CN113032350A - Method, system, electronic equipment and storage medium for processing remote sensing data - Google Patents
Method, system, electronic equipment and storage medium for processing remote sensing data Download PDFInfo
- Publication number
- CN113032350A CN113032350A CN202110581342.7A CN202110581342A CN113032350A CN 113032350 A CN113032350 A CN 113032350A CN 202110581342 A CN202110581342 A CN 202110581342A CN 113032350 A CN113032350 A CN 113032350A
- Authority
- CN
- China
- Prior art keywords
- data
- remote sensing
- preset
- data format
- format file
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/172—Caching, prefetching or hoarding of files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/11—File system administration, e.g. details of archiving or snapshots
- G06F16/116—Details of conversion of file system types or formats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/174—Redundancy elimination performed by the file system
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
Abstract
The application relates to a method, a system, an electronic device and a storage medium for processing remote sensing data, wherein the method comprises the following steps: the method comprises the steps of obtaining multi-source remote sensing data, converting the multi-source remote sensing data into a plurality of preset data format files, carrying out spatial position calculation and spatial logic fusion on the preset data format files according to RPC information in the multi-source remote sensing data, establishing a mapping relation between geographic spatial information and the preset data format files, carrying out preset positioning according to geographic region information and the mapping relation in preset services to obtain data in a data storage region of the corresponding preset data format files, carrying out data preprocessing, carrying out target identification on data processing results, and obtaining target identification results. By the method and the device, the problems of low computing efficiency and redundant storage space in the related art are solved, unnecessary temporary files generated in execution are eliminated, actual per-pixel computation is replaced by logic space computation, and time loss of necessary computation is reduced.
Description
Technical Field
The present application relates to the field of remote sensing data processing, and in particular, to a method, a system, an electronic device, and a storage medium for remote sensing data processing.
Background
With the development of remote sensing technology, people have higher and higher requirements on satellite remote sensing data, the quality requirements on the satellite remote sensing data are higher and higher, and the requirements of different works on the remote sensing data are different, so that the satellite remote sensing data needs to be preprocessed, the data quality is improved, and the requirements of different people on the satellite remote sensing data are met, so that the processing of the satellite remote sensing data is particularly important.
At present, no effective solution is provided for the problems of low computational efficiency and redundant storage space in the related art.
Disclosure of Invention
The embodiment of the application provides a method, a system, electronic equipment and a storage medium for processing remote sensing data, and aims to at least solve the problems of low computational efficiency and redundant storage space in the related art.
In a first aspect, an embodiment of the present application provides a method for processing remote sensing data, where the method includes:
acquiring multi-source remote sensing data, and converting the multi-source remote sensing data into a plurality of preset data format files;
according to RPC information in the multi-source remote sensing data, performing spatial position calculation on the preset data format file, performing spatial logic fusion on the preset data format file according to the result of the spatial position calculation, and establishing a mapping relation between geographic spatial information and the preset data format file;
according to geographical area information in a preset service and the mapping relation, carrying out preset positioning to obtain a corresponding preset data format file and a data storage area of the preset data format file;
reading data in the data storage area, and performing data preprocessing on the data to obtain a data processing result;
and carrying out target identification on the data processing result through a target identification algorithm to obtain a target identification result.
In some embodiments, obtaining multi-source remote sensing data, and converting the multi-source remote sensing data into a plurality of preset data format files includes:
the method comprises the steps of obtaining multi-source remote sensing data, and converting the multi-source remote sensing data into a plurality of RAW data format files, wherein the multi-source remote sensing data comprise a single remote sensing image, a plurality of remote sensing images and a video remote sensing image, and the RAW data format files comprise BSQ basic data formats, BIL basic data formats and BIP basic data formats.
In some embodiments, the performing spatial position calculation on the preset data format file according to the RPC information in the multi-source remote sensing data, performing spatial logic fusion on the preset data format file according to a result of the spatial position calculation, and establishing a mapping relationship between the geospatial information and the preset data format file includes:
performing finite point orthotropic transformation on the RAW data format file through RPC calculation according to RPC information in the multi-source remote sensing data;
and mapping the geographical space information with the file name of the RAW data format file according to the orthographic transformation result to generate a space-file mapping table.
