Automatic screening method and system for regional coverage data set

Abstract

The invention discloses an automatic screening method and system for a regional coverage data set, relates to the technical field of automatic image processing, optimizes a remote sensing data set screening process of large-region coverage, and improves screening efficiency. The method comprises the following steps: classifying massive single-scene vector files in a vector range of a target area according to quality grade elements, and performing the following processing on each quality data set to complete screening of an area coverage data set: classifying into a plurality of imaging task data sets according to product ID (Identity) elements; obtaining an effective coverage area of each imaging task data set according to the target area vector range and the cloud cover element; the imaging task data set with the largest effective coverage area is input into a region coverage data set; and correcting the vulnerability vector range, and inputting the imaging task data set into the area coverage data set according to the corrected vulnerability vector range. The method can be applied to the fields of electronic maps, navigation and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic image processing, and in particular to the technical field of screening remote sensing images. Background Art

[0002] In recent years, the increasing number of satellites and breakthroughs in ultra-high-speed satellite-borne laser data transmission technology have led to exponential growth in remote sensing data volumes. A single satellite can generate terabytes of data per day, and global datasets can reach petabytes. Faced with the increasingly complex task of producing high-temporal and spatial resolution remote sensing data, it is crucial to quickly and accurately select the optimal image combinations from this vast amount of remote sensing data while ensuring complete coverage of regional targets.

[0003] Currently, there are two main methods for selecting the best image combination from massive remote sensing data products: The first method is manual screening. This method has the following problems: First, it cannot guarantee data overlap. Some data may have gaps that are difficult for the human eye to detect, resulting in incomplete coverage of the target area. Data overlap can also be excessive, increasing processing time and difficulty. Second, manual screening makes it difficult to ensure apparent consistency and minimize cloud cover, resulting in suboptimal screening results. Third, manual screening is time-consuming and labor-intensive, seriously impacting the timeliness of data production.

[0004] The second method relies on the data retrieval service provided by the remote sensing platform. Users retrieve data by setting the target area, imaging time range, quality level, and cloud cover threshold. This screening method has the following problems: On the one hand, if the conditions are set too broadly, the screening results will contain multiple layers of duplication and high data redundancy; on the other hand, if the conditions are set too strictly, the screening results may not fully cover the target area. Finally, manual selection is still required to obtain the optimal remote sensing data, that is, it still relies on manual screening.

[0005] In summary, the screening methods in the prior art generally rely on manual screening, which has problems such as low efficiency and inability to achieve optimal screening, and cannot be effectively solved. Summary of the Invention

[0006] This invention optimizes the screening process for remote sensing datasets covering large areas and uses automated screening to improve screening efficiency without manual intervention. It has a high degree of automation, strong reliability, high timeliness, and low cost. The invention provides the following solutions: Solution 1: A method for automatically screening regional coverage datasets, comprising the following steps: Step S1, obtaining a large number of single-scene vector files within the vector range of the target area based on remote sensing data, wherein the single-scene vector files include quality grade elements, product ID elements, and cloud cover elements; Step S2, classifying the single scene vector file into a plurality of quality data sets according to the quality grade elements in the single scene vector file, and performing the following processing steps S3-S7 on each quality data set with the quality grade elements as priority; Step S3, classifying the quality dataset into a plurality of imaging task datasets according to the product ID element in the single scene vector file; Step S4, obtaining the effective coverage area of ​​each imaging task data set according to the target area vector range and the cloud cover element in the single scene vector file; Step S5, sorting all imaging task data sets according to the effective coverage areas of the respective imaging task data sets, and entering the imaging task data set with the largest effective coverage area into the regional coverage data set; Step S6, obtaining a vulnerability vector range according to the imaging task dataset of the area coverage dataset and the target area vector range, and correcting the vulnerability vector range to obtain a corrected vulnerability vector range; Step S7, according to the corrected vulnerability vector range, recording the imaging task dataset within the corrected vulnerability vector range into the regional coverage dataset; Step S8: All single-scene vector files in the imaging task data in the area coverage dataset are used as screening results, wherein each single-scene vector file includes cloud cover elements, coverage area and quality level elements, thereby completing the screening of the area coverage dataset.

