A multi-dimensional retrieval method, device, medium and product for ground feature spectral data

Abstract

The present invention discloses a multi-dimensional retrieval method, device, medium and product for surface object spectral data, which relates to the field of hyperspectral remote sensing. The method comprises: establishing an attribute table; obtaining acquisition point information and historical spectral data information; generating a unique spatial identification code for the acquisition point information; performing spectral acquisition encoding on the acquisition point information according to the spatial identification code to obtain encoded acquisition point information; encoding the historical spectral data information to obtain encoded historical spectral data information; establishing a spectral acquisition record table according to the attribute table, the encoded acquisition point information and the encoded historical spectral data information; and realizing multi-dimensional retrieval of surface object spectral data according to the spectral acquisition record table and instructions to be retrieved. The present invention can realize efficient processing and analysis of massive spectral data.

Description

Technical Field

[0001] The present invention relates to the field of hyperspectral remote sensing, and in particular to a method, device, medium and product for multi-dimensional retrieval of ground object spectral data. Background Art

[0002] The ground object spectral database is a database that collects the measured spectra of typical ground objects and can cover the spectra and characteristic parameters of a variety of typical ground targets. The construction of a high-quality ground object spectral database is an indispensable part of basic and applied research in remote sensing. It plays a very important role in developing new methods for remote sensing information processing and improving the level of remote sensing. Over the years, various domestic and foreign institutions have acquired a large amount of spectral data and established a series of spectral databases based on different disciplinary backgrounds. These spectral databases have played a very important role in promoting the development and application of remote sensing technology.

[0003] With the continuous development of hyperspectral imaging technology, the acquired spectral data of ground objects are becoming more and more abundant and detailed. These data not only contain information in the visible light band, but also extend to the infrared, microwave and other spectral bands. Different bands and their characteristic combinations can reflect different ground objects and their corresponding physical and chemical information. Therefore, how to effectively retrieve these multi-dimensional spectral data has become an important research issue.

[0004] At present, remote sensing data presents typical "big data" characteristics, which are a combination of obvious high-dimensional, multi-scale, non-stationary internal features and large-capacity, multi-type, high-efficiency, difficult-to-identify, and high-value external features. Therefore, the acquired ground object spectral data must have "fine" features such as detailed ground object categories, high ground object spectral resolution, and ground object long-time series spectral data. It also requires that the ground object types must be comprehensive, and the ground object spectra must have multiple spectral bands such as visible light, near infrared or thermal infrared, and even microwaves. The spectrum should be as "comprehensive" as possible. Therefore, ground object spectral data retrieval faces the challenge of the big data era. In the big data era, remote sensing data presents an explosive growth trend, and data mining is an effective method and important means of remote sensing analysis. Compared with the traditional remote sensing information extraction process, data mining emphasizes automation more. Starting from a large amount of spectral data or the entire spectral library, it uses artificial neural networks, decision trees, and deep learning methods to automatically search and discover the internal connections and hidden knowledge between data. And the massive spectral data requires efficient storage, management, and retrieval methods to quickly extract the information of interest to users.

[0005] Ground feature spectral data are widely used in many fields, such as agriculture, forestry, urban planning, environmental monitoring, etc. These fields have different requirements for the processing and analysis of spectral data, which has promoted the continuous development of multi-dimensional data management and retrieval research.

[0006] There is a need for multi-dimensional data management in the retrieval of ground feature spectral data. Multi-dimensional data management refers to classifying and organizing data according to different attributes or characteristics for efficient query and analysis. For ground feature spectral data, its multi-dimensional characteristics make it difficult for traditional data management methods to meet the needs. Therefore, it is necessary to study multi-dimensional data retrieval methods suitable for the characteristics of spectral data to achieve efficient processing and analysis of massive spectral data. Summary of the invention

[0007] The purpose of the present invention is to provide a multi-dimensional retrieval method, device, medium and product for ground object spectral data, which can realize efficient processing and analysis of massive spectral data.

