CN115795075A - Universal model construction method for remote sensing image product - Google Patents
Universal model construction method for remote sensing image product Download PDFInfo
- Publication number
- CN115795075A CN115795075A CN202211507673.7A CN202211507673A CN115795075A CN 115795075 A CN115795075 A CN 115795075A CN 202211507673 A CN202211507673 A CN 202211507673A CN 115795075 A CN115795075 A CN 115795075A
- Authority
- CN
- China
- Prior art keywords
- file
- product
- remote sensing
- sensing image
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a method for constructing a universal model of a remote sensing image product, which comprises the steps of constructing a definition model of the remote sensing image product according to file composition, attributes and quality inspection indexes of the remote sensing image product; marking the file attribute, the semantic attribute and the quality inspection index semantic attribute of the remote sensing image product; instantiating and creating a remote sensing image product model object; updating a product file composition model and product file semantic attributes through different algorithm modules; and based on the semantic structure model of the remote sensing image product and the latest entity data value, the automatic collection of the remote sensing image processing interface is realized. The invention adopts a universal model to describe remote sensing image products with different types and different sources and quality inspection semantics, realizes the updating of product semantics of each functional module constructed by a remote sensing image system, improves the construction progress of the remote sensing image product quality inspection system, greatly reduces the construction cost of the remote sensing image product quality inspection system, and improves the consistency of interoperation of the remote sensing image products among different modules of the system.
Description
Technical Field
The invention relates to the technical field of remote sensing images and remote sensing image quality inspection, in particular to a general expression method for file composition and quality inspection semantic composition and state of remote sensing image products produced and processed by different satellite manufacturers.
Background
The satellite data products have multiple sources, each satellite product is produced by different manufacturers and specified naming standards, when the remote sensing image quality inspection platform is designed, data produced by different manufacturers and specified naming production need to be compatible, consistent quality inspection process design and system development need to be provided for data products of the same type and different sources, only one set of quality inspection system is built for one type of data products, and low-level invalid repetition of the multi-source satellite data product quality inspection system is avoided.
The quality inspection operation support management platform needs to implement functional plug-ins, flow design and task management for quality inspection of different types of satellite data products, and also needs to perform different flow branch operations on certain index data values of each type of products, collect and store quality inspection results, and in order to consider the expandability and the universality of the quality inspection platform, a set of unified model compatible with all product attribute definitions needs to be constructed, so that satellite data products aligned between the quality inspection operation support management platform and the algorithm plug-ins and between the algorithm plug-ins and the algorithm plug-ins are implemented.
The remote sensing satellite product comprises three different sensor sources of an optical satellite, a radar and a laser, each sensor comprises a sensor correction product, a digital orthographic product, an elevation product, an index product, a reflectivity product and the like, the file composition of each product is different, and how to construct a set of unified remote sensing satellite product file management model provides a unified access model for different remote sensing satellite products.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a universal model construction method for semantic definition of composition and quality inspection of a sensing image product, which can meet the requirement of universal structure definition of different types of remote sensing image product compositions, realize that a heterogeneous platform provides a uniform semantic model for semantic attributes disclosed by file matching, file access and product and quality inspection of a multi-source remote sensing image product, and provide methods for accessing, instantiating, updating and collecting product semantics in different links of product operation by a management platform and an algorithm plug-in the remote sensing image processing and quality inspection processes.
The purpose of the invention is realized by the following technical scheme:
a method for building a universal model of a remote sensing image product comprises the following steps:
a, constructing a remote sensing image product definition model according to the composition, the attribute and the quality inspection indexes of a remote sensing image product file;
b, marking the file attribute, the semantic attribute and the quality inspection index semantic attribute of the remote sensing image product;
step C, instantiation creation of a remote sensing image product model object;
d, updating the product file composition model and the semantic attributes of the product file through different algorithm modules;
and E, automatically collecting a remote sensing image processing interface based on the semantic structure model of the remote sensing image product and the latest entity data value.
