Glacier extraction method, device and equipment based on meteorological satellite remote sensing data

Abstract

The present invention provides a glacier extraction method, device and equipment based on meteorological satellite remote sensing data, including: obtaining meteorological satellite remote sensing data corresponding to a study area, and generating target multi-band data based on the meteorological satellite remote sensing data; determining the glacier index corresponding to each pixel point in the study area based on the target multi-band data through a pre-constructed glacier index determination model, so as to determine the initial glacier determination result corresponding to the study area using the glacier index; wherein the glacier index determination model includes a glacier prediction section and other object prediction sections; determining the water body determination result corresponding to each pixel point in the study area based on the target multi-band data; and masking the initial glacier determination result using the water body determination result to obtain the target glacier determination result corresponding to the study area. The present invention can significantly improve the accuracy of the glacier determination result.

Description

Technical Field

[0001] The present invention relates to the technical field of glacier extraction, and in particular to a glacier extraction method, device and equipment based on meteorological satellite remote sensing data. Background Art

[0002] Global temperatures continue to rise, and glaciers are melting faster. Rapid and accurate extraction of glacier distribution data will greatly deepen the understanding of climate change mechanisms, thereby providing solid support for effectively responding to climate change. With the development of remote sensing technology, more and more studies are being conducted on extracting glaciers based on remote sensing data. The global coverage and high-efficiency observation capabilities of meteorological satellites can quickly capture the dynamic changes of global glaciers, providing important data support and scientific basis for glacier research. At present, there are many methods for extracting glaciers using remote sensing, but the accuracy of glacier extraction by such methods is affected by the selection of thresholds, and the accuracy of glacier extraction needs to be improved. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a glacier extraction method, device and equipment based on meteorological satellite remote sensing data, which can significantly improve the accuracy of glacier determination results.

[0004] In a first aspect, an embodiment of the present invention provides a glacier extraction method based on meteorological satellite remote sensing data, comprising:

[0005] Acquire meteorological satellite remote sensing data corresponding to the study area, and generate target multi-band data based on the meteorological satellite remote sensing data;

[0006] The glacier index corresponding to each pixel point in the study area is determined based on the target multi-band data through a pre-constructed glacier index determination model, so as to determine the initial glacier determination result corresponding to the study area using the glacier index; wherein the glacier index determination model includes a glacier prediction section and other object prediction sections;

[0007] Determine the water body determination result corresponding to each pixel point in the study area based on the target multi-band data;

[0008] The initial glacier determination result is masked using the water body determination result to obtain a target glacier determination result corresponding to the study area.

[0009] In one embodiment, the step of determining the glacier index corresponding to each pixel point in the study area based on the target multi-band data by using a pre-constructed glacier index determination model includes:

[0010] Inputting the target multi-band data into the glacier prediction division to obtain a first calculation result of the glacier prediction division, wherein the first calculation result is positively correlated with the possibility that the pixel point is a glacier pixel point;

[0011] and, inputting the target multi-band data into the other object prediction section to obtain a second calculation result of the other object prediction section, wherein the positivity of the second calculation result is related to the possibility that the pixel point is a vegetation, bare soil or cloud pixel point;

[0012] Based on the first calculation result and the second calculation result, a glacier index corresponding to each pixel point in the study area is determined.

[0013] In one embodiment, the target multi-band data includes green band surface reflectivity, red band surface reflectivity, near infrared band surface reflectivity, first short infrared band surface reflectivity, and second short infrared band surface reflectivity; the expression of the glacier index determination model is as follows:

[0014]

[0015] Among them, NDGI is the glacier index, For the Glacier Prediction Division, For the predicted divisions of other objects, B2 is the surface reflectance of the green band, B3 is the surface reflectance of the red band, B4 is the surface reflectance of the near-infrared band, B5 is the surface reflectance of the first short infrared band, and B6 is the surface reflectance of the second short infrared band.

[0016] In one embodiment, the step of using the glacier index to determine the initial glacier determination result corresponding to the study area includes:

[0017] For each pixel point in the study area, if the glacier index corresponding to the pixel point is greater than 0, the pixel point is determined to be a glacier pixel point; if the glacier index corresponding to the pixel point is less than or equal to 0, the pixel point is determined to be a non-glacier pixel point, so as to obtain the initial glacier determination result corresponding to the study area.

[0018] In one embodiment, the step of determining the water body determination result corresponding to each pixel point in the study area based on the target multi-band data includes:

[0019] For each pixel point in the study area, if the surface reflectance in the near-infrared band corresponding to the pixel point is less than a preset threshold, the pixel point is determined to be a water body pixel point; if the surface reflectance in the near-infrared band corresponding to the pixel point is greater than or equal to the preset threshold, the pixel point is determined to be a non-water body pixel point, so as to obtain the water body judgment result corresponding to the study area.