[0008] To achieve the above object, the present invention provides the following solutions:

[0009] In a first aspect, the present invention provides a multi-dimensional retrieval method for ground object spectral data, the multi-dimensional retrieval method for ground object spectral data comprising:

[0010] Establish an attribute table; the attribute table includes: a sensor parameter attribute table, a typical ground object classification attribute table and a spectral typical feature attribute table.

[0011] Acquire collection point information and historical spectral data information; the collection point information includes: spectral collection data of hyperspectral satellite image pixels at the collection point and ground collection and survey data corresponding to the collection point; the historical spectral data information includes spectral data of different typical ground objects obtained by field measurement using ground object spectral instruments in previous work, typical ground object spectral data collected from other spectral databases at home and abroad, and related supporting parameter information.

[0012] A unique spatial identification code is generated for the collection point information.

[0013] The collection point information is spectrally encoded according to the space identification code to obtain encoded collection point information.

[0014] The historical spectrum data information is encoded to obtain encoded historical spectrum data information.

[0015] A spectrum collection record table is established according to the attribute table, the encoded collection point information and the encoded historical spectrum data information.

[0016] According to the spectrum collection record table and the instructions to be searched, multi-dimensional search of ground object spectrum data is realized.

[0017] Optionally, generating a unique spatial identification code for the collection point information specifically includes:

[0018] GIS software is used to determine whether the collection point information is valid and obtain a determination result.

[0019] If the judgment result is no, the collection point information is converted to generate a unique space identification code.

[0020] If the judgment result is yes, a unique spatial identification code is generated for the collection point information.

[0021] Optionally, the judgment conditions for judging whether the collection point information is valid by using GIS software include: whether the collection point location is appropriate, whether the collection point geographic reference meets the requirements, and whether the collection point attribute name and data format and type meet the requirements.

[0022] Optionally, performing spectrum collection encoding on the collection point information according to the space identification code to obtain the encoded collection point information specifically includes:

[0023] According to the spatial identification code, the spectral acquisition data of the hyperspectral satellite image pixel of the acquisition point is encoded according to the spatial dimension, the temporal dimension and the sensor dimension to obtain a first spectral acquisition code.

[0024] According to the spatial identification code, the ground collection and survey data corresponding to the collection point are encoded according to the spatial dimension, the time dimension, and the sensor dimension to obtain a second spectrum collection code.

[0025] Optionally, encoding the historical spectrum data information to obtain the encoded historical spectrum data information specifically includes:

[0026] The historical spectral data information is standardized to obtain standardized historical spectral data.

[0027] The standardized historical spectrum data is encoded to obtain a third spectrum acquisition code.

[0028] Optionally, the instructions to be retrieved include: attribute query, spatial query and multi-attribute joint query.

[0029] Optionally, the multi-dimensional retrieval method for ground object spectral data further includes: spectral curve display, spectral data spatial position display, spectral data attribute information viewing and map display.

[0030] In a second aspect, the present invention provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described multi-dimensional retrieval methods for spectral data of ground objects.

[0031] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned multi-dimensional retrieval methods for spectral data of ground objects.

[0032] In a fourth aspect, the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned multi-dimensional retrieval methods for spectral data of ground objects.

[0033] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0034] The present invention provides a multi-dimensional retrieval method, device, medium and product for spectral data of ground objects. By establishing an attribute table and encoding the acquired collection point information and historical spectral data information, a spectral collection record table is established to achieve multi-dimensional management of spectral data; and then, according to the spectral collection record table and the instructions to be retrieved, comprehensive retrieval and customized retrieval of different characteristic attributes of different ground object types can be achieved. Compared with the traditional automatic search of remote sensing information and the discovery of the inherent connection and hidden knowledge between data, the present invention can quickly retrieve the spectral related information of interest to the user, thereby achieving efficient processing and analysis of massive spectral data. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 This is a diagram of the application environment of a multi-dimensional retrieval method for ground object spectral data in one embodiment of the present invention.