In some embodiments, the obtaining, by performing preset positioning according to geographic area information in a preset service and the mapping relationship, a corresponding preset data format file and a data storage area of the preset data format file includes:
obtaining ROI regional information in a preset service, performing vector intersection judgment on the ROI regional information and the mapping relation, obtaining a corresponding RAW data format file,
and performing RPC reverse calculation according to the ROI information to obtain a corresponding data storage area in the RAW data format file.
In some embodiments, reading data in the data storage area, and performing data preprocessing on the data to obtain a data processing result includes:
reading data in a RAW data format file corresponding to ROI (region of interest) information, and performing data preprocessing and data fusion splicing on the data to obtain a data processing result, wherein the data preprocessing comprises orthorectification, control point correction and radiation correction; the range of the data processing result is the range specified by the ROI area information, and the volume of the data processing result is the volume specified by the ROI area information.
In some embodiments, performing target recognition on the data processing result through a target recognition algorithm, and obtaining a target recognition result includes:
and carrying out target identification on the data processing result through a target identification algorithm to obtain a target identification result, storing the target identification result as structured data and outputting the structured data, wherein the target identification algorithm comprises a CNN convolutional neural network algorithm, and the structured data comprises longitude, latitude, time, satellite, target identity and thumbnail.
In some embodiments, before obtaining multi-source remote sensing data and converting the multi-source remote sensing data into a plurality of preset data format files, the method further includes:
and constructing a data acquisition module to realize user management, wherein the data acquisition module can at least directly read the file in the local storage space and complete data loading through a C language basic I/O library.
In a second aspect, an embodiment of the present application provides a system for processing remote sensing data, where the system includes a data acquisition module, a mapping construction module, a region location module, a data preprocessing module, and a target identification module;
the data acquisition module acquires multi-source remote sensing data and converts the multi-source remote sensing data into a plurality of preset data format files;
the mapping construction module performs spatial position calculation on the preset data format file according to RPC information in the multi-source remote sensing data, performs spatial logic fusion on the preset data format file according to the result of the spatial position calculation, and establishes a mapping relation between geographic spatial information and the preset data format file;
the area positioning module performs preset positioning to acquire a corresponding preset data format file and a data storage area of the preset data format file according to geographical area information in a preset service and the mapping relation;
the data preprocessing module reads the data in the data storage area and performs data preprocessing on the data to obtain a data processing result;
and the target recognition module performs target recognition on the data processing result through a target recognition algorithm to obtain a target recognition result.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the method for processing remote sensing data according to the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a storage medium, in which a computer program is stored, where the computer program is configured to implement the method for processing remote sensing data according to the first aspect when the computer program runs.
Compared with the related art, the method, the system, the electronic device and the storage medium for processing the remote sensing data provided by the embodiment of the application convert the multi-source remote sensing data into a plurality of preset data format files by acquiring the multi-source remote sensing data, perform spatial position calculation on the preset data format files according to RPC information in the multi-source remote sensing data, perform spatial logic fusion on the preset data format files according to the result of the spatial position calculation, establish the mapping relation between geographic spatial information and the preset data format files, perform preset positioning according to the geographic area information and the mapping relation in preset services to acquire the data storage areas of the corresponding preset data format files and the preset data format files, read data in the data storage areas to perform data preprocessing to obtain data processing results, and perform target identification on the data processing results, and obtaining a target identification result. The problems of low computational efficiency and redundant storage space in the related art are solved, unnecessary temporary files generated in execution are eliminated, the actual per-pixel calculation is replaced by the logic space calculation, and the time loss of necessary calculation is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flowchart of steps of a method for processing remote sensing data according to the related art;
FIG. 2 is a block diagram of a remote sensing data processing system according to an embodiment of the application;
FIG. 3 is a flow chart of steps of a method of processing remote sensing data according to an embodiment of the application;
FIG. 4 is a schematic flow chart diagram of a method for processing remote sensing data according to an embodiment of the present application;
fig. 5 is an internal structural diagram of an electronic device according to an embodiment of the present application.
