Method and system for generating global mosaic of geostationary meteorological satellites based on multiple features

Abstract

The present invention discloses a method and system for generating a global jigsaw puzzle of a geostationary meteorological satellite based on multiple features, and relates to the field of satellite jigsaw puzzle fusion. The method comprises: obtaining an original satellite image set; performing preprocessing based on the original satellite image set to obtain a satellite image data set; performing data splicing and fusion based on the satellite image data set to generate a meteorological satellite jigsaw puzzle; performing cloud detection based on the meteorological satellite jigsaw puzzle to generate a meteorological satellite cloud map. The method solves the technical problems of low quality of satellite jigsaw puzzle images and difficulty in splicing and fusion in the prior art, and achieves the technical effect of improving the quality of satellite jigsaw puzzle images and generating a high-standard global jigsaw puzzle of geostationary meteorological satellites.

Description

Technical Field

[0001] The present application relates to the technical field of data splicing and fusion, and in particular to the field of satellite jigsaw fusion, and specifically to a method and system for generating a global jigsaw puzzle of a geostationary meteorological satellite based on multiple features. Background Art

[0002] In response to the needs of global monitoring, global forecasting, and global services, based on the Fengyun satellites and satellite data from other regions received and processed by the Satellite Meteorological Center, and based on standard file names, images, and data specifications, we will build a global product system for geostationary satellites, polar-orbiting satellites, and high-resolution satellites, as well as a global product system that integrates remote sensing data with other data. We will regularly generate global geostationary satellite cloud images, satellite cloud image products of neighboring countries, major continents and oceans in the world, and other regions of the world, and improve the timeliness of satellite cloud image generation and distribution. However, in the existing technology, the cloud image quality taken by a single satellite is low and contains less content. When fusing multiple cloud image images, it is common for them to be difficult to stitch together. Summary of the invention

[0003] Based on this, it is necessary to provide a method and system for generating a global mosaic of geostationary meteorological satellites based on multiple features to address the above technical issues.

[0004] In a first aspect, a method for generating a global mosaic of geostationary meteorological satellites based on multiple features is provided, the method comprising: obtaining an original satellite image set; performing preprocessing based on the original satellite image set to obtain a satellite image data set; performing data splicing and fusion based on the satellite image data set to generate a meteorological satellite mosaic; performing cloud detection based on the meteorological satellite mosaic to generate a meteorological satellite cloud map.

[0005] In a second aspect, a global jigsaw puzzle generation system for geostationary meteorological satellites based on multiple features is provided, the system comprising: an original satellite image set acquisition module, the original satellite image set acquisition module is used to obtain an original satellite image set; a satellite image data set acquisition module, the satellite image data set acquisition module is used to perform preprocessing based on the original satellite image set to obtain a satellite image data set; a meteorological satellite jigsaw puzzle generation module, the meteorological satellite jigsaw puzzle generation module is used to perform data splicing and fusion based on the satellite image data set to generate a meteorological satellite jigsaw puzzle; a meteorological satellite cloud map generation module, the meteorological satellite cloud map generation module is used to perform cloud detection based on the meteorological satellite jigsaw puzzle to generate a meteorological satellite cloud map.

[0006] According to a third aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps according to the first aspect when executing the computer program.

[0007] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps described in the first aspect are implemented.

[0008] The above-mentioned multi-feature-based geostationary meteorological satellite global puzzle generation method and system use this method to solve the problem of low satellite puzzle image quality and difficulty in stitching and fusion in the prior art, and achieve the technical effect of improving the quality of satellite puzzle images and generating a high-standard geostationary meteorological satellite global puzzle.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a flow chart of a method for generating a global mosaic of geostationary meteorological satellites based on multiple features in one embodiment;

[0011] Figure 2 A schematic diagram of a process for generating a satellite image data set according to a method for generating a global mosaic of geostationary meteorological satellites based on multiple features in one embodiment;

[0012] Figure 3 It is a structural block diagram of a global mosaic generation system of geostationary meteorological satellites based on multiple features in one embodiment;

[0013] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment.