[0037] Figure 2 A schematic flow chart of a method for multi-dimensional retrieval of ground object spectral data provided by an embodiment of the present invention.

[0038] Figure 3 A schematic diagram of a multi-dimensional management and retrieval method for spectral data provided by an embodiment of the present invention.

[0039] Figure 4 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] The multi-dimensional retrieval method for ground object spectral data provided by the embodiment of the present invention can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the instruction to be retrieved to the server 104. After the server 104 receives the instruction to be retrieved, the server 104 establishes an attribute table for the instruction to be retrieved; the attribute table includes: a sensor parameter attribute table, a typical ground object classification attribute table and a spectral typical feature attribute table; obtains collection point information and historical spectral data information; the collection point information includes: the spectral collection data of the pixel of the high-spectral satellite image at the collection point and the ground collection and survey data corresponding to the collection point; the historical spectral data information includes different typical ground object target spectral data obtained by field measurement using ground object spectral instruments in previous work, typical ground object spectral data collected in other spectral databases at home and abroad and related supporting parameter information; generates a unique spatial identification code for the collection point information; performs spectral collection encoding on the collection point information according to the spatial identification code to obtain the encoded collection point information; encodes the historical spectral data information to obtain the encoded historical spectral data information; establishes a spectral collection record table according to the attribute table, the encoded collection point information and the encoded historical spectral data information; realizes multi-dimensional retrieval of ground object spectral data according to the spectral collection record table and the instruction to be retrieved. The server 104 can feed back the obtained spectrum collection record table to the terminal 102. In addition, in some embodiments, the multi-dimensional retrieval method of ground feature spectrum data can also be implemented by the server 104 or the terminal 102 alone, such as the terminal 102 can directly search for the to-be-searched instruction, or the server 104 can obtain the to-be-searched instruction from the data storage system and search for the to-be-searched instruction.

[0043] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0044] In an exemplary embodiment, Figure 2 and Figure 3 As shown, a multi-dimensional retrieval method for ground object spectral data is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In an embodiment of the present invention, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S1 to S7. Among them:

[0045] S1: Establish an attribute table; the attribute table includes: a sensor parameter attribute table, a typical ground object classification attribute table and a spectral typical feature attribute table.

[0046] S2: Obtaining the collection point information and historical spectral data information; the collection point information includes: the spectral collection data of the hyperspectral satellite image pixel at the collection point and the ground collection and survey data corresponding to the collection point; the historical spectral data information includes the spectral data of different typical ground objects obtained by field measurement using ground object spectral instruments in previous work, the typical ground object spectral data collected from other spectral databases at home and abroad, and their related supporting parameter information.

[0047] S3: Generate a unique spatial identification code for the collection point information.

[0048] S4: performing spectrum collection encoding on the collection point information according to the space identification code to obtain encoded collection point information.

[0049] S5: Encode the historical spectrum data information to obtain encoded historical spectrum data information.

[0050] S6: establishing a spectrum collection record table according to the attribute table, the encoded collection point information and the encoded historical spectrum data information.

[0051] S7: Implement multi-dimensional retrieval of ground object spectral data according to the spectral collection record table and the instructions to be retrieved; the instructions to be retrieved include: attribute query, spatial query and multi-attribute joint query.

[0052] The implementation of the above steps S1 to S7 not only realizes the management of a table for typical objects at target collection points when the attributes are greatly different, but also facilitates further efficient retrieval by combining conventional fields with extended fields; it also realizes the storage of a large amount of spectral data according to spatial dimensions, spatially encodes the main identification of the collection points, and establishes spatial indexes for the location coordinates of the collection points, which not only optimizes the retrieval efficiency but also facilitates the distributed storage of spectral data; it also realizes the storage of spectral data in tables according to the time dimension, and stores the current data and historical data of the spectral data separately, which is convenient for adapting to different retrieval requirements and improving the system response speed; it also realizes the encoding of relevant attributes according to the sensor dimension, the object classification dimension, and the spectral feature dimension, and respectively establishes the sensor parameter attribute table, the typical object classification attribute table, and the spectral typical feature attribute table, which provides strong support for the construction of the spectral library; finally, it realizes the comprehensive retrieval and customized retrieval of different feature attributes of different object types, and customizes the screening rules and sorting rules for specific attributes according to different retrieval requirements, as well as customizes the attribute visibility on demand, which improves the retrieval efficiency and flexibility.

