Intelligent analysis and management method and system for land surveying and mapping data

Abstract

The invention relates to the technical field of land surveying and mapping, in particular to an intelligent analysis and management method and system for land surveying and mapping data, and the method comprises the steps: obtaining first surveying and mapping data and second surveying and mapping data of the same surveying and mapping area, and carrying out the preprocessing of the first surveying and mapping data and the second surveying and mapping data; constructing a joint model and a double-flow network, analyzing the preprocessed first surveying and mapping data and the preprocessed second surveying and mapping data through the joint model and the double-flow network, and outputting topographic data; extracting a plurality of feature values from the first surveying and mapping data according to a preset acquisition frequency to form a surveying and mapping feature sequence; inputting the surveying and mapping feature sequence into a preset vegetation multilayer state model, and obtaining vegetation vertical space distribution information and ground elevation data through the vegetation multilayer state model; classifying and managing the land of the surveying and mapping area based on the vertical spatial distribution information of the vegetation, correcting the topographic data by using the ground elevation data, and outputting the corrected topographic data to improve the accuracy of the topographic data.

Description

Technical Field

[0001] The present invention relates to the technical field of land surveying and mapping, and in particular to a method and system for intelligent analysis and management of land surveying and mapping data. Background Art

[0002] As a key means of acquiring, processing and analyzing spatial information of land and its appurtenances, land surveying and mapping technology provides a reliable basis for understanding the various attributes of land. It is widely used in the fields of land management, urban planning and engineering construction.

[0003] Digital surveying and mapping technology GNSS technology has become one of the important technologies in the field of modern surveying and mapping due to its significant advantages such as high precision and strong real-time performance. It can achieve real-time positioning on a global scale, without being restricted by factors such as weather and terrain, which has brought great convenience to land surveying and mapping. With its fast and accurate characteristics, 3D laser scanning technology can obtain a large amount of 3D coordinate data on the surface of objects in a short time, form a detailed 3D model, and provide rich information for subsequent analysis and processing. Remote sensing measurement technology uses sensors on platforms such as satellites and aircraft to observe the earth's surface from a distance and obtain land information over a large area. It has the advantages of high efficiency and macroscopic. Laser radar technology (LiDAR) can penetrate obstacles such as vegetation and adapt to the surveying and mapping of complex terrain.

[0004] Traditional surveying and mapping mainly adopts a single surveying and mapping method and conducts analysis based on a single data source. A single data source may have errors and is prone to accumulated errors during data processing, affecting the accuracy and reliability of surveying and mapping results.

[0005] To this end, we propose an analysis and management method to improve the accuracy of surveying and mapping data through the method of multi-source data fusion. Summary of the invention

[0006] The present invention integrates LiDAR data and SAR data to improve the accuracy of surveying and mapping data. At the same time, it integrates the vertical structural characteristics of vegetation (number of layers and density) to classify the vegetation covering the land, and further realizes the classification of land types based on the classification of vegetation.

[0007] The technical solution proposed by the present invention is: a method for intelligent analysis and management of land surveying and mapping data, the method comprising:

[0008] Acquire first surveying and mapping data and second surveying and mapping data of the same surveying and mapping area, and preprocess the first surveying and mapping data and the second surveying and mapping data;

[0009] Constructing a joint model and a dual-stream network, analyzing the preprocessed first surveying and mapping data and the second surveying and mapping data through the joint model and the dual-stream network, and outputting terrain data;

[0010] Extracting multiple characteristic values ​​from the first surveying and mapping data according to a preset acquisition frequency to form a surveying and mapping characteristic sequence; inputting the surveying and mapping characteristic sequence into a preset vegetation multi-layer state model, and obtaining vegetation vertical spatial distribution information and ground elevation data through the vegetation multi-layer state model;

[0011] The land in the surveying and mapping area is classified and managed based on the vertical spatial distribution information of vegetation. At the same time, the terrain data is corrected using the ground elevation data and the corrected terrain data is output to improve the accuracy of the terrain data.

[0012] Preferably, the first surveying and mapping data is LiDAR elevation data, and the second surveying and mapping data is Synthetic Aperture Radar SAR elevation data; the preprocessing includes time-space reference alignment and error model calibration;

[0013] The spatiotemporal alignment includes:

[0014] The first surveying and mapping data and the second surveying and mapping data are converted to a unified coordinate system, and the first surveying and mapping data is subjected to elevation conversion, specifically: ,in, Represents the converted elevation data, Represents the elevation data before conversion. It indicates the height of the geoid level;

[0015] rasterizing the first surveying and mapping data into a grid network, resampling the second surveying and mapping data through a bilinear interpolation algorithm and converting the data into the same grid network;

[0016] The error model calibration includes:

[0017] Calibrate the noise of the first survey data ,in, Indicates the first surveying and mapping data error;

[0018] Calibrate the noise of the second survey data ,in, Indicates the second surveying and mapping data error.