Description of the drawings: 20. a data acquisition module; 21. a mapping construction module; 22. an area positioning module; 23. a data preprocessing module; 24. and an object identification module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The technology on which the technical scheme is realized is as follows;
multi-source remote sensing data: the digital image acquisition system comprises data of different meta-resolutions, different pixel resolutions, different regions, different types (visible light, multispectral, hyperspectral, SAR, InSAR, infrared and the like) and different means (satellite remote sensing, aerial remote sensing and the like) with unfixed finger number, and data storage forms such as a single image, a plurality of images, a video remote sensing image and the like;
giant remote sensing data: the data size of a single file in the multi-source remote sensing data description is larger than 2GB, and the data of a plurality of multi-source remote sensing data files can be simultaneously processed in near real time and at high speed. Wherein the supported total file size is smaller than or equal to the size of the actual physical storage space but larger than 2 TB;
the calculation process required for data processing: the method comprises the processes of orthorectification, control point fine correction, radiation correction, data fusion, image enhancement, image extraction and the like;
calculating process of target identification: performing target identification operation by using a CNN algorithm, and forming structured data by using unstructured remote sensing data;
a data computing environment: the general computing environment refers to a conventional von Neumann computer, wherein a CPU (Central processing Unit) is not higher than a quad-core eight-thread 3GHz, a memory is not higher than 16GB, a GPU (graphics processing Unit) frequency is not more than 1.8GHz, and a video memory is not more than 6.2 GB;
near real-time in target fast recognition: the total operation time for executing the target identification operation under the condition of the data computing environment is less than 2 minutes, wherein the total operation time does not include the time for basic transmission and reading of original data in a network or by a CD/hard disk and the like;
roi (region Of interest): a region of interest (ROI), which is an image region selected from an image in machine vision, image processing, and which is a focus of interest for image analysis; various operators (operators) and functions are commonly used on machine vision software such as Halcon, OpenCV, Matlab and the like to obtain a region of interest (ROI); the ROI is used for delineating the target to be read, so that the processing time can be reduced, and the precision can be increased;
RPC (rational polymeric Coefficient): rational polynomial coefficients, the nature of the RPC model is a Rational Function Model (RFM). The image point coordinates (r, c) are expressed as polynomial ratios with corresponding ground point space coordinates (P, L, H) as independent variables, and RFM does not need internal and external orientation elements, thereby avoiding the geometric process of imaging.
In the related art, fig. 1 is a flowchart of steps according to a remote sensing data processing method in the related art, and as shown in fig. 1, the remote sensing data processing method in the related art includes the steps of:
s102, converting the multi-source remote sensing data into a RAW data format file or a custom high-speed file format file:
thereby realizing data preparation of subsequent calculation such as decompression, high-speed processing and the like. The RAW format mainly comprises three basic formats of BIP/BSQ/BIL, which means that each pixel is described in a storage space in a file by a physical space.
S104, respectively carrying out preprocessing operation on the converted data files:
the preprocessing operations include, but are not limited to, orthorectification, control point rectification, radiation correction, etc. to meet the image quality and image spatialization requirements necessary for subsequent calculations. After calculation, the results are saved as one or more temporary files.
S106, carrying out data fusion and splicing operation on the plurality of preprocessed images:
and performing data fusion and splicing to form a large-volume image so as to recover the potential target segmented in the plurality of images. And after calculation, saving the whole file as a temporary file. The file volume is larger than a single file, and increases with the number of files.
S108, framing the generated fusion splicing data
The calculation results of the data fusion and splicing operations have a huge characteristic, and in order to better process the results, framing processing is required. The calculation result is a plurality of cut files, and a single file has a size which can be processed by a memory and is generally smaller than 2 GB.
S110, cutting the plurality of images after framing again:
and cutting the image into a small tile sequence which can be read by the CNN image, wherein the image adopts an RGB/RGBA/GRAY format, and the data bit width is 8bit/10 bit.
S112, respectively carrying out target identification operation on the sequence tiles after cutting:
such as CNN inference calculation, etc., and performs recognition calculation of the target model in the image. If a target is found, the structured information is saved.