[0053] In another exemplary embodiment of the present invention, an attribute table is established for attribute information such as sensor parameters, typical land object classification and typical spectral characteristics involved in spectral data organization and management. The attribute table will form a spectral acquisition record table together with the attribute information such as spatial attributes and time attributes obtained in subsequent steps, thereby facilitating the identification of spectral characteristics of typical land objects and spectral retrieval.

[0054] S101: Create a sensor parameter attribute table according to the sensor type dimension to record the sensor parameters of various space and ground platforms.

[0055] Among them, the method for creating a sensor parameter attribute table according to the sensor type dimension described in step S101 records in detail the sensor attributes such as instrument platform, sensor model, measurement altitude (km), imaging width (km), spectral range (nm), number of bands, spectral resolution (nm), spatial resolution (m), regression period (days), imaging time, field of view angle, instantaneous field of view angle, central wavelength (nm), half-wave width, signal-to-noise ratio, etc., so as to facilitate further spectral retrieval and spectral analysis, as shown in Table 1.

[0056] Table 1 Sensor parameter attribute table

[0057]

[0058]

[0059] S102: Creating a hierarchical classification attribute table of typical land objects according to the land object classification dimension, taking into account the spectral characteristics and surface coverage types of typical land objects, and performing fixed-length numerical coding of the unified hierarchical classification of typical land objects.

[0060] Among them, the method of creating a typical land object classification attribute table according to the land object classification dimension described in step S102 is to classify the typical land objects in a hierarchical manner while taking into account the spectral characteristics of the typical land objects and the surface cover type. Typical land objects are classified into two levels according to major categories and subcategories. The major categories include vegetation, water bodies, rocks and minerals, soil, ice and snow frozen soil, and artificial targets. Subcategories are further subdivided level by level under the major categories, which is conducive to playing a role in spectral data management and application analysis. Typical land object classification adopts fixed-length numerical coding to facilitate improving spectral retrieval efficiency. The hierarchical classification attributes of some typical land objects are shown in Table 2.

[0061] Table 2 Classification and attributes of some typical land features

[0062] grade Feature Coding Feature Type 1 1 vegetation 2 1101 arable land 3 110101 paddy fields 3 110102 dry land … … …

[0063] S103: Creating a spectral typical feature attribute table according to the spectral feature dimension, recording spectral type features, spectral single features, regional statistical features and aggregated texture features.

[0064] Among them, the method of creating a typical spectral feature attribute table according to the spectral feature dimension described in step S103 records spectral type features, spectral single features, regional statistical features and aggregated texture features, and performs fixed-length numerical feature encoding on the spectrum according to spectral feature parameters such as redshift / blueshift, peak position, peak width, etc. in the spectral curve, which facilitates the spectral feature recognition and spectral retrieval of typical ground objects. Some typical spectral feature attributes are shown in Table 3.

[0065] Table 3 Typical characteristic properties of some spectra

[0066] Peak Peak width Spectral morphology Spectral curve uncertainty Collection point 1 Collection point 2 … … … … …

[0067] In another exemplary embodiment of the present invention, according to the needs of hyperspectral business monitoring, collection point information can be extracted or screened from various types of field investigation data or hyperspectral images. As typical ground object spectral samples accumulate and business needs change, the collection point information will be adjusted accordingly; typical ground object spectral data and its supporting parameter information obtained by field measurements using ground object spectral instruments in previous work and spectral data and its supporting parameter information in relevant typical ground object spectral databases at home and abroad are collected and summarized.

