Surveying information acquisition method and system based on remote sensing technology

Abstract

This application discloses a method and system for acquiring surveying and mapping information based on remote sensing technology, belonging to the field of remote sensing surveying and mapping technology. The method first acquires the types of surveying and mapping information generated from the remote sensing data to be processed; then, it decomposes, verifies, and performs feature matching analysis on the surveying and mapping information types to obtain the analysis results of each core surveying and mapping description; in response to cleaning, updating, and constraint parameter revision operations, it optimizes the feature assignment of the analysis results; combined with the revised positioning points, it filters and downloads the corresponding surveying and mapping elements to complete data derivation and generate remote sensing derived data; based on the optimized analysis results, it trains remote sensing image recognition parameters, and performs element fusion, confidence verification, and feedback convergence comparison between the trained remote sensing image data and the remote sensing derived data to finally determine the surveying and mapping information acquisition method. This method effectively improves the accuracy and efficiency of remote sensing surveying and mapping data analysis, is suitable for remote sensing surveying and mapping engineering operations with diverse terrains and large areas, and has high engineering application value.

Description

Technical Field

[0001] This disclosure relates to the technical field of remote sensing mapping, and in particular to methods and systems for acquiring mapping information based on remote sensing technology. Background Technology

[0002] Remote sensing mapping technology, with its advantages of wide detection range, fast acquisition speed, and no terrain limitations, has been widely applied in surveying and mapping engineering fields such as land surveying, topographic surveying, resource exploration, and geographic information updating. At present, conventional remote sensing mapping information acquisition methods mostly rely on satellite or aerial photography equipment to collect raw remote sensing images, and then use fixed recognition algorithms to complete ground feature extraction, feature resolution, and data statistics to obtain the corresponding mapping information.

[0003] Current remote sensing mapping processing technologies still have several technical shortcomings. First, existing technologies typically perform unified analysis and processing on mixed raw remote sensing data. Various mapping elements are intertwined, without classifying and separating the core mapping content. Different land cover features are prone to overlapping interference, leading to low data analysis accuracy. Second, traditional remote sensing data lacks standardized verification processes. Raw data commonly suffers from missing features, inconsistent formats, and non-standard value selection. Abnormal data directly enters the analysis process, further reducing the quality of mapping data. Third, existing mapping systems offer limited data modification methods, mostly supporting only simple deletion and re-entry, and cannot address issues related to cleaning periods or derivative data. The traditional recognition model has fixed parameters and cannot adaptively update them based on manual revisions. It also has weak adaptability to special scenarios such as complex images, cloud cover, and blurred edges, resulting in a high false detection rate. Furthermore, the existing surveying and mapping data retrieval mostly adopts a full loading mode, which results in a huge amount of data processing and high computing power consumption. In addition, it lacks a visual anomaly warning and human-computer interaction revision module, making it difficult to investigate abnormal data and resulting in poor data traceability. This makes it difficult to meet the requirements of high-precision, high-efficiency, and intelligent remote sensing and mapping operations at present.

[0004] In summary, existing remote sensing mapping information acquisition technologies suffer from drawbacks such as high data heterogeneity, insufficient standardization, weak revision capabilities, poor adaptability of identification models, high computational consumption, and difficulty in anomaly detection. Therefore, there is an urgent need to design a novel mapping information acquisition method based on remote sensing technology to address these technical problems. Summary of the Invention

[0005] To address the technical problems existing in related technologies, this disclosure provides a method and system for acquiring surveying and mapping information based on remote sensing technology.

[0006] A method for acquiring mapping information based on remote sensing technology, characterized in that the method includes: Obtain pre-generated mapping information types corresponding to the remote sensing data to be processed, wherein the mapping information types contain at least several elements of core mapping description content, and the several core mapping description contents are obtained by mining the remote sensing data to be processed; The surveying and mapping information types are analyzed to obtain the analysis results corresponding to each core surveying and mapping description content; In response to the revision operation for the first core description content of the surveying and mapping, the analysis results of the first core description content of the surveying and mapping are optimized to obtain optimized analysis results, wherein the first core description content of the surveying and mapping is any one of the plurality of core description contents of the surveying and mapping; Based on the elements of the first core mapping description content, the first core mapping description content is extracted, and data derivation processing is performed on it to generate corresponding remote sensing derivation data; Collect remote sensing image data, train the recognition parameters of the remote sensing image data based on the optimized analysis results, compare the trained remote sensing image data with the remote sensing derived data to obtain the comparison results, and determine the final mapping information acquisition method based on the comparison results.

[0007] In this application, the types of surveying and mapping information are analyzed to obtain analysis results corresponding to each core description of surveying and mapping, including: The surveying and mapping information types are broken down to obtain multiple element description contents that correspond one-to-one with several core surveying and mapping description contents. Retrieve preset historical surveying and mapping information association relationships, wherein the association relationship is the correspondence between historical surveying and mapping information features and analysis result features, and includes the mapping relationship between element description content features and analysis result features; For each element description, the corresponding feature content is extracted, and combined with the aforementioned relationship, the extracted feature content is matched and entered into the analysis results of the corresponding core surveying and mapping description content.