One or more embodiments of the present invention may have the following advantages over the prior art:
the invention provides a general modeling method of a remote sensing image product based on product file definition, attribute and quality inspection index definition, provides a specific modeling method of the remote sensing image product, solves the interface definition between a specific product file class and a semantic definition interface, and provides specific processes of establishing, updating and collecting a product definition model by specific algorithm modules of remote sensing image standardized product production, cloud detection, radiation detection and the like. The method can be widely applied to the construction of a multi-source heterogeneous remote sensing image processing and quality inspection system platform based on flow modeling, solves the problems that a remote sensing image processing and scheduling module obtains and manages the latest state of a product, provides a set of public data model for a software management platform due to the characteristics of data multi-source and format difference and the like of a product algorithm plug-in, and provides a set of public data model for product operation of the algorithm plug-in.
Drawings
FIG. 1 is a flowchart of a method for constructing a universal model of a remote sensing image product based on product file definition and attribute and quality inspection index definition;
FIGS. 2a and 2b are examples of remote sensing image product definition model structures and optical satellite product structures formed based on the product definition structures according to the embodiment of the invention;
3a, 3b and 3c are example XML files of remote sensing image products initialization example XML files and algorithm modules after standardized processing in the embodiment; and instantiating the XML after passing through the cloud amount checking algorithm module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings.
As shown in figure 1, the invention relates to a remote sensing image product universal model construction method based on product file definition, attribute and quality inspection index definition, which adopts a universal model to describe remote sensing image products of different types and sources and quality inspection semantics, realizes the update of product semantics of each functional module constructed by a remote sensing image system, improves the construction progress of the remote sensing image product quality inspection system, greatly reduces the construction cost of the remote sensing image product quality inspection system, and improves the consistency of interoperation of the remote sensing image products among different modules of the system. The method specifically comprises the following steps:
and 5, automatically collecting a remote sensing image processing interface based on the semantic structure model of the remote sensing image product and the latest entity data value.
The step 1 specifically includes:
1.1 constructing a structural model of the remote sensing image product file composition;
as shown in fig. 2a, the semantic model of the remote sensing image product is a general semantic model for performing structured expression on entity files and combination files contained in the remote sensing image product by using a hierarchical structure model, and organizing the semantic attributes and quality inspection index attributes of the remote sensing image product, the contained entity files and the combination files as nodes contained in the remote sensing image product. The entity file comprises a file name, a file type, a file matching template definition and an instance data value definition; the combined file comprises a file name, a file type and an instance data value definition, wherein at least one entity file is defined. The file matching template definition is described by using a syntax of a combination of "$ (dynamic parameter key) + static character string", wherein the value of "$ (dynamic parameter key)" contained in the syntax is unique after a specific product is instantiated, and the file name contained in the product is formed by combining the "$ (dynamic parameter key)" and the static character string to express an entity file contained in the product.
1.2, marking the semantic attributes of the remote sensing image product and the semantic attributes of the quality inspection indexes;
referring to fig. 2b, the semantic attributes and quality inspection index attributes of the remote sensing image product are used as a part of entity files and combined files of each layer, including attribute names, attribute types and whether the attributes are available, the attributes are divided into basic attributes and expression attributes, the basic attributes are the attributes of the file types, and the expression attributes are generated by operation expressions including the basic attributes.
1.3, marking the file type of the remote sensing image product composition;
the Image file data format types comprise TIF, erdas Image, JP2 and TIL file types; the rational function model file data comprises TXT and a plurality of self-defined XML formats; the data type of the projection parameter file comprises data formats of prj and Proj 4; the metadata file and the quality inspection metadata file are in XML format, and the microphotograph file and the thumbgraph file belong to the digital positive shot image file types.
