Long-time sequence remote sensing image data processing method, system, equipment, medium and product

Abstract

The invention discloses a long-time sequence remote sensing image data processing method, system and device, a medium and a product, and relates to the field of remote sensing image data analysis and application, and the method comprises the steps: dividing a research region into a plurality of regions of interest based on vector data; performing standardization processing on the long-time sequence remote sensing image data in each region of interest, extracting raster data of the long-time sequence remote sensing image data, and storing the raster data in a database; performing statistical analysis on the raster data to generate a remote sensing image data analysis result; and based on the database, visualizing the metadata information of the long-time sequence remote sensing image data in each region of interest and the remote sensing image data analysis result, so that the data processing efficiency can be improved, the method is not limited by a research region, and the data expansibility and the user interactivity are improved.

Description

Technical Field

[0001] The present application relates to the field of remote sensing image data analysis and application, and in particular to a method, system, equipment, medium and product for processing long-term series remote sensing image data. Background Art

[0002] With the continuous development of remote sensing technology and the rapid growth of data volume, traditional data processing and analysis methods face many challenges. The existing remote sensing image data analysis platform has the following technical problems:

[0003] 1. Low data processing efficiency: Traditional remote sensing image data processing methods usually require repeated processing of raw image data, resulting in low data processing efficiency and heavy workload for users.

[0004] 2. Limited research area: Existing remote sensing image data analysis platforms are usually designed for specific research areas and lack flexible support for different regions, which limits the research scope of users.

[0005] 3. Poor data scalability: Traditional remote sensing image data analysis platforms usually use fixed data models and processing procedures, which are difficult to adapt to the expansion and integration of new data sources, limiting the scalability of the system.

[0006] 4. Insufficient user interactivity: Existing remote sensing image data analysis platforms usually lack intuitive and easy-to-use user interfaces, and users need to have certain professional knowledge and programming skills to perform data analysis and visualization. Summary of the invention

[0007] The purpose of this application is to provide a long-term remote sensing image data processing method, system, equipment, medium and product to solve the above-mentioned problems existing in the existing remote sensing image data analysis platform.

[0008] To achieve the above objectives, this application provides the following solutions:

[0009] In a first aspect, the present application provides a method for processing long-time series remote sensing image data, comprising:

[0010] Based on vector data, the study area is divided into several areas of interest; the vector data includes administrative boundary data and latitude and longitude ranges;

[0011] Standardize the long-time series remote sensing image data in each region of interest, extract the raster data of the long-time series remote sensing image data, and store them in a database; the raster data includes the maximum value index, minimum value index, average value index and standard deviation index of the remote sensing image data in the region of interest;

[0012] Statistically analyzing the raster data to generate remote sensing image data analysis results; the statistical analysis includes historical year-on-year, month-on-month, linear trend analysis, historical cumulative statistics, mutation detection, and anomaly statistics;

[0013] Based on the database, the metadata information of the long-term series remote sensing image data in each of the regions of interest and the analysis results of the remote sensing image data are visualized; the metadata information includes the star payload, file name, file path, file size, acquisition date, spatial resolution, temporal resolution and cloud coverage.

[0014] Optionally, based on vector data, divide the study area into several areas of interest, including:

[0015] Establishing index codes according to the administrative boundary data;

[0016] According to the index code, the study area is partitioned into several areas of interest; one index code corresponds to one area of ​​interest; the attributes of the area of ​​interest include the Chinese and English names of the country, province, city, the unique administrative code and the administrative boundary level; the administrative boundary levels include national, provincial and municipal levels.

[0017] Optionally, based on vector data, divide the study area into several areas of interest, including:

[0018] Based on the longitude and latitude range, the longitude and latitude of the study area are divided into several areas of interest.

[0019] Optionally, based on the database, the metadata information of the long-time series remote sensing image data in each of the regions of interest and the analysis results of the remote sensing image data are visualized, which also includes:

[0020] When visually querying more than two regions of interest, metadata information in the two or more regions of interest is jointly calculated to generate joint metadata information.