[0008] It is understood that this claim achieves refined decomposition of mixed surveying and mapping information, breaking down multiple types of mixed surveying and mapping elements into independent element descriptions, avoiding interference between different land cover features. It completes feature mapping and matching based on historical surveying and mapping information relationships, automatically extracts features using historical big data patterns, and inputs the analysis results, reducing subjective errors caused by manual intervention. It achieves automated, structured, and standardized data analysis, effectively improving the accuracy of element feature extraction, reducing the workload of manual analysis, and improving the efficiency and accuracy of remote sensing surveying and mapping data analysis.

[0009] In this application, before the step of splitting the surveying and mapping information types to obtain multiple element descriptions that correspond one-to-one with several core surveying and mapping descriptions, the method further includes: A global verification operation is carried out on the types of surveying and mapping information, which includes verification of the completeness of mandatory features, verification of feature standardization, and verification of the consistency of feature value taking methods. After combining the aforementioned correlations to match and input the feature content into the analysis results of the corresponding core mapping description content, the method further includes: For each core description of the surveying and mapping work, add feature tags related to the revision operation.

[0010] Understandably, this claim adds a global verification process before data splitting to screen and correct the original surveying and mapping data from three dimensions: completeness, standardization, and consistency. This eliminates inferior data with missing fields, inconsistent formats, or non-uniform values, ensuring the quality of input data from the source and preventing abnormal data from interfering with subsequent analysis processes. Simultaneously, revision feature tags are added to the analysis results, giving each core surveying and mapping content a traceable attribute. This facilitates the identification of revision records and tracking of data changes, improving the manageability and traceability of surveying and mapping data, and providing a labeling basis for subsequent revisions and optimizations.

[0011] In this application, in response to a revision operation on the first core mapping description content, the analysis results of the first core mapping description content are optimized to obtain optimized analysis results, including: In response to the revision operation on the first core description content of the surveying and mapping, the features in the analysis results of the first core description content that are related to the current revision operation are optimized and adjusted to obtain the optimized analysis results. The revision operation includes at least one of the following: cleaning operation, update operation, and constraint parameter revision operation.

[0012] It is understandable that this claim establishes a multi-type revision and optimization mechanism, addressing issues such as data noise, parameter lag, and insufficient constraints in surveying and mapping data by setting up three types of revision methods: cleaning, updating, and constraint parameters. This allows for targeted optimization of abnormal features in the core surveying and mapping content, rather than overall batch modification, improving the flexibility and accuracy of data optimization. It solves the problems of traditional remote sensing surveying and mapping data modification being singular, unable to be fine-tuned, and having poor fault tolerance, enhancing the system's adaptability to complex remote sensing scenarios.

[0013] In this application, the response to the revision operation of the first core mapping description content optimizes and adjusts the features related to the current revision operation in the analysis results of the first core mapping description content, and performs at least one of the following processing operations: In response to the cleaning operation on the first core description content of the mapping, the cleaning start time and cleaning end time corresponding to this cleaning operation are assigned to the cleaning range feature included in the analysis result of the first core description content of the mapping; In response to the update operation for the first core description content of the mapping, the derived parameters corresponding to this update operation are assigned to the derived parameter features included in the analysis results of the first core description content of the mapping. In response to the constraint parameter revision operation for the first core mapping description content, the constraint period corresponding to this constraint parameter revision operation is assigned to the constraint boundary features included in the analysis result of the first core mapping description content.

[0014] It is understood that this claim explicitly assigns and solidifies values ​​to the three types of revision operations, writing the cleaning period, derived parameters, and constraint cycle into the corresponding feature fields. This ensures that each revision operation generates clear, quantifiable, and storable feature parameters, avoiding the problems of unrecorded manual revisions, ambiguous parameters, and unclear boundaries. It digitizes revision behavior and standardizes parameters, facilitating the system's accurate recording of every optimization detail, while providing a real and effective data source of revision features for subsequent model training, ensuring that subsequent parameter training closely matches actual surveying and mapping conditions.

[0015] In this application, the step of training the recognition parameters of the remote sensing image data based on the optimized analysis results involves performing at least one of the following processing operations: Extract the cleaning start time and cleaning end time from the optimized analysis results. Set the remote sensing image pixel positioning coordinates corresponding to the cleaning start time as the identification start difference of the remote sensing image data, and set the remote sensing image pixel positioning coordinates corresponding to the cleaning end time as the identification end difference of the remote sensing image data to complete the parameter training. Derivative parameters are extracted from the optimized analysis results, and based on these parameters, the training of derived values ​​for the derived control nodes associated with remote sensing image data is completed. The constraint period is extracted from the optimized analysis results, and the processing parameters of the corresponding constraint nodes in the remote sensing image data are trained based on the constraint period.

[0016] It is understood that this claim relies on the optimized analysis results to perform targeted training on remote sensing image recognition parameters, updating parameters for recognition differences, derived control nodes, and constraint nodes respectively. This overcomes the shortcomings of traditional remote sensing recognition models, such as fixed parameters and poor versatility, enabling recognition parameters to dynamically and adaptively adjust based on manual revisions. It improves the adaptability of remote sensing images to complex time periods, complex terrain features, and constrained conditions, reducing the probability of missed and false detections, and significantly enhancing the accuracy of intelligent remote sensing image recognition.

