Image data directory generation method and device, storage medium and electronic equipment

Abstract

The invention discloses an image data directory generation method and device, a storage medium and electronic equipment. The image data directory generation method provided by the specification comprises the following steps: acquiring remote sensing image data, and storing the remote sensing image data in a shared storage space; determining a target area to which the remote sensing image data belongs, and archiving the remote sensing image to an image database according to the target area; determining image features of the remote sensing image data, and marking the remote sensing image data according to contents contained in the remote sensing image data; determining a knowledge graph of the remote sensing image data according to the image features and the labels; and generating an image data directory according to the remote sensing image data and the knowledge graph.

Description

Technical Field

[0001] The present specification relates to the field of computer technology, and in particular to a method, device, storage medium and electronic device for generating an image data directory. Background Art

[0002] With the development of remote sensing earth observation technology, high-resolution remote sensing images have become diverse, complex and massive. Multi-dimensional, multi-scale and multi-modal image data have shown an explosive growth trend, and the amount of data has rapidly expanded from the Gigabyte (GB) level to the Petabyte (PB) level. Traditional large-capacity remote sensing image data management is based on relational databases and large-space storage disks, which makes it difficult to achieve high efficiency, flexibility and robustness of remote sensing data. In addition, traditional remote sensing data management and analysis technologies are difficult to meet the high-precision, high-timeliness and diversified needs of the big data era.

[0003] Remote sensing image data catalogs organize and classify massive heterogeneous remote sensing data to form an image list with unified format and standardized data, and realize multi-dimensional, comprehensive query and visual display. Traditional remote sensing data catalogs are often a set of ledgers, which usually copy and archive data offline according to the geographical scope of the project. The data management is scattered, the format is inconsistent, the information is incomplete, and it is difficult to support subsequent complex queries.

[0004] Therefore, how to generate an image data catalog that can intelligently and efficiently retrieve map information and knowledge from massive spatiotemporal remote sensing image data is an urgent problem to be solved. Summary of the invention

[0005] The present specification provides a method, device, storage medium and electronic device for generating an image data directory, so as to at least partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions: This specification provides a method for generating an image data directory, including: Acquire remote sensing image data, and store the remote sensing image data in a shared storage space; Determine the target area to which the remote sensing image data belongs, and archive the remote sensing image into an image database according to the target area; Determining image features of the remote sensing image data, and marking the remote sensing image data according to content contained in the remote sensing image data; Determine a knowledge graph of the remote sensing image data according to the image features and the annotations; An image data catalog is generated based on the remote sensing image data and the knowledge graph.

[0007] Optionally, acquiring remote sensing image data and storing the remote sensing image data in a shared storage space specifically includes: Obtain public remote sensing image data through public data services, and obtain proprietary remote sensing image data through private networks; The public remote sensing image data and the proprietary remote sensing image data are determined as remote sensing image data and stored in a common storage space.

[0008] Optionally, determining a target area to which the remote sensing image data belongs, and archiving the remote sensing image into an image database according to the target area specifically includes: Determining the target administrative region to which the image contained in the remote sensing image data belongs; According to the target administrative area, the remote sensing image data is filed into a folder corresponding to the target administrative area in an image database.

[0009] Optionally, archiving the remote sensing image data into a folder corresponding to the target administrative area in an image database specifically includes: Decompressing the original data of the remote sensing image data to obtain raster data, metadata and thumbnail data of the remote sensing image data; The raster data of the remote sensing image data is archived into a folder corresponding to the target administrative area in a first image database, and the metadata and the thumbnail data are archived into a folder corresponding to the target administrative area in a second image database.

[0010] Optionally, archiving the remote sensing image data into a folder corresponding to the target administrative area in an image database specifically includes: According to a preset division rule, the remote sensing image data is divided into blocks to obtain block image data of the remote sensing image data; The block image data of the remote sensing image data are archived into a folder corresponding to the target administrative area in an image database.