[0021] Optionally, when visually querying two regions of interest, the combined metadata information is:

[0022] C=A×countA+B×countB / (countA+countB);

[0023] Among them, A is the metadata information of the first study area of ​​interest, countA is the number of valid pixels in the first study area of ​​interest; B is the metadata information of the second study area of ​​interest, countB is the number of valid pixels in the second study area of ​​interest; C is the metadata information after combination.

[0024] Optionally, based on the database, the metadata information of the long-time series remote sensing image data in each of the regions of interest and the analysis results of the remote sensing image data are visualized, which also includes:

[0025] Using a data compression algorithm to compress the long-time series remote sensing image data, and slicing the compressed remote sensing image data;

[0026] Use browser cache and server cache mechanisms to cache remote sensing image data after data slicing;

[0027] Asynchronous loading technology is used to load the remote sensing image data after slicing the cached data in the background.

[0028] In a second aspect, the present application provides a long-time series remote sensing image data processing system, comprising:

[0029] A region division module is used to divide the study area into a number of regions of interest based on vector data; the vector data includes administrative boundary data and latitude and longitude ranges;

[0030] A raster data extraction module is used to perform standardization processing on the long-time series remote sensing image data in each area of ​​interest, extract the raster data of the long-time series remote sensing image data, and store it in a database; the raster data includes a regional maximum value index, a regional minimum value index, a regional average value index, and a regional standard deviation index;

[0031] A statistical analysis module is used to statistically analyze the raster data and generate remote sensing image data analysis results; the statistical analysis includes historical year-on-year, month-on-month, linear trend analysis, historical cumulative statistics, mutation detection and anomaly statistics;

[0032] A visualization module is used to visualize the metadata information of the long-term remote sensing image data in each of the areas of interest and the analysis results of the remote sensing image data based on the database; the metadata information includes star payload, file name, file path, file size, acquisition date, spatial resolution, temporal resolution and cloud coverage.

[0033] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-described long-term remote sensing image data processing methods.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described long-time series remote sensing image data processing methods.

[0035] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned long-term remote sensing image data processing methods.

[0036] According to the specific embodiments provided by the present application, the present application discloses the following technical effects: based on vector data, the present application divides the study area into several regions of interest, and processes the long-term series remote sensing image data in each region of interest, thereby effectively avoiding repeated processing of the original long-term series remote sensing image data, improving data processing efficiency, and reducing user workload; secondly, the vector data includes administrative boundary data and longitude and latitude ranges, so the divided regions of interest include global regions, that is, it is possible to analyze and study the long-term series remote sensing image data of any region in the world, and the user's research scope is not limited; when new remote sensing image data needs to be analyzed, the same method is used. The division is carried out in the above manner, and the long-time series remote sensing image data in each area of ​​interest is standardized, the raster data of the long-time series remote sensing image data is extracted, and stored in the database, which can quickly adapt to the expansion and integration of new data sources and improve the scalability of the system; finally, the application also generates remote sensing image data analysis results by statistically analyzing the raster data, and visualizes the metadata information and remote sensing image data analysis results of the long-time series remote sensing image data in each area of ​​interest, thereby lowering the user's usage threshold and allowing users to perform data analysis and visualization without professional knowledge and programming skills, and intuitively display the final analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 This is a flow chart of a method for processing long-time series remote sensing image data in one embodiment of the present application;

[0039] Figure 2 A schematic diagram of a process for extracting indicators from raster data provided by an embodiment of the present application;

[0040] Figure 3 This is a schematic diagram of a database for data storage according to another embodiment of the present application;

[0041] Figure 4 A schematic diagram of year-on-year results provided in an embodiment of the present application;

[0042] Figure 5 A schematic diagram of month-on-month statistics provided in an embodiment of the present application;

[0043] Figure 6 A schematic diagram of monthly cumulative statistics provided by another embodiment of the present application.

[0044] Figure 7 A schematic diagram of long time series statistics provided by an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0047] With the development of remote sensing technology, the acquisition and accumulation of long-term remote sensing image data are increasing. However, the storage, processing and analysis of massive remote sensing image data face many challenges, such as large data volume, high processing complexity, and low analysis efficiency. This application proposes a strategy of block-by-block statistical storage of historical data, and real-time API calls to merge and count data from different regions, to achieve efficient long-term series analysis and statistical functions on the WEB side; and combined with the WMS service in the Geoserver map, to achieve long-term spatial visualization of series and publication of geographic information. This application adopts a mode of separating data processing and visualization to achieve efficient and continuous long-term series remote sensing image data monitoring and analysis functions.