[0020] In one embodiment, the step of masking the initial glacier determination result using the water body determination result to obtain the target glacier determination result corresponding to the study area includes:

[0021] For each glacier pixel point in the initial glacier determination result, if the glacier pixel point is identified as a water body pixel point in the water body determination result, the glacier pixel point is removed from the initial glacier determination result to obtain the target glacier determination result corresponding to the study area.

[0022] In one embodiment, the step of generating target multi-band data based on the meteorological satellite remote sensing data includes:

[0023] Extracting multi-band data from the meteorological satellite remote sensing data according to the specified multiple bands;

[0024] The multi-band data is resampled to unify the spatial resolution of the multi-band data to obtain target multi-band data.

[0025] In a second aspect, an embodiment of the present invention further provides a glacier extraction device based on meteorological satellite remote sensing data, comprising:

[0026] A data acquisition module is used to acquire meteorological satellite remote sensing data corresponding to the study area, and generate target multi-band data based on the meteorological satellite remote sensing data;

[0027] A glacier determination module is used to determine the glacier index corresponding to each pixel point in the study area based on the target multi-band data through a pre-constructed glacier index determination model, so as to determine the initial glacier determination result corresponding to the study area using the glacier index; wherein the glacier index determination model includes a glacier prediction section and other object prediction sections;

[0028] A water body determination module, used to determine the water body determination result corresponding to each pixel point in the study area based on the target multi-band data;

[0029] The masking module is used to mask the initial glacier determination result using the water body determination result to obtain the target glacier determination result corresponding to the study area.

[0030] 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.

[0031] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0032] The embodiments of the present invention provide a glacier extraction method, device and equipment based on meteorological satellite remote sensing data. The method first obtains meteorological satellite remote sensing data corresponding to a study area, and generates target multi-band data based on the meteorological satellite remote sensing data. Then, a glacier index corresponding to each pixel point in the study area is determined based on the target multi-band data through a pre-constructed glacier index determination model, so as to determine an initial glacier determination result corresponding to the study area using the glacier index. The glacier index determination model includes a glacier prediction section and other object prediction sections. Then, a water body determination result corresponding to each pixel point in the study area is determined based on the target multi-band data. Finally, the initial glacier determination result is masked using the water body determination result to obtain a target glacier determination result corresponding to the study area. The above method respectively utilizes the prediction part of other objects to eliminate the influence of different landforms on glacier extraction, and utilizes the water body determination result to eliminate the influence of water body on glacier extraction, which significantly improves the accuracy of glacier determination results; in addition, the glacier index determination model provided by the embodiment of the present invention has high versatility. When making glacier determinations in different regions, the generated glacier index can be compared with a fixed threshold to obtain an initial glacier determination result. Compared with the threshold selection problem faced by the prior art, the embodiment of the present invention can realize glacier extraction more universally and quickly.

[0033] 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.

[0034] 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

[0035] 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.

[0036] Figure 1A schematic flow chart of a glacier extraction method based on meteorological satellite remote sensing data provided by an embodiment of the present invention;

[0037] Figure 2 A schematic diagram of a spectrum curve of a typical ground object provided by an embodiment of the present invention;

[0038] Figure 3 An overall flow chart of a glacier extraction method based on meteorological satellite remote sensing data provided by an embodiment of the present invention;

[0039] Figure 4 A schematic diagram of the structure of a glacier extraction device based on meteorological satellite remote sensing data provided by an embodiment of the present invention;

[0040] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] 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.

[0042] At present, there are many methods for extracting glaciers using remote sensing means, but there is no universal and fast method, especially for meteorological satellite remote sensing data. Moreover, the glacier extraction accuracy of such methods is affected by the selection of thresholds, and the glacier extraction accuracy needs to be improved. Based on this, the present invention provides a glacier extraction method, device and equipment based on meteorological satellite remote sensing data, which can significantly improve the universality of the glacier extraction method and improve the accuracy of glacier determination results.

[0043] To facilitate understanding of this embodiment, firstly, a glacier extraction method based on meteorological satellite remote sensing data disclosed in an embodiment of the present invention is described in detail, see Figure 1 The flowchart of a glacier extraction method based on meteorological satellite remote sensing data is shown in FIG. 1 , and the method mainly includes the following steps S102 to S108:

[0044] Step S102, obtaining meteorological satellite remote sensing data corresponding to the study area, and generating target multi-band data based on the meteorological satellite remote sensing data.