[0011] Optionally, before determining the image features of the remote sensing image data, the method further includes: determining the cloud content of the remote sensing image data; If the cloud content is not greater than the first specified content, determining the remote sensing image data as low cloud image data; If the cloud content is greater than the first specified content and not greater than the second specified content, determining the remote sensing image data as cloudy image data; If the cloud content is greater than the second specified content, the remote sensing image data is deleted.

[0012] Optionally, the method further comprises: Periodically determining and updating basic indicators and spatial indicators of the image data directory according to each remote sensing data image contained in the image data directory; Among them, the basic indicators include at least the total amount of image data and the increment of image data; the spatial indicators include at least the image coverage rate, image overlap rate and image update rate.

[0013] This specification provides a device for generating an image data directory, the device comprising: An acquisition module, used for acquiring remote sensing image data and storing the remote sensing image data in a shared storage space; An archiving module, used for determining the target area to which the remote sensing image data belongs, and archiving the remote sensing image into an image database according to the target area; A labeling module, used to determine the image features of the remote sensing image data and label the remote sensing image data according to the content contained in the remote sensing image data; A determination module, used to determine the knowledge graph of the remote sensing image data according to the image features and the annotations; A generation module is used to generate an image data catalog based on the remote sensing image data and the knowledge graph.

[0014] This specification provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned image data directory generation method is implemented.

[0015] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned image data directory generation method when executing the program.

[0016] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects: In the image data directory generation method provided in the present specification, remote sensing image data is acquired and stored in a shared storage space; a target area to which the remote sensing image data belongs is determined, and the remote sensing image is archived into an image database according to the target area; image features of the remote sensing image data are determined, and the remote sensing image data is labeled according to the content contained in the remote sensing image data; a knowledge graph of the remote sensing image data is determined according to the image features and the annotations; and an image data directory is generated according to the remote sensing image data and the knowledge graph.

[0017] The image data catalog generation method provided in this manual can be used to construct an intelligent image data catalog driven by data and knowledge, realizing the aggregation, storage, management, distribution, online retrieval and visualization of massive remote sensing image data, and meeting the user's needs for remote sensing data acquisition and retrieval. At the same time, full automation and intelligence are achieved in the steps of image update, extraction, storage, archiving, etc., monitoring and early warning are carried out at key nodes, and the robustness of the system is improved through server parallelism. The use of this method can not only improve the data processing speed, but also enhance the availability and reliability of the data, facilitate image query, grasp the data situation, and assist in data analysis, providing data support for subsequent remote sensing data special applications and large model training. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings: Figure 1 A flowchart of a method for generating an image data directory in this specification; Figure 2 A schematic diagram of an image data directory generating device provided in this specification; Figure 3 The corresponding Figure 1 Schematic diagram of electronic equipment. DETAILED DESCRIPTION

[0019] The combination of knowledge and data-driven is one of the important trends in the development of science and technology today. Knowledge-driven relies on the prior knowledge of experts to make comprehensive decisions, while data-driven uses data to discover potential rules and trends. The combination of the two can overcome the subjectivity and limitations of expert decision-making, find the scientific principles behind the data rules, process data faster, and accumulate knowledge more effectively, thereby improving the accuracy and efficiency of decision-making. The combination of knowledge and data-driven is applied to the construction of remote sensing image data catalogs. On the one hand, big data solutions represented by Hadoop and Spark have the characteristics of high capacity, high speed, and multiple types. Through the spatiotemporal big data technology, remote sensing image data management solutions are customized, and hybrid storage models are established to integrate and manage massive discrete data, overcome the defects of traditional data management such as scattered, chaotic, and messy, and bring revolutionary development from both theoretical and technical levels; on the other hand, different semantic ontologies are constructed according to different categories of image features, image metadata is parsed through templates, and image time and space management is strengthened. Then, a layer of multi-level visual features describing remote sensing images is constructed through deep learning technology, and image information is comprehensively represented through knowledge graphs, simplifying the data search and analysis and mining process, realizing the cataloging management and value of spatial data, and showing great potential in the fields of space computing and land planning.

