization algorithm according to claim 1, characterized in that, The specific content of S8 includes: S81. Based on the generated final optimized geographical information model M opt , extract the terrain feature data of geographical coordinates (x i , y i ), the elevation value Z after final optimization ″ fused , slope θ(x i , y i ), and curvature κ(x i , y i ) from the model; S82. Based on the extracted geographic information data, use the real estate surveying and mapping map generation algorithm to preliminarily identify the real estate boundaries in the terrain model, and determine the initial position B of the real estate boundary by analyzing the changes in the elevation value Z ″ fused , slope θ(x i , y i ), and curvature κ(x i , y i ): init :[[]]END]] B init = {(x i , y i ) | f(B(x i , y i )) = 0}; Among them, f(B(x i , y i )) is the boundary determination function; S83. Introduce a topology-sensitive boundary optimization algorithm to further adjust the initial real estate boundary B init and dynamically adjust the position of the boundary line according to the extracted terrain feature data: B opt = argmin B {∑ i,j [f(B(x i ,y j ))·w(x i ,y j ) + λ·T(x i ,y j )]}; Among them, B opt is the optimized real estate boundary line, w(x i , y j ) is the weight factor, λ is the smoothing parameter, and T(x i , y j ) is the topology-sensitive function; S84. Project the optimized real estate boundary line B opt onto the three-dimensional digital elevation model M opt , and combine it with the optimized terrain feature data θ(x i , y i ) and κ(x i , y i ) to generate a real estate surveying and mapping map that includes the real estate boundary and terrain features; S85. In the generated surveying and mapping map, the real estate boundary B opt and the main topographic features are detailedly marked, and the marking positions and attribute values are determined by the geographical coordinates (x i , y i ) and the corresponding elevation value Z ″ fused , and are associated with the final optimized geographical information model M opt . S86. Save the generated real estate surveying and mapping map as a digital file in a specified format, and the digital file contains a geographic information model and terrain feature annotations.

Images