[0045] In one example, data of a specified band can be extracted from the acquired meteorological satellite remote sensing data, and then the extracted data can be unified to the same spatial resolution to obtain target multi-band data. The target multi-band data includes green band surface reflectivity, red band surface reflectivity, near infrared band surface reflectivity, first short infrared band surface reflectivity, and second short infrared band surface reflectivity.

[0046] Step S104, determining the glacier index corresponding to each pixel point in the study area based on the target multi-band data through a pre-constructed glacier index determination model, so as to determine the initial glacier determination result corresponding to the study area using the glacier index.

[0047] Among them, the glacier index determination model includes a glacier prediction division and an other object prediction division. The first calculation result of the glacier prediction division is positively correlated with the possibility that the pixel point is a glacier pixel point. The positivity of the second calculation result of the other object prediction division is related to the possibility that the pixel point is a vegetation, bare soil or cloud pixel point. The other object prediction division is used to eliminate the influence of other objects on glacier extraction. In one example, the target multi-band data is input into the glacier index determination model to obtain the glacier index corresponding to each pixel point in the study area. The glacier index is compared with the threshold of 0 to extract the pixel points belonging to the glacier and obtain the initial glacier determination result. The initial glacier determination result is binary data, in which the pixel point with a pixel value of 0 is a non-glacier pixel point, and the pixel point with a pixel value of 1 is a glacier pixel point.

[0048] Step S106, determining the water body determination result corresponding to each pixel point in the study area based on the target multi-band data.

[0049] In one example, the existing water body extraction algorithm can be used to determine the water body determination result corresponding to each pixel point in the study area based on the target multi-band data. The water body determination result is binary data, in which the pixel point with a pixel value of 0 is a non-water body pixel point, and the pixel point with a pixel value of 1 is a water body pixel point.

[0050] Step S108, masking the initial glacier determination result with the water body determination result to obtain the target glacier determination result corresponding to the study area.

[0051] In one example, for the same pixel point, if it is a glacier pixel point in the initial glacier determination result, but is a water body pixel point in the water body determination result, the pixel point is removed from the initial glacier determination result to obtain the target glacier determination result eliminating the water body image.

[0052] The above method respectively utilizes the prediction part of other objects to eliminate the influence of different landforms on glacier extraction, and utilizes the water body determination result to eliminate the influence of water body on glacier extraction, which significantly improves the accuracy of glacier determination results; in addition, the glacier index determination model provided by the embodiment of the present invention has high versatility. When making glacier determinations in different regions, the generated glacier index can be compared with a fixed threshold to obtain an initial glacier determination result. Compared with the threshold selection problem faced by the prior art, the embodiment of the present invention can realize glacier extraction more universally and quickly.

[0053] To facilitate understanding of the aforementioned embodiments, the embodiments of the present invention provide a specific implementation of a glacier extraction method based on meteorological satellite remote sensing data.

[0054] Step 1, obtaining meteorological satellite remote sensing data corresponding to the study area, and generating target multi-band data based on the meteorological satellite remote sensing data, including:

[0055] (1) Reading meteorological satellite remote sensing data corresponding to the study area. In the embodiment of the present invention, the MERSI sensor data of the FY3D satellite is selected as the data source of the embodiment, specifically, the atmospherically corrected FY3D / MERSI multi-band composite data of a certain period is read and used as the meteorological satellite remote sensing data corresponding to the study area.

[0056] (2) Extracting multi-band data from meteorological satellite remote sensing data according to the specified multiple bands. In an embodiment of the present invention, it is necessary to extract the bands required for calculating the glacier index NDGI, including the green band B2, the red band B3, the near infrared band B4, the first short infrared band B5, and the second short infrared band B6. For example, according to the requirements of the glacier index NDGI algorithm, the bands with central wavelengths of 0.550 μm (green band B2), 0.650 μm (red band B3), 0.865 μm (near infrared band B4), 1.380 μm (first short infrared band B5) and 1.640 μm (second short infrared band B6) are extracted.

[0057] (3) Resample the multi-band data to unify the spatial resolution of the multi-band data and obtain the target multi-band data. In practical applications, due to the different spatial resolutions of different band data of FY3D / MERSI, the resampling method is used to unify the extracted bands to a resolution of 500 m.