[0020] In combination with the above ideas, this specification proposes an image data directory generation method that can build an intelligent and efficient directory.

[0021] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0022] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0023] Figure 1 The following is a flowchart of a method for generating an image data directory in this specification, which specifically includes the following steps: S100: Acquire remote sensing image data, and store the remote sensing image data in a shared storage space.

[0024] All steps in the method for generating an image data directory provided in this specification can be implemented by any electronic device with computing functions, such as terminals, servers and other devices. This specification mainly describes the execution subject as a server.

[0025] This method is mainly used to generate a remote sensing image data directory used in various maps. Based on this, in this step, the remote sensing image data corresponding to the directory can be first obtained. The obtained remote sensing data will be stored in a shared storage space for use in subsequent steps.

[0026] In order to obtain more diverse and high-quality massive remote sensing images, when acquiring remote sensing image data, specifically, public remote sensing image data can be acquired through public data services, and proprietary remote sensing image data can be acquired through a private network; the public remote sensing image data and the proprietary remote sensing image data are determined as remote sensing image data and stored in a shared storage space.

[0027] When acquiring remote sensing image data, most of the remote sensing image data is public remote sensing image data, which can be obtained from various remote sensing image data sources, such as various public data services Sentinel, Landsat, MODIS, etc. Some data is proprietary image data, which can be obtained through a private network. Whether it is public image data or proprietary image data, it can be stored in a shared storage space after acquisition. The shared storage space can be, for example, NFS, OSS and other storage spaces.

[0028] S102: Determine the target area to which the remote sensing image data belongs, and archive the remote sensing image into an image database according to the target area.

[0029] After a large amount of remote sensing image data is acquired in step S100, the remote sensing image data can be further archived in this step to facilitate the subsequent generation of a remote sensing image data directory. Archiving is a process of systematically organizing and preserving completed files, materials, or things that need to be preserved for a long time, which ensures the integrity and accessibility of the files or materials and provides convenience for possible future access or reference.

[0030] In this method, the automatic archiving of image data can be realized through a workflow, including automatic downloading, decompression, data extraction, data analysis, quality evaluation, data statistics and data service steps. The remote sensing image data directory is mainly used in maps. Therefore, in order to facilitate the user's query to the greatest extent, in this method, the remote sensing image data is archived according to the area to which the remote sensing image data belongs. Specifically, the target administrative area to which the image contained in the remote sensing image data belongs is determined; according to the target administrative area, the remote sensing image data is archived into a folder corresponding to the target administrative area in the image database.

[0031] Specifically, the image database can be scanned regularly, and the newly added unarchived data scanned can be automatically downloaded to the local server. The provincial administrative division name to which the remote sensing image data belongs can be calculated based on the longitude and latitude of the remote sensing image data, and the data can be moved and archived to the corresponding administrative division folder and uploaded to the database according to the administrative division.

[0032] In addition, in order to save storage space and facilitate transmission, in most cases, the original data of the remote sensing image data obtained is a compressed file, such as a *.tar type file, so the original data needs to be decompressed to obtain other types of remote sensing image data. Specifically, the original data of the remote sensing image data can be decompressed to obtain the raster data, metadata and thumbnail data of the remote sensing image data; the raster data of the remote sensing image data is archived in a folder corresponding to the target administrative area in the first image database, and the metadata and the thumbnail data are archived in a folder corresponding to the target administrative area in the second image database.

[0033] Typically, the data obtained after decompressing the original data may include at least raster data (*.tiff), metadata (*.xml), and thumbnail data (*.png or *.jpg). In order to facilitate subsequent sorting and application, different types of files can be stored in different databases. In this method, the raster data can be stored in a first image database such as NFS, HDFS, etc., and the metadata and thumbnail data can be stored in a second image database such as OSS object storage MinIO, etc., and this specification does not impose specific restrictions on this.