[0007] Furthermore, in one embodiment of the present invention, the vulnerability vector range is corrected in step S6, and the specific correction process is as follows: Step S61, expanding the vulnerability vector range by a fixed length as a preliminary corrected vulnerability vector range; Step S62, obtaining a covered vector range in the regional vector range according to the vulnerability vector range, the imaging task dataset in the regional coverage dataset, and the regional vector range; Step S63, traversing the coverage range of each single-view vector file in the plurality of imaging task datasets that have not been recorded in the regional coverage dataset, and if there is a single-view vector file whose coverage range is included in the covered vector range, recording the imaging task dataset containing the single-view vector file into the regional coverage dataset, determining that the single-view vector file data is redundant data, and deleting the redundant data; Step S64: Recalculate the vulnerability vector range of the area in the regional coverage dataset as the corrected vulnerability vector range based on the imaging task dataset and the target area vector range in the regional coverage dataset. If the coverage range of no single-scene vector file is included in the covered vector range, use the initially corrected vulnerability vector range in step 61 as the corrected vulnerability vector range.

[0008] Solution 2: An automated screening system for regional coverage datasets, including the following modules: Module 1 is used to obtain a large number of single-scene vector files within the vector range of the target area based on remote sensing data, wherein the single-scene vector files include quality grade elements, product ID elements and cloud cover elements; Module 2, for classifying the single scene vector file into a plurality of quality data sets according to the quality grade elements in the single scene vector file, and performing the processing described in the following modules 3 to 7 on each quality data set with the quality grade elements as priority; Module three, for classifying the quality dataset into multiple imaging task datasets according to product ID elements in the single scene vector file; Module 4 is used to obtain the effective coverage area of ​​each imaging task dataset based on the target area vector range and the cloud cover element in the single scene vector file; Module five is used to sort all imaging task datasets according to the effective coverage areas of the respective imaging task datasets, and enter the imaging task dataset with the largest effective coverage area into the regional coverage dataset; Module six is ​​used to obtain a vulnerability vector range based on the imaging task dataset of the area coverage dataset and the target area vector range, and correct the vulnerability vector range to obtain a corrected vulnerability vector range; Module seven, for recording the imaging task dataset within the corrected vulnerability vector range into the regional coverage dataset according to the corrected vulnerability vector range; Module eight is used to use all single-scene vector files in the imaging task data in the regional coverage dataset as screening results, wherein each single-scene vector file includes cloud cover elements, coverage area and quality level elements, to complete the screening of the regional coverage dataset.

[0009] Solution 3: An electronic device according to the present invention comprises a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; Memory for storing computer programs; The processor is configured to implement the steps of any of the above methods when executing the program stored in the memory.

[0010] Solution 4: A computer-readable storage medium according to the present invention stores a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0011] The present invention is an automated screening method for regional coverage datasets, which effectively improves the efficiency of automated screening of remote sensing datasets covering large areas. It does not require human intervention and has a high degree of automation, strong reliability, high timeliness, and low cost. Specific beneficial effects include: 1. The method for automatically screening regional coverage datasets described in the present invention divides a large number of single-scene vector files within the target regional vector range into multiple quality datasets according to quality level factors, thereby ensuring that the data screening results are data of the best quality; in each quality dataset, the data are classified into multiple imaging task datasets according to the product ID elements in the single-scene vector files, thereby improving the temporal consistency of the screening results and being more conducive to the subsequent image processing process; the effective coverage area of ​​each imaging task is calculated in combination with the regional vector range and the cloud cover element, and the imaging task dataset with the largest effective coverage area is entered into the regional coverage dataset; according to the corrected vulnerability vector range, the imaging task dataset within the corrected vulnerability vector range is entered into the regional coverage dataset to complete the screening of the regional coverage dataset, thereby achieving effective coverage of the best quality within the target regional range. The present invention effectively improves the efficiency of automated screening of remote sensing datasets covering large areas, does not require manual participation, and has a high degree of automation, strong reliability, high timeliness and low cost.

[0012] 2. The present invention discloses an automated screening method for regional coverage datasets. The present invention corrects the range of the vulnerability vector to ensure overlap between scenes. By correcting the vulnerability range, the present invention screens the effective coverage range of each scene and deletes redundant scenes, thereby minimizing the number of scenes and improving the efficiency of automated screening.

[0013] 3. The automated screening method for regional coverage datasets described in the present invention was tested using Jilin-1 satellite data products. The test results showed that the target area could be fully covered using 33 imaging missions, and the number of scenes used was optimized from 7447 to 1436, with the number of scenes used being optimized to 19.28%. Among them, Category A products included 1334 scenes, and Category B products included 102 scenes. Cloud cover was used to calculate effective coverage, and the cloud cover ratio in the target area was approximately 0.23%.

[0014] The method for automatically screening regional coverage data sets described in the present invention can be applied to fields such as electronic maps and navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 1 is a flow chart of the method for automatically screening regional coverage datasets according to the first embodiment.

[0016] Figure 2 It is a vector diagram of the target area described in the second embodiment.

