A basic geographic information linkage updating method and system
Through multi-source data acquisition and real-time dynamic change detection, automatic database updates and comprehensive data verification, the problems of low update efficiency and data consistency of traditional geographical information systems are solved, and the rapid response and high-precision update of geographical information are realized, and the emergency situation is supported. decision-making and management.
Patent Information
- Application Number
- CN202411118278.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-15
AI Technical Summary
Traditional geographic information system update methods take a long time and are difficult to capture rapid geographical changes, resulting in delayed data updates, unable to meet the needs of real-time geographic information services, and are inefficient when processing large-scale or complex geographic data, making it prone to data inconsistency problems.
Using multiple data sources (satellite remote sensing, drone aerial photography, ground sensors) to collect geographic information data in real time, generate comprehensive data through image processing and data fusion, establish a geographic information change detection model, automatically update the database and synchronize the data, and establish data verification mechanism to optimize the update process.
It significantly improves the update speed and accuracy of the geographic information system, ensures data immediacy and accuracy, supports efficient decision-making and management, especially in emergencies, and improves the reliability and consistency of geographic information applications.
Smart Images

Figure CN118626582B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of geographic information system technology, and in particular to a basic geographic information linkage updating method and system. Background Art
[0002] With the rapid development of cities and changes in the geographical environment, the traditional geographic information system (GIS) update process faces many challenges. Traditional methods mainly rely on periodic manual surveys and single data sources, such as satellite remote sensing or ground surveys. This method is not only time-consuming, but also difficult to capture rapidly occurring geographical changes. In addition, the separation of data collection and processing leads to delays in data updates, making it difficult to meet the needs of real-time geographic information services. This method is inefficient when processing large-scale or complex geographic data, and is prone to data inconsistency problems.
[0003] In view of the problems existing in the prior art, the necessity of the present invention is obvious. First, the existing geographic information updating method cannot achieve high-efficiency and high-precision data updating, which limits the application effect of geographic information systems in emergency response and daily management. Secondly, due to reliance on a single data source or an overly simple updating mechanism, the existing system often cannot accurately reflect the real-time changes in the geographic environment, resulting in information lag in the decision support system.
[0004] Therefore, developing a method and system that can integrate multiple data sources and update and verify the linkage update of geographic information in real time is of great significance to improving the efficiency and accuracy of geographic information management. Summary of the invention
[0005] Based on the above objectives, the present invention provides a basic geographic information linkage update method and system.
[0006] A basic geographic information linkage updating method comprises the following steps:
[0007] S1: Real-time collection of geographic information data using multiple data sources including satellite remote sensing, drone aerial photography, and ground sensors;
[0008] S2: Receives multi-source geographic information data from S1 and performs pre-processing, including applying image processing algorithms to perform image correction and stitching on satellite remote sensing and drone aerial photography data, and using data fusion algorithms to integrate ground sensor data with image data to generate comprehensive geographic information data;
[0009] S3: Based on the comprehensive geographic information data output by S2, a geographic information change detection model is established to identify new, changed or disappeared features;
[0010] S4: Automatically updates the geographic information database based on the changes in geographic information detected by S3, and synchronizes the updated geographic information to related devices through the network to ensure consistency and real-time update of geographic information between devices;
[0011] S5: Establish a data verification mechanism to verify the accuracy and completeness of updated geographic information data, and feed back the verification results to the data collection and processing links to optimize the geographic information linkage update method.
[0012] Optionally, the S1 specifically includes:
[0013] S11: Satellite remote sensing data collection: geographical information data covering the whole country is collected regularly every day through high-resolution remote sensing satellites. The satellite remote sensing data includes multi-spectral and panchromatic image data, which are used to provide terrain and land feature information across the whole country;
[0014] S12: drone aerial photography data collection, using drones equipped with high-precision camera equipment to take high-resolution aerial photos of the urban area and predetermined areas around it according to a predetermined flight route and time interval, and collect geographic information data. The drone aerial photography data includes orthophotos and oblique images, which are used to capture terrain changes and ground object information of the urban area and surrounding areas;
[0015] S13: ground sensor data collection step, arranging multiple high-precision ground sensors in the selected urban area and the predetermined monitoring area to monitor and collect local geographic information data in real time, the ground sensors include laser radar sensors and high-precision GPS sensors, the laser radar sensors are used to obtain terrain profile and height data, and the high-precision GPS sensors are used to provide accurate geographic coordinates and location information;
[0016] S14: Data aggregation, transmitting the satellite remote sensing data, UAV aerial photography data and ground sensor data collected in S11, S12 and S13 to the central data processor through the wireless communication network for preliminary aggregation and storage.