[0048] like Figure 1 As shown, a method for processing long-time series remote sensing image data provided by an embodiment of the present application includes:

[0049] Step 101: Divide the study area into several areas of interest based on vector data; the vector data includes administrative boundary data and longitude and latitude ranges.

[0050] Step 102: Standardize the long-time series remote sensing image data in each region of interest, extract the raster data of the long-time series remote sensing image data, and store it in a database; the raster data includes the maximum value index, minimum value index, average value index and standard deviation index of the remote sensing image data in the region of interest.

[0051] Step 103: Statistically analyze the raster data to generate remote sensing image data analysis results; the statistical analysis includes historical year-on-year, month-on-month, linear trend analysis, historical cumulative statistics, mutation detection and deviation statistics.

[0052] Step 104: Based on the database, the metadata information of the long-term remote sensing image data in each of the regions of interest and the analysis results of the remote sensing image data are visualized; the metadata information includes the star payload, file name, file path, file size, acquisition date, spatial resolution, temporal resolution and cloud coverage.

[0053] In an exemplary embodiment, in order to avoid repeated processing of the original image data, the above step 101 is replaced by the following steps 201 to 202:

[0054] Step 101 specifically includes:

[0055] Step 201: Create an index code based on the administrative boundary data.

[0056] Step 202: According to the index code, the study area is partitioned into a number of regions of interest; one index code corresponds to one region of interest; the attributes of the region of interest include the Chinese and English names of the country, province, city, the unique administrative code and the administrative boundary level; the administrative boundary levels include national, provincial and municipal levels.

[0057] In an exemplary embodiment, step 101 can also be divided according to the longitude and latitude of the study area, specifically including: based on the longitude and longitude range, dividing the longitude and latitude of the study area into several areas of interest.

[0058] In another exemplary embodiment of the present application, in order to simultaneously perform visual query on multiple regions of interest, before the above step 104, the method may further include the following steps.

[0059] When visually querying more than two regions of interest, metadata information in the two or more regions of interest is jointly calculated to generate joint metadata information.

[0060] Furthermore, when visually querying two regions of interest, the combined metadata information is:

[0061] C=A×countA+B×countB / (countA+countB);

[0062] Among them, A is the metadata information of the first study area of ​​interest, countA is the number of valid pixels in the first study area of ​​interest; B is the metadata information of the second study area of ​​interest, countB is the number of valid pixels in the second study area of ​​interest; C is the metadata information after combination.

[0063] In another exemplary embodiment of the present application, in order to improve user experience, before the above step 104, the method may further include the following steps to improve method performance.

[0064] A data compression algorithm is used to compress the long-time series remote sensing image data, and data slicing is performed on the compressed remote sensing image data.

[0065] The browser cache and server cache mechanism are used to cache the remote sensing image data after data slicing.

[0066] Asynchronous loading technology is used to load the remote sensing image data after slicing the cached data in the background.

[0067] The MODIS vegetation remote sensing image data from 2000 to 2023 is used as the test data set. The data spatial resolution is 250m. The HDF file of a single block of data is about 90-300M in size. The entire China region is used as a research demonstration area. Based on this, the system design is carried out. The above-mentioned long-term series remote sensing image data processing method is used to process the relevant data, and a remote sensing image data analysis platform is constructed. The platform includes a data storage module, a data processing module, and a visualization module. The specific solution design is as follows:

[0068] 1. Data storage module.

[0069] This application is based on a distributed file system for data storage, with the goal of supporting the storage and processing of large-scale data. This means that the physical storage resources managed by the file system are not necessarily directly connected to the local node, but are connected to the node (i.e., any computer) through a computer network; or a complete hierarchical file system formed by combining several different logical disk partitions or volumes.

[0070] In this way, a distributed file system is built, multiple servers are connected or multiple hard disks are mounted on one service to achieve storage and access of massive data, thereby providing high reliability and scalability.

[0071] This application provides an efficient, reliable, and scalable data storage solution that combines a distributed file system and cloud storage services to meet the needs of large-scale remote sensing image data storage and management.