[0034] At the same time, through structural analysis of metadata, the four points of the remote sensing image data, that is, the four vertices of the remote sensing image data, can be determined, and based on this, the coverage area polygon file Polygon (*.wkt) of the remote sensing image data can be generated. This file can also be stored as part of the remote sensing image data in a separate database, such as Postgis and other spatial databases.

[0035] Additionally, in order to facilitate the annotation of remote sensing image data in the subsequent process, when executing this step, the remote sensing image data can also be sliced, that is, processed in blocks. Specifically, the remote sensing image data can be processed in blocks according to the preset division rules to obtain the block image data of the remote sensing image data; the block image data of the remote sensing image data is archived in the folder corresponding to the target administrative area in the image database. Among them, the division rules can be preset according to the specific situation. For example, the remote sensing image data can be cut and divided according to 1024×1024px, and the obtained block image data and the subsequent annotation results of the block image data are stored together in OSS object storage such as MinIO. For another example, in order to facilitate the access of carriers such as browsers in the application stage, the final remote sensing image data can be sliced ​​into block image data of 256×256px size, stored in a database such as HBase, and a corresponding spatiotemporal index is established. In short, different slicing methods can be considered when facing different application scenarios. Of course, various slicing methods can be used at the same time to apply to a variety of different systems.

[0036] Additionally, in actual applications, there are many ways to trigger archiving. For example, the remote sensing image data in the shared storage space can be scanned regularly, the remote sensing image data that has been stored in the storage can be removed, and the newly added remote sensing image data can be automatically stored in the storage; for example, when the total storage capacity of the shared storage space reaches a certain threshold, such as 90%, the remote sensing image data can be automatically stored in the storage, and this specification does not make specific restrictions on this.

[0037] At the same time, in the process of archiving, the remote sensing image data can also be additionally screened. Since the satellite will be severely affected by weather factors when shooting remote sensing images, there is a high probability that some of the remote sensing image data finally obtained will be of poor quality and unusable. To address this impact, the cloud content of the remote sensing image data can be specifically determined; if the cloud content is not greater than the first specified content, the remote sensing image data is determined as low cloud image data; if the cloud content is greater than the first specified content and not greater than the second specified content, the remote sensing image data is determined as cloudy image data; if the cloud content is greater than the second specified content, the remote sensing image data is deleted.

[0038] When satellites take remote sensing images of the ground from above, it is easy to take pictures of clouds. Therefore, for each remote sensing image data obtained, the cloud content in the remote sensing image data can be determined, that is, the proportion of the picture occupied by clouds in the picture of the remote sensing image. According to the cloud content of the remote sensing image data, the remote sensing image data can be distinguished and screened. If the cloud content in a remote sensing image data is low, that is, not greater than the first specified content, then the remote sensing image data can be determined to be a low-cloud image data of higher quality; if the cloud content in a remote sensing image data is high, that is, the cloud content is greater than the first specified content and not greater than the second specified content, then the remote sensing image data can be determined to be a cloudy image data of lower quality; and if the cloud content in a remote sensing image data is very high, that is, greater than the second specified content, then the remote sensing image data can be considered unavailable at this time and can be directly deleted. Among them, the first specified content and the second specified content can be set according to specific needs, and the first specified content is less than the second specified content. For example, the first specified content can be 20%, and the second specified content can be 90%, etc. This specification does not make specific restrictions on this.

[0039] Additionally, in the case of massive amounts of remote sensing image data, it is quite time-consuming to complete the archiving of all remote sensing image data. Therefore, in this method, the priority for archiving remote sensing image data can also be specified. For example, in the manner of archiving according to the target area to which the remote sensing image data belongs, the priority of processing the remote sensing image data can be divided according to factors such as the user's attention to the images of different target areas, the importance of the city, the distribution of remote sensing image data, and the timeliness of the data. Of course, in addition to the above rules, users can also set other rules or actively increase the priority of a certain remote sensing image data, and this manual does not make specific restrictions on this.