[0014] Explanation of the reference numerals: original satellite image set acquisition module 11, satellite image data set acquisition module 12, meteorological satellite jigsaw puzzle generation module 13, meteorological satellite cloud map generation module 14. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0016] like Figure 1 As shown, the present application provides a method for generating a global mosaic of geostationary meteorological satellites based on multiple features, the method comprising:

[0017] Obtain the original satellite image set;

[0018] A geostationary meteorological satellite refers to a geosynchronous meteorological satellite, which is a meteorological satellite operating in a geosynchronous orbit above the equator. The orbit of the geostationary meteorological satellite is located about 35,800 kilometers above the earth's equator, and it runs synchronously with the earth's rotation and remains stationary relative to the earth. The geostationary meteorological satellite can observe a fixed area of ​​one-third of the earth's surface and conduct continuous meteorological observations on the same target area. In this application, it refers to the use of Fengyun-2H, Fengyun-4A, GOES-16 / GOES-17, MSG 0 and Himawari-8 geostationary meteorological satellite data are stitched together. Specifically, in actual business, GOES17 has been replaced by GOES18, Himawari-8 has been replaced by Himawari-9, and FY4A has been replaced by FY4B. This application also supports other geostationary satellites for jigsaw puzzle generation to produce a global geostationary meteorological satellite jigsaw puzzle. Here, only an example is given. In the method for generating a global jigsaw puzzle of a geostationary meteorological satellite based on multiple features, multiple features refer to multiple features extracted from the image data of the geostationary meteorological satellite, including brightness temperature features, cloud top height, cloud phase features, and texture features, etc., which are processed by standardization, projection normalization, etc., and according to the stitching scheme, the global geostationary satellite stitching data is generated by stitching and fusion, and cloud information is identified and extracted from it, and it is fused with the global background image to generate a geostationary satellite global cloud jigsaw puzzle. The method for generating a global jigsaw puzzle of a geostationary meteorological satellite based on multiple features combines multiple features and algorithms, aiming to improve the quality and resolution of meteorological satellite images and provide more accurate and comprehensive data support for meteorological analysis and prediction.

[0019] The data sent from the geostationary meteorological satellite is received through the ground receiving station, and the data is sorted out based on the data to obtain the unprocessed original images of the geostationary meteorological satellite, and the images are integrated to obtain the original satellite image set. By obtaining the original satellite image set, basic data support is provided for subsequent data processing, analysis and application. By processing and analyzing these original data, information about the earth's atmosphere, surface and clouds can be extracted, and the image data can be processed to provide a basis for the subsequent generation of the geostationary satellite global cloud puzzle.

[0020] Performing preprocessing based on the original satellite image set to obtain a satellite image data set;

[0021] The purpose of preprocessing the original satellite image set is to remove or reduce errors and noise in the data, improve data quality, and provide a reliable basis for subsequent data analysis and application. The preprocessing includes performing radiation correction on the original satellite image set to obtain a first corrected satellite image set, performing geometric correction on the first corrected satellite image set to obtain a second corrected satellite image set, performing geographic feature registration on the second corrected satellite image set, and generating the satellite image data set. Radiation correction refers to the correction of systematic and random radiation distortion or distortion caused by external factors, data acquisition and transmission systems, and the process of eliminating or correcting image distortion caused by radiation errors. The causes of radiation errors can be divided into: sensor response characteristics, solar radiation conditions, and atmospheric transmission conditions, etc.; geometric correction refers to the remote sensing imaging process. Under the combined influence of multiple factors, the geometric position, shape, size, dimension, orientation and other characteristics of the objects on the original image are often inconsistent with the corresponding ground objects. This inconsistency is geometric deformation, also known as geometric distortion. Geometric correction is a professional term in remote sensing. Generally, it refers to the use of a series of mathematical models to correct and eliminate the deformation caused by factors such as photographic material deformation, objective lens distortion, atmospheric refraction, earth curvature, earth rotation, terrain undulation, etc. when the geometric position, shape, size, orientation and other characteristics of the objects on the original image are inconsistent with the expression requirements in the reference system. Geographic registration generally refers to setting a coordinate system for raster data without a known coordinate system. The main principle is to match the feature points in the data with the corresponding control points with known coordinates to achieve coordinate registration of the entire data. By preprocessing the original satellite image set, the quality, accuracy and reliability of meteorological satellite data can be significantly improved, providing more reliable data support for subsequent meteorological monitoring, forecasting, climate research and other related fields.