1.4, defining and explaining a remote sensing image entity file template; when a remote sensing image product definition model is carried out, firstly, files contained in the product are analyzed for classification: one is an entity file (SingleFile) and the other is a group file (GroupFile). One remote sensing image file at least comprises one entity file, and can also be a combined file (GroupFile) formed by the entity file and the combined file (GroupFile). On the basis, a remote sensing image product hierarchical inclusion structure is established. For the combined file in the product containing the sub-members, file access and semantic name labeling are facilitated, and the semantic names of the contained files cannot be repeated.
The step 2 specifically includes the following steps:
2.1, analyzing the file composition of the remote sensing image product;
as shown in fig. 3a, the remote sensing image product is divided according to product hierarchy: original image products, sensor correction products, geometric correction products, digital surface models, index products and other special products; the sensor correction product file comprises an original image file, a rational function model file, a micro-map file, a thumb map file, a coordinate range file, a projection parameter file, a metadata file and a quality inspection metadata file. Products of different types including optics, radars, lasers, hyperspectrum and the like are divided according to different sensors; although the basic semantics of the same type of products are the same, the content and data format of files made by different data manufacturers have certain differences, especially metadata.
2.2, marking the attribute of the entity file of the remote sensing image product;
referring to fig. 3a, the remote sensing image product entity file attribute description includes five attributes of an available | prohibited and a data value (value) for a file name (name), a file type (type), a file template matching expression (template), and whether a file is usable (use) in an initialization state. These attribute descriptions are stored in the form of strings. The file names are semantic names, file template parameter definitions are defined, all entity file directory file names contained in the product are analyzed, the composed semantics are decomposed into combinations of one or more dynamic keywords and one or more static character strings, the file paths and the file names of all files in the product can be matched, the dynamic keywords contained in all the files are the same, and the corresponding character strings are the same during matching. And the data value is the name of the file matched with the current file after instantiation.
2.3 marking the attribute of the remote sensing image product combination file;
referring to fig. 3b, the definition of the semantic attribute and the quality inspection index semantic attribute of the remote sensing image product is the definition of the remote sensing image product and the semantic model containing the file thereof, and the product entity combination file attribute includes a semantic name (name), a file data type (type), whether the file is available (use) in an initialization state, an optional value available | prohibited and a data value (value); these attribute descriptions are stored in the form of strings. The file names are semantic names, file template parameter definitions are defined, all entity file directory file names contained in the product are analyzed, the composed semantics of the entity file directory file names are decomposed into combinations of one or more dynamic keywords and one or more static character strings, the file paths and the file names of all files in the product can be matched, the dynamic keywords contained in all the files are the same, and the corresponding character strings are the same during matching. And the data value is the name of the file matched with the current file after instantiation. The product semantic attributes comprise product basic semantic attributes and operational expression semantic attributes; the semantic definition of the product quality inspection index is the same as the semantic attribute definition of the product.
Marking semantic attributes of remote sensing image products: the semantic attribute of the remote sensing image product is closely related to the file type, the file attribute is an expression form of the file content metadata of the remote sensing image product, and the file or product attribute needs to be accessed and modified by a platform or other modules. The file semantic attributes are intensively related to the file metadata, the basic attributes of the file semantic attributes are a subset of the metadata, and the extended attributes of the file semantic attributes are calculated based on the operation expressions of the basic attributes.
Marking the quality inspection indexes of the remote sensing image products: referring to fig. 3b, the remote sensing image product quality inspection indexes are statistical features and evaluation characteristics about remote sensing quality description. The remote sensing quality inspection indexes relate to the remote sensing image product and the statistical characteristics of the remote sensing image product containing files, or the attributes related to the image application target, and comprise data integrity, data validity, image quality indexes, radiation quality indexes and the like. The quality evaluation comprises the evaluation of product integrity effectiveness, geometric quality, image radiation quality and product comprehensive quality. Because the quality evaluation index needs to be carried out by a corresponding quality inspection index service module, the state of whether the model can be used or not is set as a prohibited state (prohibited) during the initialization and construction of the model, and the state of the model can be set as usable (available) only after the model is processed by a corresponding index algorithm module.