[0040] For example, the frequency of updating remote sensing image data may be different for different target areas. Generally, 70 large and medium-sized cities in the country update full coverage data on a monthly basis, the remaining small and medium-sized cities update full coverage data on a quarterly basis, and other regions (including foreign regions) update full coverage data on an annual basis. For areas with higher real-time requirements, the data update frequency can be set according to actual monitoring needs. For some special cases, such as the impact of remote sensing data in the target area where natural disasters occur, the target area where hot events are located, or the remote sensing image data specified by the user, if standard image data products need to be provided in a timely manner, they can be temporarily adjusted to priority.

[0041] S104: Determine image features of the remote sensing image data, and annotate the remote sensing image data according to content included in the remote sensing image data.

[0042] After completing the archiving process of the remote sensing image data in step S102, the knowledge of each remote sensing image data can be extracted in this step. In this method, the knowledge of the remote sensing image data can mainly include the influencing features of the remote sensing image data and the annotations obtained by identifying the contents captured by the remote sensing image data.

[0043] Among them, the influencing features of remote sensing image data can be extracted from the metadata of remote sensing image data, and the extracted influencing features may include but are not limited to satellite / sensor information, boundary range, administrative district, acquisition time, band information, cloud information, whether it is a built-up area, etc. The annotation of remote sensing image data can be carried out by identifying the main objects in the remote sensing image data, judging the category of the objects and marking them. The categories may include but are not limited to cultivated land, gardens, woodlands, grasslands, residential areas, commercial areas, industrial areas, transportation land, bare land, water areas, etc. At the same time, the spatial relationship between entities in the remote sensing image data can be additionally identified and annotated in the form of semantic description, such as rivers passing through urban areas, roads connecting multiple residential areas, etc.

[0044] S106: Determine a knowledge graph of the remote sensing image data according to the image features and the annotations.

[0045] In this step, the image features extracted and the annotations determined in step S104 can be used to form a knowledge graph of remote sensing image data. For each remote sensing image data, a corresponding knowledge graph can be determined. The knowledge graph records the image features and annotations of the remote sensing image data in the form of text descriptions, and stores them in the database as knowledge of the remote sensing image data. At the same time, each remote sensing image data will establish an association relationship with its own knowledge graph for subsequent query during application.

[0046] S108: Generate an image data catalog based on the remote sensing image data and the knowledge graph.

[0047] Finally, an image data directory can be generated based on the knowledge graph generated in step S106 and the remote sensing image data itself.

[0048] Since the image data directory generated by this method is a data and knowledge driven image data directory, the online data query system established based on the image data directory generated by this method can support multi-condition attribute query and spatial query. Spatial query supports administrative division number data, ROI area retrieval or upload vector data and other operations. At the same time, it can also provide search functions based on natural language or tags. For example, if the user enters "images of GF2 urban area in Hangzhou in the past three months", users can find the data they need more easily.

[0049] Furthermore, since the image data directory generated by this method includes annotations of remote sensing image data, the image data directory generated by this method can also support flexible semantic retrieval. When a user uploads an image to search for similar images, the image data directory can automatically identify the semantics of the image and search. For example, if a user uploads an image containing a port, the image data directory can identify the "port" content and search based on the semantics of "images containing ports". Furthermore, when the quick view of the search results is superimposed on the map, the user can click on the image to display the basic features and annotations of the image, that is, the semantic features.

[0050] Additionally, in addition to generating the image data directory itself, the method can also periodically manage and detect the remote sensing image data to ensure the quality of the image data directory. Specifically, the basic index and spatial index of the image data directory can be periodically determined and updated based on each remote sensing data image included in the image data directory; wherein the basic index at least includes the total amount of image data and the image data increment; the spatial index at least includes the image coverage rate, the image overlap rate, and the image update rate.