[0019] Preferably, the constructing of the joint model and the dual-stream network, analyzing the pre-processed first surveying and mapping data and the second surveying and mapping data through the joint model and the dual-stream network, and outputting the terrain data includes:

[0020] Step 2.1: construct a joint model based on the Kalman filter algorithm, fuse the first surveying and mapping data with the second surveying and mapping data, and obtain the elevation data vector of the surveying and mapping area, specifically including:

[0021] Step 2.1.1: Assume that the elevation of the terrain in the survey area is in the time period If there is no change within the time period The first The elevation vector of the raster is ;in Indicates The elevation values ​​of a grid network;

[0022] Assume the state equation is: ; ;

[0023] in, Indicates The LiDAR elevation vector of each grid, Indicates SAR elevation vector of each grid; represents the identity matrix, represents the process noise vector, , ; represents the process noise covariance, Represents terrain change error;

[0024] Step 2.1.2: After fusing the LiDAR elevation vector and the SAR elevation vector, The elevation vector of a grid is , where the observation matrix ;

[0025] The first surveying and mapping data noise and the second surveying and mapping data noise constitute the measurement noise covariance matrix ;

[0026] Let Kalman gain ; where the updated error covariance matrix ; Indicates The prediction error covariance matrix of the grid;

[0027] The Kalman gain after substituting the observation matrix and noise covariance matrix is: ;

[0028] Then the updated elevation vector is ; .

[0029] Preferably, the constructing of the joint model and the dual-stream network, analyzing the pre-processed first surveying and mapping data and the second surveying and mapping data through the joint model and the dual-stream network, and outputting the terrain data, further includes:

[0030] Constructing a two-stream network based on the updated elevation vector and outputting terrain data includes the following sub-steps:

[0031] Step 2.2.1. Get LiDAR elevation vector and the SAR elevation vector as well as ;

[0032] Generate 6-channel input tensor for each grid ; Among them, the first and second channels are used to input the updated LiDAR elevation vector and the first mapping data error; the third and fourth channels are used to input the updated SAR elevation vector and the second mapping data error; the fifth and sixth channels are used to input the diagonal elements of the updated error covariance matrix;

[0033] The input blocks are constructed in 5×5 areas to capture terrain continuity, specifically ,in Represents a grid The adjacent grids of Indicates the number of layers of the grid network in the vertical direction;

[0034] Step 2.2.2: Construct a convolutional network 1, wherein the convolutional network 1 includes 3 convolutional layers, each of which includes 3×3 convolutions. The convolutional network 1 extracts the LiDAR elevation vector features from the input tensor, and after normalization, forms a LiDAR elevation vector feature set. ;

[0035] Step 2.2.3, construct a convolutional network 2, wherein the convolutional network 2 includes 3 convolutional layers, each of which includes 3×3 convolutions. The SAR elevation vector features are extracted from the input tensor through the convolutional network 2, and the SAR elevation vector feature set is formed after normalization. ;

[0036] Step 2.2.4: Construct convolutional network 3, and resample the SAR elevation vector features to the grid network to obtain a new SAR elevation vector feature set. , and then calculate the attention weight: ;

[0037] Fusion and Get fusion features ;

[0038] Step 2.2.5: Construct a terrain decoder, decode the fusion features, obtain the corresponding raster fusion elevation data, and output the raster fusion elevation data and the raster network of the surveying and mapping area through the output layer. The raster fusion elevation data and the raster network of the surveying and mapping area constitute the terrain data. , the terrain decoder includes three 3×3 convolutional layers and one output layer.

[0039] Preferably, extracting a plurality of characteristic values ​​from the first surveying and mapping data according to a preset acquisition frequency to form a surveying and mapping characteristic sequence includes:

[0040] Taking the vegetation fall event as the time node, multiple elevation feature values ​​are extracted from the first surveying and mapping data to form a surveying and mapping feature sequence ;

[0041] Constructing a surveying and mapping feature sequence from multiple surveying and mapping feature sequences ;in, Indicates Time nodes; Indicates time node The first sampling The LiDAR elevation feature values ​​of the grid; Indicates the number of collections.