[0017] In this application, the comparison between the trained remote sensing image data and the remote sensing derived data includes: The remote sensing derived data is fused with the transitional elements of the trained remote sensing image data; The confidence level of the text associated with remote sensing data is verified. If the confidence level of the text associated with remote sensing data is found to be abnormal, the cause of the abnormality is analyzed and the abnormality analysis result is generated. Based on the anomaly analysis results, feedback correction is performed on the text associated with the remote sensing data, the feedback results are determined, and the convergence of remote sensing derived data is triggered to complete the data comparison.

[0018] It is understood that this claim employs a comparison logic of element fusion, confidence level verification, and feedback convergence to integrate remote sensing derived data with image transitional elements, fully preserving the advantageous characteristics of both types of data. Confidence level verification promptly captures anomalies in the text data and analyzes and provides feedback on the causes of these anomalies, driving automatic convergence and optimization of the remote sensing derived data. This overcomes the shortcomings of traditional single comparison methods, such as low fault tolerance and lack of self-correction, enhancing the stability and reliability of data comparison and further ensuring the accuracy of the final mapping results.

[0019] In this application, after parsing and analyzing the surveying and mapping information types to obtain the analysis results corresponding to each core surveying and mapping description, the method further includes: The remote sensing data revision window is displayed. The remote sensing data revision window has multiple built-in functional modules, namely the sequence number of several core mapping description contents, the identification time period, the mapping requirement information, and the revision module. If there is a second surveying core description content with an abnormal response among several surveying core description contents, then a warning message is displayed at the corresponding location of the second surveying core description content, wherein the warning message is used to indicate that the second surveying core description content has an abnormal response.

[0020] Understandably, this claim seeks to establish a visual remote sensing data revision window, integrating and displaying surveying sequence number, identification time period, surveying requirements, and revision modules to achieve visualized management and control of surveying data. Simultaneously, it provides targeted early warning annotations for surveying elements exhibiting abnormal responses, enabling rapid location of anomalous data and assisting staff in promptly troubleshooting data anomalies such as lag, distortion, and delays. This reduces the difficulty of manual investigation, improves anomaly identification efficiency, and enhances the system's human-computer interaction capabilities and ease of maintenance.

[0021] In this application, prior to a revision operation targeting the first mapping core description, the method further includes: The trigger operation of the revision module corresponding to the first core description content of the surveying and mapping will be determined as a revision operation for the first core description content of the surveying and mapping. During the revision process for the first core mapping description, the method further includes: The revision page corresponding to the first core mapping description is retrieved and displayed within the remote sensing data revision window, and the revision work of the first core mapping description is completed through the revision page.

[0022] Understandably, this claim simplifies manual operation logic and reduces the risk of accidental touches and modifications by triggering the identification and judgment of revision operations through a module. During the revision process, a dedicated revision page is automatically retrieved, enabling independent editing and control of single elements and avoiding data corruption caused by mixed modifications of multiple elements. The human-computer interaction process is optimized, simplifying manual revision steps and improving the convenience, security, and specificity of revision operations, making it suitable for batch maintenance of large volumes of remote sensing mapping data.

[0023] In this application, the step of extracting the first surveying and mapping core description content based on its elements includes: The transitional positioning point corresponding to this revision operation is used as the central positioning point, and the scope of this revision is defined by combining the difference between the time periods before and after the preset training. Traverse all core descriptions of surveying and mapping, extract the identification time period of each core description of surveying and mapping, and filter out the core descriptions of surveying and mapping that have overlapping identification time periods and revision ranges. Among them, the overlapping core descriptions of surveying and mapping include the first core description of surveying and mapping. Based on the selected elements of the overlapping core mapping description content, the corresponding core mapping description content is downloaded from the database to complete the data extraction.

[0024] It is understood that this claim defines the revision scope centered on the revision positioning point, and selects surveying and mapping elements with overlapping time periods for targeted download and extraction, without the need to batch load all surveying and mapping database resources. It accurately delineates the processing objects, reduces the amount of invalid data processing, and lowers server read / write pressure and computing power consumption. Simultaneously, it accurately extracts the core content of the target surveying and mapping, ensuring the relevance of data extraction, improving data retrieval speed, and achieving lightweight, high-efficiency data extraction, suitable for large-scale, high-capacity remote sensing surveying and mapping engineering operations.

[0025] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects.

[0026] 1. Achieve refined hierarchical analysis of surveying and mapping data, improving data regularity. This invention breaks down surveying and mapping information into element descriptions corresponding to multiple core surveying and mapping descriptions. Simultaneously, it performs a global check on data integrity, standardization, and value consistency before data analysis, solving the technical pain points of traditional remote sensing surveying and mapping data, such as mixed data, chaotic features, and inconsistent formats. By establishing a correlation mapping relationship between historical surveying and mapping information and analysis results, it accurately extracts element features and completes matching and input, significantly improving the regularity and standardization of remote sensing surveying and mapping data analysis, providing a reliable data foundation for subsequent data processing.