[0051] In this method, the impact coverage is the ratio of the area covered by all remote sensing image data in a region to the total area of ​​the region, which can be specifically expressed as cr = ca / ​​ta, where ca is the area of ​​the union of all remote sensing image data in the region, and ta is the total area of ​​the region. The calculation unit is square kilometers (km 2). The image overlap rate is the ratio of the area covered by multiple remote sensing image data in a region to the area covered by all remote sensing image data in the region. It can be specifically expressed as or = (aa – ca) / ca, where aa is the sum of the areas of all images in a region without deduplication. The image update rate is the ratio of the area of ​​images updated in a region within a period to the total area of ​​the region. It can be specifically expressed as ur = ma / ta, where ma is the area of ​​the union of the images updated monthly, and the area of ​​repeated areas is calculated only once. It is worth mentioning that the areas mentioned in the above indicators are calculated after clipping according to the regional boundaries.

[0052] The image data catalog generation method provided in this manual can be used to construct an intelligent image data catalog driven by data and knowledge, realizing the aggregation, storage, management, distribution, online retrieval and visualization of massive remote sensing image data, and meeting the user's needs for remote sensing data acquisition and retrieval. At the same time, full automation and intelligence are achieved in the steps of image update, extraction, storage, archiving, etc., monitoring and early warning are carried out at key nodes, and the robustness of the system is improved through server parallelism. The use of this method can not only improve the data processing speed, but also enhance the availability and reliability of the data, facilitate image query, grasp the data situation, and assist in data analysis, providing data support for subsequent remote sensing data special applications and large model training.

[0053] The above is the image data directory generation method provided in this specification. Based on the same idea, this specification also provides a corresponding image data directory generation device, such as Figure 2 shown.

[0054] Figure 2 A schematic diagram of an image data directory generation device provided in this specification specifically includes: An acquisition module 200 is used to acquire remote sensing image data and store the remote sensing image data in a shared storage space; The filing module 202 is used to determine the target area to which the remote sensing image data belongs, and to file the remote sensing image into an image database according to the target area; The labeling module 204 is used to determine the image features of the remote sensing image data and label the remote sensing image data according to the content contained in the remote sensing image data; A determination module 206, configured to determine a knowledge graph of the remote sensing image data according to the image features and the annotations; The generation module 208 is used to generate an image data catalog based on the remote sensing image data and the knowledge graph.

[0055] Optionally, the acquisition module 200 is specifically used to acquire public remote sensing image data through public data services and acquire proprietary remote sensing image data through a private network; determine the public remote sensing image data and the proprietary remote sensing image data as remote sensing image data, and store them in a shared storage space.

[0056] Optionally, the archiving module 202 is specifically used to determine the target administrative region to which the image contained in the remote sensing image data belongs; based on the target administrative region, the remote sensing image data is archived into a folder corresponding to the target administrative region in the image database.

[0057] Optionally, the archiving module 202 is specifically used to decompress the original data of the remote sensing image data to obtain the raster data, metadata and thumbnail data of the remote sensing image data; archive the raster data of the remote sensing image data into a folder corresponding to the target administrative area in the first image database, and archive the metadata and the thumbnail data into a folder corresponding to the target administrative area in the second image database.

[0058] Optionally, the archiving module 202 is specifically used to perform block processing on the remote sensing image data according to a preset division rule to obtain block image data of the remote sensing image data; and archive the block image data of the remote sensing image data into a folder corresponding to the target administrative area in the image database.

[0059] Optionally, the device also includes a screening module 210, which is specifically used to determine the cloud content of the remote sensing image data; if the cloud content is not greater than a first specified content, the remote sensing image data is determined as low cloud image data; if the cloud content is greater than the first specified content and not greater than a second specified content, the remote sensing image data is determined as cloudy image data; if the cloud content is greater than the second specified content, the remote sensing image data is deleted.

[0060] Optionally, the device also includes an update module 212, which is specifically used to periodically determine and update the basic indicators and spatial indicators of the image data directory based on each remote sensing data image contained in the image data directory; wherein the basic indicators include at least the total amount of image data and the image data increment; the spatial indicators include at least image coverage, image overlap, and image update rate.