[0058] Step 2: Determine the Normalized Difference Glacier Index (NDGI) corresponding to each pixel point in the study area based on the target multi-band data using the pre-built glacier index determination model, including:

[0059] (1) The target multi-band data is input into the glacier prediction section to obtain the first calculation result of the glacier prediction section. The first calculation result is positively correlated with the possibility that the pixel point is a glacier pixel point. That is, the larger the value of the first calculation result, the greater the possibility that the pixel is a glacier pixel point.

[0060] (2) Input the target multi-band data into the other object prediction section to obtain the second calculation result of the other object prediction section, and the positivity of the second calculation result is related to the possibility that the pixel point is a vegetation, bare soil or cloud pixel point. The other object prediction section is specifically the vegetation and bare soil prediction part. For example, when the second calculation result is positive, it indicates that the pixel point is less likely to be a vegetation or bare soil pixel point, and when the second calculation result is negative, it indicates that the pixel point is more likely to be a vegetation or bare soil pixel point.

[0061] (3) Based on the first calculation result and the second calculation result, determine the glacier index corresponding to each pixel point in the study area. In one example, the first calculation result and the second calculation result can be processed by a summation, weighting or other calculation method to obtain the glacier index corresponding to each pixel point.

[0062] In the specific implementation, first (1) read the FY3D / MERSI band data after screening and processing in step 1, and then use the following formula to determine the glacier index NDGI corresponding to each pixel point:

[0063]

[0064] Among them, NDGI is the glacier index, For the Glacier Prediction Division, For the prediction divisions of other objects, B2 is the surface reflectivity of the green band (i.e. the surface reflectivity with a central wavelength of 0.550 μm), B3 is the surface reflectivity of the red band (i.e. the surface reflectivity with a central wavelength of 0.650 μm), B4 is the surface reflectivity of the near-infrared band (i.e. the surface reflectivity with a central wavelength of 0.865 μm), B5 is the surface reflectivity of the first short infrared band (i.e. the surface reflectivity with a central wavelength of 1.380 μm), and B6 is the surface reflectivity of the second short infrared band (i.e. the surface reflectivity with a central wavelength of 1.640 μm).

[0065] See also Figure 2 The spectral curve diagram of a typical landform is shown in the figure. The spectral characteristics of the glacier pixel with high reflectivity in the B2 and B3 bands and low reflectivity in the B5 and B6 bands are used to construct the spectral curve. Part. The larger the value, the more likely the pixel is a glacier. At the same time, according to the spectral curve, the reflectance of the B4 (near infrared) band of vegetation and bare soil is greater than the reflectance of the B3 (red) band. Based on this characteristic, In addition, it is found in practice that the B4 reflectivity of clouds and thin clouds is often greater than the B3 reflectivity. The probability of misclassification of glaciers and clouds is further reduced.

[0066] Step 3: Use the glacier index to determine the initial glacier determination results corresponding to the study area, including:

[0067] For each pixel point in the study area, if the glacier index corresponding to the pixel point is greater than 0, the pixel point is determined to be a glacier pixel point and the pixel point is assigned a value of 1. If the glacier index corresponding to the pixel point is less than or equal to 0, the pixel point is determined to be a non-glacier pixel point and the pixel point is assigned a value of 0 to obtain the initial glacier determination result corresponding to the study area.

[0068] Furthermore, in order to verify the accuracy of the above-mentioned glacier extraction, an embodiment of the present invention provides an example of a typical ground object reflectance and related index as shown in Table 1 below. Table 1 shows that the NDGI of the pixel point at the glacier is greater than 0, while the NDGI values ​​of the pixel points at other ground objects are all less than 0. At the same time, Table 1 also shows two ice and snow indices NDSI_B5 and NDSI_B6. It can be seen that there is no obvious regularity in the ice and snow indices of the pixel points at the glacier and other ground objects, which makes it difficult to select the threshold, thereby affecting the accuracy of glacier extraction.

[0069] Table 1

[0070]

[0071]

[0072] Note:

[0073] 1) Sample refers to the overall performance of a large number of samples.

[0074] 2) NDGI is the glacier index; NDSI_B5 and NDSI_B6 are two ice and snow indices, and their formulas are as follows:

[0075]

[0076]

[0077] Among them, B2 corresponds to a central wavelength of 0.550 μm, B3 has a central wavelength of 0.650 μm, B4 has a central wavelength of 0.865 μm, B5 has a central wavelength of 1.380 μm, and B6 has a central wavelength of 1.640 μm.

[0078] Step 4: Determine the water body determination result corresponding to each pixel point in the study area based on the target multi-band data, including:

[0079] For each pixel point in the study area, if the surface reflectance in the near-infrared band corresponding to the pixel point is less than the preset threshold, the pixel point is determined to be a water body pixel point; if the surface reflectance in the near-infrared band corresponding to the pixel point is greater than or equal to the preset threshold, the pixel point is determined to be a non-water body pixel point, so as to obtain the water body judgment result corresponding to the study area.