As can be seen from S102 to S112 in the related art, the remote sensing data processing method in the related art mainly achieves performance improvement in a manner of improving hardware performance of a computing device, performing cluster supercomputing, and improving a computing algorithm of each node. However, the improvement of the related algorithm cannot solve the basic problems existing in the above S102 to S112, which mainly includes the following four points;
first, after each operation except S112, a temporary file stored in the hard disk is formed, which results in storage space consumption and I/O (input/output) time loss at least 5 times as much as the original file volume;
second, the data fusion and stitching operation in S106 must be guaranteed to be the same ground resolution since it is derived as one image. If the lowest resolution is selected, the information amount of the high-resolution image is lost, if the highest resolution is selected, the space for storing data is increased, the processing time for performing super-resolution processing when the data resolution is increased is additionally increased, and more I/O time loss is required to be borne; secondly, data information loss or I/O redundancy can be caused by a data standard normalization process when visible light, multiple spectra, SAR and the like are stored in one picture;
thirdly, in the framing process of S108, in order to ensure that the potential target is not divided into a plurality of images, the framed images must have an overlapping data area, the length and width of the overlapping area are the calculated size of the maximum size of the target to be identified and the size of the framed image, and the size of a single image is:
target width = Max (target 1 width, target 2 width, target 3 width …)
Target height = Max (target 1 height, target 2 height, target 3 height …)
Number of frames = original image volume/maximum frame volume
Framing width = [ original image width/(original image volume/maximum framing volume) ] + target width
Framing height = [ original height/(original volume/maximum framing volume) ] + target height
Framing volume = framing width × (framing height)
Total data space after framing = frame volume and frame number
Because the data after framing has data redundancy, redundant data I/O and loss of calculation time are brought.
The fourth point, S110 tiling, is the same data redundancy operation as S108, with the same loss of I/O and computation time.
The embodiment of the application provides a system for processing remote sensing data, fig. 2 is a structural block diagram of the system for processing remote sensing data according to the embodiment of the application, and as shown in fig. 2, the system comprises a data acquisition module 20, a mapping construction module 21, an area positioning module 22, a data preprocessing module 23 and a target identification module 24;
the data acquisition module 20 acquires multi-source remote sensing data and converts the multi-source remote sensing data into a plurality of preset data format files;
the mapping construction module 21 performs spatial position calculation on a preset data format file according to RPC information in the multi-source remote sensing data, performs spatial logic fusion on the preset data format file according to a spatial position calculation result, and establishes a mapping relation between geographic spatial information and the preset data format file;
the area positioning module 22 performs preset positioning to acquire a corresponding preset data format file and a data storage area of the preset data format file according to the geographical area information and the mapping relation in the preset service;
the data preprocessing module 23 reads data in the data storage area, and performs data preprocessing on the data to obtain a data processing result;
the target recognition module 24 performs target recognition on the data processing result through a target recognition algorithm to obtain a target recognition result.
According to the embodiment of the application, the data acquisition module acquires multi-source remote sensing data and converts the multi-source remote sensing data into a plurality of preset data format files; the mapping construction module performs spatial position calculation on a preset data format file according to RPC information in the multi-source remote sensing data, performs spatial logic fusion on the preset data format file according to a spatial position calculation result, and establishes a mapping relation between geographic spatial information and the preset data format file; the area positioning module performs preset positioning to acquire a corresponding preset data format file and a data storage area of the preset data format file according to geographical area information and a mapping relation in a preset service; the data preprocessing module reads data in the data storage area and performs data preprocessing on the data to obtain a data processing result; the target recognition module carries out target recognition on the data processing result to obtain a target recognition result, the problems of low calculation efficiency and redundant storage space in the related technology are solved, unnecessary temporary files generated in execution are eliminated, actual per-pixel calculation is replaced by logic space calculation, and time loss of necessary calculation is reduced.
The embodiment of the application provides a method for processing remote sensing data, fig. 3 is a flow chart of steps of the method for processing remote sensing data according to the embodiment of the application, and as shown in fig. 3, the method comprises the following steps:
s302, obtaining multi-source remote sensing data, and converting the multi-source remote sensing data into a plurality of preset data format files;
s304, according to RPC information in the multi-source remote sensing data, performing spatial position calculation on a preset data format file, according to the result of the spatial position calculation, performing spatial logic fusion on the preset data format file, and establishing a mapping relation between geographic spatial information and the preset data format file;
s306, according to the geographical area information and the mapping relation in the preset service, carrying out preset positioning to obtain the corresponding preset data format file and the data storage area of the preset data format file;
s308, reading the data in the data storage area, and performing data preprocessing on the data to obtain a data processing result;
and S310, performing target recognition on the data processing result through a target recognition algorithm to obtain a target recognition result.