The step 3 specifically includes:
3.1, constructing a remote sensing file type of a remote sensing product;
because the remote sensing product is composed of two types of files, namely an entity file (SingleFile) and a combined file (GroupFile), according to the model definition, the entity file and the combined file have file attributes (semantic name and file type) and also contain product semantic attributes and quality inspection index attributes related to the file, in order to realize the unified management of different types of objects, a common base class (CFileObjectBase) needs to be defined, and the creation of the file and the related product semantic attributes and quality inspection index attributes, the update of available states, the value calculation interface and the like are realized. When a specific file type object is defined, selecting an implementation class to select and derive from an entity file or a combined file according to the file composition structure of the file, identifying the file type of the implementation class, and instantiating and transmitting the semantic name of the implementation class through a constructor interface according to different file composition structures.
3.2 instantiating and constructing remote sensing file types of remote sensing products;
3.2.1 File class registration based on a plug-in mechanism. In order to solve the problem of creating an instantiated file class instance based on a file type and realize the registration and instantiation of a plurality of different types of files, the file plugin implementation method based on the dynamic library module is provided, the dynamic library module provides a fixed function interface, and the fixed function interface comprises: 1: whether a product defines a plug-in (isproductdefplug), 2: number of acquired plug-ins (getplugncount), 3: type of acquired plug-ins (getplugType), and 4: whether a created plug-in instance (creatPluginInstance) is a plug-in. The plug-in management library judges whether the plug-in is a product type registration plug-in by loading a dynamic link library under a file directory, dynamically searching whether the plug-in contains an isproductdefplug function pointer and calling the function pointer. And the file types registered in the product definition plug-in are retrieved and registered in the currently registered plug-in environment.
3.2.2 creating a product definition model class structure;
based on the product definition model file, according to the product definition hierarchical structure model, according to the product definition type, searching the corresponding implementation class and the corresponding plug-in from the registration class, completing the creation of the class instance object by creating the plug-in instance (creatPluginInstance) object, and on this basis, instantiating and creating the file contained in the combined file and adding the file into the class instance list for management by setting the product definition model as a parameter.
3.2.3 instantiation of product definition model class product files;
and searching all files under the current directory and the subdirectories according to the product file directory to be instantiated, selecting one file which is available for initialization from the product files as a file template parameter definition of a main file for matching, and synchronizing the actual character string corresponding to the matched dynamic keyword into other entity files in the current product once matching is successful to form complete expression of the entity files in the product. And after matching is finished, judging whether real product instantiation operation is realized by checking whether the currently available files exist.
The step 4 includes:
4.1 method for establishing and updating product definition model by remote sensing image algorithm module
Product file model instance creation: instantiating the specified product according to the remote sensing image product definition model to form initialized product definition instantiation model data; the basic attribute of each type file in the product definition depends on internal implementation, and the corresponding basic type is obtained by a function interface provided by the class. For a remote sensing image product, the type of the remote sensing image product is a combined file class, if the combined class does not have a special self-defined file attribute, the combined class is only used as a file management class and can be realized through a basic combined file class, the basic combined file class only realizes the management of an included entity file and a combined file and the management of a derivative attribute and a quality inspection index definition attribute, for the basic attribute, the included value of the basic attribute needs to be realized through the synchronous exchange of the file classes, and the quality inspection index attribute and the derivative attribute are calculated through an external plug-in and a calculation formula. This property creation process can only be passed through the definition of the product definition by modifying the product definition file or by the product definition visualization tool software.
Product file attribute value status and value update: the definition of the property of the product file is realized through an internally defined function, the internal property is expressed by providing a read-only state and a read-write state, the internal state value of the file can be synchronized into the property value through a class-defined interface, and the writable property value can also be written into the file through a public interface.