[0072] In terms of raw data storage, first, a distributed file system (such as HDFS, GFS) is used to store Moderate-resolution Imaging Spectroradiometer (MODIS) vegetation remote sensing image data; the distributed file system supports large-scale data storage and parallel access, providing high reliability and data persistence. Then, through data segmentation and copy mechanisms, the security and availability of the data are ensured; for data that has been pre-processed (stitching, projection conversion, cropping, format conversion), cloud storage services (such as AWS S3, Azure Blob Storage) are used for storage; the cloud storage service provides elastic expansion capabilities and low-cost storage, supports data lifecycle management and access control; through cloud storage services, data can be stored and accessed on demand, reducing storage costs. Among them, in the field of data storage, the copy mechanism (Replication) is an important data management strategy, which is mainly used to improve the availability, reliability, and scalability of data, that is, to store another copy somewhere else. This application adopts the synchronous update data mode.

[0073] In order to achieve structured data management, a data table structure based on MySQL was designed. By creating a data index table, metadata information such as the star mark, payload, file name, file path, file size, acquisition date, spatial resolution, temporal resolution, and cloud coverage of vegetation remote sensing image data is stored.

[0074] By establishing a remote sensing image data storage system, cloud storage is selected for data files. The data also needs to be structured and managed, and MySQL database tables are established. These storage information is the corresponding metadata information, that is, the data index table, to achieve efficient data storage and data search access.

[0075] Create indexes for key fields to improve data retrieval efficiency; to improve the efficiency of database table indexing, turn off fuzzy queries when searching for queries. Design a metadata management mechanism to store and manage sensor information, processing parameters and other related information of remote sensing image data. Use encryption and access control mechanisms to protect the security and privacy of remote sensing image data. By adopting the above data storage solution, build an efficient, reliable and scalable remote sensing image data storage system. The system can meet the needs of large-scale data storage and management, support efficient data retrieval and analysis, and provide a solid data foundation for the application of remote sensing image data.

[0076] 2. Data processing module. The processing results of this module need to be stored in the above-mentioned data storage module.

[0077] MODIS250m vegetation remote sensing image data is medium-to-high resolution data with a large amount of data. In order to achieve dynamic and long-term combined analysis, this application uses a partitioned and blocked processing method to preprocess the data, extract the corresponding indicators and perform structured metadata storage, such as maximum, minimum, average, standard deviation, and the number of samples involved in the indicator calculation. These indicators can be freely expanded and combined for analysis in the subsequent WEB visualization interface.

[0078] Among them, the zoning and blocking method in this application is to divide the scope into national, provincial and municipal levels based on administrative boundary data; the blocking is carried out in a fixed longitude and latitude range.

[0079] The area can be divided into multiple areas of interest by using the block method alone, or by using a fixed longitude and latitude range alone. The area can also be divided into multiple areas of interest by using the block method at the same time. First, the administrative boundary data is used for zoning, and then the longitude and latitude of each area of ​​interest are divided into blocks to generate smaller areas of interest.

[0080] The specific data processing process is as follows:

[0081] Step 401: Clean the collected global and national vector data, establish a unique index code for each administrative boundary data in each vector file, organize its attributes, including the Chinese and English names of the country, province, and city, the unique administrative code (100010), and the administrative boundary level (national, provincial, and municipal), and store this information in the database. At the same time, store the cleaned vector file as a local file and publish it in the Geo Server service to facilitate the use of the front-end interface in the subsequent visualization service. At the same time, generate a pyramid file from the raster data, save it as a local file, and store the data in the database of the first module to facilitate the subsequent front-end display.

[0082] Among them, the GeoServer service is a J2EE implementation of the OpenGIS Web server specification. GeoServer can be used to easily publish map data, allowing users to update, delete, and insert feature data. GeoServer can easily and quickly share spatial geographic information among users.

[0083] Step 402: Extracting data indicators of raster data such as Figure 2 As shown in the figure, the raster data is the vegetation remote sensing image data. First, the raster data and vector data are read in a standardized manner, the administrative boundaries in each vector file are traversed, the raster data is extracted according to the administrative boundary range, the extracted data is cleaned, and the number of pixels, the maximum value, minimum value, and average value of the area of ​​interest are obtained, and the standard deviation and other indicators are calculated.