[0027] 2. Supports differentiated and flexible revisions, enhancing the controllability of data optimization. This invention adds a multi-type revision operation mechanism, which can optimize the core descriptive features of surveying and mapping from three different dimensions: cleaning, updating, and constraint parameters. It accurately assigns key features such as cleaning time periods, derived parameters, and constraint cycles. At the same time, it builds a visual remote sensing data revision window, realizing abnormal data early warning, location display, and pop-up revision functions. It solves the problems of rigid traditional remote sensing surveying and mapping data modification processes, single modification dimensions, and difficulty in anomaly investigation, improving the flexibility and intuitiveness of surveying and mapping data revision, and reducing the threshold for manual operation.

[0028] 3. Optimize intelligent recognition training logic to significantly improve remote sensing recognition accuracy. This invention relies on optimized analysis results to train remote sensing image recognition parameters in a targeted manner. Parameter optimization is performed on recognition difference quantities, derived control nodes, and constraint processing nodes, achieving a high degree of adaptation between recognition parameters and surveying revision data. This overcomes the shortcomings of traditional remote sensing image recognition parameters being fixed and having poor adaptability, enabling the recognition model to fit the characteristics of surveying data under different revision scenarios, effectively reducing recognition errors and improving the accuracy of remote sensing image data recognition.

[0029] 4. Achieve data fusion, convergence, and verification to ensure the accuracy of surveying results. This invention fuses remote sensing derived data with image transition elements, combines a text confidence verification mechanism to identify data anomalies, and optimizes the convergence of remote sensing derived data through feedback processing. This overcomes the shortcomings of traditional remote sensing surveying comparison methods, such as their reliance on a single approach, difficulty in identifying abnormal data, and poor data convergence. It ensures the reliability of surveying information from multiple dimensions, including data comparison, anomaly verification, and feedback correction, thus avoiding surveying errors caused by data deviations.

[0030] 5. Reduce the scope of data processing and decrease database computational pressure. This invention defines the revision scope by centering on the revision positioning point, and selects the core mapping content with overlapping time periods for targeted download processing, eliminating the need to batch load all remote sensing mapping data. This effectively reduces the amount of data processed, decreases the computational power consumption of database read and write operations, improves the overall operational efficiency of remote sensing mapping information acquisition, processing, and analysis, and is suitable for large-scale, large-volume remote sensing mapping operation scenarios, possessing significant engineering application and promotion value.

[0031] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this disclosure. Attached Figure Description

[0032] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the principles of this application.

[0033] Figure 1This is a schematic diagram of the architecture of a remote sensing-based mapping information acquisition system provided in an embodiment of this application. Figure 2 This is a flowchart illustrating the method for acquiring surveying and mapping information based on remote sensing technology provided in an embodiment of this application. Detailed Implementation

[0034] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0035] To facilitate the explanation of the above-mentioned methods and systems for acquiring surveying and mapping information based on remote sensing technology, please refer to the references. Figure 1 This application provides a schematic diagram of the communication architecture of a remote sensing-based mapping information acquisition system 100 disclosed in an embodiment of this application. The remote sensing-based mapping information acquisition system 100 may include a mapping data processing terminal 200 and a mapping image acquisition device 300, wherein the mapping data processing terminal 200 and the mapping image acquisition device 300 are communicatively connected.

[0036] In specific implementations, the surveying data processing terminal 200 can be a desktop computer, tablet computer, laptop computer, mobile phone, or other surveying image acquisition device capable of data processing and data communication, without further limitations.

[0037] Based on the above, please refer to the following: Figure 2 This is a schematic flowchart of a remote sensing-based mapping information acquisition method provided in an embodiment of this application. The remote sensing-based mapping information acquisition method can be applied to... Figure 1 The mapping image acquisition device 300 in the middle, further, the mapping information acquisition method based on remote sensing technology may specifically include the content described in steps S101-S105.

[0038] In step 101, the types of pre-generated mapping information corresponding to the remote sensing data to be processed are obtained.

[0039] Here, the remote sensing data to be processed can be data collected by drones, etc. The types of surveying and mapping information can include at least several core surveying and mapping descriptive contents (such as basic surveying and mapping information, thematic surveying and mapping information, remote sensing image information, control measurement results, etc.). Among them, the multiple core surveying and mapping descriptive contents can be obtained by mining the remote sensing data to be processed.

[0040] In this embodiment, unprocessed raw remote sensing data of the hilly area is retrieved. Data mining algorithms are used to extract textures, identify edges, and cluster pixels in the remote sensing images to generate four preset core mapping descriptions. Before data analysis, a global verification is performed on the types of mapping information: a mandatory feature integrity check verifies whether any of the four types of elements are missing mandatory fields such as boundary coordinates and elevation values; a feature standardization check ensures that coordinates are retained to four decimal places; and a feature value consistency check ensures that elevation data uses the Geodetic 2000 coordinate system, eliminating raw data with incorrect formats and abnormal parameters.

[0041] In step 102, the types of surveying and mapping information are analyzed to obtain the analysis results corresponding to each core description of surveying and mapping.

[0042] The method for analyzing the types of surveying and mapping information is as follows: extract the influencing factors corresponding to each type of surveying and mapping information, check whether the influencing factors match in the actual surveying and mapping process, and correct the influencing factors if they do not match.