[0061] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 Provides a method for generating an image data catalog.

[0062] This manual also provides Figure 3 The schematic structure diagram of the electronic device shown in FIG. Figure 3 As mentioned above, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Of course, in addition to the software implementation, this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0063] For the improvement of a technology, it can be clearly distinguished whether it is a hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0064] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0065] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0066] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0067] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0068] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0071] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0072] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0073] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0074] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0075] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0077] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0078] The above description is only an embodiment of this specification and is not intended to limit this specification. For those skilled in the art, this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification should be included in the scope of the claims of this application.

Claims

1. A method for generating an image data directory, characterized in that: include: Acquire remote sensing image data, and store the remote sensing image data in a shared storage space; Determine the target area to which the remote sensing image data belongs, and archive the remote sensing image into an image database according to the target area; Determining image features of the remote sensing image data, and marking the remote sensing image data according to content contained in the remote sensing image data; Determine a knowledge graph of the remote sensing image data according to the image features and the annotations; An image data catalog is generated based on the remote sensing image data and the knowledge graph.

2. The method according to claim 1, characterized in that Acquiring remote sensing image data and storing the remote sensing image data in a shared storage space specifically includes: Obtain public remote sensing image data through public data services, and obtain proprietary remote sensing image data through private networks; The public remote sensing image data and the proprietary remote sensing image data are determined as remote sensing image data and stored in a common storage space.

3. The method according to claim 1, characterized in that Determining the target area to which the remote sensing image data belongs, and archiving the remote sensing image into an image database according to the target area, specifically includes: Determining the target administrative region to which the image contained in the remote sensing image data belongs; According to the target administrative area, the remote sensing image data is filed into a folder corresponding to the target administrative area in an image database.

4. The method according to claim 3, characterized in that Archiving the remote sensing image data into a folder corresponding to the target administrative area in an image database includes: Decompressing the original data of the remote sensing image data to obtain raster data, metadata and thumbnail data of the remote sensing image data; The raster data of the remote sensing image data is archived into a folder corresponding to the target administrative area in a first image database, and the metadata and the thumbnail data are archived into a folder corresponding to the target administrative area in a second image database.

5. The method according to claim 3, characterized in that Archiving the remote sensing image data into a folder corresponding to the target administrative area in an image database includes: According to a preset division rule, the remote sensing image data is divided into blocks to obtain block image data of the remote sensing image data; The block image data of the remote sensing image data are archived into a folder corresponding to the target administrative area in an image database.

6. The method according to claim 1, characterized in that Before determining the image features of the remote sensing image data, the method further includes: determining the cloud content of the remote sensing image data; If the cloud content is not greater than the first specified content, determining the remote sensing image data as low cloud image data; If the cloud content is greater than the first specified content and not greater than the second specified content, determining the remote sensing image data as cloudy image data; If the cloud content is greater than the second specified content, the remote sensing image data is deleted.

7. The method according to claim 1, characterized in that The method further comprises: Periodically determining and updating basic indicators and spatial indicators of the image data directory according to each remote sensing data image contained in the image data directory; Among them, the basic indicators include at least the total amount of image data and the increment of image data; the spatial indicators include at least the image coverage rate, image overlap rate and image update rate.

8. An image data catalog generation device, characterized in that: include: An acquisition module, used for acquiring remote sensing image data and storing the remote sensing image data in a shared storage space; An archiving module, used for determining the target area to which the remote sensing image data belongs, and archiving the remote sensing image into an image database according to the target area; A labeling module, used to determine the image features of the remote sensing image data and label the remote sensing image data according to the content contained in the remote sensing image data; A determination module, used to determine the knowledge graph of the remote sensing image data according to the image features and the annotations; A generation module is used to generate an image data catalog based on the remote sensing image data and the knowledge graph.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

Images