Through steps S302 to S310 in the embodiment of the application, multi-source remote sensing data are obtained, the multi-source remote sensing data are converted into a plurality of preset data format files, according to RPC information in the multi-source remote sensing data, spatial position calculation is carried out on the preset data format files, according to the result of the spatial position calculation, spatial logic fusion is carried out on the preset data format files, the mapping relation between geographic spatial information and the preset data format files is established, according to geographic region information and the mapping relation in preset services, preset positioning is carried out to obtain the corresponding preset data format files and the data storage regions of the preset data format files, data in the data storage regions are read for data preprocessing, data processing results are obtained, and target recognition is carried out on the data processing results to obtain target recognition results. The problems of low computational efficiency and redundant storage space in the related art are solved, unnecessary temporary files generated in execution are eliminated, the actual per-pixel calculation is replaced by the logic space calculation, and the time loss of necessary calculation is reduced.
In some embodiments, obtaining the multi-source remote sensing data, and converting the multi-source remote sensing data into a plurality of preset data format files includes:
the method comprises the steps of obtaining multi-source remote sensing data, and converting the multi-source remote sensing data into a plurality of RAW data format files, wherein the multi-source remote sensing data comprise a single remote sensing image, a plurality of remote sensing images and a video remote sensing image, and the RAW data format files comprise BSQ basic data formats, BIL basic data formats and BIP basic data formats.
In some embodiments, the calculating the spatial position of the preset data format file according to the RPC information in the multi-source remote sensing data, performing spatial logic fusion on the preset data format file according to the result of the spatial position calculation, and establishing the mapping relationship between the geospatial information and the preset data format file includes:
performing finite point orthotropic transformation on the RAW data format file through RPC calculation according to RPC information in the multi-source remote sensing data;
and mapping the geographic space information and the file name of the RAW data format file according to the result of the orthometric transformation to generate a space-file mapping table.
In some embodiments, the obtaining the corresponding preset data format file and the data storage area of the preset data format file by performing the preset positioning according to the geographical area information and the mapping relationship in the preset service includes:
obtaining ROI regional information in the preset service, performing vector intersection judgment on the ROI regional information and the mapping relation, obtaining a corresponding RAW data format file,
and performing RPC reverse calculation according to the ROI information to obtain a data storage area in the corresponding RAW data format file.
In some embodiments, reading data in the data storage area, and performing data preprocessing on the data to obtain a data processing result includes:
reading data in an RAW data format file corresponding to the ROI information, and performing data preprocessing and data fusion splicing on the data to obtain a data processing result, wherein the data preprocessing comprises orthorectification, control point correction and radiation correction; the range of the data processing result is defined by the ROI region information, and the volume of the data processing result is defined by the ROI region information.
In some embodiments, performing target recognition on the data processing result through a target recognition algorithm, and obtaining a target recognition result includes:
and carrying out target identification on the data processing result through a target identification algorithm to obtain a target identification result, storing the target identification result as structured data and outputting the structured data, wherein the target identification algorithm comprises a CNN convolutional neural network algorithm, and the structured data comprises longitude, latitude, time, satellite, target identity and thumbnail.
In some embodiments, before obtaining the multi-source remote sensing data and converting the multi-source remote sensing data into a plurality of preset data format files, the method further includes:
and constructing a data acquisition module to realize user management, wherein the data acquisition module can at least directly read the file in the local storage space and complete data loading through the C language basic I/O library.
The specific embodiment of the present application provides a method for processing remote sensing data, fig. 4 is a schematic flow chart of the method for processing remote sensing data according to the specific embodiment of the present application, and as shown in fig. 4, the method includes the following steps:
step 1, inputting:
the data acquisition module is constructed and acquires multi-source remote sensing data, the data acquisition module can realize user management under different means, including modes of passive, active, network push, medium copy and the like, and the most basic mode is to directly read files in a local storage space and use a C language basic I/O library to realize data loading.