[0042] Preferably, the step of inputting the surveying and mapping feature sequence into a preset vegetation multi-layer state model, and obtaining vegetation vertical spatial distribution information and ground elevation data through the vegetation multi-layer state model, includes:

[0043] Constructing a vegetation layer relationship model: ,in Indicates Layer vegetation density, Indicates the vertical distance between layers. represents the attenuation ratio, Indicates the error value;

[0044] Set up inter-layer timing constraints ,in, Indicates Layer vegetation at time node When falling The laser echo amplitude of the vegetation layer, It represents the increase in the laser echo amplitude due to the reduction of shielding by the upper vegetation;

[0045] Construct a hierarchical graph model, including:

[0046] The height and density of each layer of vegetation are used as nodes;

[0047] The vegetation layer relationship model and temporal constraints between each layer of vegetation are used as edges;

[0048] Construct the maximum joint probability ,in, Representing LiDAR measurement data and state equation The residual of the output data; Represents the constraints provided by the inter-layer relationship model; where ;

[0049] Use Markov Chain Monte Carlo MCMC sampling to iteratively update parameters :

[0050] ;

[0051] in, represents the MCMC step size; Represents iteration The following parameters, represents the iterated covariance;

[0052] Assume the probability of acceptance ; with probability Accept the updated parameters, otherwise keep the original values ​​of the parameters;

[0053] Conduct ground information inversion, including:

[0054] If you know the The bottom elevation of the vegetation layer is , assuming that Layer height meets ; Indicates Layer and The vertical distance between layers;

[0055] Based on the surveying and mapping feature sequence, obtain the LiDAR elevation feature value when all the ground vegetation falls off, that is, when the ground is bare , correction Get ground elevation ,in .

[0056] Preferably, the method of correcting the terrain data using the ground elevation data and outputting the corrected terrain data comprises:

[0057] Get the original And the output of the two-stream network ;

[0058] Will and Align in space, that is, use the Kriging interpolation algorithm to Interpolate to the grid network output by the two-stream network, and the interpolation is ,in Indicates the width of the grid;

[0059] Calculate the residual ;

[0060] Build a lightweight UNet and input , output residual correction ;in Represents the grid network terrain gradient, the UNet includes 4 encoding layers and 1 decoding layer;

[0061] Then, the corrected ,in represents the dynamic weight, , Represents the slope parameter, which is used to control the rate of change of dynamic weight; Represents the standard deviation of the elevation of each grid in the raster network output by the two-stream network; Represents the priority threshold. When , the difference correction is used first;

[0062] The corrected raster elevation data obtained after decoding will replace the raster elevation data output by the dual-stream network.

[0063] Preferably, the land in the surveying and mapping area is classified and managed based on the vertical spatial distribution information of vegetation, including:

[0064] Perform GMM fitting on the LiDAR laser echo of each grid to extract the number of layers and parameters of each layer;

[0065] Count the number of vegetation layers penetrated by LiDAR in each season to form a penetration layer data set;

[0066] If in time , No. The vegetation density of the vegetation layer is Comparison When the value drops beyond the threshold, it is marked as falling off; Elevation of vegetation layer Comparison If the change exceeds the elevation change threshold, it is judged that the vegetation structure has changed; record the Time of first fall of vegetation layer , the first shedding time of multiple layers of vegetation constitutes a shedding time series ;

[0067] The number of layers, layer density and bottom elevation form a vertical space vector, the first fall-off time is added to the vertical space feature vector to form a space-time vector, and the space-time vector is normalized to form a space-time feature vector ;

[0068] The classification model is constructed by XGBoost algorithm. Input into a pre-trained classification model to classify vegetation.

[0069] A land surveying and mapping data intelligent analysis and management system comprises: a processor, a memory connected to the processor, and a communication module. The system is used to execute the land surveying and mapping data intelligent analysis and management method.

[0070] A computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the land surveying and mapping data intelligent analysis and management method.

[0071] Beneficial effects of the present invention:

[0072] 1. The present invention complements the high precision of LiDAR with the strong penetration ability of SAR, and combines the dynamic fusion of dual-stream networks to solve the data blind spot problem of traditional single sensors in multi-layer vegetation areas (such as rainforests) and improve terrain data.