[0017] Optionally, the S2 specifically includes:
[0018] S21: Image correction: geometric correction and radiation correction are performed on the received satellite remote sensing and drone aerial photography data. The geometric correction is used to correct the image data to a unified geographic coordinate system; the radiation correction is used to eliminate the effects of atmospheric scattering and absorption;
[0019] S22: Image stitching, stitching the calibrated satellite remote sensing data and drone aerial photography data, using image stitching algorithms to stitch multiple image data into a seamless integrated image;
[0020] S23: Data fusion, using a data fusion algorithm based on weighted average to integrate ground sensor data with the stitched image data to generate comprehensive geographic information data;
[0021] S24: Data generation, converting and storing the fused data in two formats, vector data and raster data.
[0022] Optionally, the S22 specifically includes:
[0023] S221: Preliminary registration of the calibrated satellite remote sensing data and the drone aerial photography data is performed, a registration algorithm based on feature points is used, a set of feature points in the image is selected as registration points, and registration parameters are calculated by the least square method to align the images in space;
[0024] S222: Perform feature matching processing on the registered image data, use the scale-invariant feature transformation algorithm to extract feature points in the image, calculate feature descriptors, and match feature descriptors through the nearest neighbor search algorithm to find corresponding feature point pairs between the images:
[0025] S223: Based on the feature matching results, an image fusion algorithm is used to seamlessly stitch the images. Specifically, a Poisson fusion algorithm is used to solve the Poisson equation to smooth the image boundaries and eliminate stitching gaps.
[0026] Optionally, the S23 specifically includes:
[0027] S231: preprocessing the stitched image data and ground sensor data, including pixel value standardization processing on the image data and interpolation processing on the ground sensor data;
[0028] S232: Calculate the weights of the image data and the ground sensor data. Suppose the weight of the image data is , the weight of the ground sensor data is , then the weight calculation formula is: ;
[0029] S233: The preprocessed image data and ground sensor data are integrated using a data fusion algorithm based on weighted average. The formula is: ,in, It is the integrated geographic information data after fusion. is the standardized image data, is the interpolated ground sensor data, and are the weights of image data and ground sensor data respectively.
[0030] Optionally, the S3 specifically includes:
[0031] S31: Feature extraction, extracting features of objects from the comprehensive geographic information data output by S2, specifically using a convolutional neural network to extract the shape, color and texture features of the objects;
[0032] S32: Model training, based on the extracted ground feature data, the geographic information change detection model is trained using sparse coding and dictionary learning algorithms;
[0033] S33: Change detection, applying the trained geographic information change detection model to the comprehensive geographic information data acquired in real time, and identifying the addition, change or disappearance of features by comparing the current features of features with the features stored in the model;
[0034] S34: Result output: Generate a geographic information change report based on the change detection results, marking the newly added, changed or disappeared features.
[0035] Optionally, the S32 specifically includes:
[0036] S321: Randomly select some features from the extracted ground feature data as the initial dictionary and express it as , the initial dictionary is a matrix, each column represents an initial eigenvector;
[0037] S322: Sparse coding, for each feature Sparse representation is performed by optimizing the sparse coefficient vector , so that Represented as a dictionary The linear combination of , the optimization objective function of sparse coding is:
[0038] ,in, is a sparse coefficient vector, is the sparse regularization parameter, is the L2 norm, , is the L1 norm;
[0039] S323: Dictionary update: based on the sparse coding result, update the dictionary matrix D, and optimize the dictionary to better represent the feature data of the ground object by minimizing the reconstruction error. The optimization objective function of the dictionary update is:
[0040] ,in, is the updated dictionary matrix, For the feature vectors, is the corresponding sparse coefficient vector, is the number of feature data;
[0041] S324: Iterative optimization, repeating S322 and S323, iteratively optimizing the sparse coefficient vector and the dictionary matrix until the convergence condition is met or the preset number of iterations is reached, and finally obtaining a trained geographic information change detection model, which is expressed as: ,in, is the set of all feature vectors of land objects, is the dictionary matrix after training, is the corresponding sparse coefficient matrix.
[0042] Optionally, the S33 specifically includes:
[0043] S331: Extracting the features of the objects from the current comprehensive geographic information data and generating the current object feature vector ;
[0044] S332: Feature matching, the current feature vector Compare with the dictionary features stored in the model to calculate the current feature vector In the dictionary Sparse representation in ;
[0045] S333: Calculate the matching error between the current feature and the feature stored in the model. The matching error calculation formula is: ,in, is the matching error of the current feature, is the current feature vector, is the dictionary matrix, is the sparse coefficient vector of the current feature;
[0046] S334: Change determination, setting a predetermined error threshold , when the matching error Exceeding the threshold When the matching error is within the threshold If the feature is different from the previously recorded features in the model, it is judged as a new feature or disappearance.