[0017] Figure 3 This is a schematic diagram of the coverage data set of the target area described in the second embodiment.

[0018] Figure 4 This is a schematic diagram of the screening results of the target area described in the second embodiment based on the imaging task dimension.

[0019] Figure 5 This is a schematic diagram of the storage result of the first imaging task of the target area described in the second embodiment.

[0020] Figure 6 This is a schematic diagram of the storage results of the vulnerability area imaging task described in Implementation Method 2.

[0021] Figure 7 Schematic diagram of the automated screening results of the target area described in the second embodiment. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe various embodiments of the present invention in conjunction with the accompanying drawings. The embodiments described with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be understood as limiting the present invention.

[0023] Implementation method 1: This implementation method describes an automated screening method for a regional coverage dataset, such as Figure 1 As shown, the following steps are included: Step S1, obtaining a large number of single-scene vector files within the vector range of the target area based on remote sensing data, wherein the single-scene vector files include quality grade elements, product ID elements, and cloud cover elements; Step S2, classifying the single scene vector file into a plurality of quality data sets according to the quality grade elements in the single scene vector file, and performing the following processing steps S3-S7 on each quality data set with the quality grade elements as priority; Step S3, classifying the quality dataset into a plurality of imaging task datasets according to the product ID element in the single scene vector file; Step S4, obtaining the effective coverage area of ​​each imaging task data set according to the target area vector range and the cloud cover element in the single scene vector file; Step S5, sorting all imaging task data sets according to the effective coverage areas of the respective imaging task data sets, and entering the imaging task data set with the largest effective coverage area into the regional coverage data set; Step S6, obtaining a vulnerability vector range according to the imaging task dataset of the area coverage dataset and the target area vector range, and correcting the vulnerability vector range to obtain a corrected vulnerability vector range; Step S7, according to the corrected vulnerability vector range, recording the imaging task dataset within the corrected vulnerability vector range into the regional coverage dataset; Step S8: All single-scene vector files in the imaging task data in the area coverage dataset are used as screening results, wherein each single-scene vector file includes cloud cover elements, coverage area and quality level elements, thereby completing the screening of the area coverage dataset.

[0024] In this embodiment, the single scene vector file in step S1 preferably includes data products that meet user requirements within the vector range, including but not limited to attribute information of the data products, such as cloud cover elements, single scene area elements, etc.

[0025] In this embodiment, step S4 specifically involves obtaining the effective coverage area of ​​each imaging task dataset based on the regional vector range and the cloud cover element in the single-scene vector file, preferably through the open source GDAL library function.

[0026] In this embodiment, step S6 specifically includes performing an intersection operation on the imaging task dataset vector and the target area vector of the input area coverage dataset based on the imaging task dataset and the target area vector range to obtain an intersection vector; performing an intersection operation on the intersection vector and the target area vector to obtain a vulnerability vector range, and correcting the vulnerability vector range to obtain a corrected vulnerability vector range; The method of this embodiment is an automatic screening method for regional coverage datasets, which divides a large number of single-scene vector files within the target area vector range into multiple quality datasets according to quality level factors, ensuring that the data screening results are the best quality data; in each quality dataset, it is classified into multiple imaging task datasets according to the product ID elements in the single-scene vector files, thereby improving the temporal consistency of the screening results and being more conducive to the subsequent image processing process; the effective coverage area of ​​each imaging task is calculated in combination with the regional vector range and the cloud cover element, and the imaging task dataset with the largest effective coverage area is entered into the regional coverage dataset; according to the corrected vulnerability vector range, the imaging task dataset within the corrected vulnerability vector range is entered into the regional coverage dataset to complete the screening of the regional coverage dataset, and achieve the best quality effective coverage within the target area. The present invention effectively improves the efficiency of automatic screening of remote sensing datasets covering large areas, does not require manual participation, has a high degree of automation, strong reliability, high timeliness and low cost.

[0027] Implementation 2: This implementation further limits the method for automatically screening regional coverage datasets described in Implementation 1. In this implementation, the vulnerability vector range described in step S6 is corrected. The specific correction process is as follows: Step S61, expanding the vulnerability vector range by a fixed length as a preliminary corrected vulnerability vector range; Step S62, obtaining a covered vector range in the regional vector range according to the vulnerability vector range, the imaging task dataset in the regional coverage dataset, and the regional vector range; Step S63, traversing the coverage range of each single-view vector file in the plurality of imaging task datasets that have not been recorded in the regional coverage dataset, and if there is a single-view vector file whose coverage range is included in the covered vector range, recording the imaging task dataset containing the single-view vector file into the regional coverage dataset, determining that the single-view vector file data is redundant data, and deleting the redundant data; Step S64: Recalculate the vulnerability vector range of the area in the regional coverage dataset as the corrected vulnerability vector range based on the imaging task dataset and the target area vector range in the regional coverage dataset. If the coverage range of no single-scene vector file is included in the covered vector range, use the initially corrected vulnerability vector range in step 61 as the corrected vulnerability vector range.