Designing an algorithm module, updating semantic attributes of product quality inspection: as shown in fig. 3c, for the defined quality inspection semantic attributes, the quality inspection attribute is set as disabled (prohibited) when the product definition is initialized, and the quality inspection algorithm module completes the calculation or labeling of the corresponding quality inspection index according to the design and implementation of the quality inspection function. The quality inspection indicators can be set to available (available) only after the corresponding quality inspection process is completed, and the data values of the quality inspection indicators are written into the quality inspection metadata file and the quality inspection results are synchronized to the product semantic model file.
4.2 remote sensing image product standardization processing algorithm to update product semantics
The standardization processing algorithm of the remote sensing image product realizes that the initial sensor correction products produced by different satellite manufacturers are produced into the optical satellite sensor correction product with unified standard, and realizes the updating of the product definition model. The algorithm comprises the following steps: 1) Reading a product definition model needing remote sensing image product standardization, and instantiating a product definition file structure of the product definition model; 2) Acquiring basic image data, a rational function model and basic metadata according to the semantic name of the current file, and generating derivative data such as a standard metadata file, a quality inspection metadata file, a micro graph and a thumb graph file; 3) The state of whether the standard metadata file, the quality inspection metadata file, the thumbnail and the thumb file generated as described above are available is set from disabled to available.
4.3 remote sensing image product cloud cover detection algorithm to update product semantics
The cloud detection algorithm of the remote sensing image product is realized by calling a cloud recognition model algorithm based on deep learning network model training to calculate a cloud range (cloudbound) and a cloud percentage (CloudPercent) based on a current product definition model, storing the cloud range and the cloud percentage (CloudPercent) into a corresponding semantic file, and updating the attribute state and the attribute value of the quality inspection semantic attribute cloud percentage (CloudPercent) in the product definition model. The algorithm comprises the following steps: 1) Reading a product definition model needing remote sensing image product standardization, and instantiating a product definition file structure of the product definition model; 2) Acquiring a file object of a file thumbnail name (preview) contained in a current remote sensing image product, and acquiring a corresponding instance file path name as input image data; acquiring a semantic file name file definition cloud volume range (cloudbound) and quality inspection metadata (metadata) in a product definition model to obtain corresponding example file path names which are respectively used as files for storing the cloud volume range and the cloud volume percentage; and calling a cloud identification model algorithm based on deep learning network model training, calculating the cloud coverage area and cloud volume percentage (CloudPercent) of the image, and writing the cloud coverage area and the cloud volume percentage into a corresponding file. 3) Setting the availability status of the quality control attribute definition name (CloudPercent) in the product definition model from forbidden (prohibited) to available (available), and writing the cloud amount percentage (CloudPercent) value into the corresponding semantic attribute value item (value).
4.4 remote sensing image product radiation anomaly detection algorithm to update product semantics
The remote sensing image product radiation anomaly detection algorithm is realized based on a current product definition model, the remote sensing image product radiation anomaly detection algorithm is called to detect the radiation anomaly type, the radiation anomaly is classified and stored into a corresponding semantic file, and the attribute state and the attribute value corresponding to the quality inspection semantic attribute radiation anomaly in the product definition model are updated. The algorithm comprises the following steps: 1) Reading a product definition model needing remote sensing image product standardization, and instantiating a product definition file structure of the product definition model; 2) Acquiring a file object of a file thumbnail name (previewimage) contained in a current remote sensing image product, and acquiring a corresponding example file path name as input image data; obtaining a semantic file name quality inspection metadata file (qualitydata) in a product definition model, obtaining a corresponding instance file path name, and using the instance file path name as a file for storing the radiation anomaly classification attribute; and calling a remote sensing image product radiation anomaly detection algorithm based on deep learning network model training, calculating whether the image contains radiation problems such as CCD splicing, color cast, tapping, missing, code disorder and the like, and writing the radiation problems into a corresponding file. 3) Setting the usable (use) state of a quality control attribute definition name in the product definition model, namely CCD splicing (CCDEdgeJoingcheck), color cast (ColorOffsetcheck), tap (TapCheck), missing (ImageMissingcheck) and random code (random Codecheck) from forbidden (prohibited) to usable (available), and writing each type of radiation problem value into a corresponding semantic attribute value item (value).