[0043] The calibrated surveying information was broken down into four categories of feature descriptions, corresponding to four core surveying descriptions: topographic elevation, feature boundaries, vegetation cover, and water body distribution. Pre-defined historical surveying information relationships were retrieved from the database, storing mapping rules between feature texture features, boundary contour features, pixel grayscale features, and analysis results. For each category of feature descriptions, grayscale histograms were used to extract features, and contour moments were used to extract boundary features. The extracted features were automatically matched and entered into the analysis results of the corresponding core surveying description. Simultaneously, a revision marker feature was added to each analysis result for subsequent tracking and recording of revision operations.

[0044] In one possible implementation embodiment, the second process of the mapping information acquisition method based on remote sensing technology provided in this application embodiment, step 102 can be implemented by steps 1021 to 1023, which will be described below.

[0045] In step 1021, the surveying information types are split to obtain multiple element description contents that correspond one-to-one with several core surveying description contents.

[0046] The specific processing method for splitting the data is as follows: Data is processed according to the specified standards for different types of surveying and mapping information. In one possible implementation, before executing step 1021, the following process may also be performed: a global verification of the surveying information types, wherein the global verification may include verification of the integrity of mandatory features, verification of feature standardization, and verification of the consistency of feature value methods; only after the surveying information types have passed the global verification will the process proceed to step 1021.

[0047] In step 1022, the preset historical surveying and mapping information association is retrieved.

[0048] Here, the relationship can include the correspondence between the features of the element description content and the features of the analysis results.

[0049] In step 1023, for each element description, the corresponding feature content is extracted, and combined with the aforementioned relationship, the extracted feature content is matched and entered into the analysis results of the corresponding core surveying and mapping description content.

[0050] In one possible implementation, after step 1023 is completed, the following processing can also be performed: for the analysis results corresponding to each core mapping description content, add features related to the revision operation (such as cleaning range features, derived parameter features, and constraint boundary features, etc.) to each analysis result.

[0051] In one possible implementation, after performing step 102 above, the following processing can also be performed: displaying a remote sensing data revision window, wherein the remote sensing data revision window may include multiple sequence numbers corresponding to multiple core mapping description contents, multiple identification time periods (i.e., identification areas), multiple mapping requirement information, and multiple revision modules; in response to a second core mapping description content with an abnormal response among the multiple core mapping description contents, displaying warning information at the location corresponding to the second core mapping description content, wherein the warning information can be used to indicate that the loudness of the second core mapping description content is abnormal.

[0052] The terminal interface displays a remote sensing data revision window, which sequentially shows the sequence number of the four types of core mapping description content, the identification time period, the mapping accuracy requirements, and an independent revision module. In this embodiment, vegetation cover element is detected as the second core mapping description content with an abnormal response. The vegetation pixel recognition response delay exceeds 300ms. The system marks the corresponding location of the vegetation element in red and pops up a yellow warning pop-up window to indicate the abnormal data response, facilitating priority investigation and handling by staff. When staff click on the revision module corresponding to the water body distribution element, the system retrieves a dedicated revision page, supporting manual modification of parameters such as boundary thresholds and cleaning time periods.

[0053] The detailed steps for breaking down surveying and mapping information types, the visual window display, and the anomaly warning prompts are as follows: This invention performs a hierarchical and precise segmentation process for surveying and mapping information, combining remote sensing and mapping element attributes to complete the classification and decomposition. The detailed steps are as follows: (1) Element classification determination: Read the total dataset of surveying and mapping information after global calibration, and pre-divide it into four major element categories: terrain, land features, vegetation and water bodies according to the remote sensing surveying and mapping industry standards. Determine the element category to which each pixel set and coordinate dataset in the original surveying and mapping data belongs, and remove invalid stray data without classification attributes.

[0054] (2) Boundary separation segmentation: The feature boundary separation algorithm is adopted, using the gray threshold, contour edge and spectral difference of different mapping elements as the segmentation boundary to physically separate multiple types of elements mixed in the same data frame, splitting out independent original element subsets, and avoiding data adhesion and interference between different core elements.

[0055] (3) Feature content mapping and matching: Establish a one-to-one mapping relationship between feature subsets and core mapping content. Match the topographic elevation subset with the topographic elevation core description content, the feature outline subset with the feature boundary core description content, the vegetation grayscale subset with the vegetation cover core description content, and the water pixel subset with the water body distribution core description content.

[0056] (4) Formatted generation of feature description content: The format of each matched subset is encapsulated, and the feature number, collection time period, coordinate range, feature parameters and precision threshold are uniformly entered to generate standardized and structured independent feature description content, thus completing the mapping information type splitting operation; after splitting, each feature description content is independent of each other and does not interfere with each other, and feature extraction and data analysis can be performed separately.

[0057] After the data is split, a remote sensing data revision window pops up on the terminal interface. The window displays the sequence number of the four types of core mapping description content, the identification time period, the mapping accuracy requirements, and an independent revision module. In this embodiment, vegetation cover was detected as the second type of core mapping description content with an abnormal response. The vegetation pixel recognition response delay exceeded 300ms. The system highlighted the corresponding location of the vegetation element in red and popped up a yellow warning window, indicating the abnormal data response and facilitating priority investigation and handling by staff. Staff can click on the revision module corresponding to the water body distribution element, and the system will retrieve a dedicated revision page, supporting manual modification of parameters such as boundary thresholds and cleaning time periods.

[0058] In step 103, in response to the revision operation for the first core description of the surveying and mapping, the analysis results of the first core description of the surveying and mapping are optimized to obtain optimized analysis results.