[0028] In this embodiment, the fixed length described in step S61 is preferably 200 meters.

[0029] This embodiment further limits step S6 and explains the scheme for step S6. Step 61 of this method, described as expanding the vulnerability vector range by a fixed length to form a new vulnerability vector range, aims to increase overlap between scene data, preventing low overlap between scenes, which could affect subsequent data production. Furthermore, excessive overlap can also increase redundant data, so setting the length too high is not recommended. Furthermore, this embodiment corrects the vulnerability vector range to ensure overlap between scenes, enabling effective coverage screening, removing redundant scenes, and minimizing the number of scenes.

[0030] This embodiment provides an example, and the specific steps are as follows: S100 selects the target area. The vector diagram of the target area is as follows: Figure 2 As shown in the figure, the colors represent the vector diagram of the entire area; the cloud cover ratio is set to [0,100%], the quality level is set to [A,B,C,D], and the imaging time range is from March 1, 2025 to April 30, 2025. According to the above conditions, a total of 122 imaging times and 7447 scene data products of Jilin-1 satellite data products are searched, and a single scene vector file is generated. The vector file contains product ID elements, cloud cover elements and quality level elements. The coverage dataset diagram of the target area is shown in the figure. Figure 3 As shown, Figure 3 The red box in the middle is the vector of all images covering the vector area. There are many images and the overlap rate between images is extremely high; S200 divides all single-scene data into four quality data sets based on the quality level elements in the single-scene vector file; with the quality level elements as the priority, the following steps S300-S700 are performed in each quality data set in sequence until the regional vector range is fully covered; To ensure the apparent consistency of coverage data in a large area, S300 should give priority to the imaging task with the largest single imaging coverage area. Therefore, all single-view data in each quality data set are classified as imaging tasks based on the product ID element in the single-view vector file, such as Figure 4 As shown in the figure, the boxes represent the vectors of all images, and boxes of different colors represent different imaging tasks. Due to the large number of imaging tasks in this area, color cannot be used as a full distinction, and is only for illustration; S400 obtains the effective coverage area of ​​each imaging task dataset using the open source GDAL library function based on the target area vector range and the cloud cover elements in the single scene vector file; S500 sorts all imaging tasks according to their effective coverage areas, and enters the imaging task dataset with the largest effective coverage area into the regional coverage dataset; in the target area, the imaging task with the largest effective coverage area, i.e., the first imaging task, into the database. Figure 5 As shown, the green box represents the valid coverage image vector for the first imaging task; S600: obtaining a vulnerability vector range according to the imaging task dataset of the area coverage dataset and the target area vector range, and correcting the vulnerability vector range to obtain a corrected vulnerability vector range; The specific correction process of correcting the vulnerability vector range is as follows: Step 601: Expand the vulnerability vector range by a fixed length as a preliminary corrected vulnerability vector range; The fixed length is 200 meters; Step 602: Obtain a covered vector range in the regional vector range according to the vulnerability vector range, the imaging task dataset in the regional coverage dataset, and the regional vector range; Step 603: traverse the coverage range of each single-view vector file in the plurality of imaging task datasets that are not recorded in the regional coverage dataset. If the coverage range of a single-view vector file is included in the covered vector range, record the imaging task dataset containing the single-view vector file into the regional coverage dataset, determine that the single-view vector file data is redundant, and delete the redundant data. In step 604, the vulnerability vector range of the area in the regional coverage dataset is recalculated as the corrected vulnerability vector range based on the imaging task dataset and the target area vector range in the regional coverage dataset. If the coverage range of no single-scene vector file is included in the covered vector range, the initially corrected vulnerability vector range described in step 61 is used as the corrected vulnerability vector range.

[0031] S700 records the imaging task data set within the corrected vulnerability vector range into the regional coverage data set according to the corrected vulnerability vector range. The schematic diagram of the vulnerability area imaging task storage result is as follows: Figure 6 As shown, the red box is the effective coverage image vector of the current optimal imaging task screened based on the vulnerability area; S800 uses all single-view vector files in the imaging task data in the regional coverage dataset as screening results. Each single-view vector file includes cloud cover elements, coverage area and quality level elements, completing the screening of the regional coverage dataset. The schematic diagram of the automatic screening results of the target area is shown in FIG. Figure 7 As shown, the green box represents the effective coverage image vector after screening based on this embodiment.