[0022] like Figure 2 As shown, the original satellite image set is subjected to radiometric correction to obtain a first corrected satellite image set;

[0023] Performing geometric correction based on the first corrected satellite image set to obtain a second corrected satellite image set;

[0024] Geographic feature registration is performed based on the second corrected satellite image set to generate the satellite image data set.

[0025] The purpose of performing radiation correction on the original satellite image set is to eliminate or reduce radiation errors caused by various factors. The radiation correction includes absolute radiation correction and relative radiation correction. The purpose of absolute radiation correction is to convert the observation data recorded by the satellite sensor into the real surface reflectivity or radiance. The key to absolute radiation correction is to establish an accurate radiation transfer model to simulate the transmission process of solar radiation in the atmosphere. These models need to input atmospheric parameters and surface parameters to calculate the influence of the atmosphere on solar radiation and remove it from the satellite observation data. After absolute radiation correction, the satellite data can be directly used in the fields of surface characteristic analysis, climate change research, etc. The purpose of relative radiation correction is to eliminate the radiation difference between different pixels or different images in the same image to ensure that they have a consistent radiation scale. The relative radiation correction method includes correction based on pseudo-invariant features, correction based on statistics, and histogram matching. Relative radiation correction is usually used for the fusion and comparison of multi-source remote sensing data, as well as the analysis of time series remote sensing data. By performing relative radiation correction on the original satellite image set, the corrected original satellite image set is obtained as the first corrected satellite image set, which provides technical support for subsequent data fusion.

[0026] The purpose of geometric correction is to eliminate the geometric distortion of images caused by factors such as internal distortion of the sensor, curvature of the earth, and atmospheric refraction, to ensure that the geographical features on the image are consistent with their actual positions on the earth, and to make the objects on the image have the correct spatial position and geometric shape. This can ensure that the remote sensing image is consistent with the actual geographical location and terrain features, and improve the spatial accuracy and reliability of the data. Geometric correction can be divided into system geometric correction and geometric precision correction. System geometric correction is usually performed during the remote sensing image acquisition process, and the geometric distortion is reduced or eliminated through calibration and parameter setting inside the sensor. Collective precision correction is performed when the user processes the remote sensing data, and further corrects the distortion by using ground control points and geometric correction models. To correct the geometric distortion of the positive image, feature points with clear geographic coordinates and easy to identify, such as road intersections and corners of buildings, are selected on the first corrected satellite image set, and a geometric correction model is established to describe the mapping relationship between the pixel coordinates and the geographic coordinates on the first corrected satellite image set. The remote sensing image is corrected using the established geometric correction model to convert the pixel coordinates on the image into correct geographic coordinates. The accuracy of the correction result is verified by comparing the corrected image with the reference data. When the correction result is accurate, a second corrected satellite image set is obtained. The second corrected satellite image set is a set of images of the original satellite image set after radiation correction and geometric correction, and has higher spatial accuracy and reliability.

[0027] Geographic feature registration is to ensure that satellite images acquired from different sources and at different times have consistent coordinate systems and positioning accuracy in geographic space. A known geographic coordinate system, such as WGS84, UTM, etc., is obtained, and the second corrected satellite image set is subjected to geographic feature registration to generate the satellite image data set. The satellite image data set has a consistent geographic coordinate system and positioning accuracy, and can be used for subsequent fusion of multi-source remote sensing data.

[0028] Obtaining geographic information data corresponding to the original satellite image set;

[0029] Performing format conversion and coordinate registration on the geographic information data to obtain geographic feature data;

[0030] The geographic feature data and the second corrected satellite image set are fused to generate the satellite image data set.

[0031] Geographic information data generally include digital elevation models, vector map data, land use and coverage data, etc. The geographic information data provides the three-dimensional shape, distribution of objects and attribute information of the earth's surface. The geographic information data corresponding to the original satellite image set refers to the geographic information data corresponding to the images taken in the original satellite image set. Since the geographic information data comes from different data sources and has different formats and coordinate systems, the purpose of format conversion and coordinate registration is to ensure that these data are consistent with the satellite image set in terms of format and coordinate system, so as to facilitate subsequent data fusion. For example, the geographic information data is converted from the original format to a universal geographic data format using GIS software, and then the geographic information data is projected into the same coordinate system as the satellite image set, and the geographic feature data and the second corrected satellite image set are data fused. According to the attribute information of the geographic feature data, the corresponding areas on the satellite image are marked or classified. Then, based on geographic system software, such as GIS software, the registered geographic information data layer is superimposed with the second corrected satellite image set, and the distribution and characteristics of the geographic information data are directly seen on the satellite image, and multiple layers containing satellite images and geographic information data are generated. The images are integrated to obtain a satellite image data set, which provides a foundation for the subsequent generation of a meteorological satellite puzzle.