[0059] The optimized steps in this application include two steps: correction and updating of the analysis results. Correction is used to correct data with minor differences or missing data, while updating is used to replace or update the original data.

[0060] This embodiment selects water body distribution elements as the first core mapping description content and performs three types of revision operations: cleaning, updating, and constraint parameter revision. The cleaning operation sets the start time to the 2nd second of image acquisition and the end time to the 18th second, removing abnormal water body pixels caused by cloud obstruction during this period. The updating operation imports water body derived calculation parameters, setting the water area expansion coefficient to 1.02 to correct for pixel mixing errors at the waterfront edge. The constraint parameter revision operation sets the constraint period to 7 days, limiting the water body mapping data for this area to be updated once every 7 days. These parameters are then assigned to the cleaning range feature, derived parameter feature, and constraint boundary feature, respectively, generating optimized water body distribution element analysis results.

[0061] Here, the first core mapping description content can be any one of multiple core mapping description contents.

[0062] In one possible implementation, step 103 can be implemented as follows: in response to a revision operation on the first mapping core description content, the features in the analysis results of the first mapping core description content that are related to the current revision operation are optimized and adjusted to obtain an optimized analysis result. The revision operation may include at least one of the following: cleaning operation, update operation, and constraint parameter revision operation.

[0063] In one possible implementation, following the foregoing, the above-mentioned optimization processing of the features related to the revision operation in the analysis results of the first core mapping description content in response to the revision operation can be achieved in the following manner: performing at least one of the following processes: in response to the cleaning operation of the first core mapping description content, assigning the cleaning start time period and cleaning end time period corresponding to the current cleaning operation to the cleaning range feature included in the analysis results of the first core mapping description content; in response to the update operation of the first core mapping description content, assigning the derived parameters corresponding to the current update operation to the derived parameter feature included in the analysis results of the first core mapping description content; in response to the constraint parameter revision operation of the first core mapping description content, assigning the constraint period corresponding to the current constraint parameter revision operation to the constraint boundary feature included in the analysis results of the first core mapping description content.

[0064] In one possible implementation, before responding to a revision operation for the first core mapping description content, the following processing may also be performed: the triggering operation of the revision module corresponding to the first core mapping description content is determined as a revision operation for the first core mapping description content. Accordingly, when responding to a revision operation for the first core mapping description content, the following processing may also be performed: the revision page corresponding to the first core mapping description content is retrieved and displayed in the remote sensing data revision window, and the revision operation for the first core mapping description content is completed through the revision page, wherein the revision page can be used to revise the first core mapping description content.

[0065] In step 104, the first mapping core description content is extracted based on the elements of the first mapping core description content, and data derivation processing is performed on it to generate corresponding remote sensing derived data.

[0066] The derivative steps in this application can be understood as steps for mining the core description content of the first surveying and mapping.

[0067] In one possible implementation, the extraction of the first core mapping description content based on its elements can be achieved as follows: The transitional positioning point corresponding to the current revision operation is used as the central positioning point, and the scope of the current revision is defined by combining the difference in time periods before and after the current revision obtained through preset training; all core mapping description contents are traversed, and the identification time periods of each core mapping description content are extracted; core mapping description contents whose identification time periods overlap with the revision scope are selected, wherein the overlapping core mapping description contents include the first core mapping description content; based on the elements of the overlapping core mapping description contents, the overlapping core mapping description contents are downloaded from the database.

[0068] In step 105, remote sensing image data is collected, and the recognition parameters of the remote sensing image data are trained based on the optimized analysis results. The trained remote sensing image data is compared with the remote sensing derived data to obtain the comparison results. Based on the comparison results, the final mapping information acquisition method is determined.

[0069] In one possible implementation, the above-mentioned training of recognition parameters for the remote sensing image data based on the optimized analysis results can be achieved by performing at least one of the following processes: extracting the cleaning start time period and cleaning end time period from the optimized analysis results; setting the remote sensing image pixel positioning coordinates corresponding to the cleaning start time period as the recognition start difference amount of the remote sensing image data; setting the remote sensing image pixel positioning coordinates corresponding to the cleaning end time period as the recognition end difference amount of the remote sensing image data; and completing parameter training; extracting derived parameters from the optimized analysis results; and training derived values ​​for the derived control nodes associated with the remote sensing image data based on the derived parameters; and extracting constraint periods from the optimized analysis results; and training processing parameters for the constraint nodes corresponding to the remote sensing image data based on the constraint periods.

[0070] For example, taking the first core mapping description content as mapping core description content 1 among multiple mapping core description contents as an example, after confirming the construction of remote sensing image data corresponding to mapping core description content 1, the identification difference quantity of remote sensing image data can be trained based on cleaning parameters. Specifically, the cleaning start time period and cleaning end time period can be extracted from the optimized analysis results corresponding to mapping core description content 1, and the identification start difference quantity of the constructed remote sensing image data can be trained as the remote sensing image pixel positioning coordinates corresponding to the cleaning start time period, and the identification end difference quantity of the remote sensing image data can be trained as the remote sensing image pixel positioning coordinates corresponding to the cleaning end time period.