[0084] Step 403: This step is to store the data in step 402. In order to improve query efficiency and facilitate data expansion, the data is stored in separate tables according to different levels of vector files.

[0085] Through the above data preprocessing, the historical raster data is extracted and stored in the database table by partition, and structured data is obtained to provide platform services for subsequent long-term remote sensing image data. The above processes are all based on the flow scheduling method and are driven by data. When new raster data enters, the flow scheduling is triggered and the subsequent process is automatically completed and stored. The same is true for new vector data.

[0086] The regional combination is calculated as follows:

[0087] When more than two study areas are selected, the data of the two study areas will be jointly calculated to obtain new monthly data for display. The calculation method is as follows:

[0088] C=A×countA+B×countB / (countA+countB)(1)

[0089] Among them, A is the metadata information of the first study area of ​​interest, countA is the number of valid pixels in the first study area of ​​interest; B is the metadata information of the second study area of ​​interest, countB is the number of valid pixels in the second study area of ​​interest; C is the metadata information after combination.

[0090] The above steps 401-403 extract the value of raster data based on administrative boundary data. For example, taking the vector data of China's provincial boundaries as an example, China has 34 provinces and MODIS NDVI data for a total of 22 years. According to steps 401-403, the NDVI values ​​corresponding to the 34 provinces in China are extracted and stored in the database. When selecting and analyzing on the interface, the user clicks on Henan Province, and the 22-year historical data of Henan Province will be queried from the database for year-on-year, month-on-month, historical statistics, and deviation statistics. This is the statistics of a single region, and the combined statistics means that the user can select Henan, and then select Hebei, Shanxi, and Shandong for a total of 4 provinces, which is a combined analysis. The analysis formula is shown in formula (1); when querying 2-n areas of interest, all of them can be accumulated, and n is an integer greater than 0. This part of the accumulation algorithm is completed in the backend of the service, and steps 401-403 only provide data preprocessing. )

[0091] 3. Visualization module.

[0092] The front end of this visualization module adopts the VUE.js framework, combined with the OpenLayers map framework and Geoserver service, to realize the visualization and interactive functions of remote sensing image data and provide tile map services for remote sensing image data.

[0093] In order to improve the efficiency of front-end interaction, the spatial data format uses GeoJSON's compression format BPF, which compresses vector data 10 times, greatly improving the loading and interaction of front-end vector data. The back-end uses server-side languages ​​such as Node.js and Python to provide storage, retrieval and processing services for remote sensing image data in the form of microservices. Its main functional modules are as follows:

[0094] 1) Remote sensing image visualization, based on the improved map slicing service of openlayers, realizes online rendering of raster data and supports loading HDF, NetCDF, GeoTIFF and other formats.

[0095] 2) Spatial query function, which supports spatial query methods such as click, and conducts statistics and analysis of remote sensing image data information and long time series in specific areas.

[0096] 3) Statistical analysis: Provides historical year-on-year, month-on-month, linear trend analysis, historical cumulative statistics, mutation detection, deviation statistics and other analysis functions.

[0097] Interaction Design:

[0098] Intuitive User Interface: The user interface is simple and intuitively designed to be easy for users to operate and understand.

[0099] Interactive Legend: Provides an interactive legend that allows users to dynamically adjust visualization parameters.

[0100] Map navigation: Provides map navigation functions such as pan, zoom, and full screen to facilitate users to browse data.

[0101] Information pop-up window: When you click a map feature, related attribute information and statistical data will pop up.

[0102] In order to improve user experience, performance is improved in the following aspects:

[0103] Data compression: Use appropriate data compression algorithms (such as LZW, DEFLATE) to reduce the amount of data transmitted.

[0104] Data slicing: Cut large remote sensing images into small tiles to achieve efficient data loading and display.

[0105] Data caching: Use browser caching and server-side caching mechanisms to reduce duplicate data requests.