[0068] Among them, in the method of obtaining the information of the collection points in step S2, the types of collection points mainly include pixel spectral sampling points and field spectrometer measurement points; there are three ways to obtain the collection points: manual selection, automatic extraction from surface cover patches and automatic extraction from remote sensing images. The method of manually selecting the collection points is to select appropriate collection points for the area of ​​interest considering the requirements of easy observation and adaptation to the resolution of hyperspectral satellite images; the method of automatically extracting the collection points from the surface cover patches is to uniformly extract and screen the appropriate collection points according to certain rules based on the two constraints of the distance between two points of the same type of features and the buffer width of the collection points (the features in the buffer are homogeneous features); the method of automatically extracting the collection points from the remote sensing images is to first perform unsupervised classification on the remote sensing images, then extract the classification patches, and then use the same method as the surface cover patches to extract and screen the collection points.

[0069] The historical spectral data information is cleaned and normalized for the spectral data of different typical land objects obtained by field measurements using land object spectral instruments in previous work, the spectral data of typical land objects collected in other domestic and foreign spectral databases, and their related supporting parameter information, so as to eliminate the differences in naming, type, accuracy, attributes, etc. of spectral data and their attribute data from different sources, and appropriately map and convert the input data. The common attributes of typical land objects are stored in basic fields, and the unique attributes of typical land objects are stored in extended fields in JSON format, thereby forming a unified spectral data structure.

[0070] The acquisition point information obtained in step S2 is encoded into the database according to the spatial dimension, and the encoding is a fixed-length numerical code. At the same time, the longitude and latitude coordinates converted to integers are recorded to facilitate rapid spatial retrieval. The acquisition point coordinate code will be used as part of the spectral sampling code.

[0071] The method of encoding the collection point information according to the spatial dimension and entering it into the database involves the combination of geographic information system (GIS) and database technology, which is a further processing of the collection point information. First, the validity of the collection point information is checked using GIS software, including three aspects of inspection: (1) Whether the location of the collection point is appropriate. By superimposing the collection point on the high-resolution satellite image, it is manually visually determined whether the area near the collection point is the same homogeneous feature; (2) Whether the geographic reference of the collection point meets the requirements. For example, if the CGCS2000 coordinate system is required, but the collection point is in the WGS84 coordinate system, it does not meet the requirements. The collection point needs to be reprojected to convert it into a geographic reference that meets the requirements; (3) Whether the attribute name, data format and type of the collection point meet the requirements. For example, if the name, field length, field type, etc. of the attribute field do not meet the requirements, the collection point is converted to make it compatible with the GIS system and database; then, a unique spatial identification code is generated for each collection point information. The encoding rule is 1-bit quadrant code + 7-bit latitude value + 8-bit longitude value. The quadrant code is based on a plane rectangular coordinate system with the equator as the X-axis and the prime meridian as the Y-axis. The longitude and latitude values ​​are the values ​​of the longitude and latitude of the collection point coordinates multiplied by 100,000 and rounded. For example, if the location of the collection point is (31.701°N, 96.7568°E), it can be encoded as 0 (quadrant code) + 3170100 (latitude value) + 09675680 (longitude value); that is, step S3 specifically includes: using GIS software to determine whether the collection point information is valid and obtain a determination result; if the determination result is no, converting the collection point information to generate a unique spatial identification code; if the determination result is yes, generating a unique spatial identification code for the collection point information. Finally, a multi-layer grid spatial index is established for the collection point. The spatial index can effectively manage and retrieve these data, ensuring that real-time or near-real-time retrieval responses can be provided even with large amounts of data.

[0072] In another exemplary embodiment of the present invention, the spectral data of the hyperspectral satellite image pixel, the ground collection and survey data at the point are obtained according to the acquired collection point information, and a unified fixed-length numerical encoding is adopted.