[0073] 2. The present invention adjusts the weights of LiDAR and SAR data in real time based on the covariance matrix of Kalman filtering (such as relying on SAR in high occlusion areas), avoids local error amplification caused by fixed weights, and is suitable for surveying and mapping of complex terrain. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 The present invention is a flow chart of a method for intelligent analysis and management of land surveying and mapping data. DETAILED DESCRIPTION

[0075] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0076] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0077] refer to Figure 1 The technical solution provided by the present invention is: a land surveying and mapping data intelligent analysis management method and system, comprising the following steps:

[0078] Step 1: Acquire first surveying and mapping data and second surveying and mapping data of the same surveying and mapping area, and pre-process the first surveying and mapping data and the second surveying and mapping data.

[0079] The first surveying and mapping data is LiDAR elevation data, and the second surveying and mapping data is Synthetic Aperture Radar (SAR) elevation data.

[0080] Preprocessing includes space-time benchmark alignment and error model calibration; the space-time alignment includes:

[0081] The first surveying and mapping data and the second surveying and mapping data are converted to a unified coordinate system, and the first surveying and mapping data is subjected to elevation conversion, specifically: ,in, Represents the converted elevation data, Represents the elevation data before conversion. It indicates the height of the geoid level;

[0082] rasterizing the first surveying and mapping data into a grid network, resampling the second surveying and mapping data through a bilinear interpolation algorithm and converting the data into the same grid network;

[0083] The error model calibration includes:

[0084] Calibrate the noise of the first survey data ,in, Indicates the first surveying and mapping data error;

[0085] Calibrate the noise of the second survey data ,in, Indicates the second surveying and mapping data error.

[0086] Step 2: constructing a joint model and a dual-stream network, analyzing the pre-processed first surveying and mapping data and the second surveying and mapping data through the joint model and the dual-stream network, and outputting terrain data; including the following steps:

[0087] Step 2.1: construct a joint model based on the Kalman filter algorithm, fuse the first surveying and mapping data with the second surveying and mapping data, and obtain the elevation data vector of the surveying and mapping area, specifically including:

[0088] Step 2.1.1: Assume that the elevation of the terrain in the survey area is in the time period If there is no change within the time period The first The elevation vector of the raster is ;in Indicates The elevation values ​​of a grid network;

[0089] Assume the state equation is: ; ;

[0090] in, Indicates The LiDAR elevation vector of each grid, Indicates SAR elevation vector of each grid; represents the identity matrix, represents the process noise vector, , ; represents the process noise covariance, Represents terrain change error;

[0091] Step 2.1.2: After fusing the LiDAR elevation vector and the SAR elevation vector, The elevation vector of a grid is , where the observation matrix ;

[0092] The first surveying and mapping data noise and the second surveying and mapping data noise constitute the measurement noise covariance matrix ;

[0093] Let Kalman gain ; where the updated error covariance matrix ; Indicates The prediction error covariance matrix of the grid;

[0094] The Kalman gain after substituting the observation matrix and noise covariance matrix is: ;

[0095] Then the updated elevation vector is ; .

[0096] Constructing a two-stream network based on the updated elevation vector and outputting terrain data includes the following sub-steps:

[0097] Step 2.2.1. Get LiDAR elevation vector and the SAR elevation vector as well as ;

[0098] Generate 6-channel input tensor for each grid ; Among them, the first and second channels are used to input the updated LiDAR elevation vector and the first mapping data error; the third and fourth channels are used to input the updated SAR elevation vector and the second mapping data error; the fifth and sixth channels are used to input the diagonal elements of the updated error covariance matrix;

[0099] The input blocks are constructed in 5×5 areas to capture terrain continuity, specifically ,in Represents a grid The adjacent grids of Indicates the number of layers of the grid network in the vertical direction;

[0100] Step 2.2.2: Construct a convolutional network 1, wherein the convolutional network 1 includes 3 convolutional layers, each of which includes 3×3 convolutions. The convolutional network 1 extracts the LiDAR elevation vector features from the input tensor, and after normalization, forms a LiDAR elevation vector feature set. ;

[0101] Step 2.2.3, construct a convolutional network 2, wherein the convolutional network 2 includes 3 convolutional layers, each of which includes 3×3 convolutions. The SAR elevation vector features are extracted from the input tensor through the convolutional network 2, and the SAR elevation vector feature set is formed after normalization. ;

[0102] Step 2.2.4: Construct convolutional network 3, and resample the SAR elevation vector features to the grid network to obtain a new SAR elevation vector feature set. , and then calculate the attention weight: ;

[0103] Fusion and Get fusion features ;

[0104] Step 2.2.5: Construct a terrain decoder, decode the fusion features, obtain the corresponding raster fusion elevation data, and output the raster fusion elevation data and the raster network of the surveying and mapping area through the output layer. The raster fusion elevation data and the raster network of the surveying and mapping area constitute the terrain data. , the terrain decoder includes three 3×3 convolutional layers and one output layer.