[0032] According to the above process, the target area can be fully covered with 33 imaging missions, and the number of scenes used is optimized from 7447 to 1436 scenes, and the number of scenes used is optimized to 19.28%; among them, there are 1334 scenes for Class A products and 102 scenes for Class B products; the cloud cover factor is used to calculate the effective coverage, and the cloud cover ratio in the target area is about 0.23%.

Claims

1. A method for automatically screening regional coverage datasets, characterized in that: The following steps are involved: Step S1, obtaining a large number of single-scene vector files within the vector range of the target area based on remote sensing data, wherein the single-scene vector files include quality grade elements, product ID elements, and cloud cover elements; Step S2, classifying the single scene vector file into a plurality of quality data sets according to the quality grade elements in the single scene vector file, and performing the following processing steps S3-S7 on each quality data set with the quality grade elements as priority; Step S3, classifying the quality dataset into a plurality of imaging task datasets according to the product ID element in the single scene vector file; Step S4, obtaining the effective coverage area of ​​each imaging task data set according to the target area vector range and the cloud cover element in the single scene vector file; Step S5, sorting all imaging task data sets according to the effective coverage areas of the respective imaging task data sets, and entering the imaging task data set with the largest effective coverage area into the regional coverage data set; Step S6, obtaining a vulnerability vector range according to the imaging task dataset of the area coverage dataset and the target area vector range, and correcting the vulnerability vector range to obtain a corrected vulnerability vector range; Step S7, according to the corrected vulnerability vector range, recording the imaging task dataset within the corrected vulnerability vector range into the regional coverage dataset; Step S8: All single-scene vector files in the imaging task data in the area coverage dataset are used as screening results, wherein each single-scene vector file includes cloud cover elements, coverage area and quality level elements, thereby completing the screening of the area coverage dataset.

2. The method for automatically screening regional coverage datasets according to claim 1, characterized in that: The step S6 of correcting the vulnerability vector range is as follows: Step S61, expanding the vulnerability vector range by a fixed length as a preliminary corrected vulnerability vector range; Step S62, obtaining a covered vector range in the regional vector range according to the vulnerability vector range, the imaging task dataset in the regional coverage dataset, and the regional vector range; Step S63, traversing the coverage range of each single-view vector file in the plurality of imaging task datasets that have not been recorded in the regional coverage dataset, and if there is a single-view vector file whose coverage range is included in the covered vector range, recording the imaging task dataset containing the single-view vector file into the regional coverage dataset, determining that the single-view vector file data is redundant data, and deleting the redundant data; Step S64: Recalculate the vulnerability vector range of the area in the regional coverage dataset as the corrected vulnerability vector range based on the imaging task dataset and the target area vector range in the regional coverage dataset. If the coverage range of no single-scene vector file is included in the covered vector range, use the initially corrected vulnerability vector range in step 61 as the corrected vulnerability vector range.

3. An automated screening system for regional coverage datasets, characterized in that: Includes the following modules: Module 1 is used to obtain a large number of single-scene vector files within the vector range of the target area based on remote sensing data, wherein the single-scene vector files include quality grade elements, product ID elements and cloud cover elements; Module 2, for classifying the single scene vector file into a plurality of quality data sets according to the quality grade elements in the single scene vector file, and performing the processing described in the following modules 3 to 7 on each quality data set with the quality grade elements as priority; Module three, for classifying the quality dataset into multiple imaging task datasets according to product ID elements in the single scene vector file; Module 4 is used to obtain the effective coverage area of ​​each imaging task dataset based on the target area vector range and the cloud cover element in the single scene vector file; Module five is used to sort all imaging task datasets according to the effective coverage areas of the respective imaging task datasets, and enter the imaging task dataset with the largest effective coverage area into the regional coverage dataset; Module six is ​​used to obtain a vulnerability vector range based on the imaging task dataset of the area coverage dataset and the target area vector range, and correct the vulnerability vector range to obtain a corrected vulnerability vector range; Module seven, for recording the imaging task dataset within the corrected vulnerability vector range into the regional coverage dataset according to the corrected vulnerability vector range; Module eight is used to use all single-scene vector files in the imaging task data in the regional coverage dataset as screening results, wherein each single-scene vector file includes cloud cover elements, coverage area and quality level elements, to complete the screening of the regional coverage dataset.

4. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to implement the steps of the method according to any one of claims 1 to 2 when executing a program stored in a memory.

5. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Images