[0047] Optionally, the S4 specifically includes:
[0048] S41: extracting the feature data of newly added, changed or disappeared objects according to the changes in geographic information detected in step S3, and generating a change data set, including information on the location, shape, size and attributes of the objects;
[0049] S42: writing the changed data set into the geographic information database;
[0050] S43: Record detailed log information of each database update, including data change type, timestamp, and operator information;
[0051] S44: Data synchronization preparation, first generating a data synchronization package, including change data and update logs; then compressing the synchronization package using a data compression algorithm;
[0052] S45: Transmitting the data synchronization package to the relevant device through a secure network channel;
[0053] S46: Receive and decompress the data synchronization package on the relevant device, and apply the changed data to the local geographic information database.
[0054] A basic geographic information linkage update system, used to implement the above-mentioned basic geographic information linkage update method, includes the following modules:
[0055] Multi-source data acquisition module: used to collect geographic information data in real time using multiple data sources such as satellite remote sensing, drone aerial photography, and ground sensors;
[0056] Data preprocessing module: used to receive geographic information data from the multi-source data acquisition module and perform preprocessing, including applying image processing algorithms to perform image correction and splicing on satellite remote sensing and drone aerial photography data, and using data fusion algorithms to integrate ground sensor data with image data to generate comprehensive geographic information data;
[0057] Dynamic change detection module: Based on the comprehensive geographic information data output by the data preprocessing module, a geographic information change detection model is established to identify the addition, change or disappearance of land features;
[0058] Database update and synchronization module: used to automatically update the geographic information database according to the changes in geographic information detected by the dynamic change detection module, and synchronize the updated geographic information to related devices through the network to ensure the consistency and real-time update of geographic information between devices;
[0059] Data verification and feedback module: used to establish a data verification mechanism, verify the accuracy and completeness of the updated geographic information data, and feed back the verification results to the multi-source data acquisition module and data preprocessing module to optimize the geographic information linkage update system.
[0060] Beneficial effects of the present invention:
[0061] The present invention significantly improves the updating speed and accuracy of the geographic information system by adopting multi-source data collection, real-time dynamic change detection, automatic database updating and synchronization, and comprehensive data verification and feedback technology. This integration method enables geographic information to respond quickly to environmental changes and ensures the timeliness and accuracy of data, thereby supporting efficient decision-making and management. Especially in emergency situations, such as natural disasters or rapidly developing urban areas, the present invention can provide key geographic information to support rescue and planning activities.
[0062] The present invention greatly improves the consistency and reliability of data through an automated data verification mechanism and a continuous optimization feedback loop, which not only reduces problems caused by human errors or improper data processing, but also ensures the continuous updating and improvement of geographic information. By real-time monitoring of changes in geographic information and making timely adjustments, it supports a wider range of geographic information applications, such as environmental monitoring, urban planning and infrastructure management, thereby improving the operating efficiency of the entire social and economic system. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0064] Figure 1 A schematic diagram of a basic geographic information linkage updating method according to an embodiment of the present invention;
[0065] Figure 2 Schematic diagram of a basic geographic information linkage update system according to an embodiment of the present invention. DETAILED DESCRIPTION
[0066] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.
[0067] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).
[0068] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.
[0069] like Figure 1 As shown, a basic geographic information linkage updating method comprises the following steps:
[0070] S1: Use multiple data sources such as satellite remote sensing, drone aerial photography, and ground sensors to collect geographic information data in real time. Satellite remote sensing data is used for macro-geographic information monitoring covering a wide area, drone aerial photography is used to provide high-resolution geographic images of small and medium areas, and ground sensors are used to collect precise geographic information of specific locations.
[0071] S2: Receives multi-source geographic information data from S1 and performs pre-processing, including applying image processing algorithms to perform image correction and stitching on satellite remote sensing and drone aerial photography data, and using data fusion algorithms to integrate ground sensor data with image data to generate comprehensive geographic information data;
[0072] S3: Based on the comprehensive geographic information data output by S2, a geographic information change detection model is established to identify new, changed or disappeared features. The model is trained and constructed using sparse coding and dictionary learning algorithms. Specifically, a dictionary is trained to represent the features of the features, and sparse representation is used to detect changes in the features, thereby improving the accuracy and robustness of change detection.
[0073] S4: Automatically updates the geographic information database based on the changes in geographic information detected by S3, and synchronizes the updated geographic information to related devices through the network to ensure consistency and real-time update of geographic information between devices;
[0074] S5: Establish a data verification mechanism to verify the accuracy and completeness of updated geographic information data. The data verification mechanism includes manual sampling verification and automated verification, and feeds the verification results back to the data collection and processing links to optimize the geographic information linkage update method.
[0075] S1 specifically includes:
[0076] S11: Satellite remote sensing data collection: high-resolution remote sensing satellites are used to collect geographic information data covering the entire country on a daily basis. Satellite remote sensing data includes multi-spectral and panchromatic image data, which are used to provide information on terrain and land features across the country.