[0105] Step 3: extract multiple feature values ​​from the first surveying and mapping data according to a preset acquisition frequency to form a surveying and mapping feature sequence; specifically, the following steps are included: taking the vegetation fall event as a time node, extracting multiple elevation feature values ​​from the first surveying and mapping data to form a surveying and mapping feature sequence ;

[0106] Constructing a surveying and mapping feature sequence from multiple surveying and mapping feature sequences ;in, Indicates Time nodes; Indicates time node The first sampling The LiDAR elevation feature values ​​of the grid; Indicates the number of collections.

[0107] Input the surveying and mapping feature sequence into the preset vegetation multi-layer state model, and obtain the vegetation vertical spatial distribution information and ground elevation data through the vegetation multi-layer state model; specifically, the following steps are included:

[0108] Constructing a vegetation layer relationship model: ,in Indicates Layer vegetation density, Indicates the vertical distance between layers. represents the attenuation ratio, Indicates the error value;

[0109] Set up inter-layer timing constraints ,in, Indicates Layer vegetation at time node When falling The laser echo amplitude of the vegetation layer, It represents the increase in the laser echo amplitude due to the reduction of shielding by the upper vegetation;

[0110] Construct a hierarchical graph model, including:

[0111] The height and density of each layer of vegetation are used as nodes;

[0112] The vegetation layer relationship model and temporal constraints between each layer of vegetation are used as edges;

[0113] Construct the maximum joint probability ,in, Representing LiDAR measurement data and state equation Residual of output data; prior Represents the constraints provided by the inter-layer relationship model; where ;

[0114] Use Markov Chain Monte Carlo MCMC sampling to iteratively update parameters :

[0115] ;

[0116] in, represents the MCMC step size; Represents iteration The following parameters, represents the iterated covariance;

[0117] Assume the acceptance probability ; with probability Accept the updated parameters, otherwise keep the original values ​​of the parameters;

[0118] Conduct ground information inversion, including:

[0119] If you know the The bottom elevation of the vegetation layer is , assuming that Layer height meets ; Indicates Layer and The vertical distance between layers;

[0120] Based on the surveying and mapping feature sequence, obtain the LiDAR elevation feature value when all the ground vegetation falls off, that is, when the ground is bare , correction Get ground elevation ,in .

[0121] For example, vegetation is distributed vertically, and the height intervals of each layer are known, such as 0-5m for the first layer, 5-10m for the second layer, and so on. Vegetation fall reduces the upper layer cover and exposes the lower layer vegetation structure.

[0122] In this example, it is assumed that the LiDAR laser can penetrate three layers of vegetation, and the bottom elevation of the third layer of vegetation is , in autumn ( ) After the third layer falls off, the LiDAR laser penetrates to the fourth layer, and the bottom elevation of the fourth layer is , through the timing changes In this embodiment , is a fixed value, , the MCMC step size is 0.05m, and the vertical distance between layers is The prior value of is 2.0 ± 0.3 m. The parameters of the 5th and 6th layers (density and bottom elevation) and the ground elevation are iteratively calculated. .

[0123] Based on the obtained parameters such as the density of each layer of vegetation and the bottom elevation, it can be used to analyze the vegetation type and coverage of the land in the surveying area.

[0124] In this step, the purpose of setting up the hierarchical graph model is to abstract the physical data of each vegetation layer (vertical distance between layers, vegetation density, bottom elevation) and terrain parameters (ground elevation) into nodes in the hierarchical graph model, so as to clarify the dependency relationship between various variables; for example, the bottom height of the third layer affects the top height of the fourth layer; the LiDAR data and SAR data are uniformly encoded and integrated into the graph model, which solves the problem of data heterogeneity and reduces the risk of single data failure.

[0125] The hierarchical graph model can capture the dynamic evolution of parameters of each layer. For example, after the leaves fall in autumn, the density of the upper vegetation decreases, exposing the lower layer. The hierarchical graph model automatically updates the parameters of each layer. When new data is input, only the relevant nodes need to be updated locally (correcting the vertical distance between vegetation layers in the third layer, etc.).

[0126] In judging the land type, we no longer rely on the black box model, but on the combination of node parameters in the hierarchical graph model (for example, if the number of layers is greater than 3 and the bottom elevation is greater than 5m, it is forest land) to enhance the credibility of the classification results.