[0071] In one possible implementation, the above-mentioned method of calling trained remote sensing image data to identify remote sensing derived data can be achieved by: fusing the remote sensing derived data with the transition elements of the trained remote sensing image data; performing confidence verification on the remote sensing data associated text; if it is determined that the remote sensing data associated text has an abnormal confidence level, analyzing the cause of the abnormality and generating an abnormality analysis result; and determining the feedback result based on the global master clock of the remote sensing data associated text in the analysis result, and triggering the convergence state of the remote sensing derived data.

[0072] In one possible implementation, following the above example, the following processing can also be performed during the identification of remote sensing derived data: feeding back identification progress information to the remote sensing data revision window and simultaneously optimizing the identification head positioning on the transition positioning included in the remote sensing data revision window; checking the confidence event of the remote sensing image data in real time, and automatically destroying the remote sensing image data if the identification completion event is detected.

[0073] In summary, when applying the above-mentioned scheme, the beneficial effects of this scheme are as follows: 1. Achieve refined hierarchical analysis of surveying and mapping data, improving data regularity. This invention breaks down surveying and mapping information into element descriptions corresponding to multiple core surveying and mapping descriptions. Simultaneously, it performs a global check on data integrity, standardization, and value consistency before data analysis, solving the technical pain points of traditional remote sensing surveying and mapping data, such as mixed data, chaotic features, and inconsistent formats. By establishing a correlation mapping relationship between historical surveying and mapping information and analysis results, it accurately extracts element features and completes matching and input, significantly improving the regularity and standardization of remote sensing surveying and mapping data analysis, providing a reliable data foundation for subsequent data processing.

[0074] 2. Supports differentiated and flexible revisions, enhancing the controllability of data optimization. This invention adds a multi-type revision operation mechanism, which can optimize the core descriptive features of surveying and mapping from three different dimensions: cleaning, updating, and constraint parameters. It accurately assigns key features such as cleaning time periods, derived parameters, and constraint cycles. At the same time, it builds a visual remote sensing data revision window, realizing abnormal data early warning, location display, and pop-up revision functions. It solves the problems of rigid traditional remote sensing surveying and mapping data modification processes, single modification dimensions, and difficulty in anomaly investigation, improving the flexibility and intuitiveness of surveying and mapping data revision, and reducing the threshold for manual operation.

[0075] 3. Optimize intelligent recognition training logic to significantly improve remote sensing recognition accuracy. This invention relies on optimized analysis results to train remote sensing image recognition parameters in a targeted manner. Parameter optimization is performed on recognition difference quantities, derived control nodes, and constraint processing nodes, achieving a high degree of adaptation between recognition parameters and surveying revision data. This overcomes the shortcomings of traditional remote sensing image recognition parameters being fixed and having poor adaptability, enabling the recognition model to fit the characteristics of surveying data under different revision scenarios, effectively reducing recognition errors and improving the accuracy of remote sensing image data recognition.

[0076] 4. Achieve data fusion, convergence, and verification to ensure the accuracy of surveying results. This invention fuses remote sensing derived data with image transition elements, combines a text confidence verification mechanism to identify data anomalies, and optimizes the convergence of remote sensing derived data through feedback processing. This overcomes the shortcomings of traditional remote sensing surveying comparison methods, such as their reliance on a single approach, difficulty in identifying abnormal data, and poor data convergence. It ensures the reliability of surveying information from multiple dimensions, including data comparison, anomaly verification, and feedback correction, thus avoiding surveying errors caused by data deviations.

[0077] 5. Reduce the scope of data processing and decrease database computational pressure. This invention defines the revision scope by centering on the revision positioning point, and selects the core mapping content with overlapping time periods for targeted download processing, eliminating the need to batch load all remote sensing mapping data. This effectively reduces the amount of data processed, decreases the computational power consumption of database read and write operations, improves the overall operational efficiency of remote sensing mapping information acquisition, processing, and analysis, and is suitable for large-scale, large-volume remote sensing mapping operation scenarios, possessing significant engineering application and promotion value.

[0078] It should be understood that this application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for obtaining survey information based on remote sensing technology, characterized in that, The method includes: Obtain pre-generated mapping information types corresponding to the remote sensing data to be processed, wherein the mapping information types contain at least elements of multiple core mapping description contents, and the core mapping description contents are obtained by mining the remote sensing data to be processed; The surveying and mapping information types are analyzed to obtain the analysis results corresponding to each core surveying and mapping description content; In response to the revision operation for the first core description content of the surveying and mapping, the analysis results of the first core description content of the surveying and mapping are optimized to obtain optimized analysis results, wherein the first core description content of the surveying and mapping is any one of the plurality of core description contents of the surveying and mapping; Based on the elements of the first core mapping description content, the first core mapping description content is extracted, and data derivation processing is performed on it to generate corresponding remote sensing derivation data; Collect remote sensing image data, train the recognition parameters of the remote sensing image data based on the optimized analysis results, compare the trained remote sensing image data with the remote sensing derived data to obtain the comparison results, and determine the final mapping information acquisition method based on the comparison results.