[0106] Asynchronous loading: Use asynchronous loading technology to load data in the background to improve page response speed

[0107] The specific steps of visualization are as follows:

[0108] Based on the Vue.js framework, a visualization platform front-end framework for the remote sensing image data analysis platform is created. The visualization interface of the remote sensing image data analysis platform is divided into three major areas: data product selection area, spatial display area, and statistical analysis result display area.

[0109] Among them, the data product selection area is used to select areas of interest; the space display area supports users to save browsing history records. Clicking Open will reopen a new tab to view the history records. This function can help users compare the historical changes of multiple areas; the data in the statistical result display area supports downloading.

[0110] The user interaction process is as follows:

[0111] Step 1: The user selects a dataset product, such as MODIS, in the dataset selection item in the data selection module; selects NDVI in the product item, selects 2023 in the cut-off year (the cut-off year indicates the final year of the historical statistics of the data. For example, if the user wants to see the spatial resolution map of 2023 and the results from 2000 to 2023 are counted, select 2023), and selects 031 in the month item (this item is based on the day of the year: the first day of the year, so January is selected here). After selecting this part, the NDVI product distribution map of the MODIS load in January 2023 will be obtained in the spatial display area.

[0112] Step 2: Select the image map as the base map in the layer, select the Chinese provincial boundaries for administrative divisions, and select None for the mask item. After this step, the Chinese provincial boundaries will be loaded in the spatial display area. If agricultural flooding film is selected, the agricultural mask will be loaded.

[0113] In the third step, the user selects a province in China, such as Henan Province, and a pop-up window will be displayed showing the maximum, minimum and average NDVI values ​​of the region in January. At the same time, the statistical analysis area will show the historical analysis and comparison results of Henan Province, such as year-on-year, month-on-month, cumulative, long-term series and mutation detection, and the area percentage statistics of the NDVI values ​​of the region will also be performed.

[0114] In order to improve the above user experience, this application supports the user history preservation function and vector data compression release. At the same time, in order to improve the request response data, asynchronous addition, data caching, remote sensing image data pyramid and other means are adopted.

[0115] The following is the specific analysis process to supplement the third step:

[0116] According to the above, the vegetation remote sensing image data of the past 20 years is divided into blocks according to the administrative boundaries of China's provinces to generate several areas of interest. Then the data of each area of ​​interest is statistically analyzed, and the maximum value, minimum value, average value, number of samples, mean square error and other indicators are extracted and stored in the MySQL database. The structure of the data is as follows: Figure 3 shown.

[0117] The extracted indicators include the maximum, minimum, average and number of samples for each year and month. When paying attention to the historical trend of vegetation changes in a region, we often pay attention to year-on-year, month-on-month, cumulative, anomaly, historical changes, etc.

[0118] The following will explain one by one:

[0119] 1) Year-on-year (changes in a certain area in the same month): Based on the area ID, star, vector level, instrument, and month as search conditions, retrieve the corresponding data in the database, draw a bar chart, calculate the change trend of the reorganized data over time, as well as the correlation and historical mean, and obtain the year-on-year results. Figure 4 shown.

[0120] 2) Year-on-year (adjacent time, this experiment mainly shows the change trend in one year, you can select different years to view the year-on-year situation of different years): the search conditions are as follows, and the obtained data is plotted into a line graph, such as Figure 5 shown.

[0121] 3) Accumulation (accumulation is to calculate the cumulative changes in data volume over time): for example, starting from January, observe when the cumulative vegetation data stops increasing or the growth rate slows down. The search conditions for this part remain the same as above, taking the January data as a starting calculation value, or providing a threshold value. If it is greater than this threshold, calculation is performed, and if it is less than this threshold, no calculation is performed. For example, taking the starting point as 10, when the data in January is less than 10, the cumulative value is 0, and the value in February is 20, so the cumulative value in February is 20, until September, the cumulative value is 180, and when the value in October is 9, then the cumulative value in October is 180, and 9 is not added to the accumulation. The average value will also be accumulated in this way. In this way, the cumulative change result graph is obtained, such as Figure 6 shown.

[0122] 4) Long time series and anomalies (This will show more than 20 years of monthly data, line chart, anomaly refers to the comparison of the value of the month with the average of many years of history, positive value means higher than the average, negative value means lower than the average.) The search conditions for data remain the same as above. The historical average is to average the monthly data of more than 20 years, for example, the average of 20 January data. According to this rule, the long time series and anomaly result chart are obtained, such as Figure 7 shown.