Step 2, preparing:
the method comprises the steps of converting multi-source remote sensing data input in different file formats into standard RAW data format files, wherein the different file formats are respectively defined by related organizations and units, reading all pixel information of the files through related driving interfaces, and storing the pixel information into three basic formats including but not limited to BSQ/BIL/BIP. If the input contains multiple files, the conversion is performed separately for each file against a list of files.
Step 3, spatialization:
and performing finite point orthometric transformation in a memory through an RPC algorithm by utilizing shooting information such as RPC carried by an original remote sensing image, and if the input comprises a plurality of files, performing the calculation on each file aiming at a file list.
And 4, logic fusion:
and (3) mapping the data obtained after the orthographic transformation in the step (3) with the file name of the file in the RAW data format to generate a space and file mapping table, storing the space and file mapping table in a memory, if the input comprises a plurality of files, respectively performing the calculation on each file aiming at the file list, and organizing and managing all the calculated space and file mapping tables to form a logic map based on space coordinates.
Step 5, ROI positioning:
and carrying out vector intersection judgment on the ROI information input by the user, the space in the memory and the file mapping table, and confirming the corresponding RAW data format file. Then, the position of the corresponding RAW data format file and the ROI spatial position are subjected to RPC reverse calculation (World to Image), so as to obtain a specific data storage region of the corresponding RAW data format file.
Step 6, ROI data extraction:
and reading the actual data in the data storage area confirmed in the step 5 into the memory. If ROI intersect multiple RAW data format files, respectively executing the above reading
Step 7, ROI data preprocessing:
performing data preprocessing and data fusion splicing on the data read in the step 6, and forming a RAW data result in the ROI range in a memory, wherein the volume is the volume required by the ROI, and the data preprocessing comprises operations such as orthorectification, control point correction, radiation correction and the like so as to meet the image quality and image spatialization requirements required by subsequent calculation; the range of the data processing result is defined by the ROI region information, and the volume of the data processing result is defined by the ROI region information.
Step 8, target identification:
and sending the data result to a target identification module, and executing related operations such as CNN reasoning and the like.
And 9, outputting:
and saving the target identification result obtained in the step 8 as structured data for outputting, wherein the structured data comprises but is not limited to longitude, latitude, time, satellite, target identity and thumbnail.
In addition, in combination with the method for processing remote sensing data in the foregoing embodiments, the embodiments of the present application may provide a storage medium to implement. The storage medium having stored thereon a computer program; the computer program, when executed by a processor, implements any of the methods of remote sensing data processing in the above embodiments.
In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of remote sensing data processing. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
In one embodiment, fig. 5 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present application, and as shown in fig. 5, an electronic device is provided, where the electronic device may be a server, and the internal structure diagram may be as shown in fig. 5. The electronic device comprises a processor, a network interface, an internal memory and a non-volatile memory connected by an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is used for providing calculation and control capability, the network interface is used for communicating with an external terminal through network connection, the internal memory is used for providing an environment for an operating system and the running of a computer program, the computer program is executed by the processor to realize a remote sensing data processing method, and the database is used for storing data.
Those skilled in the art will appreciate that the configuration shown in fig. 5 is a block diagram of only a portion of the configuration associated with the present application, and does not constitute a limitation on the electronic device to which the present application is applied, and a particular electronic device may include more or less components than those shown in the drawings, or may combine certain components, or have a different arrangement of components.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It should be understood by those skilled in the art that various features of the above-described embodiments can be combined in any combination, and for the sake of brevity, all possible combinations of features in the above-described embodiments are not described in detail, but rather, all combinations of features which are not inconsistent with each other should be construed as being within the scope of the present disclosure.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of remote sensing data processing, the method comprising:
acquiring multi-source remote sensing data, and converting the multi-source remote sensing data into a plurality of preset data format files;
according to RPC information in the multi-source remote sensing data, performing spatial position calculation on the preset data format file, performing spatial logic fusion on the preset data format file according to the result of the spatial position calculation, and establishing a mapping relation between geographic spatial information and the preset data format file;
according to geographical area information in a preset service and the mapping relation, carrying out preset positioning to obtain a corresponding preset data format file and a data storage area of the preset data format file;
reading data in the data storage area, and performing data preprocessing on the data to obtain a data processing result;
and carrying out target identification on the data processing result through a target identification algorithm to obtain a target identification result.