2. The method of claim 1, wherein, The surveying and mapping information types are analyzed to obtain the analysis results corresponding to each core surveying and mapping description, including: The surveying and mapping information types are broken down to obtain multiple element description contents that correspond one-to-one with several core surveying and mapping description contents. Retrieve preset historical surveying and mapping information associations, where the association is the correspondence between the features of historical surveying and mapping information and the features of the analysis results, and includes the mapping relationship between the feature description content features and the features of the analysis results; For each element description, the corresponding feature content is extracted, and combined with the correlation relationship, the extracted feature content is matched and entered into the analysis results of the corresponding core surveying and mapping description content.

3. The method of claim 2, wherein, Before splitting the surveying and mapping information types to obtain multiple element descriptions that correspond one-to-one with several core surveying and mapping descriptions, the method further includes: A global verification operation is carried out on the types of surveying and mapping information, which includes verification of the completeness of mandatory features, verification of feature standardization, and verification of the consistency of feature value taking methods. After combining the aforementioned correlations to match and input the feature content into the analysis results of the corresponding core mapping description content, the method further includes: For each core description of the surveying and mapping work, add feature tags related to the revision operation.

4. The method of claim 1, wherein, In response to the revision operation on the first core mapping description content, the analysis results of the first core mapping description content are optimized to obtain optimized analysis results, including: In response to the revision operation on the first core description content of the surveying and mapping, the features in the analysis results of the first core description content that are related to the current revision operation are optimized and adjusted to obtain the optimized analysis results. The revision operation includes at least one of the following: cleaning operation, update operation, and constraint parameter revision operation.

5. The method of claim 4, wherein, In response to the revision operation on the first core mapping description content, the features in the analysis results of the first core mapping description content that are related to the current revision operation are optimized and adjusted, and at least one of the following processing operations is performed: In response to the cleaning operation on the first core description content of the mapping, the cleaning start time and cleaning end time corresponding to this cleaning operation are assigned to the cleaning range feature included in the analysis result of the first core description content of the mapping; In response to the update operation for the first core description content of the mapping, the derived parameters corresponding to this update operation are assigned to the derived parameter features included in the analysis results of the first core description content of the mapping. In response to the constraint parameter revision operation for the first core mapping description content, the constraint period corresponding to this constraint parameter revision operation is assigned to the constraint boundary features included in the analysis result of the first core mapping description content; Prior to responding to a revision operation on the first mapping core description content, the method further includes: The trigger operation of the revision module corresponding to the first core description content of the surveying and mapping will be determined as a revision operation for the first core description content of the surveying and mapping. During the revision process for the first core mapping description, the method further includes: The revision page corresponding to the first core mapping description is retrieved and displayed in the remote sensing data revision window, and the revision work of the first core mapping description is completed through the revision page.

6. The method of claim 1, wherein, The process of training the recognition parameters of the remote sensing image data based on the optimized analysis results involves performing at least one of the following processing operations: Extract the cleaning start time and cleaning end time from the optimized analysis results. Set the remote sensing image pixel positioning coordinates corresponding to the cleaning start time as the identification start difference of the remote sensing image data, and set the remote sensing image pixel positioning coordinates corresponding to the cleaning end time as the identification end difference of the remote sensing image data to complete the parameter training. Derivative parameters are extracted from the optimized analysis results, and based on these parameters, the training of derived values ​​for the derived control nodes associated with remote sensing image data is completed. The constraint period is extracted from the optimized analysis results, and the processing parameters of the corresponding constraint nodes in the remote sensing image data are trained based on the constraint period.

7. The method of claim 1, wherein, The trained remote sensing image data is compared with the remote sensing derived data, including: The remote sensing derived data is fused with the transitional elements of the trained remote sensing image data; The confidence level of the text associated with remote sensing data is verified. If the confidence level of the text associated with remote sensing data is found to be abnormal, the cause of the abnormality is analyzed and the abnormality analysis result is generated. Based on the anomaly analysis results, feedback correction is performed on the text associated with the remote sensing data, the feedback results are determined, and the convergence of remote sensing derived data is triggered to complete the data comparison.

8. The method of claim 1, wherein, After analyzing the types of surveying and mapping information to obtain the analysis results corresponding to each core description of surveying and mapping, the method further includes: The remote sensing data revision window is displayed. The remote sensing data revision window has multiple built-in functional modules, namely the sequence number of several core mapping description contents, the identification time period, the mapping requirement information, and the revision module. If there is a second surveying core description content with an abnormal response among several surveying core description contents, then a warning message will be displayed at the corresponding location of the second surveying core description content. The warning message is used to indicate that the second surveying core description content has an abnormal response.

9. The method of claim 1, wherein, The step of extracting the first surveying and mapping core description content based on its elements includes: The transitional positioning point corresponding to this revision operation is used as the central positioning point, and the scope of this revision is defined by combining the difference between the time periods before and after the preset training. Traverse all core descriptions of surveying and mapping, extract the identification time period of each core description of surveying and mapping, and filter out the core descriptions of surveying and mapping that have overlapping identification time periods and revision ranges. Among them, the overlapping core descriptions of surveying and mapping include the first core description of surveying and mapping. Based on the selected elements of the overlapping core mapping description content, the corresponding core mapping description content is downloaded from the database to complete the data extraction.

10. A remote sensing technology-based survey information acquisition system, characterized by comprising: a remote sensing device; a data processing device; and a data transmission device. The method includes a processor and a memory that communicate with each other, the processor being configured to read a computer program from the memory and execute it to implement the method of any one of claims 1-9.

Images