[0077] S12: UAV aerial photography data collection: using UAVs equipped with high-precision camera equipment to take high-resolution aerial photos of urban areas and surrounding areas according to predetermined flight routes and time intervals to collect geographic information data. UAV aerial photography data includes orthophotos and oblique images, which are used to capture terrain changes and ground object information in urban areas and surrounding areas;
[0078] S13: ground sensor data collection step, deploying multiple high-precision ground sensors in the selected urban area and the predetermined monitoring area to monitor and collect local geographic information data in real time, the ground sensors include laser radar sensors and high-precision GPS sensors, the laser radar sensors are used to obtain terrain profile and height data, and the high-precision GPS sensors are used to provide accurate geographic coordinates and location information;
[0079] S14: Data aggregation, transmitting the satellite remote sensing data, UAV aerial photography data and ground sensor data collected in S11, S12 and S13 to the central data processor through the wireless communication network for preliminary aggregation and storage to ensure the consistency and integrity of the data; through the above steps, using multiple data sources such as satellite remote sensing, high-resolution UAV aerial photography and ground sensors, real-time collection of geographic information data with wide coverage, high accuracy and detailed information has been achieved, achieving comprehensive and accurate monitoring of geographic information, providing a more reliable data foundation, and thus greatly improving the updating efficiency and accuracy of geographic information.
[0080] S2 specifically includes:
[0081] S21: Image correction, which performs geometric correction and radiation correction on the received satellite remote sensing and drone aerial photography data. Geometric correction is used to correct the image data to a unified geographic coordinate system to eliminate geometric distortion caused by the sensor's viewing angle and terrain undulations; radiation correction is used to eliminate the effects of atmospheric scattering and absorption to ensure the radiation consistency of the image data.
[0082] S22: Image stitching, stitching the calibrated satellite remote sensing data and drone aerial photography data. Specifically, the image stitching algorithm is used to stitch multiple image data into a seamless integrated image. The stitching process includes image registration, feature matching and stitching to ensure the continuity and consistency of the image.
[0083] S23: Data fusion, using a data fusion algorithm based on weighted average to integrate ground sensor data with the stitched image data. The weighted average algorithm gives different weights to different data sources, comprehensively considers the accuracy and reliability of each data source, and fuses the precise geographic coordinates and altitude information provided by the ground sensor with the terrain and object features in the image data to generate comprehensive geographic information data;
[0084] S24: Data generation: converting and storing the fused data in two formats, including vector data and raster data, to generate comprehensive geographic information data for subsequent use to meet the needs of different application systems.
[0085] In S22, multiple image data are stitched together into a seamless integrated image, specifically including:
[0086] S221: Perform preliminary registration on the calibrated satellite remote sensing data and drone aerial photography data. Use a feature point-based registration algorithm to select a set of feature points in the image as registration points, and calculate the registration parameters through the least squares method (LSM) to align the images in space. The registration formula is: ,in, represents the registration transformation matrix, For the image The coordinates of the feature points, is the coordinate of the corresponding feature point in the registration image, is the number of feature points, Indicates that the objective function reaches the minimum value value;
[0087] S222: Perform feature matching on the registered image data, use the Scale-Invariant Feature Transform (SIFT) algorithm to extract feature points in the image, calculate feature descriptors, and match feature descriptors through the Nearest Neighbor Search (NNS) algorithm to find corresponding feature point pairs between the images:
[0088] S223: Based on the feature matching results, an image fusion algorithm is used to seamlessly stitch the images. Specifically, a Poisson Blending algorithm is used to solve the Poisson equation to smooth the image boundaries and eliminate the stitching gaps. The Poisson Blending formula is as follows: ,in, represents the Laplace operator, is the image fusion result to be solved, is the image gradient field;
[0089] The above steps use image stitching algorithms to stitch multiple image data into a seamless integrated image; through image registration, feature matching and stitching processing, the geometric distortion and stitching gaps between images are eliminated, high-quality integrated image data are generated, high-precision integration and consistency processing of geographic information data are achieved, and more reliable and detailed geographic information basic data are provided.
[0090] Data fusion in S23 specifically includes:
[0091] S231: preprocessing the stitched image data and ground sensor data, including pixel value standardization processing on the image data and interpolation processing on the ground sensor data, so as to facilitate fusion with the image data;
[0092] S232: Calculate the weights of the image data and the ground sensor data. According to the accuracy and reliability of the data sources, weight coefficients are assigned to the image data and the ground sensor data respectively. Suppose the weight of the image data is , the weight of the ground sensor data is , then the weight calculation formula is: ;
[0093] S233: The preprocessed image data and ground sensor data are integrated using a data fusion algorithm based on weighted average. The formula is: ,in, It is the integrated geographic information data after fusion. is the standardized image data, is the interpolated ground sensor data, and are the weights of image data and ground sensor data respectively; through the above steps, a data fusion algorithm based on weighted average is adopted to integrate the ground sensor data with the stitched image data to generate comprehensive geographic information data. This method effectively integrates data from different sources through standardized processing and weight calculation of data sources, improves the accuracy and reliability of geographic information data, and realizes the generation of detailed and accurate geographic information basic data.