2. The method of claim 1, wherein obtaining multi-source remote sensing data and converting the multi-source remote sensing data into a plurality of preset data format files comprises:
the method comprises the steps of obtaining multi-source remote sensing data, and converting the multi-source remote sensing data into a plurality of RAW data format files, wherein the multi-source remote sensing data comprise a single remote sensing image, a plurality of remote sensing images and a video remote sensing image, and the RAW data format files comprise BSQ basic data formats, BIL basic data formats and BIP basic data formats.
3. The method of claim 1, wherein the step of performing spatial position calculation on the preset data format file according to RPC information in the multi-source remote sensing data, the step of performing spatial logic fusion on the preset data format file according to a result of the spatial position calculation, and the step of establishing a mapping relationship between the geographic spatial information and the preset data format file comprises the steps of:
performing finite point orthotropic transformation on the RAW data format file through RPC calculation according to RPC information in the multi-source remote sensing data;
and mapping the geographical space information with the file name of the RAW data format file according to the orthographic transformation result to generate a space-file mapping table.
4. The method of claim 1, wherein performing a preset location to obtain a corresponding preset data format file and a data storage area of the preset data format file according to geographical area information in a preset service and the mapping relationship comprises:
obtaining ROI regional information in a preset service, performing vector intersection judgment on the ROI regional information and the mapping relation, obtaining a corresponding RAW data format file,
and performing RPC reverse calculation according to the ROI information to obtain a corresponding data storage area in the RAW data format file.
5. The method of claim 1, wherein reading the data in the data storage area, and performing data preprocessing on the data to obtain a data processing result comprises:
reading data in a RAW data format file corresponding to ROI (region of interest) information, and performing data preprocessing and data fusion splicing on the data to obtain a data processing result, wherein the data preprocessing comprises orthorectification, control point correction and radiation correction; the range of the data processing result is the range specified by the ROI area information, and the volume of the data processing result is the volume specified by the ROI area information.
6. The method of claim 1, wherein performing target recognition on the data processing result through a target recognition algorithm to obtain a target recognition result comprises:
and carrying out target identification on the data processing result through a target identification algorithm to obtain a target identification result, storing the target identification result as structured data and outputting the structured data, wherein the target identification algorithm comprises a CNN convolutional neural network algorithm, and the structured data comprises longitude, latitude, time, satellite, target identity and thumbnail.
7. The method of claim 1, wherein prior to obtaining the multi-source remote sensing data and converting the multi-source remote sensing data into a plurality of preset data format files, the method further comprises:
and constructing a data acquisition module to realize user management, wherein the data acquisition module can at least directly read the file in the local storage space and complete data loading through a C language basic I/O library.
8. A system for processing remote sensing data is characterized by comprising a data acquisition module, a mapping construction module, a region positioning module, a data preprocessing module and a target identification module;
the data acquisition module acquires multi-source remote sensing data and converts the multi-source remote sensing data into a plurality of preset data format files;
the mapping construction module performs spatial position calculation on the preset data format file according to RPC information in the multi-source remote sensing data, performs spatial logic fusion on the preset data format file according to the result of the spatial position calculation, and establishes a mapping relation between geographic spatial information and the preset data format file;
the area positioning module performs preset positioning to acquire a corresponding preset data format file and a data storage area of the preset data format file according to geographical area information in a preset service and the mapping relation;
the data preprocessing module reads the data in the data storage area and performs data preprocessing on the data to obtain a data processing result;
and the target recognition module performs target recognition on the data processing result through a target recognition algorithm to obtain a target recognition result.
9. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor, when executing the computer program, implements a method of remote sensing data processing according to any of claims 1 to 7.