The product data collection in the step 5 includes:
5.1 remote sensing image product class Structure Collection
Collecting product structure, after finishing remote sensing image product data processing and quality inspection result, collecting product definition model layer, product definition type, attribute collection can be data collection of multiple layers, as a layer structure model, in order to map with common relational table database, it needs to select attribute semanteme and quality inspection index semanteme contained in a certain layer in the product definition model, select partial or all attribute items, and establish mapping relation through XPath grammar structure, as collecting product model structure, and establish collecting data table structure. Because the product definition file contains a hierarchical structure file, collection can be performed based on file types when a relational data table structure is created, and a collection object comprises the attributes of the file (file name, file type and instantiated file data value) and also comprises the semantic attributes of the product and the semantic attributes of quality inspection indexes. And generating semantic quality inspection mapping relations among the names of the data tables, the names of the table fields and the types, and realizing data collection based on the file types.
5.2 remote sensing image product example data Collection
And (3) product example data collection, searching the established product type structure collection model based on the updated product file, loading the model based on the instantiated product file, collecting the data type corresponding table structure and the product definition attribute corresponding model according to the requirement, and realizing the collection of the corresponding type data and the collection of the records of the data table.
Although the embodiments of the present invention have been described above, the above description is only for the purpose of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method for constructing a universal model of a remote sensing image product is characterized by comprising the following steps:
a, constructing a remote sensing image product definition model according to the composition, the attribute and the quality inspection indexes of a remote sensing image product file;
b, marking the file attribute, the semantic attribute and the quality inspection index semantic attribute of the remote sensing image product;
step C, instantiation creation of a remote sensing image product model object;
d, updating the product file composition model and the semantic attributes of the product file through different algorithm modules;
and E, automatically collecting a remote sensing image processing interface based on the semantic structure model of the remote sensing image product and the latest entity data value.
2. The method for constructing a universal model of remote sensing image products as claimed in claim 1, wherein said step a specifically comprises:
a1, defining a remote sensing image product file composition model;
a2, defining the semantic attribute item and quality inspection index item structure of the remote sensing image product;
a3, marking the file type of the remote sensing image product composition;
and A4, defining and explaining the remote sensing image entity file template.
3. The method for constructing a universal model of a remote-sensing image product according to claim 2, wherein the remote-sensing image product is composed of files, the files are divided into an entity file and a combined file according to the file composition, and the entity file is composed of a main file and a plurality of dependent files; the combined file is composed of one or more entity files and a combined file; the entity file comprises a semantic name, a file type, a file template matching expression and a data value; the combined file includes a semantic name, a file type, and a data value.
4. A method of constructing a universal model for remote-sensing Image products as claimed in claim 3, wherein said Image file data format types include TIF, erdas Image, JP2, TIL file types; the rational function model file data comprises TXT and a plurality of self-defined XML formats; the data type of the projection parameter file comprises data formats of prj and Proj 4; the metadata file and the quality inspection metadata file are in XML format, and the thumbnail file and the thumb picture file belong to the digital positive shooting image file type.
5. The method for constructing a universal model of remote-sensing image products as claimed in claim 1, wherein the labeling of the attributes of the remote-sensing image product files in step B comprises: analyzing the composition of the remote sensing image product file; marking the attribute of the entity file of the remote sensing image product; and marking the attributes of the remote sensing image product combination file.
6. The method for constructing a universal model of remote-sensing image products according to claim 5, wherein,
the remote sensing image product comprises the following components according to the product level division: the method comprises the following steps that an original image product, a sensor correction product, a geometric correction product, a digital surface model and an index product are divided according to different sensors, wherein the original image product, the sensor correction product, the geometric correction product, the digital surface model and the index product comprise optics, radar, laser and hyperspectrum;
the remote sensing image product entity file attributes comprise file names, file types, file template matching expressions, file availability in an initialization state, optional values and data values;
the remote sensing image product entity combination file attributes comprise file names, file types, whether files are available in an initialization state, optional values and data values;
the remote sensing image product quality inspection indexes comprise data integrity, data validity, image quality indexes and radiation quality indexes.