[0094] S3 specifically includes:
[0095] S31: Feature extraction, extracting features of objects from the comprehensive geographic information data output by S2. Specifically, a convolutional neural network (CNN) is used to extract the shape, color and texture features of the objects. The extracted feature data is used for the training of subsequent change detection models.
[0096] S32: Model training: Based on the extracted feature data, the geographic information change detection model is trained using the sparse coding and dictionary learning algorithm. The training process includes building a sparse dictionary and optimizing sparse representation to improve the model's ability to detect changes in features.
[0097] S33: Change detection, applying the trained geographic information change detection model to the comprehensive geographic information data acquired in real time, identifying the addition, change or disappearance of the features by comparing the current features with the features stored in the model. The specific process includes matching the current features with the features in the dictionary and calculating the matching error. When the error exceeds a preset threshold, it is determined that the feature has changed.
[0098] S34: Result output: Generate a geographic information change report based on the change detection results, and mark the new, changed or disappeared features of the objects. Through the above steps, a geographic information change detection model is established based on the comprehensive geographic information data output by S2. The model extracts the features of objects through a convolutional neural network and is trained using sparse coding and dictionary learning algorithms. It can effectively identify the addition, change or disappearance of objects.
[0099] S32 specifically includes:
[0100] S321: Randomly select some features from the extracted ground feature data as the initial dictionary and express it as , the initial dictionary Is a matrix, each column represents an initial feature vector, and the initial dictionary construction formula is: ,in, For the The initial eigenvectors, is the number of dictionary columns, that is, the number of feature vectors;
[0101] S322: Sparse coding, for each feature Sparse representation is performed by optimizing the sparse coefficient vector , so that Represented as a dictionary The linear combination of , the optimization objective function of sparse coding is:
[0102] ,in, is a sparse coefficient vector, is the sparse regularization parameter, is the L2 norm, , is the L1 norm;
[0103] S323: Dictionary update: based on the sparse coding result, update the dictionary matrix D, and optimize the dictionary to better represent the feature data of the ground object by minimizing the reconstruction error. The optimization objective function of the dictionary update is:
[0104] ,in, is the updated dictionary matrix, For the feature vectors, is the corresponding sparse coefficient vector, is the number of feature data;
[0105] S324: Iterative optimization, repeating S322 and S323, iteratively optimizing the sparse coefficient vector and the dictionary matrix until the convergence condition is met or the preset number of iterations is reached, and finally obtaining a trained geographic information change detection model, which is expressed as: ,in, is the set of all feature vectors of land objects, is the dictionary matrix after training, is the corresponding sparse coefficient matrix. Through initial dictionary construction, sparse coding, dictionary update and iterative optimization, the dictionary matrix and sparse coefficients are gradually optimized, and finally an efficient change detection model is obtained. The model can accurately represent and identify changes in land features, thereby improving the updating efficiency and accuracy of geographic information data.
[0106] The addition, change or disappearance of the identified features in S33 specifically include:
[0107] S331: Extract the features of the objects from the current comprehensive geographic information data, use the same convolutional neural network (CNN) as S31 to extract the shape, color and texture features of the objects, and generate the current object feature vector ;
[0108] S332: Feature matching, the current feature vector Compare with the dictionary features stored in the model to calculate the current feature vector In the dictionary Sparse representation in ;
[0109] S333: Calculate the matching error between the current feature and the feature stored in the model. The matching error calculation formula is: ,in, is the matching error of the current feature, is the current feature vector, is the dictionary matrix, is the sparse coefficient vector of the current feature;
[0110] S334: Change determination, setting a predetermined error threshold , when the matching error Exceeding the threshold When the matching error is within the threshold Through the above steps, the changes of features of land objects can be accurately detected, the dynamic changes of land objects can be effectively identified, the real-time monitoring and updating of geographic information data can be realized, and a more reliable and detailed data basis can be provided, thereby greatly improving the updating efficiency and accuracy of geographic information.
[0111] S4 specifically includes:
[0112] S41: extracting the feature data of newly added, changed or disappeared objects according to the changes in geographic information detected in step S3, and generating a change data set, including information on the location, shape, size and attributes of the objects;
[0113] S42: Writing the changed data set into the geographic information database, specifically including the following steps:
[0114] First, the data format of the changed data is converted to meet the storage format requirements of the database;
[0115] Then, use database transaction management technology to ensure the consistency and integrity of the changed data during the writing process, including data insertion, update and deletion operations;
[0116] S43: Record detailed log information of each database update, including data change type, timestamp, and operator information, for subsequent audit and tracing;
[0117] S44: Data synchronization preparation, first generating a data synchronization package, including change data and update logs; then using a data compression algorithm to compress the synchronization package to reduce the amount of data transmitted over the network;
[0118] S45: Transmit the data synchronization package to the relevant equipment through a secure network channel. The Transmission Control Protocol (TCP) is used to ensure the reliability of data transmission, and encryption technology is used to protect the security of data during transmission.