[0127] Step 4: Classify and manage the land in the surveying area based on the vertical spatial distribution information of vegetation, and use the ground elevation data to correct the terrain data, and output the corrected terrain data to improve the accuracy of the terrain data.

[0128] The classification management of land in the surveying and mapping area based on the vertical spatial distribution information of vegetation includes the following steps:

[0129] Perform GMM fitting on the LiDAR laser echo of each grid to extract the number of layers and parameters of each layer;

[0130] Count the number of vegetation layers penetrated by LiDAR in each season to form a penetration layer data set;

[0131] If in time , No. The vegetation density of the vegetation layer is Comparison When the value drops beyond the threshold, it is marked as falling off; Elevation of vegetation layer Comparison If the change exceeds the elevation change threshold, it is judged that the vegetation structure has changed; record the Time of first fall of vegetation layer , the first shedding time of multiple layers of vegetation constitutes a shedding time series ;

[0132] The number of layers, layer density and bottom elevation form a vertical space vector, the first fall-off time is added to the vertical space feature vector to form a space-time vector, and the space-time vector is normalized to form a space-time feature vector ;

[0133] The classification model is constructed by XGBoost algorithm. Input the pre-trained classification model to classify vegetation. For example, if the number of vegetation layers is greater than 4, the vegetation density is greater than 0.7, and the bottom elevation is greater than 5m, it can be judged as a forest; if the number of vegetation layers is 1 and the bottom elevation is less than 1m, it can be judged as a grassland.

[0134] The method of correcting the terrain data using the ground elevation data and outputting the corrected terrain data includes the following steps:

[0135] Get the original And the output of the two-stream network ;

[0136] Will and Align in space, that is, use the Kriging interpolation algorithm to Interpolate to the grid network output by the two-stream network, and the interpolation is ,in Indicates the width of the grid;

[0137] Calculate the residual ;

[0138] Build a lightweight UNet and input , output residual correction ;in Represents the grid network terrain gradient, the UNet includes 4 encoding layers and 1 decoding layer;

[0139] Then, the corrected ,in represents the dynamic weight, , Represents the slope parameter, which is used to control the rate of change of dynamic weight; Represents the standard deviation of the elevation of each grid in the raster network output by the two-stream network; Represents the priority threshold. When , the difference correction is used first;

[0140] The corrected raster elevation data obtained after decoding will replace the raster elevation data output by the dual-stream network.

[0141] The present invention also provides a land surveying and mapping data intelligent analysis and management system, comprising: a processor and a memory and a communication module connected to the processor, and the system is used to execute the land surveying and mapping data intelligent analysis and management method.

[0142] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for intelligent analysis and management of land surveying and mapping data.

[0143] In some preferred embodiments, the method further includes the step of managing the dual-stream network output and the corrected raster elevation data, specifically:

[0144] Add identification label one and timestamp one to the raster network data output by the dual-stream network, and add identification label two and timestamp two to the corrected raster elevation data;

[0145] Distinguish the versions of the raster network data and the corrected raster elevation data according to timestamp 1 and timestamp 2; distinguish the data types according to identification tag 1 and identification tag 2;

[0146] Recording the correction process of the grid network data through the correction log, including the replacement time of the elevation data and the corresponding grid information, wherein the grid information includes the grid width and the coordinates of the grid center point;

[0147] Import the corrected raster elevation data into PostGIS to support SQL queries, and publish WMS or WFS services through GeoServer to support team calls;

[0148] The data lake LakeFS is used to store different versions of raster network data and corrected raster elevation data.

[0149] In the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium mentioned above in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0150] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0151] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be subject to any changes or modifications.

Claims

1. A land surveying and mapping data intelligent analysis and management method, characterized in that: The method comprises: Acquire first surveying and mapping data and second surveying and mapping data of the same surveying and mapping area, and preprocess the first surveying and mapping data and the second surveying and mapping data; Constructing a joint model and a dual-stream network, analyzing the preprocessed first surveying and mapping data and the second surveying and mapping data through the joint model and the dual-stream network, and outputting terrain data; Extracting multiple characteristic values ​​from the first surveying and mapping data according to a preset acquisition frequency to form a surveying and mapping characteristic sequence; inputting the surveying and mapping characteristic sequence into a preset vegetation multi-layer state model, and obtaining vegetation vertical spatial distribution information and ground elevation data through the vegetation multi-layer state model; The land in the surveying and mapping area is classified and managed based on the vertical spatial distribution information of vegetation. At the same time, the terrain data is corrected using the ground elevation data and the corrected terrain data is output to improve the accuracy of the terrain data.