7. The method for constructing a universal model of a remote sensing image product according to claim 1, wherein the step C specifically comprises:
c1, constructing remote sensing file type classes of remote sensing products; realizing corresponding instantiation classes according to file types, and registering the types and type instance objects;
c2, instantiating and constructing remote sensing file types of remote sensing products; and searching the contained files according to the specified product file root directory, carrying out instantiation matching on the file template according to the defined main file, instantiating the template field values contained in the file template, and instantiating the associated files.
8. The method for constructing a universal model of a remote sensing image product according to claim 7, wherein the step C2 specifically comprises:
c2.1 registering file types of file plug-ins based on the dynamic library module;
c2.2 creating a product definition model class structure;
c2.3 instantiates the product definition model class product file.
9. The method for constructing a universal model of remote sensing image products as claimed in claim 1, wherein said step D comprises
D1, establishing a product definition model instance by a remote sensing image algorithm module, updating the state and the value of the attribute value of a product file, and finishing the semantic attribute updating of product quality inspection by a design algorithm module;
d2, updating product semantics by a standardized processing algorithm of the remote sensing image product;
d3, updating product semantics by a cloud amount detection algorithm of the remote sensing image product;
and D4, updating product semantics by a remote sensing image product radiation anomaly detection algorithm.
10. The method for constructing a universal model of remote sensing image products as claimed in claim 1, wherein the product data collection in step E comprises: collecting remote sensing image product class structures and collecting remote sensing image product example data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211507673.7A CN115795075B (en) | 2022-11-29 | 2022-11-29 | Method for constructing universal model of remote sensing image product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211507673.7A CN115795075B (en) | 2022-11-29 | 2022-11-29 | Method for constructing universal model of remote sensing image product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115795075A true CN115795075A (en) | 2023-03-14 |
| CN115795075B CN115795075B (en) | 2023-08-11 |
Family
ID=85442798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211507673.7A Active CN115795075B (en) | 2022-11-29 | 2022-11-29 | Method for constructing universal model of remote sensing image product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115795075B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116501304A (en) * | 2023-06-28 | 2023-07-28 | 中国科学院空天信息创新研究院 | Cloud-based model creation method and device for remote sensing product production algorithm |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150071528A1 (en) * | 2013-09-11 | 2015-03-12 | Digitalglobe, Inc. | Classification of land based on analysis of remotely-sensed earth images |
| CN109885586A (en) * | 2019-01-24 | 2019-06-14 | 武汉大学 | Support the ontology model construction method and device of remote sensing image and data product retrieval |
| WO2020258303A1 (en) * | 2019-06-28 | 2020-12-30 | 西门子股份公司 | Semantic model instantiation method, system and device |
| CN112559534A (en) * | 2020-12-24 | 2021-03-26 | 山东省国土测绘院 | Remote sensing image data filing management system and method |
| CN113590894A (en) * | 2021-07-12 | 2021-11-02 | 浙江大学 | Dynamic and efficient remote sensing image metadata warehousing retrieval method |
| CN113761971A (en) * | 2020-06-02 | 2021-12-07 | 中国人民解放军战略支援部队信息工程大学 | Method and device for constructing target knowledge graph of remote sensing image |
| CN115017354A (en) * | 2022-06-23 | 2022-09-06 | 郑州大学 | Task-driven remote sensing image metadata semantic reasoning method under space-time constraint |
-
2022