[0073] In step S4, it specifically includes:

[0074] S401: According to the spatial identification code, encoding the spectral acquisition data of the hyperspectral satellite image pixel of the acquisition point according to the spatial dimension, the time dimension, and the sensor dimension to obtain a first spectral acquisition code;

[0075] The spectral collection data of the pixel of the hyperspectral satellite image at the collection point is encoded according to the spatial dimension, time dimension and sensor dimension. The code is a fixed-length character code and can be used as the main identifier of the spectral data of the pixel of the collection point. The spectral collection data of the pixel of the hyperspectral satellite image at the collection point includes the spectral data of the pixel of the ground object, the name of the satellite image and the high spatial resolution image footprint picture corresponding to the collection point; the pixel spectral collection data of each period of the hyperspectral satellite image corresponding to the collection point is used as a monitoring collection of the collection point and recorded in the spectral collection record table; a collection point can have multiple spectral collection data from different sensors and different phases.

[0076] Among them, the method of encoding the spectral acquisition data of the hyperspectral satellite image pixel of the acquisition point according to the spatial dimension, the temporal dimension, and the sensor dimension in step S401 involves the generation of the primary key in the distributed database, which needs to take into account the global uniqueness and scalability. In order to ensure the scalability of the database, the data is dispersed into different databases and tables by using the method of sub-library and sub-table. A distributed unique code generator is used to generate a globally unique spectral acquisition code for each record, and then this code is used as the primary key in different databases and tables. This ensures that even in different databases and tables, the primary key is globally unique, thereby avoiding the problem of primary key conflicts. The encoding rule for spectral acquisition is 16-bit spatial code + 12-bit time code + 4-bit sensor code. The 16-bit spatial code is the same as the spatial identification code in step 3. The 12-bit time code is in the format of 4-bit year + 2-bit month + 2-bit day + 2-bit hour + 2-bit minute. For example, 3:50 am on July 8, 2023 can be encoded as 202307080350. The spectral sensor code is a 2-bit series code + 2-bit sequence code, and it is added to record which image the pixel spectral acquisition data is collected from and a high-spatial resolution footprint image centered on the longitude and latitude coordinates of the pixel that is in the same phase or similar phase as the hyperspectral image.

[0077] S402: According to the spatial identification code, the ground collection and survey data corresponding to the collection point are encoded according to the spatial dimension, the time dimension, and the sensor dimension to obtain a second spectrum collection code.

[0078] The ground collection and investigation data corresponding to the collection point are encoded according to the spatial dimension, time dimension and sensor dimension. The encoding is a fixed-length character encoding and can be used as the main identification of the collection point collection data. The ground collection and investigation data corresponding to the collection point include the ground object spectrum data and ground object attribute information data measured by the ground object spectrometer instrument at the collection point, and the ground object target attribute investigation record data corresponding to the collected pixel spectrum data; the ground collection and investigation data of the collection point is recorded in the spectrum collection record table as a monitoring collection and investigation of the collection point; a collection point can have multiple ground collection and investigation data from different sensors at different times;

[0079] Among them, the method of encoding the ground collection and investigation data corresponding to the collection points described in step S402 according to the spatial dimension, time dimension, and sensor dimension is basically the same as the encoding method in step S401. What needs to be additionally recorded are the field photos corresponding to the ground collection and investigation data of each collection point.

[0080] In another exemplary embodiment of the present invention, the historical spectral data information is obtained, and the collected and summarized historical spectral data information is standardized according to the spectral standard specification to obtain standardized historical spectral data; then the historical spectral data is encoded and a historical spectral data record table is filled in. The historical spectral data record table references the sensor parameter table, the ground object classification table, and the spectral typical feature table as the basic attributes of the spectral data after the standardized processing.

[0081] In step S5, it specifically includes:

[0082] S501: performing standardization processing on the historical spectrum data information to obtain standardized historical spectrum data.

[0083] S502: Encode the standardized historical spectrum data to obtain a third spectrum collection code.