[0119] S46: Receive and decompress the data synchronization package on the relevant device, and apply the changed data to the local geographic information database; through the above steps, the geographic information database is automatically updated according to the geographic information changes detected by S3, and the updated geographic information is synchronized to the relevant devices through the network to ensure the consistency and real-time update of geographic information between devices. This method forms a complete geographic information update and synchronization mechanism through change data extraction, database update, log recording, data synchronization preparation, network transmission, and device update, thereby realizing efficient, reliable update and real-time sharing of geographic information data.
[0120] S5 specifically includes:
[0121] S51: Establish a rule system for verifying the accuracy and integrity of geographic information data. The rule system includes geometric consistency rules, attribute consistency rules and logical consistency rules to detect various potential errors and inconsistencies in geographic information data.
[0122] S52: Use the automated validation tool in the Geographic Information System (GIS) to perform preliminary validation on the updated geographic information data, detect errors and inconsistencies in the data through preset validation rules, and generate an automated validation report listing all found problems and potential errors;
[0123] S53: Randomly extract some data from the automated verification report for manual verification. The verification content includes the geometric position, attribute information and logical relationship of the features to ensure the accuracy and reliability of the automated verification results.
[0124] S54: Error analysis step: perform error analysis based on the automated verification report and manual sampling verification results, identify systematic errors and random errors in the data, use error analysis tools to calculate error distribution and error size, and generate an error analysis report; the error calculation formula is: ,in, For the The error of the ground feature, To verify the actual value in the data, is the value predicted by the model;
[0125] S55: Feedback the error analysis report and verification results to the data collection and processing link. For systematic errors, adjust the algorithm parameters of data collection and processing; for random errors, optimize the data processing process to reduce the probability of error occurrence; the systematic error adjustment formula is: ,in, For the corrected data, is the original data, is the correction factor;
[0126] S56: All verification reports, error analysis reports and feedback processing records shall be archived for subsequent audit and quality control. The archived content shall include verification time, verification personnel, problems found, treatment measures and improvement plans. The above method forms a complete verification and feedback mechanism through data verification rule formulation, automated verification, manual sampling verification, error analysis, feedback processing and archiving of verification results, ensuring the high quality and high reliability of geographic information data, realizing the continuous optimization and improvement of geographic information data, thereby greatly improving the updating efficiency and accuracy of geographic information.
[0127] like Figure 2 As shown, a basic geographic information linkage update system is used to implement the above-mentioned basic geographic information linkage update method, including the following modules:
[0128] Multi-source data acquisition module: used to collect geographic information data in real time using multiple data sources such as satellite remote sensing, drone aerial photography, and ground sensors. Satellite remote sensing data is used to cover nationwide geographic information monitoring, drone aerial photography is used to provide high-resolution geographic images of urban areas and surrounding areas, and ground sensors are used to collect precise geographic information of specific locations;
[0129] Data preprocessing module: used to receive geographic information data from the multi-source data acquisition module and perform preprocessing, including applying image processing algorithms to perform image correction and splicing on satellite remote sensing and drone aerial photography data, and using data fusion algorithms to integrate ground sensor data with image data to generate comprehensive geographic information data;
[0130] Dynamic change detection module: Based on the comprehensive geographic information data output by the data preprocessing module, a geographic information change detection model is established to identify the addition, change or disappearance of features. The model is trained using sparse coding and dictionary learning algorithms, and by comparing the current feature characteristics with the features stored in the model, the matching error is calculated and the changes in the features are judged;
[0131] Database update and synchronization module: used to automatically update the geographic information database according to the changes in geographic information detected by the dynamic change detection module, and synchronize the updated geographic information to related devices through the network to ensure the consistency and real-time update of geographic information between devices;
[0132] Data verification and feedback module: used to establish a data verification mechanism, verify the accuracy and completeness of the updated geographic information data, and feed back the verification results to the multi-source data acquisition module and data preprocessing module to optimize the geographic information linkage update system.
[0133] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.