2. The land surveying and mapping data intelligent analysis and management method according to claim 1, characterized in that: The first surveying and mapping data is LiDAR elevation data, and the second surveying and mapping data is Synthetic Aperture Radar SAR elevation data; the preprocessing includes time-space reference alignment and error model calibration; The spatiotemporal alignment includes: The first surveying and mapping data and the second surveying and mapping data are converted to a unified coordinate system, and the first surveying and mapping data is subjected to elevation conversion, specifically: ,in, Represents the converted elevation data, Represents the elevation data before conversion. It indicates the height of the geoid level; rasterizing the first surveying and mapping data into a grid network, resampling the second surveying and mapping data through a bilinear interpolation algorithm and converting the data into the same grid network; The error model calibration includes: Calibrate the noise of the first survey data ,in, Indicates the first surveying and mapping data error; Calibrate the noise of the second survey data ,in, Indicates the second surveying and mapping data error.

3. The land surveying and mapping data intelligent analysis and management method according to claim 2, characterized in that: The constructing of the joint model and the dual-stream network, analyzing the pre-processed first surveying and mapping data and the second surveying and mapping data through the joint model and the dual-stream network, and outputting terrain data, includes: Step 2.1: construct a joint model based on the Kalman filter algorithm, fuse the first surveying and mapping data with the second surveying and mapping data, and obtain the elevation data vector of the surveying and mapping area, specifically including: Step 2.1.1: Assume that the elevation of the terrain in the survey area is in the time period If there is no change within the time period The first The elevation vector of the raster is ;in Indicates The elevation values ​​of a grid network; Assume the state equation is: ; ; in, Indicates The LiDAR elevation vector of each grid, Indicates SAR elevation vector of each grid; represents the identity matrix, represents the process noise vector, , ; represents the process noise covariance, Represents terrain change error; Step 2.1.2: After fusing the LiDAR elevation vector and the SAR elevation vector, The elevation vector of a grid is , where the observation matrix ; The first surveying and mapping data noise and the second surveying and mapping data noise constitute the measurement noise covariance matrix ; Let Kalman gain ; where the updated error covariance matrix ; Indicates The prediction error covariance matrix of the grid; The Kalman gain after substituting the observation matrix and noise covariance matrix is: ; Then the updated elevation vector is ; .

4. The land surveying and mapping data intelligent analysis and management method according to claim 3 is characterized in that: The constructing of the joint model and the dual-stream network, analyzing the pre-processed first surveying and mapping data and the second surveying and mapping data through the joint model and the dual-stream network, and outputting the terrain data, further includes: Constructing a two-stream network based on the updated elevation vector and outputting terrain data includes the following sub-steps: Step 2.2.

1. Get LiDAR elevation vector and the SAR elevation vector as well as ; Generate 6-channel input tensor for each grid ; Among them, the first and second channels are used to input the updated LiDAR elevation vector and the first mapping data error; the third and fourth channels are used to input the updated SAR elevation vector and the second mapping data error; the fifth and sixth channels are used to input the diagonal elements of the updated error covariance matrix; The input blocks are constructed in 5×5 areas to capture terrain continuity, specifically ,in Represents a grid The adjacent grids of Indicates the number of layers of the grid network in the vertical direction; Step 2.2.2: Construct a convolutional network 1, wherein the convolutional network 1 includes 3 convolutional layers, each of which includes 3×3 convolutions. The convolutional network 1 extracts the LiDAR elevation vector features from the input tensor, and after normalization, forms a LiDAR elevation vector feature set. ; Step 2.2.3, construct a convolutional network 2, wherein the convolutional network 2 includes 3 convolutional layers, each of which includes 3×3 convolutions. The SAR elevation vector features are extracted from the input tensor through the convolutional network 2, and the SAR elevation vector feature set is formed after normalization. ; Step 2.2.4: Construct convolutional network 3, and resample the SAR elevation vector features to the grid network to obtain a new SAR elevation vector feature set. , and then calculate the attention weight: ; Fusion and Get fusion features ; Step 2.2.5: Construct a terrain decoder, decode the fusion features, obtain the corresponding raster fusion elevation data, and output the raster fusion elevation data and the raster network of the surveying and mapping area through the output layer. The raster fusion elevation data and the raster network of the surveying and mapping area constitute the terrain data. , the terrain decoder includes three 3×3 convolutional layers and one output layer.