[0084] The historical spectral data information is standardized according to the spectral standard specification to obtain standardized historical spectral data. The spectral data standardization is to eliminate the differences in naming, type, precision, attributes, etc. of spectral data and its attribute data from different sources, and to properly map and convert the input data. The data that cannot be mapped is stored in the extended field in JSON format, thereby forming a unified spectral data structure. Each spectral curve consists of a spectral curve value file (.mdl) and a spectral curve attribute file (.scp).

[0085] In another exemplary embodiment of the present invention, in order to reflect visibility, the multi-dimensional retrieval method for ground feature spectral data further includes: spectral curve display, spectral data spatial position display, spectral data attribute information viewing and map display.

[0086] Through the above steps, we have obtained the spectral acquisition data of the pixels of the hyperspectral satellite images at the acquisition points, the ground acquisition and survey data corresponding to the acquisition points, and the historical spectral data information, and realized the multi-dimensional data management of the space, time, sensor, spectral characteristics and ground object type. The comprehensive retrieval of spectral attributes is based on the aforementioned multi-dimensional management of spectral data, relying on the sub-library and sub-table technology and the classification forwarding and aggregation technology. According to the spatial and temporal dimension information in the retrieval keywords, the retrieval request is dynamically matched to the corresponding spatiotemporal distributed database retrieval service node, and the retrieval result set is summarized; the spatial index, time index, ground object classification index and other dimensional indexes are used to improve the retrieval efficiency; advanced retrieval options are provided, supporting multi-attribute joint retrieval, supporting the customized visibility of each attribute of the retrieval results, and supporting filtering and sorting in the result table; supporting the display of spectral curves in charts, the location of the acquisition points on the map, the display of the footprints of the acquisition points, and the display of the on-site photos of the acquisition points.

[0087] Among them, the spectral attribute comprehensive retrieval method realizes the comprehensive retrieval and customized retrieval of different characteristic attributes of different types of objects, including the following retrieval features:

[0088] (1) It supports the retrieval of spectral data according to multiple dimensions such as time, space, sensor, and object classification. With the support of multi-dimensional fixed-length coding, it realizes efficient retrieval of spectral data.

[0089] (2) It supports presenting different attribute retrieval options according to typical land object classifications (vegetation, water bodies, rocks, minerals, soil, and artificial targets, etc.), thus achieving refined retrieval of spectral data.

[0090] (3) It supports the retrieval of spectral data in separate databases and tables. By parsing the time and space information in the search keywords, the search request is sent to the search service corresponding to different database tables, thereby obtaining one or more search result sets, which are further merged into one search result set for return. The spectral data is stored in separate databases according to the administrative regions to which it belongs, and is stored in separate tables according to current and historical data, thereby effectively controlling the data size of a single table and greatly improving the search efficiency.

[0091] (4) It supports customized filtering and sorting rules for specific attributes, as well as customized attribute visibility on demand, which improves retrieval efficiency and flexibility.

[0092] (5) Supports the graphical display of spectral curves, and realizes the display of single spectrum and superposition of multiple spectrums, which is conducive to intuitive comparison and analysis of spectral characteristics; supports the display of collection points on the map, and realizes the viewing of the geographical attributes of the spectrum from the collection points on the map and the location of the collection points on the map from the records in the search result table; supports the display of footprint pictures and on-site photos of the collection points, which can intuitively understand the surrounding environment of the collection points.

[0093] The present invention can realize the attribute fusion management of typical objects at target collection points when the attributes are greatly different; and store spectral data in partitions according to spatial dimensions, store spectral data in tables according to current and historical data, encode the main identification of the collection point and the spectral collection data of the collection point, and encode the relevant attributes of the standardized historical spectral data according to the sensor dimension, the object classification dimension and the spectral feature dimension, thereby realizing multi-dimensional management of spectral data; and realizes comprehensive retrieval and customized retrieval of different characteristic attributes of different object types, and customizes screening rules and sorting rules for specific attributes according to different retrieval requirements, as well as customizes attribute visibility on demand, thereby improving retrieval efficiency and flexibility.