[0032] Performing data splicing and fusion based on the satellite image data set to generate a meteorological satellite mosaic;

[0033] Data stitching is the process of merging multiple satellite images into a continuous and seamless image. In this application, according to the stitching scheme preset by the system, the existing data is automatically read regularly, and the matching is checked in turn. According to the stitching scheme that meets the conditions, the global geostationary satellite HDF format brightness temperature data is generated by stitching and fusion. The L1 data of the similar infrared band of the geostationary meteorological satellite is obtained through FTP, and the data is standardized to generate source data in HDF format; the data of the geostationary meteorological satellite is projected and normalized, and the brightness temperature is calculated using the calibration table or calibration parameters to obtain the intermediate standard data of each satellite; according to the pre-set stitching scheme, the existing data is automatically read regularly, and the matching is checked in turn. According to the stitching scheme that meets the conditions, the global geostationary satellite HDF format brightness temperature data is generated by stitching and fusion; the meteorological satellite puzzle is generated. The meteorological satellite puzzle refers to a continuous, seamless satellite image covering a wider area formed by processing, aligning and stitching multiple meteorological satellite images. It is usually used in meteorological monitoring, weather forecasting, climate change research and other fields to provide scientists and researchers with comprehensive information on the earth's atmosphere, clouds, surface features, etc.

[0034] Based on the satellite image data set, extracting a set of all pixel points, wherein the set of all pixel points includes a plurality of pixel points;

[0035] Based on the multiple pixel points, pixel parameter fusion is performed according to the satellite image data set to obtain a pixel parameter fusion result;

[0036] The meteorological satellite mosaic is generated according to the pixel parameter fusion result.

[0037] Pixels are the basic building blocks of digital images. In remote sensing image processing, a pixel refers specifically to each discrete geographic coordinate point in the image with a specific spectral value, such as the reflectance or radiation value of the red, green, blue and other bands. Each pixel corresponds to a tiny area on the surface, and the size of this area depends on the spatial resolution of the remote sensing image. For example, if the spatial resolution of a remote sensing image is 1 meter, then each pixel represents an area of ​​1 meter × 1 meter on the surface; select specific pixel points from the satellite image data set for extraction; pixel parameter fusion is a process of integrating the information of the pixel points extracted from the satellite image data set, including standardizing the pixel points to generate source data in HDF format, projecting and normalizing the data of the geostationary meteorological satellite, and calculating the brightness temperature using a calibration table or calibration parameters to obtain intermediate standard data of the geostationary meteorological satellite; splicing and fusion are performed according to a splicing scheme that meets the conditions to generate the HDF format brightness temperature data of the geostationary meteorological satellite. The brightness temperature data is expressed as the brightness values ​​of different pixels in the remote sensing image, for example, the intensity-chromaticity-saturation of the pixel points is changed to generate a more complete and accurate pixel description. After completing the pixel parameter fusion, the meteorological satellite puzzle is generated according to the pixel parameter fusion result, that is, the fused data is processed to ensure the consistency of the generated meteorological satellite puzzle in spatial resolution and geometric morphology. The generated meteorological satellite puzzle is a continuous image that can reflect the distribution and changes of meteorological phenomena in the study area. By combining remote sensing image processing and data fusion technology, it aims to extract and integrate information from multiple satellite images to generate a high-quality meteorological satellite mosaic.

[0038] Extracting a first pixel point according to the plurality of pixel points;

[0039] Read the number of covered satellites corresponding to the first pixel point;

[0040] Determine whether the number of coverage satellites is 1;

[0041] If the number of covered satellites is 1, matching the first satellite pixel point parameter according to the satellite image data set;

[0042] The first satellite pixel point parameter is added to the pixel parameter fusion result.