[0134] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A basic geographic information linkage update method, characterized in that: The following steps are involved: S1: Real-time collection of geographic information data using multiple data sources including satellite remote sensing, drone aerial photography, and ground sensors; S2: Receives multi-source geographic information data from S1 and performs pre-processing, including applying image processing algorithms to perform image correction and stitching on satellite remote sensing and drone aerial photography data, and using data fusion algorithms to integrate ground sensor data with image data to generate comprehensive geographic information data; S3: Based on the comprehensive geographic information data output by S2, a geographic information change detection model is established to identify new, changed or disappeared features; S4: Automatically updates the geographic information database based on the changes in geographic information detected by S3, and synchronizes the updated geographic information to related devices through the network to ensure consistency and real-time update of geographic information between devices; S5: Establish a data verification mechanism to verify the accuracy and completeness of updated geographic information data, and feed back the verification results to the data collection and processing links to optimize the geographic information linkage update method, including: S51: Establish a rule system for verifying the accuracy and integrity of geographic information data. The rule system includes geometric consistency rules, attribute consistency rules and logical consistency rules to detect potential errors and inconsistencies in geographic information data. S52: Use the automated validation tools in the GIS to perform preliminary validation on the updated GIS data, detect errors and inconsistencies in the data through the validation rules established in S51, and generate an automated validation report listing all problems and potential errors found; S53: Randomly extract some data from the automated verification report for manual verification, and the verification content includes the geometric position, attribute information and logical relationship of the features; S54: Perform error analysis based on the automated verification report and manual verification results, identify systematic errors and random errors in the data, use error analysis tools to calculate error distribution and error size, and generate an error analysis report; the error calculation formula is: ,in, For the The error of the ground feature, To verify the actual value in the data, The values predicted by the geographic information change detection model; S55: Feedback the error analysis report and verification results to the data collection and processing link. For systematic errors, adjust the algorithm parameters of data collection and processing; for random errors, optimize the data processing process to reduce the probability of error occurrence. The systematic error adjustment formula is: ,in, For the corrected data, is the original data, is the correction factor; S56: All verification reports, error analysis reports and feedback processing records shall be archived, including verification time, verification personnel, problems found, processing measures and improvement plans.
2. A basic geographic information linkage updating method according to claim 1, characterized in that: The S1 specifically includes: S11: Satellite remote sensing data collection: geographical information data covering the whole country is collected regularly every day through high-resolution remote sensing satellites. The satellite remote sensing data includes multi-spectral and panchromatic image data, which are used to provide terrain and land feature information across the whole country; S12: drone aerial photography data collection, using drones equipped with high-precision camera equipment to take high-resolution aerial photos of the urban area and predetermined areas around it according to a predetermined flight route and time interval, and collect geographic information data. The drone aerial photography data includes orthophotos and oblique images, which are used to capture terrain changes and ground object information of the urban area and surrounding areas; S13: ground sensor data collection step, arranging multiple high-precision ground sensors in the selected urban area and the predetermined monitoring area to monitor and collect local geographic information data in real time, the ground sensors include laser radar sensors and high-precision GPS sensors, the laser radar sensors are used to obtain terrain profile and height data, and the high-precision GPS sensors are used to provide accurate geographic coordinates and location information; S14: Data aggregation, transmitting the satellite remote sensing data, drone aerial photography data and ground sensor data collected in S11, S12 and S13 to the central data processor through the wireless communication network for preliminary aggregation and storage.
3. A basic geographic information linkage updating method according to claim 1, characterized in that: The S2 specifically includes: S21: Image correction: geometric correction and radiation correction are performed on the received satellite remote sensing and drone aerial photography data. The geometric correction is used to correct the image data to a unified geographic coordinate system; the radiation correction is used to eliminate the effects of atmospheric scattering and absorption; S22: Image stitching, stitching the calibrated satellite remote sensing data and drone aerial photography data, using image stitching algorithms to stitch multiple image data into a seamless integrated image; S23: Data fusion, using a weighted average-based data fusion algorithm to integrate ground sensor data with the stitched image data to generate comprehensive geographic information data; S24: Data generation, converting and storing the fused data in two formats, vector data and raster data.
4. A basic geographic information linkage updating method according to claim 3, characterized in that: The S22 specifically includes: S221: Preliminary registration of the calibrated satellite remote sensing data and the drone aerial photography data is performed, a registration algorithm based on feature points is used, a set of feature points in the image is selected as registration points, and registration parameters are calculated by the least square method to align the images in space; S222: Perform feature matching processing on the registered image data, use the scale-invariant feature transformation algorithm to extract feature points in the image, calculate feature descriptors, and match feature descriptors through the nearest neighbor search algorithm to find corresponding feature point pairs between the images: S223: Based on the feature matching results, an image fusion algorithm is used to seamlessly stitch the images. Specifically, a Poisson fusion algorithm is used to solve the Poisson equation to smooth the image boundaries and eliminate stitching gaps.
5. A basic geographic information linkage updating method according to claim 4, characterized in that: The S23 specifically includes: S231: preprocessing the stitched image data and ground sensor data, including pixel value standardization processing on the image data and interpolation processing on the ground sensor data; S232: Calculate the weights of the image data and the ground sensor data. Suppose the weight of the image data is , the weight of the ground sensor data is , then the weight calculation formula is: ; S233: The preprocessed image data is integrated with the ground sensor data using a data fusion algorithm based on weighted average. The formula is: ,in, It is the integrated geographic information data after fusion. is the standardized image data, is the interpolated ground sensor data, and are the weights of image data and ground sensor data respectively.