[0123] 5) Mutation detection: Mutation detection is to check the changing trend of data changes. This is the same data source as the year-on-year data, but the statistical analysis method is inconsistent.

[0124] This application provides an efficient, flexible and easy-to-use remote sensing image data analysis platform. By adopting the strategy of partition preprocessing and structured storage, this application can significantly improve data processing efficiency and reduce the workload of users. By providing vector data of different levels at the global and provincial levels, and supporting the combined statistical analysis of multiple research areas, this application can meet the research needs of users in different regions and improve the flexibility of data analysis.

[0125] In addition, this application adopts the design concept of data-driven services, supports the expansion and integration of new data sources, and improves the scalability of the system. By providing an intuitive and easy-to-use visual interface, this application lowers the user's usage threshold, allowing users to perform data analysis and visualization without professional knowledge and programming skills.

[0126] Based on the same inventive concept, the embodiment of the present application also provides a long-time series remote sensing image data processing system for implementing the long-time series remote sensing image data processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more long-time series remote sensing image data processing system embodiments provided below can refer to the limitations of the long-time series remote sensing image data processing method above, and will not be repeated here.

[0127] In an exemplary embodiment, a long-time series remote sensing image data processing system is provided, comprising:

[0128] The region division module is used to divide the study area into several regions of interest based on vector data; the vector data includes administrative boundary data and latitude and longitude ranges.

[0129] The raster data extraction module is used to standardize the long-term remote sensing image data in each area of ​​interest, extract the raster data of the long-term remote sensing image data, and store it in a database; the raster data includes a regional maximum value index, a regional minimum value index, a regional average value index and a regional standard deviation index.

[0130] The statistical analysis module is used to statistically analyze the raster data and generate remote sensing image data analysis results; the statistical analysis includes historical year-on-year, month-on-month, linear trend analysis, historical cumulative statistics, mutation detection and anomaly statistics.

[0131] A visualization module is used to visualize the metadata information of the long-term remote sensing image data in each of the areas of interest and the analysis results of the remote sensing image data based on the database; the metadata information includes star payload, file name, file path, file size, acquisition date, spatial resolution, temporal resolution and cloud coverage.

[0132] This application adopts an efficient data processing and storage strategy. By preprocessing long-term remote sensing data and storing corresponding indicators in a structured manner, it reduces the steps of repeatedly processing remote sensing image data and greatly reduces the workload of users. This method not only improves data processing efficiency, but also lays a solid foundation for subsequent data analysis and visualization.

[0133] Taking into account the uncertainty of the study area, this application provides vector data of different levels at the global and national provincial levels, extracts and stores indicators for each sub-region. This partition preprocessing method enables the system to flexibly support the combined statistical analysis of multiple study areas. Users can select different areas for data query and analysis according to their research needs, without the need to repeatedly process the original remote sensing image data, which greatly improves data processing efficiency.

[0134] In addition, this application adopts the design concept of data-driven services and supports the expansion of new data. This flexible expansion mechanism enables the system to meet the analysis requests of different users and supports real-time online expansion of user-defined research areas. Through structured storage and efficient data query, users can quickly obtain the required data and conduct further analysis and visualization.

[0135] In order to provide a better user experience, this application also designs an intuitive visualization interface. Users can query, analyze and visualize data through an interactive interface without writing complex codes or using professional geographic information system software. The design of the visualization interface takes into account the user's usage habits and needs, and provides an intuitive and easy-to-use operation method, allowing users to quickly get started and obtain the required information.

[0136] In summary, this application provides users with an efficient, flexible and easy-to-use remote sensing data analysis platform by adopting technical means such as partition preprocessing, structured storage, data-driven services and visual interfaces. This platform can meet the diverse needs of different users, improve data processing efficiency, and provide powerful tools and support for the application and decision support of remote sensing data.

[0137] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as long-term series remote sensing image data, metadata information of long-term series remote sensing image data, and analysis results of the remote sensing image data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a long-term series remote sensing image data processing method is implemented.