[0043] According to the plurality of pixels, any pixel is extracted as the first pixel; after determining the first pixel, the number of covered satellites is read based on the first pixel, that is, the image data of which satellites the pixel is covered in is read, and the position of the first pixel in the satellite image data set is determined, that is, how many satellites contain the data of the first pixel, and then it is determined whether the number of covered satellites is 1. If the number of covered satellites is 1, it means that only one satellite's image data covers the pixel, and the covered satellite is recorded as the first satellite, and then the image data of the satellite is further processed to extract parameters related to the first pixel, such as searching for the specific value of the pixel on the satellite image on the covered satellite, such as brightness, temperature, reflectivity, etc., without considering the data fusion of multiple satellite pixels, and the first satellite pixel parameter is directly added to the pixel parameter fusion result as the first pixel parameter. By obtaining the pixel whose number of covered satellites is 1 and directly adding it to the pixel parameter fusion result, a more complete pixel parameter description can be generated, which provides a basis for subsequent remote sensing image fusion.

[0044] If the number of covered satellites is not 1, matching the satellite pixel point parameter set according to the number of covered satellites;

[0045] The satellite pixel point parameter set is sorted by sub-satellite point distance to obtain first screening satellite pixel point parameters and second screening satellite pixel point parameters;

[0046] Calculate the sub-satellite point distance difference based on the first screening satellite pixel point parameter and the second screening satellite pixel point parameter to obtain a first sub-satellite point distance difference;

[0047] Based on the first sub-satellite point distance difference, a first pixel parameter fusion result is calculated according to the first screened satellite pixel point parameters and the second screened satellite pixel point parameters, and the first pixel parameter fusion result is added to the pixel parameter fusion result.

[0048] When the number of covered satellites is not 1, it is first necessary to extract the parameters of the corresponding pixel points from the image data set of the satellite. For example, if the corresponding pixel point is displayed in the images taken by two different satellites, the satellite pixel point parameter set is matched according to the number of covered satellites, that is, different satellite image data sets will provide the pixel point parameters of the corresponding pixel point to form a satellite pixel point parameter set; the subsatellite point refers to the projection point of the satellite on the ground. According to the distance between the subsatellite point of each satellite and the corresponding pixel point, the satellite pixel point parameter sets are sorted. The subsatellite point distance reflects the difference in the viewing angle of the satellite observing the pixel point; in the sorted satellite pixel point parameter set, the two satellite pixel point parameters closest to each other are selected as the first screening satellite pixel point parameters and the second screening satellite pixel point parameters; the distance difference with the two closest satellite subsatellite points is calculated: dif= distanceA-distanceB, where distanceA is the distance between the corresponding pixel point and the first screening satellite pixel point parameter sub-satellite point, and distanceB is the distance between the corresponding pixel point and the second screening satellite pixel point parameter sub-satellite point; if dif is less than -400 kilometers, the value of the first screening satellite is taken; if dif is greater than 400 kilometers, the value of the second screening satellite is taken; if dif is between -400 kilometers and 400 kilometers, the weighted average weight is calculated: weight = (dif-(-400)) / (400-(-400)), then the value of the corresponding pixel point is taken as value = (1-weight)*valueA+weight*valueB, where valueA is the value of the first screening satellite, and valueB is the value of the second screening satellite. Based on the first sub-satellite point distance difference, according to the first screening satellite pixel point parameters and the second screening satellite pixel point parameters, the first pixel parameter fusion result is calculated, and the first pixel parameter fusion result is added to the pixel parameter fusion result. The image data from multiple satellites are used to fuse the parameters of the same pixel point to improve the spatial resolution and spectral resolution of remote sensing data, while reducing the errors caused by different observation angles.

[0049] Cloud detection is performed based on the meteorological satellite mosaic to generate a meteorological satellite cloud map.

[0050] Extract a variety of cloud-related features from satellite images, such as brightness, texture, edges, etc., to reflect the different characteristics of the cloud layer and provide a data basis for subsequent cloud detection. Then, according to actual needs and experimental results, select and optimize the feature set to achieve the best cloud detection effect. According to the actual needs and experimental results and cloud-related features, a cloud detector is constructed. According to the output results of the cloud detector, cloud information is automatically identified and extracted to generate a meteorological satellite cloud map. Cloud detection is performed based on meteorological satellite puzzles, and meteorological satellite cloud maps with practical application value are generated. The meteorological satellite cloud maps have broad application prospects.