[0094] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store instructions to be retrieved and spectral acquisition record tables. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a multi-dimensional retrieval method for ground object spectral data is implemented.

[0095] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0096] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the above-mentioned method embodiments are implemented when the processor executes the computer program.

[0097] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0098] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0099] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0100] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0101] The database involved in each embodiment provided by the present invention may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided by the present invention may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0102] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0103] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A multi-dimensional retrieval method for ground object spectral data, characterized in that: The multi-dimensional retrieval method for ground object spectral data comprises: Establishing an attribute table; the attribute table includes: a sensor parameter attribute table, a typical ground object classification attribute table and a spectral typical feature attribute table; Acquire collection point information and historical spectral data information; the collection point information includes: the spectral collection data of the hyperspectral satellite image pixel at the collection point and the ground collection and survey data corresponding to the collection point; the historical spectral data information includes the spectral data of different typical ground objects obtained by field measurement using ground object spectral instruments in previous work, the typical ground object spectral data collected from other spectral databases at home and abroad, and their related supporting parameter information; Generating a unique spatial identification code for the collection point information; Performing spectrum collection encoding on the collection point information according to the space identification code to obtain encoded collection point information; Encoding the historical spectrum data information to obtain encoded historical spectrum data information; Establishing a spectrum collection record table according to the attribute table, the encoded collection point information and the encoded historical spectrum data information; According to the spectrum collection record table and the instructions to be searched, multi-dimensional search of ground object spectrum data is realized; the instructions to be searched include: attribute query, spatial query and multi-attribute joint query; Generate a unique spatial identification code for the collection point information, specifically including: Using GIS software to determine whether the collection point information is valid, and obtaining a determination result; If the judgment result is no, the collection point information is converted to generate a unique space identification code; If the judgment result is yes, a unique spatial identification code is generated for the collection point information; The conditions for judging whether the collection point information is valid by using GIS software include: whether the location of the collection point is appropriate, whether the geographic reference of the collection point meets the requirements, and whether the attribute name, data format and type of the collection point meet the requirements; The spectral collection encoding of the collection point information is performed according to the spatial identification code to obtain the encoded collection point information, specifically including: According to the spatial identification code, the spectral acquisition data of the pixel of the hyperspectral satellite image at the acquisition point is encoded according to the spatial dimension, the time dimension, and the sensor dimension to obtain a first spectral acquisition code; in order to ensure the scalability of the database, the data is dispersed into different databases and tables by using a sub-library and sub-table method, and a distributed unique code generator is used to generate a globally unique spectral acquisition code for each record, and then this code is used as a primary key in different databases and tables; According to the spatial identification code, the ground collection and survey data corresponding to the collection point are encoded according to the spatial dimension, the time dimension, and the sensor dimension to obtain a second spectral collection code; in order to ensure the scalability of the database, the data is dispersed into different databases and tables by using a sub-library and sub-table method, and a distributed unique code generator is used to generate a globally unique spectral collection code for each record, and then this code is used as a primary key in different databases and tables; The historical spectrum data information is encoded to obtain the encoded historical spectrum data information, specifically including: Performing standardization processing on the historical spectral data information to obtain standardized historical spectral data; The standardized historical spectrum data is encoded to obtain a third spectrum collection code.

2. The multi-dimensional retrieval method for ground object spectral data according to claim 1, characterized in that: The multi-dimensional retrieval method for ground object spectral data also includes: spectral curve display, spectral data spatial position display, spectral data attribute information viewing and map display.

3. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the multi-dimensional retrieval method for ground object spectral data as described in claim 1 or 2.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the multi-dimensional retrieval method for ground object spectral data according to claim 1 or 2 is implemented.

5. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the multi-dimensional retrieval method for ground object spectral data according to claim 1 or 2 is implemented.

Images