6. A basic geographic information linkage updating method according to claim 1, characterized in that: The S3 specifically includes: S31: Feature extraction, extracting features of objects from the comprehensive geographic information data output by S2, specifically using a convolutional neural network to extract the shape, color and texture features of the objects; S32: Model training, based on the extracted ground feature data, the geographic information change detection model is trained using sparse coding and dictionary learning algorithms; S33: Change detection, applying the trained geographic information change detection model to the comprehensive geographic information data acquired in real time, and identifying the addition, change or disappearance of features by comparing the current features of features with the features stored in the model; S34: Result output: Generate a geographic information change report based on the change detection results, marking the newly added, changed or disappeared features.
7. A basic geographic information linkage updating method according to claim 6, characterized in that: The S32 specifically includes: S321: Randomly select some features from the extracted ground feature data as the initial dictionary and express it as , the initial dictionary is a matrix, each column represents an initial feature vector; S322: Sparse coding, for each feature Sparse representation is performed by optimizing the sparse coefficient vector , so that Represented as a dictionary matrix The linear combination of the dictionary matrix For the initial dictionary After iterative updating, the optimization objective function of sparse coding is: ,in, is a sparse coefficient vector, is the sparse regularization parameter, is the L2 norm, , is the L1 norm; S323: Dictionary update: based on the sparse coding result, the initial dictionary is updated, and the initial dictionary is optimized to better represent the feature data of the ground object by minimizing the reconstruction error. The optimization objective function of the initial dictionary update is: ,in, For the feature vectors, is the corresponding sparse coefficient vector, is the number of feature data; S324: Iterative optimization, repeat S322 and S323, iteratively optimize the sparse coefficient vector and update the initial dictionary until the convergence condition is met or the preset number of iterations is reached, and finally a trained geographic information change detection model is obtained, and its expression is: ,in, is the set of all feature vectors of land objects, is the corresponding sparse coefficient matrix.
8. A basic geographic information linkage updating method according to claim 7, characterized in that: The S33 specifically includes: S331: Extracting the features of the objects from the current comprehensive geographic information data and generating the current object feature vector ; S332: Feature matching, the current feature vector Compare with the dictionary features stored in the model to calculate the current feature vector In the dictionary matrix Sparse representation in ; S333: Calculate the matching error between the current feature and the feature stored in the model. The matching error calculation formula is: ,in, is the matching error of the current feature, is the current feature vector, is the sparse coefficient vector of the current feature; S334: Change determination, setting a predetermined error threshold , when the matching error Exceeding the threshold When the matching error is within the threshold If the feature is different from the previously recorded features in the model, it is judged as a new feature or disappearance.
9. A basic geographic information linkage updating method according to claim 1, characterized in that: The S4 specifically includes: S41: extracting the feature data of newly added, changed or disappeared objects according to the changes in geographic information detected in step S3, and generating a change data set, including information on the location, shape, size and attributes of the objects; S42: writing the changed data set into the geographic information database; S43: Record detailed log information of each geographic information database update, including data change type, timestamp, and operator information; S44: Data synchronization preparation, first generating a data synchronization package, including change data and update logs; then compressing the synchronization package using a data compression algorithm; S45: Transmitting the data synchronization package to the relevant device through a secure network channel; S46: Receive and decompress the data synchronization package on the relevant device, and apply the changed data to the local geographic information database.
10. A basic geographic information linkage update system, used to implement a basic geographic information linkage update method as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Multi-source data acquisition module: used to collect geographic information data in real time using multiple data sources such as satellite remote sensing, drone aerial photography, and ground sensors; Data preprocessing module: used to receive geographic information data from the multi-source data acquisition module and perform preprocessing, including applying image processing algorithms to perform image correction and splicing on satellite remote sensing and drone aerial photography data, and using data fusion algorithms to integrate ground sensor data with image data to generate comprehensive geographic information data; Dynamic change detection module: Based on the comprehensive geographic information data output by the data preprocessing module, a geographic information change detection model is established to identify the addition, change or disappearance of land features; Database update and synchronization module: used to automatically update the geographic information database according to the changes in geographic information detected by the dynamic change detection module, and synchronize the updated geographic information to related devices through the network to ensure the consistency and real-time update of geographic information between devices; Data verification and feedback module: used to establish a data verification mechanism, verify the accuracy and completeness of the updated geographic information data, and feed back the verification results to the multi-source data acquisition module and data preprocessing module to optimize the geographic information linkage update system.
Citation Information
Patent Citations
On-orbit satellite image geometric positioning accuracy evaluation method on basis of multi-source remote sensing data
CN104574347A
Sparse reconstruction-based dual-time phase remote-sensing image change detecting method
CN104700411A
Method and system for dynamically updating geographic space data based on remote sensing image
CN105551028A
Remote sensing image change detection method based on multi-feature evidence fusion and structural similarity
CN116912691A
Rapid map making method and system based on GIS data
CN117635859A