[0051] Build a cloud detector based on the cloud detection dataset;

[0052] The meteorological satellite puzzle is input into the cloud detector to obtain the meteorological satellite cloud map.

[0053] Extract a variety of cloud-related features from satellite images, design a cloud detector for cloud detection, wherein meteorological satellite image samples containing clouds and cloudless areas are collected, including different weather conditions, seasons, geographical locations and satellite sensor types, to train the cloud detector, wherein the threshold in the global range of latitude direction is corrected according to the solar declination angle, the threshold in the land range of longitude direction is corrected according to the solar Greenwich time angle, the transparency value in the plateau range is corrected according to the digital elevation model, the threshold is calculated, the cloud transparency is calculated according to the brightness temperature and the threshold, the cloud detector is trained, and finally the trained cloud detector is applied to the satellite image to be detected for cloud detection. According to the output result of the cloud detector, cloud information is automatically identified and extracted, and the meteorological satellite cloud map is generated in combination with the meteorological satellite puzzle. A cloud detector is constructed based on the cloud detection data set, and this cloud detector is used to generate a meteorological satellite cloud map, which can clearly show the distribution and coverage of clouds, providing an important basis for weather forecasting, climate change research, etc.

[0054] like Figure 3 As shown, the embodiment of the present application includes a global mosaic generation system of geostationary meteorological satellites based on multiple features, and the system includes:

[0055] An original satellite image set acquisition module 11, wherein the original satellite image set acquisition module 11 is used to obtain an original satellite image set;

[0056] A satellite image data set acquisition module 12, wherein the satellite image data set acquisition module 12 is used to perform preprocessing based on the original satellite image set to obtain a satellite image data set;

[0057] A meteorological satellite jigsaw puzzle generating module 13, wherein the meteorological satellite jigsaw puzzle generating module 13 is used to perform data splicing and fusion based on the satellite image data set to generate a meteorological satellite jigsaw puzzle;

[0058] The meteorological satellite cloud image generation module 14 performs cloud detection based on the meteorological satellite mosaic to generate a meteorological satellite cloud image.

[0059] Furthermore, the embodiment of the present application also includes:

[0060] A radiation correction module, wherein the radiation correction module is used to perform radiation correction on the original satellite image set to obtain a first corrected satellite image set;

[0061] A geometric correction module, wherein the geometric correction module is used to perform geometric correction based on the first corrected satellite image set to obtain a second corrected satellite image set;

[0062] A geographic feature registration module is used to perform geographic feature registration based on the second corrected satellite image set to generate the satellite image data set.

[0063] Furthermore, the embodiment of the present application also includes:

[0064] A geographic information data acquisition module, wherein the geographic information data acquisition module is used to obtain geographic information data corresponding to the original satellite image set;

[0065] A geographic feature data acquisition module, which is used to perform format conversion and coordinate registration on the geographic information data to obtain geographic feature data;

[0066] A data fusion module is used to fuse the geographic feature data and the second corrected satellite image set to generate the satellite image data set.

[0067] Furthermore, the embodiment of the present application also includes:

[0068] A pixel point extraction module, the pixel point extraction module is used to extract all pixel point sets based on the satellite image data set, wherein the all pixel point sets include a plurality of pixel points;

[0069] A pixel parameter fusion result acquisition module, wherein the pixel parameter fusion result acquisition module is used to perform pixel parameter fusion based on the plurality of pixel points and the satellite image data set to obtain a pixel parameter fusion result;

[0070] A meteorological satellite jigsaw puzzle generation module is used to generate the meteorological satellite jigsaw puzzle according to the pixel parameter fusion result.

[0071] Furthermore, the embodiment of the present application also includes:

[0072] A pixel point module, the pixel point module is used to extract a first pixel point according to the multiple pixel points;

[0073] A coverage satellite number acquisition module, the coverage satellite number acquisition module is used to read the number of coverage satellites corresponding to the first pixel point;

[0074] A coverage satellite quantity determination module, wherein the coverage satellite quantity determination module is used to determine whether the coverage satellite quantity is 1;

[0075] A satellite pixel matching module, wherein the satellite pixel matching module is used to match a first satellite pixel parameter according to the satellite image data set if the number of covered satellites is 1;

[0076] A satellite pixel point parameter adding module is used to add the first satellite pixel point parameter to the pixel parameter fusion result.

[0077] Furthermore, the embodiment of the present application also includes:

[0078] A satellite number matching module, wherein the satellite number matching module is used to match the satellite pixel point parameter set according to the number of covered satellites if the number of covered satellites is not 1;

[0079] A sub-satellite point distance sorting module, wherein the sub-satellite point distance sorting module is used to sort the satellite pixel point parameter set by sub-satellite point distance to obtain a first screening satellite pixel point parameter and a second screening satellite pixel point parameter;

[0080] A sub-satellite point distance difference calculation module, wherein the sub-satellite point distance difference calculation module is used to calculate the sub-satellite point distance difference based on the first screening satellite pixel point parameter and the second screening satellite pixel point parameter to obtain a first sub-satellite point distance difference;

[0081] A pixel parameter fusion result calculation module is used to calculate a first pixel parameter fusion result based on the first sub-satellite point distance difference, according to the first screened satellite pixel point parameters and the second screened satellite pixel point parameters, and add the first pixel parameter fusion result to the pixel parameter fusion result.

[0082] Furthermore, the embodiment of the present application also includes:

[0083] A cloud detector building module, wherein the cloud detector building module is used to build a cloud detector based on a cloud detection dataset;

[0084] A meteorological satellite puzzle input module is used to input the meteorological satellite puzzle into the cloud detector to obtain the meteorological satellite cloud map.

[0085] For the specific embodiment of the geostationary meteorological satellite global jigsaw puzzle generation system based on multiple features, please refer to the embodiment of the geostationary meteorological satellite global jigsaw puzzle generation method based on multiple features above, which will not be repeated here. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0086] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, 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 news data and data such as time attenuation factors. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a global jigsaw puzzle generation method for geostationary meteorological satellites based on multiple features.

[0087] 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 application, and does not constitute a limitation on the computer device to which the solution of the present application 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.

[0088] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of a method for generating a global mosaic of geostationary meteorological satellites based on multiple features when executing the computer program.

[0089] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for generating a global mosaic of geostationary meteorological satellites based on multiple features are implemented.

[0090] 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.

[0091] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for generating a global mosaic of geostationary meteorological satellites based on multiple features, characterized in that: The method comprises: Obtain the original satellite image set; Performing preprocessing based on the original satellite image set to obtain a satellite image data set; Performing data splicing and fusion based on the satellite image data set to generate a meteorological satellite mosaic; Perform cloud detection based on the meteorological satellite puzzle to generate a meteorological satellite cloud map, extract a variety of cloud-related features from satellite images, including brightness, texture, and edges, to provide a data basis for cloud detection, design a cloud detector to perform cloud detection, input the meteorological satellite puzzle into the cloud detector, and obtain the meteorological satellite cloud map; Based on the satellite image data set, data splicing and fusion are performed to generate a meteorological satellite mosaic, including: Based on the satellite image data set, extracting a set of all pixel points, wherein the set of all pixel points includes a plurality of pixel points; Based on the multiple pixel points, pixel parameter fusion is performed according to the satellite image data set to obtain a pixel parameter fusion result; Generating the meteorological satellite jigsaw puzzle according to the pixel parameter fusion result; Based on the plurality of pixel points, pixel parameter fusion is performed according to the satellite image data set, including: Extracting a first pixel point according to the plurality of pixel points; Read the number of covered satellites corresponding to the first pixel point; Determine whether the number of coverage satellites is 1; If the number of covered satellites is 1, matching the first satellite pixel point parameter according to the satellite image data set; Adding the first satellite pixel point parameter to the pixel parameter fusion result; If the number of covered satellites is not 1, matching the satellite pixel point parameter set according to the number of covered satellites; Sort the satellite pixel point parameter set by the distance to the sub-satellite point, and select the two satellite pixel point parameters with the closest sub-satellite point distance as the first screening satellite pixel point parameters and the second screening satellite pixel point parameters; Calculate the sub-satellite point distance difference based on the first screening satellite pixel point parameter and the second screening satellite pixel point parameter to obtain a first sub-satellite point distance difference; Based on the first sub-satellite point distance difference, a first pixel parameter fusion result is calculated according to the first screened satellite pixel point parameters and the second screened satellite pixel point parameters, and the first pixel parameter fusion result is added to the pixel parameter fusion result.

2. The method according to claim 1, characterized in that Preprocessing is performed based on the original satellite image set to obtain a satellite image data set, including: Performing radiometric correction on the original satellite image set to obtain a first corrected satellite image set; Performing geometric correction based on the first corrected satellite image set to obtain a second corrected satellite image set; Geographic feature registration is performed based on the second corrected satellite image set to generate the satellite image data set.

3. The method according to claim 2, characterized in that Performing geographic feature registration based on the second corrected satellite image set includes: Obtaining geographic information data corresponding to the original satellite image set; Performing format conversion and coordinate registration on the geographic information data to obtain geographic feature data; The geographic feature data and the second corrected satellite image set are fused to generate the satellite image data set.

4. A global mosaic generation system of geostationary meteorological satellites based on multiple features, characterized in that: The system comprises: An original satellite image set acquisition module, wherein the original satellite image set acquisition module is used to obtain an original satellite image set; A satellite image data set acquisition module, wherein the satellite image data set acquisition module is used to perform preprocessing based on the original satellite image set to obtain a satellite image data set; A meteorological satellite jigsaw puzzle generation module, the meteorological satellite jigsaw puzzle generation module is used to perform data splicing and fusion based on the satellite image data set to generate a meteorological satellite jigsaw puzzle; A meteorological satellite cloud image generation module, the meteorological satellite cloud image generation module is used to perform cloud detection based on the meteorological satellite puzzle, generate a meteorological satellite cloud image, extract a variety of cloud-related features from satellite images, including brightness, texture, and edges, to provide a data basis for cloud detection, design a cloud detector to perform cloud detection, input the meteorological satellite puzzle into the cloud detector, and obtain the meteorological satellite cloud image; A pixel point extraction module, the pixel point extraction module is used to extract all pixel point sets based on the satellite image data set, wherein the all pixel point sets include a plurality of pixel points; A pixel parameter fusion result acquisition module, wherein the pixel parameter fusion result acquisition module is used to perform pixel parameter fusion based on the plurality of pixel points and the satellite image data set to obtain a pixel parameter fusion result; A meteorological satellite jigsaw puzzle generation module, wherein the meteorological satellite jigsaw puzzle generation module is used to generate the meteorological satellite jigsaw puzzle according to the pixel parameter fusion result; A pixel point module, the pixel point module is used to extract a first pixel point according to the multiple pixel points; A coverage satellite number acquisition module, the coverage satellite number acquisition module is used to read the number of coverage satellites corresponding to the first pixel point; A coverage satellite quantity determination module, wherein the coverage satellite quantity determination module is used to determine whether the coverage satellite quantity is 1; A satellite pixel matching module, wherein the satellite pixel matching module is used to match a first satellite pixel parameter according to the satellite image data set if the number of covered satellites is 1; A satellite pixel point parameter adding module, the satellite pixel point parameter adding module is used to add the first satellite pixel point parameter to the pixel parameter fusion result; A satellite number matching module, wherein the satellite number matching module is used to match the satellite pixel point parameter set according to the number of covered satellites if the number of covered satellites is not 1; A sub-satellite point distance sorting module, wherein the sub-satellite point distance sorting module is used to sort the satellite pixel point parameter set by sub-satellite point distance, and select two satellite pixel point parameters with the closest sub-satellite point distance as the first screening satellite pixel point parameters and the second screening satellite pixel point parameters; A sub-satellite point distance difference calculation module, wherein the sub-satellite point distance difference calculation module is used to calculate the sub-satellite point distance difference based on the first screening satellite pixel point parameter and the second screening satellite pixel point parameter to obtain a first sub-satellite point distance difference; A pixel parameter fusion result calculation module is used to calculate a first pixel parameter fusion result based on the first sub-satellite point distance difference, according to the first screened satellite pixel point parameters and the second screened satellite pixel point parameters, and add the first pixel parameter fusion result to the pixel parameter fusion result.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images