[0138] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0139] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0140] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0142] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0143] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0144] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0145] The present application uses specific examples to illustrate the principles and implementation methods of the present application. The above examples are only used to help understand the method and core ideas of the present application. At the same time, for those skilled in the art, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A method for processing long-term remote sensing image data, characterized in that: The long-term remote sensing image data processing method comprises: Based on vector data, the study area is divided into several areas of interest; the vector data includes administrative boundary data and latitude and longitude ranges; Standardize the long-time series remote sensing image data in each region of interest, extract the raster data of the long-time series remote sensing image data, and store them in a database; the raster data includes the maximum value index, minimum value index, average value index and standard deviation index of the remote sensing image data in the region of interest; Statistically analyzing the raster data to generate remote sensing image data analysis results; the statistical analysis includes historical year-on-year, month-on-month, linear trend analysis, historical cumulative statistics, mutation detection, and anomaly statistics; Based on the database, the metadata information of the long-term series remote sensing image data in each of the regions of interest and the analysis results of the remote sensing image data are visualized; the metadata information includes the star payload, file name, file path, file size, acquisition date, spatial resolution, temporal resolution and cloud coverage.

2. The long-time series remote sensing image data processing method according to claim 1, characterized in that: Based on the vector data, the study area is divided into several areas of interest, including: Establishing index codes according to the administrative boundary data; According to the index code, the study area is partitioned into several areas of interest; one index code corresponds to one area of ​​interest; the attributes of the area of ​​interest include the Chinese and English names of the country, province, city, the unique administrative code and the administrative boundary level; the administrative boundary levels include national, provincial and municipal levels.

3. The long-time series remote sensing image data processing method according to any one of claims 1 to 2, characterized in that: Based on the vector data, the study area is divided into several areas of interest, including: Based on the longitude and latitude range, the longitude and latitude of the study area are divided into several areas of interest.

4. The long-time series remote sensing image data processing method according to claim 3, characterized in that: Based on the database, the metadata information of the long-term remote sensing image data and the analysis results of the remote sensing image data in each of the regions of interest are visualized, and the method also includes: When visually querying more than two regions of interest, metadata information in the two or more regions of interest is jointly calculated to generate joint metadata information.

5. The long-time series remote sensing image data processing method according to claim 4, characterized in that: When visually querying two regions of interest, the metadata information after union is: C=A×countA+B×countB / (countA+countB); Among them, A is the metadata information of the first study area of ​​interest, countA is the number of valid pixels in the first study area of ​​interest; B is the metadata information of the second study area of ​​interest, countB is the number of valid pixels in the second study area of ​​interest; C is the metadata information after combination.

6. The long-time series remote sensing image data processing method according to claim 1, characterized in that: Based on the database, the metadata information of the long-term remote sensing image data and the analysis results of the remote sensing image data in each of the regions of interest are visualized, and the method also includes: Using a data compression algorithm to compress the long-time series remote sensing image data, and slicing the compressed remote sensing image data; Use browser cache and server cache mechanisms to cache remote sensing image data after data slicing; Asynchronous loading technology is used to load the remote sensing image data after slicing the cached data in the background.

7. A long-time series remote sensing image data processing system, characterized in that: include: A region division module is used to divide the study area into a number of regions of interest based on vector data; the vector data includes administrative boundary data and latitude and longitude ranges; A raster data extraction module is used to perform standardization processing on the long-time series remote sensing image data in each area of ​​interest, extract the raster data of the long-time series remote sensing image data, and store it in a database; the raster data includes a regional maximum value index, a regional minimum value index, a regional average value index, and a regional standard deviation index; A statistical analysis module, used for statistically analyzing the raster data and generating remote sensing image data analysis results; The statistical analysis includes historical year-on-year, month-on-month, linear trend analysis, historical cumulative statistics, mutation detection and deviation statistics; A visualization module is used to visualize the metadata information of the long-term remote sensing image data in each of the areas of interest and the analysis results of the remote sensing image data based on the database; the metadata information includes star payload, file name, file path, file size, acquisition date, spatial resolution, temporal resolution and cloud coverage.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the long-term remote sensing image data processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the long-time series remote sensing image data processing method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the long-time series remote sensing image data processing method described in any one of claims 1 to 6 is implemented.

Images