- 2022-11-29 CN CN202211507673.7A patent/CN115795075B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150071528A1 (en) * | 2013-09-11 | 2015-03-12 | Digitalglobe, Inc. | Classification of land based on analysis of remotely-sensed earth images |
| CN109885586A (en) * | 2019-01-24 | 2019-06-14 | 武汉大学 | Support the ontology model construction method and device of remote sensing image and data product retrieval |
| WO2020258303A1 (en) * | 2019-06-28 | 2020-12-30 | 西门子股份公司 | Semantic model instantiation method, system and device |
| CN113761971A (en) * | 2020-06-02 | 2021-12-07 | 中国人民解放军战略支援部队信息工程大学 | Method and device for constructing target knowledge graph of remote sensing image |
| CN112559534A (en) * | 2020-12-24 | 2021-03-26 | 山东省国土测绘院 | Remote sensing image data filing management system and method |
| CN113590894A (en) * | 2021-07-12 | 2021-11-02 | 浙江大学 | Dynamic and efficient remote sensing image metadata warehousing retrieval method |
| CN115017354A (en) * | 2022-06-23 | 2022-09-06 | 郑州大学 | Task-driven remote sensing image metadata semantic reasoning method under space-time constraint |
Non-Patent Citations (3)
| Title |
|---|
| 周翔;: "多源遥感影像管理与分发集成研究", 测绘与空间地理信息, no. 07 * |
| 许芳明;: "面向分发服务的海量影像数据管理系统设计与实现", 测绘与空间地理信息, no. 07 * |
| 黄冬梅;许琼琼;杜艳玲;贺琪;: "基于DBNMI模型的海洋遥感影像自动标注方法", 中国科学技术大学学报, no. 07 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116501304A (en) * | 2023-06-28 | 2023-07-28 | 中国科学院空天信息创新研究院 | Cloud-based model creation method and device for remote sensing product production algorithm |
| CN116501304B (en) * | 2023-06-28 | 2023-08-22 | 中国科学院空天信息创新研究院 | Cloud-based model creation method and device for remote sensing product production algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115795075B (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112270027B (en) | Paperless intelligent interactive examination method for city design based on entity model | |
| Park et al. | Information systems interoperability: What lies beneath? | |
| US5659723A (en) | Entity/relationship to object oriented logical model conversion method | |
| KR100745442B1 (en) | Support for multiple content-management data models | |
| CN113434623B (en) | Fusion method based on multi-source heterogeneous space planning data | |
| CN106663101A (en) | Ontology mapping method and apparatus | |
| Unbehauen et al. | Knowledge extraction from structured sources | |
| US8166075B2 (en) | Method for mapping an X500 data model onto a relational database | |
| CN108959353B (en) | Object data organization method | |
| CN105260300B (en) | Service test method based on accounting standard universal classification standard application platform | |
| CN114968984A (en) | Digital twin full life cycle management platform | |
| US7159171B2 (en) | Structured document management system, structured document management method, search device and search method | |
| CN115795075B (en) | Method for constructing universal model of remote sensing image product | |
| EP4155965A1 (en) | System and method for facilitating metadata identification and import | |
| Tauscher et al. | A modular graph transformation rule set for IFC‐to‐CityGML conversion | |
| CN116702892A (en) | Knowledge base generation method and device, electronic equipment and storage medium | |
| CN114880483A (en) | Metadata knowledge graph construction method, storage medium and system | |
| Krijnen | Efficient storage and retrieval of detailed building models: multi-disciplinary and long-term use of geometric and semantic construction information | |
| Varadharajulu et al. | Spatial data supply chains | |
| CN116415430B (en) | Customized SysML model conversion method oriented to space science task demonstration | |
| US11940951B2 (en) | Identification and import of metadata for extensions to database artefacts | |
| van Bennekom-Minnema | The Land Administration Domain Model Survey Package and Model Driven Architecture | |
| EP4361868A1 (en) | Access controls for modelled content using namespaces | |
| Yang et al. | Semantic enhancement and ontology for interoperability of design information systems | |
| Nassis et al. | Goal-oriented requirement engineering for XML document warehouses |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |