Sea ice identification method, device and equipment based on FY-4 satellite fusion image
Through the sea ice recognition method of Fengyun-4 satellite fusion image, the problems of low time resolution and lack of automation in sea ice recognition technology are solved, and high-precision and efficient sea ice range and offshore distance measurement are achieved to meet sea ice monitoring business needs.
Patent Information
- Application Number
- CN202411406233.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-10
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing sea ice recognition technology has low time resolution and lack of automated methods, which makes sea ice range and offshore distance measurement time-consuming and labor-intensive, the accuracy depends on the experience level of the measuring personnel, and there is no available data source under cloud occlusion.
Using the method based on Fengyun-4 satellite fusion image, the single-channel and multi-channel images are obtained for pre-processing and fusion, sea ice recognition is performed, sea ice range and offshore distance information is extracted, and HSV image fusion and ice-water separation are generated. Sea ice recognition results.
It significantly improves the accuracy and automation of sea ice recognition, meets the business needs of sea ice monitoring in time and space, and improves data reliability and efficiency.
Smart Images

Figure CN118918494A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of sea ice recognition, and in particular to a sea ice recognition method, device and equipment based on Fengyun-4 satellite fusion images. Background Art
[0002] Sea ice area and sea ice offshore distance are important factors in measuring the severity of sea ice. Existing methods generally use artificial visual interpretation, measurement and extraction of satellite remote sensing data such as Landsat8, MODIS, and GF1. There are the following disadvantages: (1) Common satellite remote sensing images have low temporal resolution. If there is cloud or fog obstruction, there will be no effective satellite data source available.
[0003] (2) There is a lack of automatic extraction methods for sea ice extent and sea ice offshore distance. The current method is generally to use GIS software to visually outline the sea ice extent and manually measure the sea ice offshore distance. This method is time-consuming and labor-intensive, there is no unified standard, and the measurement accuracy depends on the experience level of the surveyor. Summary of the invention
[0004] In view of this, the purpose of the present invention is to provide a sea ice identification method, device and equipment based on FY-4 satellite fusion images, which can significantly improve the accuracy and automation of identifying the sea ice range and the distance from the shore, thereby meeting the operational needs of sea ice monitoring in time and space.
[0005] In a first aspect, an embodiment of the present invention provides a method for identifying sea ice based on Fengyun-4 satellite fusion images, comprising: Acquire a first original image and a second original image collected by the Fengyun-4 satellite, wherein the first original image is a single-channel image and the second original image is a multi-channel image; Preprocessing the first original image and the second original image respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to the study area; The first sea area extraction result and the second sea area extraction result are fused to obtain a fused image corresponding to the study area; Sea ice is identified in the study area based on the fused image to obtain the sea ice identification result corresponding to the study area. The sea ice identification result includes sea ice range information and / or sea ice offshore distance information.
[0006] In one implementation, preprocessing the first original image and the second original image respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to the study area includes: Performing geometric correction on the first original image and the second original image to obtain a first geometrically corrected image and a second geometrically corrected image; According to the location information of the study area, the first geometrically corrected image and the second geometrically corrected image are cropped to obtain the first geometrically corrected image and the second geometrically corrected image corresponding to the study area; The sea and land mask vector file corresponding to the study area is obtained, and the first geometrically corrected image and the second geometrically corrected image corresponding to the study area are masked using the sea and land mask vector file to obtain the first sea area extraction result and the second sea area extraction result corresponding to the study area.
[0007] In one implementation, the first sea area extraction result and the second sea area extraction result are fused to obtain a fused image corresponding to the study area, including: Normalizing the first sea area extraction result and the second sea area extraction result; The normalized second sea area extraction result is converted from the RGB space to the HSV space to obtain the H component, S component and V component; Perform histogram matching on the first sea area extraction result after normalization with the V component to obtain a new V component; Perform HSV inverse transformation on the new V component, H component and S component to obtain the fused image corresponding to the study area.
[0008] In one implementation, sea ice recognition is performed on a study area based on the fused image to obtain a sea ice recognition result corresponding to the study area, including: Perform ice-water separation processing on the fused image to obtain the target ice-water separation binary image; Eliminate the seawater elements in the target ice-water separation binary map, and retain the sea ice elements in the target ice-water separation binary map to obtain the sea ice surface file; Based on the sea ice surface file, determine the sea ice extent information and / or sea ice distance from the shore corresponding to the study area.
[0009] In one embodiment, performing ice-water separation processing on the fused image to obtain a target ice-water separation binary image includes: Based on the preset ice-water segmentation threshold, the fused image is processed for ice-water separation to obtain an initial ice-water separation binary image; The area corresponding to each spot in the initial ice-water separation binary map is determined, and spots with an area smaller than a preset area threshold are removed to obtain a target ice-water separation binary map.
[0010] In one embodiment, determining sea ice extent information corresponding to a study area based on a sea ice surface file includes: The sea ice surface file is converted into a line to obtain the sea ice line file, and the range enclosed by the sea ice line file is used as the sea ice range information corresponding to the study area.
[0011] In one embodiment, determining the sea ice offshore distance information corresponding to the study area based on the sea ice surface file includes: Determine the intersection point between the sea ice line file and the preset baseline file; The longitude and latitude data of the intersection point and the preset reference point are used to determine the geodetic distance between the intersection point and the reference point to determine the sea ice offshore distance information corresponding to the study area.
[0012] In one embodiment, after sea ice recognition is performed on the study area based on the fused image to obtain a sea ice recognition result corresponding to the study area, the method further includes: Thematic maps of sea ice extent information and sea ice distance from shore are produced to generate thematic maps of sea ice extent and sea ice distance from shore corresponding to the study area.
[0013] In a second aspect, an embodiment of the present invention further provides a sea ice recognition device based on the fusion image of the Fengyun-4 satellite, comprising: An image acquisition module is used to acquire a first original image and a second original image collected by the Fengyun-4 satellite, wherein the first original image is a single-channel image and the second original image is a multi-channel image; A sea area extraction module, used for preprocessing the first original image and the second original image respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to the study area; An image fusion module is used to fuse the first sea area extraction result and the second sea area extraction result to obtain a fused image corresponding to the study area; The sea ice recognition module is used to identify sea ice in the study area based on the fused image, and obtain the sea ice recognition result corresponding to the study area. The sea ice recognition result includes sea ice range information and / or sea ice offshore distance information.
[0014] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement any one of the methods provided in the first aspect.
[0015] The embodiment of the present invention provides a method, device and equipment for sea ice identification based on the fusion image of Fengyun-4 satellite. First, a first original image and a second original image are obtained, wherein the first original image is a single-channel image and the second original image is a multi-channel image; then the first original image and the second original image are preprocessed respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to the study area; then the first sea area extraction result and the second sea area extraction result are fused to obtain a fused image corresponding to the study area; finally, sea ice is identified in the study area based on the fused image to obtain a sea ice identification result corresponding to the study area, and the sea ice identification result includes sea ice range information and / or sea ice offshore distance information. The above method integrates original images of different resolutions collected by Fengyun-4 satellite, thereby extracting sea ice range information and sea ice offshore distance information based on the fused image, forming a complete set of technical processes, thereby significantly improving the accuracy and automation of identifying sea ice range and sea ice offshore distance, thereby meeting the business needs of sea ice monitoring in time and space.
[0016] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.
[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0019] Figure 1 A schematic diagram of a process of sea ice recognition method based on FY-4 satellite fusion images provided in an embodiment of the present invention; Figure 2 A schematic diagram of the overall process of a sea ice recognition method based on FY-4 satellite fusion images provided in an embodiment of the present invention; Figure 3 A schematic diagram of an HSV image fusion process provided by an embodiment of the present invention; Figure 4 A local comparison diagram of FY4A images before and after fusion provided in an embodiment of the present invention; Figure 5A thematic map of sea ice extent provided by an embodiment of the present invention; Figure 6 A thematic map of sea ice offshore distance provided by an embodiment of the present invention; Figure 7 A schematic diagram of the structure of a sea ice recognition device based on FY-4 satellite fusion images provided in an embodiment of the present invention; Figure 8 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described in combination with the embodiments below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0021] At present, the existing technology has the following disadvantages: (1) The temporal resolution of commonly used satellite remote sensing images is low. If there is cloud and fog obstruction, there will be no effective satellite data source available. (2) There is a lack of automatic extraction methods for sea ice range and sea ice offshore distance. The current method generally uses GIS software to visually outline the sea ice range and manually measure the sea ice offshore distance. This method is time-consuming and labor-intensive, there is no unified standard, and the measurement accuracy depends on the experience level of the surveyor. Based on this, the present invention implements a sea ice identification method, device and equipment based on Fengyun-4 satellite fusion images, which can significantly improve the accuracy and automation of identifying sea ice range and sea ice offshore distance, thereby meeting the business needs of sea ice monitoring in time and space.
[0022] To facilitate understanding of this embodiment, firstly, a sea ice recognition method based on FY-4 satellite fusion images disclosed in an embodiment of the present invention is described in detail. Figure 1 The flowchart of a method for sea ice recognition based on Fengyun-4 satellite fusion images is shown, and the method mainly includes the following steps S102 to S108: Step S102, obtaining a first original image and a second original image collected by the Fengyun-4 satellite.
[0023] The Fengyun-4 satellite includes satellites A and B, the first original image is a single-channel image, and the second original image is a multi-channel image, specifically a three-channel image. In one example, the first original image is an original image with a spatial resolution of 500m, and the second original image is an original image with a spatial resolution of 1000m. Exemplarily, both the first original image and the second original image can be FY4A images, or other images collected by the Fengyun-4 satellite.
[0024] Step S104, preprocessing the first original image and the second original image respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to the study area.
[0025] Among them, the preprocessing includes geometric correction, image cropping, image masking, etc. The first sea area extraction result is the sea area extraction result with a spatial resolution of 500m, and the second sea area extraction result is the sea area extraction result with a spatial resolution of 1000m. In one example, the original image with a spatial resolution of 500m and the original image with a spatial resolution of 1000m can be preprocessed by geometric correction, image cropping, image masking, etc., respectively, to obtain the sea area extraction result with a spatial resolution of 500m and the sea area extraction result with a spatial resolution of 1000m.
[0026] Step S106, fusing the first sea area extraction result and the second sea area extraction result to obtain a fused image corresponding to the study area.
[0027] In one example, the HSV algorithm can be used to fuse the sea area extraction results with a spatial resolution of 500m and the sea area extraction results with a spatial resolution of 1000m to obtain a fused image corresponding to the study area.
[0028] Step S108, identifying sea ice in the study area based on the fused image, and obtaining a sea ice identification result corresponding to the study area.
[0029] The sea ice recognition result includes sea ice range information and / or sea ice offshore distance information. In one example, sea ice recognition is first performed based on the fused image to obtain a target ice-water separation binary map, then sea ice range information is extracted from the target ice-water separation binary map, and finally, sea water offshore distance information is extracted from the target ice-water separation binary map based on the sea ice range information.
[0030] The sea ice identification method based on the FY-4 satellite fusion image provided in the embodiment of the present invention integrates the original images of different resolutions collected by the FY-4 satellite, thereby extracting sea ice range information and sea ice offshore distance information based on the fused images, forming a complete technical process. Therefore, it can significantly improve the accuracy and automation of identifying the sea ice range and sea ice offshore distance, thereby meeting the operational needs of sea ice monitoring in time and space.
[0031] In one implementation, taking the images collected by Fengyun-4A (FY4A) as an example, the present invention uses the high temporal resolution FY4A raw data, fuses the 500m spatial resolution and 1000m spatial resolution images, extracts the sea ice range based on the fused images, and calculates the distance from the sea ice to the shore using spatial geographic analysis methods. A complete set of technical processes has been formed with high monitoring accuracy and automation, which can meet the business needs of sea ice monitoring in time and space. For details, see Figure 2 The figure shows an overall process diagram of a sea ice identification method based on FY-4 satellite fusion images. For the FY4A satellite 500m resolution data (i.e., the first original image), geometric correction is performed in combination with the 500m longitude and latitude data file, and then the image is cropped, and then the sea and land mask is performed in combination with the sea and land mask file; similarly, for the FY4A satellite 1000m resolution data (i.e., the second original image), geometric correction is performed in combination with the 1000m longitude and latitude data file, and then the image is cropped, and then the sea and land mask is performed in combination with the sea and land mask file; the two images after the sea and land mask are sequentially subjected to HSV image fusion, sea ice identification, sea ice range extraction, sea ice offshore distance extraction, thematic mapping and other operations, and the sea ice range thematic map and sea ice offshore distance thematic map corresponding to the study area can be obtained.
[0032] For ease of understanding, an embodiment of the present invention provides a specific implementation of a sea ice recognition method based on FY-4 satellite fusion images.
[0033] For the aforementioned step S102, the embodiment of the present invention provides an implementation method for obtaining the first original image and the second original image, and continues to take the FY4A image as an example, including: inputting the FY4A 500m and 1000m spatial resolution original images at the same time, and the image format is HDF5 (hierarchical data format version 5). The 500m spatial resolution is single-channel data with a central wavelength of 0.65μm. The 1000m spatial resolution is three-channel data, and the central wavelengths of the three channels are 0.47μm, 0.65μm, and 0.83μm respectively.
[0034] For the aforementioned step S104, the embodiment of the present invention provides an implementation method for preprocessing the first original image and the second original image respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to the study area, including the following steps 1.1 to 1.3: Step 1.1, geometrically correct the first original image and the second original image to obtain a first geometrically corrected image and a second geometrically corrected image. Specifically: 1) Build a longitude and latitude file in tiff (Tagged Image File Format) format. First, download any GEO (geolocation) data file in HDF5 format with a resolution of 4km in China, denoted as G1, and convert G1 into a data file G2 in tiff format containing longitude and latitude.
[0035] 2) Continuing with the FY4A image as an example, based on the latitude and longitude file G2, VRT (virtual raster format) files are constructed for the original FY4A images with a resolution of 500m and 1000m respectively: 3) Continuing with the FY4A image as an example, the VRT file is used to perform geometric correction on the 500m and 1000m resolution FY4A original images. The 500m resolution data after geometric correction (that is, the first FY4A geometrically corrected image) is recorded as F1, and the 1000m resolution data after geometric correction (that is, the second FY4A geometrically corrected image) is recorded as F2.
[0036] Step 1.2: cropping the first geometrically corrected image and the second geometrically corrected image according to the location information of the study area to obtain the first geometrically corrected image and the second geometrically corrected image corresponding to the study area.
[0037] In one example, taking FY4A image as an example, due to the large width of FY4A, the whole image has a large amount of computation and is slow to run. According to the study area, the study area of the embodiment of the present invention is Liaodong Bay and the northern waters of the Yellow Sea, and the image range of Liaodong Bay and the northern waters of the Yellow Sea is cropped.
[0038] Step 1.3, obtain the sea and land mask vector file corresponding to the study area, and use the sea and land mask vector file to mask the first geometrically corrected image and the second geometrically corrected image corresponding to the study area to obtain the first sea area extraction result and the second sea area extraction result corresponding to the study area.
[0039] In one example, the land and sea mask vector file is used to remove the land from the cropped image and retain the sea area. The data after land and sea masking are recorded as F3 (500m resolution image, i.e., the first sea area extraction result) and F4 (1000m resolution image, i.e., the second sea area extraction result).
[0040] For the aforementioned step S106, the embodiment of the present invention provides an implementation method for fusing the first sea area extraction result and the second sea area extraction result to obtain a fused image corresponding to the study area, and fusing F3 (500m resolution image) and F4 (1000m resolution image) based on the HSV fusion method. F3 is a single-channel image, and F4 is a three-channel image. After fusion, a three-channel true color image with a resolution of 500m is obtained.
[0041] Images are generally displayed in RGB (red, green, blue) space. The RGB settings of the three-channel image F4 correspond to: R-first channel, G-second channel, B-third channel. HSV refers to hue H (Hue), saturation S (Saturation), and brightness (Value). The single-channel image F3 and the three-channel image F4 are normalized to 0-1.
[0042] Based on this, the specific Figure 3 The schematic diagram of a HSV image fusion process shown includes the following steps 2.1 to 2.4: Step 2.1, normalize the first sea area extraction result and the second sea area extraction result. In one example, the single-channel image F3 and the three-channel image F4 are normalized to 0-1.
[0043] Step 2.2, convert the normalized second sea area extraction result from RGB space to HSV space to obtain H component, S component and V component.
[0044] In one example, the normalized three-channel image is transformed from the RGB space to the HSV space to obtain the H component, S component, and V component. The transformation formula is as follows: ; ; ; .
[0045] Step 2.3, performing histogram matching between the normalized first sea area extraction result and the V component to obtain a new V component.
[0046] In one example, the normalized single-channel image F3 is histogram matched with the V component to obtain a single-channel image after histogram matching, that is, a new V component, denoted as V'.
[0047] In step 2.4, perform HSV inverse transformation on the new V component, H component, and S component to obtain the FY4A fused image corresponding to the study area.
[0048] In one example, V' replaces the V component, is combined with the H component and the S component, and is inversely transformed to the HSV space to obtain the fused image F5. The inverse transformation formula is as follows; ; For example, continue to use FY4A image as an example, see Figure 4The figure shows a local comparison of FY4A images before and after fusion. The left picture is the original 1000-meter resolution image, and the right picture is the 500-meter resolution image after fusion. It can be seen that the fused image has higher accuracy.
[0049] For the aforementioned step S108, the embodiment of the present invention provides an implementation method for identifying sea ice in a study area based on fused images to obtain a sea ice identification result corresponding to the study area, including the following steps 3.1 to 3.3: Step 3.1, perform ice-water separation processing on the fused image to obtain the target ice-water separation binary image. (1) Based on the preset ice-water segmentation threshold, the fused image is processed for ice-water separation to obtain an initial ice-water separation binary map. In one example, the FY4A image is used as an example. For the FY4A fused image, the fixed threshold method is used to identify sea ice. Through multi-view image analysis, it is found that the optimal ice-water segmentation threshold for the first band of the FY4A fused image is 120. After threshold segmentation, the initial ice-water separation binary map is obtained, with the sea ice value being 1 and the sea water value being 0.
[0050] (2) Determine the area corresponding to each patch in the initial ice-water separation binary map, and remove patches with an area smaller than the preset area threshold to obtain the target ice-water separation binary map. In one example, since there will be broken patches after threshold segmentation, small area removal processing is required to remove the broken patches and obtain the entire sea ice area. The ice-water separation binary map after small area removal processing (that is, the target ice-water separation binary map) is saved in tiff format and recorded as F6.
[0051] Step 3.2, remove the seawater elements in the target ice-water separation binary map, and retain the sea ice elements in the target ice-water separation binary map to obtain the sea ice surface file.
[0052] In one example, raster-to-vector processing is first performed to convert the target ice-water separation binary image F6 into a vector surface file S1; after conversion into the vector surface file S1, the attribute value of the sea ice element is 1, and the attribute value of the sea water element is 0. The sea water element, that is, the element with an attribute value of 0 is deleted, and the sea ice surface file is retained. The sea ice surface file is the extracted sea ice, recorded as S2.
[0053] Step 3.3: Based on the sea ice surface file, determine the sea ice extent information and / or sea ice offshore distance information corresponding to the study area.
[0054] In one example, the sea ice surface file is processed into a line file to obtain a sea ice line file, and the range enclosed by the sea ice line file is used as the sea ice range information corresponding to the study area. Specifically, the sea ice surface file S2 is processed into a line file to obtain a sea ice line file S3, and the range enclosed by the line file is the sea ice range.
[0055] In one example, the intersection of the sea ice line file and the preset baseline file is determined, and then the longitude and latitude data of the intersection and the longitude and latitude data of the preset benchmark point are used to determine the geodetic distance between the intersection and the benchmark point to determine the sea ice offshore distance information corresponding to the study area. Specifically, according to the sea ice line file S3 and the given benchmark point and baseline file, the sea ice offshore distance is automatically calculated, including the following steps: (1) Calculate the intersection point J between the sea ice line file and the baseline file; (2) Analyze the longitude and latitude data of the intersection point J and the reference point; (3) Using the longitude and latitude data of the intersection point J and the reference point, calculate the geodesic distance between the intersection point J and the reference point to obtain the distance value D in kilometers. The geodesic distance is the shortest path distance between two points on the earth's surface. The calculation formula for the geodesic distance is as follows: ; Among them, R is the radius of the earth, θ1 and θ2 are the latitudes of the two points, and φ1 and φ2 are the longitudes of the two points.
[0056] Finally, convert the unit kilometers to nautical miles using the following formula: D_nmi = D*0.539956803456; Among them, D_nmi is the distance from the shore of sea ice, in nautical miles.
[0057] Furthermore, after extracting the sea ice extent information and the sea ice distance from the shore information, the sea ice extent information and the sea ice distance from the shore information are mapped to generate the sea ice extent thematic map and the sea ice distance from the shore thematic map corresponding to the study area, such as Figure 5 A thematic map of sea ice extent and Figure 6 A thematic map of sea ice distance from shore is shown.
[0058] In summary, the sea ice identification method based on the FY-4 satellite fusion image provided by the embodiment of the present invention has at least the following characteristics: 1. The FY-4 satellite image has a high temporal resolution, and the sea ice information extraction based on the FY-4 satellite image is highly timely and meets the requirements of business monitoring. 2. After image fusion, the spatial resolution of the FY-4 satellite fusion image is doubled, and it has rich spectral information and reliable accuracy. 3. It has a high degree of automation and does not require manual intervention.
[0059] Based on the above embodiments, the present invention provides a sea ice recognition device based on the fusion image of the Fengyun-4 satellite. Figure 7 The structure diagram of a sea ice recognition device based on the fusion image of the Fengyun-4 satellite is shown in FIG. The device mainly includes the following parts: An image acquisition module 702 is used to acquire a first original image and a second original image collected by the Fengyun-4 satellite, where the first original image is a single-channel image and the second original image is a multi-channel image; The sea area extraction module 704 is used to pre-process the first original image and the second original image respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to the study area; An image fusion module 706 is used to fuse the first sea area extraction result and the second sea area extraction result to obtain a fused image corresponding to the study area; The sea ice identification module 708 is used to identify the sea ice in the study area based on the fused image, and obtain the sea ice identification result corresponding to the study area. The sea ice identification result includes the sea ice range information and / or the sea ice offshore distance information.
[0060] The sea ice identification device based on the FY-4 satellite fusion image provided in the embodiment of the present invention integrates the original images of different resolutions collected by the FY-4 satellite, thereby extracting sea ice range information and sea ice offshore distance information based on the fused images, forming a complete technical process. Therefore, it can significantly improve the accuracy and automation of identifying the sea ice range and sea ice offshore distance, thereby meeting the operational needs of sea ice monitoring in time and space.
[0061] In one implementation, the sea area extraction module 704 is specifically used to: Performing geometric correction on the first original image and the second original image to obtain a first geometrically corrected image and a second geometrically corrected image; According to the location information of the study area, the first geometrically corrected image and the second geometrically corrected image are cropped to obtain the first geometrically corrected image and the second geometrically corrected image corresponding to the study area; The sea and land mask vector file corresponding to the study area is obtained, and the first geometrically corrected image and the second geometrically corrected image corresponding to the study area are masked using the sea and land mask vector file to obtain the first sea area extraction result and the second sea area extraction result corresponding to the study area.
[0062] In one implementation, the image fusion module 706 is specifically used to: Normalizing the first sea area extraction result and the second sea area extraction result; The normalized second sea area extraction result is converted from the RGB space to the HSV space to obtain the H component, S component and V component; Perform histogram matching on the first sea area extraction result after normalization with the V component to obtain a new V component; Perform HSV inverse transformation on the new V component, H component and S component to obtain the fused image corresponding to the study area.
[0063] In one embodiment, the sea ice identification module 708 is specifically configured to: Perform ice-water separation processing on the fused image to obtain the target ice-water separation binary image; Eliminate the seawater elements in the target ice-water separation binary map, and retain the sea ice elements in the target ice-water separation binary map to obtain the sea ice surface file; Based on the sea ice surface file, determine the sea ice extent information and / or sea ice distance from the shore corresponding to the study area.
[0064] In one embodiment, the sea ice identification module 708 is specifically configured to: Based on the preset ice-water segmentation threshold, the fused image is processed for ice-water separation to obtain an initial ice-water separation binary image; The area corresponding to each spot in the initial ice-water separation binary map is determined, and spots with an area smaller than a preset area threshold are removed to obtain a target ice-water separation binary map.
[0065] In one embodiment, the sea ice identification module 708 is specifically configured to: The sea ice surface file is converted into a line to obtain the sea ice line file, and the range enclosed by the sea ice line file is used as the sea ice range information corresponding to the study area.
[0066] In one embodiment, the sea ice identification module 708 is specifically configured to: Determine the intersection point between the sea ice line file and the preset baseline file; The longitude and latitude data of the intersection point and the preset reference point are used to determine the geodetic distance between the intersection point and the reference point to determine the sea ice offshore distance information corresponding to the study area.
[0067] In one embodiment, the thematic map making module is also included, which is used to: Thematic maps of sea ice extent information and sea ice distance from shore are produced to generate thematic maps of sea ice extent and sea ice distance from shore corresponding to the study area.
[0068] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.
[0069] An embodiment of the present invention provides an electronic device. Specifically, the electronic device includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned implementation methods.
[0070] Figure 8A structural diagram of an electronic device provided in an embodiment of the present invention, the electronic device 100 includes: a processor 80, a memory 81, a bus 82 and a communication interface 83, wherein the processor 80, the communication interface 83 and the memory 81 are connected via the bus 82; the processor 80 is used to execute an executable module stored in the memory 81, such as a computer program.
[0071] The memory 81 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 83 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.
[0072] The bus 82 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0073] Among them, the memory 81 is used to store programs, and the processor 80 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiments of the present invention can be applied to the processor 80 or implemented by the processor 80.
[0074] The processor 80 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 80. The above processor 80 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to execute, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 81, and the processor 80 reads the information in the memory 81 and completes the steps of the above method in combination with its hardware.
[0075] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be referred to the previous method embodiments, which will not be repeated here.
[0076] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0077] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims
1. A sea ice recognition method based on Fengyun-4 satellite fusion images, characterized in that: include: Acquire a first original image and a second original image collected by the Fengyun-4 satellite, wherein the first original image is a single-channel image, and the second original image is a multi-channel image; Preprocessing the first original image and the second original image respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to the study area; fusing the first sea area extraction result and the second sea area extraction result to obtain a fused image corresponding to the study area; Sea ice is identified in the study area based on the fused image to obtain a sea ice identification result corresponding to the study area, wherein the sea ice identification result includes sea ice range information and / or sea ice offshore distance information.
2. The sea ice recognition method based on FY-4 satellite fusion images according to claim 1 is characterized in that: Preprocessing the first original image and the second original image respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to the study area includes: Performing geometric correction on the first original image and the second original image to obtain a first geometrically corrected image and a second geometrically corrected image; Performing image cropping on the first geometrically corrected image and the second geometrically corrected image according to the location information of the study area to obtain the first geometrically corrected image and the second geometrically corrected image corresponding to the study area; Obtain a sea and land mask vector file corresponding to the study area, and use the sea and land mask vector file to perform mask processing on the first geometrically corrected image and the second geometrically corrected image corresponding to the study area to obtain a first sea area extraction result and a second sea area extraction result corresponding to the study area.
3. The sea ice recognition method based on FY-4 satellite fusion images according to claim 1 is characterized in that: The first sea area extraction result and the second sea area extraction result are fused to obtain a fused image corresponding to the study area, including: Normalizing the first sea area extraction result and the second sea area extraction result; Convert the normalized second sea area extraction result from the RGB space to the HSV space to obtain an H component, an S component, and a V component; Performing histogram matching on the first sea area extraction result after the normalization process and the V component to obtain a new V component; Perform HSV inverse transformation on the new V component, the H component and the S component to obtain a fused image corresponding to the study area.
4. The sea ice recognition method based on FY-4 satellite fusion images according to claim 1 is characterized in that: Performing sea ice recognition on the study area based on the fused image to obtain a sea ice recognition result corresponding to the study area includes: Performing ice-water separation processing on the fused image to obtain a target ice-water separation binary image; Eliminating the seawater elements in the target ice-water separation binary map and retaining the sea ice elements in the target ice-water separation binary map to obtain a sea ice surface file; Based on the sea ice surface file, the sea ice extent information and / or the sea ice distance from the shore information corresponding to the study area is determined.
5. The sea ice recognition method based on FY-4 satellite fusion images according to claim 4 is characterized in that: The fused image is processed for ice-water separation to obtain a target ice-water separation binary image, including: Based on a preset ice-water segmentation threshold, performing ice-water separation processing on the fused image to obtain an initial ice-water separation binary image; The area corresponding to each image spot in the initial ice-water separation binary image is determined, and the image spots whose areas are smaller than a preset area threshold are removed to obtain a target ice-water separation binary image.
6. The sea ice recognition method based on FY-4 satellite fusion images according to claim 4 is characterized in that: Based on the sea ice surface file, determining the sea ice range information corresponding to the study area includes: The sea ice surface file is processed into a line file to obtain a sea ice line file, and the range enclosed by the sea ice line file is used as the sea ice range information corresponding to the study area.
7. The sea ice recognition method based on FY-4 satellite fusion images according to claim 6 is characterized in that: Based on the sea ice surface file, determining the sea ice offshore distance information corresponding to the study area includes: Determining the intersection point of the sea ice line file and a preset baseline file; The longitude and latitude data of the intersection point and the longitude and latitude data of a preset reference point are used to determine the geodetic distance between the intersection point and the reference point, so as to determine the sea ice offshore distance information corresponding to the study area.
8. The sea ice recognition method based on FY-4 satellite fusion images according to claim 1 is characterized in that: After performing sea ice recognition on the study area based on the fused image to obtain a sea ice recognition result corresponding to the study area, the method further includes: Thematic maps are prepared for the sea ice extent information and the sea ice distance from shore information to generate a thematic map of sea ice extent and a thematic map of sea ice distance from shore corresponding to the study area.
9. A sea ice recognition device based on Fengyun-4 satellite fusion images, characterized in that: include: An image acquisition module, used to acquire a first original image and a second original image collected by the Fengyun-4 satellite, wherein the first original image is a single-channel image and the second original image is a multi-channel image; A sea area extraction module, used for preprocessing the first original image and the second original image respectively to generate a first sea area extraction result and a second sea area extraction result corresponding to a study area; An image fusion module, used for fusing the first sea area extraction result and the second sea area extraction result to obtain a fused image corresponding to the study area; The sea ice recognition module is used to identify sea ice in the study area based on the fused image to obtain a sea ice recognition result corresponding to the study area, wherein the sea ice recognition result includes sea ice range information and / or sea ice offshore distance information.
10. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 8.
Citation Information
Patent Citations
Method for automatically and accurately identifying sea ice edge
CN102567730A
Weight-adaptive multi-feature block fusion traffic sign identification method
CN110490194A
Sea ice recognition method and system based on multi-source optical remote sensing image
CN112633171A
Sea ice target extraction method based on SAR data and multispectral data fusion
CN112906645A
Remote sensing monitoring evaluation method for sea ice disasters
CN113484924A