10. A storage medium, in which a computer program is stored, wherein the computer program is configured to carry out the method of remote sensing data processing according to any one of claims 1 to 7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110581342.7A CN113032350A (en) | 2021-05-27 | 2021-05-27 | Method, system, electronic equipment and storage medium for processing remote sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110581342.7A CN113032350A (en) | 2021-05-27 | 2021-05-27 | Method, system, electronic equipment and storage medium for processing remote sensing data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113032350A true CN113032350A (en) | 2021-06-25 |
Family
ID=76455800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110581342.7A Pending CN113032350A (en) | 2021-05-27 | 2021-05-27 | Method, system, electronic equipment and storage medium for processing remote sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113032350A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023164929A1 (en) * | 2022-03-01 | 2023-09-07 | 中国科学院深圳先进技术研究院 | Multi-source remote sensing image fusion method and apparatus, device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100100835A1 (en) * | 2008-10-16 | 2010-04-22 | Curators Of The University Of Missouri | Visualizing geographic-area change detected from high-resolution, remotely sensed imagery |
| CN109493332A (en) * | 2018-11-06 | 2019-03-19 | 北京京航计算通讯研究所 | Optimization vector based on ENVI chooses ROI remote sensing image pretreatment system |
| CN112053364A (en) * | 2020-09-30 | 2020-12-08 | 成都星时代宇航科技有限公司 | Data processing method and device, remote sensing data service platform and readable storage medium |
| CN112417199A (en) * | 2020-12-03 | 2021-02-26 | 深圳前海微众银行股份有限公司 | Remote sensing image retrieval method, device, system and storage medium |
-
2021
- 2021-05-27 CN CN202110581342.7A patent/CN113032350A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100100835A1 (en) * | 2008-10-16 | 2010-04-22 | Curators Of The University Of Missouri | Visualizing geographic-area change detected from high-resolution, remotely sensed imagery |
| CN109493332A (en) * | 2018-11-06 | 2019-03-19 | 北京京航计算通讯研究所 | Optimization vector based on ENVI chooses ROI remote sensing image pretreatment system |
| CN112053364A (en) * | 2020-09-30 | 2020-12-08 | 成都星时代宇航科技有限公司 | Data processing method and device, remote sensing data service platform and readable storage medium |
| CN112417199A (en) * | 2020-12-03 | 2021-02-26 | 深圳前海微众银行股份有限公司 | Remote sensing image retrieval method, device, system and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023164929A1 (en) * | 2022-03-01 | 2023-09-07 | 中国科学院深圳先进技术研究院 | Multi-source remote sensing image fusion method and apparatus, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111080656A (en) | Image processing method, image synthesis method and related device | |
| CN112163577B (en) | Character recognition method and device in game picture, electronic equipment and storage medium | |
| WO2021146937A1 (en) | Character recognition method, character recognition device and storage medium | |
| WO2021174940A1 (en) | Facial detection method and system | |
| CN110944201A (en) | Method, device, server and storage medium for video duplicate removal compression | |
| Fang et al. | Aerial-BiSeNet: A real-time semantic segmentation network for high resolution aerial imagery | |
| JP2008052602A (en) | Image density conversion method, image enhancement processor, and its program | |
| CN103970901A (en) | Geographic information graphic data integration method | |
| CN113032350A (en) | Method, system, electronic equipment and storage medium for processing remote sensing data | |
| CN116415298A (en) | Medical data desensitization method and system | |
| Ma et al. | Log-can: local-global class-aware network for semantic segmentation of remote sensing images | |
| CN113506305A (en) | Image enhancement method, semantic segmentation method and device for three-dimensional point cloud data | |
| US20190220699A1 (en) | System and method for encoding data in an image/video recognition integrated circuit solution | |
| CN113538502A (en) | Picture clipping method and device, electronic equipment and storage medium | |
| US20180146214A1 (en) | Elimination of artifacts from lossy encoding of digital images by color channel expansion | |
| CN116469172A (en) | Bone behavior recognition video frame extraction method and system under multiple time scales | |
| WO2023273515A1 (en) | Target detection method, apparatus, electronic device and storage medium | |
| WO2023272495A1 (en) | Badging method and apparatus, badge detection model update method and system, and storage medium | |
| CN115223181A (en) | Text detection-based method and device for recognizing characters of seal of report material | |
| Eken et al. | Resource-and content-aware, scalable stitching framework for remote sensing images | |
| CN106686387A (en) | Picture compression method for photographing surface of odometer style water meter | |
| CN105160624A (en) | Geographic information picture automatic registration method and apparatus | |
| CN112615993A (en) | Depth information acquisition method, binocular camera module, storage medium and electronic equipment | |
| CN111583168A (en) | Image synthesis method, image synthesis device, computer equipment and storage medium | |
| CN111079581A (en) | Method and device for identifying human skin |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |
|
| RJ01 | Rejection of invention patent application after publication |