5. The method for intelligent analysis and management of land surveying and mapping data according to claim 4, characterized in that: The step of extracting a plurality of characteristic values ​​from the first surveying and mapping data according to a preset acquisition frequency to form a surveying and mapping characteristic sequence includes: Taking the vegetation fall event as the time node, multiple elevation feature values ​​are extracted from the first surveying and mapping data to form a surveying and mapping feature sequence ; Constructing a surveying and mapping feature sequence from multiple surveying and mapping feature sequences ;in, Indicates Time nodes; Indicates time node The first sampling The LiDAR elevation feature values ​​of the grid; Indicates the number of collections.

6. A land surveying and mapping data intelligent analysis and management method according to claim 5, characterized in that: The step of inputting the surveying and mapping feature sequence into a preset vegetation multi-layer state model and obtaining vegetation vertical spatial distribution information and ground elevation data through the vegetation multi-layer state model includes: Constructing a vegetation layer relationship model: ,in Indicates Layer vegetation density, Indicates the vertical distance between layers. represents the attenuation ratio, Indicates the error value; Set up inter-layer timing constraints ,in, Indicates Layer vegetation at time node When falling The laser echo amplitude of the vegetation layer, It represents the increase in the laser echo amplitude due to the reduction of shielding by the upper vegetation; Construct a hierarchical graph model, including: The height and density of each layer of vegetation are used as nodes; The vegetation layer relationship model and temporal constraints between each layer of vegetation are used as edges; Construct the maximum joint probability ,in, Representing LiDAR measurement data and state equation The residual of the output data; Represents the constraints provided by the inter-layer relationship model; where ; Use Markov Chain Monte Carlo MCMC sampling to iteratively update parameters : ； in, represents the MCMC step size; Represents iteration The following parameters, represents the iterated covariance; Assume the probability of acceptance ; with probability Accept the updated parameters, otherwise keep the original values ​​of the parameters; Conduct ground information inversion, including: If you know the The bottom elevation of the vegetation layer is , assuming that Layer height meets ; Indicates Layer and The vertical distance between layers; Based on the surveying and mapping feature sequence, obtain the LiDAR elevation feature value when all the ground vegetation falls off, that is, when the ground is bare , correction Get ground elevation ,in .

7. A land surveying and mapping data intelligent analysis and management method according to claim 6, characterized in that: The method of correcting the terrain data by using the ground elevation data and outputting the corrected terrain data comprises: Get the original And the output of the two-stream network ; Will and Align in space, that is, use the Kriging interpolation algorithm to Interpolate to the grid network output by the two-stream network, and the interpolation is ,in Indicates the width of the grid; Calculate the residual ; Build a lightweight UNet and input , output residual correction ;in Represents the grid network terrain gradient, the UNet includes 4 encoding layers and 1 decoding layer; Then, the corrected ,in represents the dynamic weight, , Represents the slope parameter, which is used to control the rate of change of dynamic weight; Represents the standard deviation of the elevation of each grid in the raster network output by the dual-stream network; Represents the priority threshold. When , the difference correction is used first; The corrected raster elevation data obtained after decoding will replace the raster elevation data output by the dual-stream network.

8. The method for intelligent analysis and management of land surveying and mapping data according to claim 7, characterized in that: Classify and manage the land in the surveying area based on the vertical spatial distribution information of vegetation, including: Perform GMM fitting on the LiDAR laser echo of each grid to extract the number of layers and parameters of each layer; Count the number of vegetation layers penetrated by LiDAR in each season to form a penetration layer data set; If in time , No. The vegetation density of the vegetation layer is Comparison When the value drops beyond the threshold, it is marked as falling off; Elevation of vegetation layer Comparison If the change exceeds the elevation change threshold, it is judged that the vegetation structure has changed; record the Time of first fall of vegetation layer , the first shedding time of multiple layers of vegetation constitutes a shedding time series ; The number of layers, layer density and bottom elevation form a vertical space vector, the first fall-off time is added to the vertical space feature vector to form a space-time vector, and the space-time vector is normalized to form a space-time feature vector ; The classification model is constructed by XGBoost algorithm. Input into a pre-trained classification model to classify vegetation.

9. A land surveying and mapping data intelligent analysis and management system, comprising: A processor and a memory and a communication module connected to the processor, characterized in that the system is used to execute a land surveying and mapping data intelligent analysis and management method as described in any one of claims 1-8 above.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a land surveying and mapping data intelligent analysis and management method as described in any one of claims 1 to 8.

Images