[0080] Specifically, it includes: reading the B4 near-infrared band (0.865μm) data after screening and processing in step 1; judging whether the reflectivity of the B4 near-infrared band (0.865μm) is less than 100, if it is less than 100, the pixel is judged as a water body pixel and assigned a value of 1; if it is greater than or equal to 100, the pixel is judged as a non-water body pixel and assigned a value of 0; after the above process, water body binary data is obtained, and the water body binary data is also the water body judgment result.

[0081] Although the NDGI index performs well in extracting glaciers, a large number of practices (based on FY3D / MERSI, AQUA / MODIS and other data) have found that some water bodies and glaciers cannot be distinguished based on a threshold of 0, such as the examples of glacier and water body reflectance and related indexes shown in Table 2. Sufficient literature has shown that the reflectance of water bodies in the visible light range is extremely low. In practice, a large number of samples extracted show that the reflectance of water bodies in the B4 near-infrared band (0.865μm) is basically less than 100. Therefore, this characteristic of water bodies is used to eliminate the influence of water bodies on glacier extraction.

[0082] Table 2

[0083]

[0084] Note: 1) Sample refers to the specific point extraction to illustrate the above description. 2) NDGI is the glacier index; NDSI_B5 and NDSI_B6 are two ice and snow indices, see Table 1 for details.

[0085] Step 5, using the water body determination result to mask the initial glacier determination result to obtain the target glacier determination result corresponding to the study area, including: for each glacier pixel point in the initial glacier determination result, if the glacier pixel point is identified as a water body pixel point in the water body determination result, then the glacier pixel point is removed from the initial glacier determination result to obtain the target glacier determination result corresponding to the study area.

[0086] Specifically, it includes: reading the glacier binary data calculated in step 3 and the water body binary data calculated in step 4. Using the water body binary data to mask the glacier binary data, when the pixel value in the water body binary data is 1, the corresponding pixel in the glacier binary data is determined to be a water body and assigned a value of 0. After the above, the glacier binary distribution image is finally output, and the glacier binary distribution image is used as the target glacier determination result.

[0087] The above-mentioned glacier extraction method based on meteorological satellite remote sensing data provided by the embodiment of the present invention develops a glacier index based on full consideration of the spectral differences between different objects. The NDGI values ​​of different objects vary significantly. By setting the threshold value to 0, glaciers can be effectively distinguished from other objects, successfully solving the threshold selection problem faced when using traditional indices such as the ice and snow index in glacier research.

[0088] Furthermore, the embodiment of the present invention also provides Figure 3 The overall flow chart of a glacier extraction method based on meteorological satellite remote sensing data shown in the figure includes: data reading; band screening; band resampling; reading data from each band to calculate the glacier index NDGI, if the NDGI is greater than 0, it is judged as a glacier, if the NDGI is less than or equal to 0, it is judged as a non-glacier, so as to obtain a glacier determination result; reading NIR (near infrared) data, if the NIR is greater than 100, it is judged as a water body, if the NIR is less than or equal to 0, it is judged as a non-water body, so as to obtain a water body determination result; water body masking, outputting the glacier binary result.

[0089] In summary, the embodiments of the present invention have at least the following features: (1) A "new" glacier index NDGI for meteorological satellite data has been developed. (2) The threshold selection problem faced when using traditional indices such as the ice and snow index NDSI in glacier extraction has been solved. (3) Compared with the previous glacier extraction, the index is more accurate and the results are more reliable.

[0090] Based on the above embodiments, the present invention provides a glacier extraction device based on meteorological satellite remote sensing data. Figure 4 The schematic diagram of the structure of a glacier extraction device based on meteorological satellite remote sensing data is shown in FIG. The device mainly includes the following parts:

[0091] The data acquisition module 402 is used to acquire meteorological satellite remote sensing data corresponding to the study area, and generate target multi-band data based on the meteorological satellite remote sensing data;

[0092] The glacier determination module 404 is used to determine the glacier index corresponding to each pixel point in the study area based on the target multi-band data through a pre-constructed glacier index determination model, so as to determine the initial glacier determination result corresponding to the study area using the glacier index; wherein the glacier index determination model includes a glacier prediction section and other object prediction sections;

[0093] A water body determination module 406 is used to determine the water body determination result corresponding to each pixel point in the study area based on the target multi-band data;

[0094] The masking module 408 is used to mask the initial glacier determination result using the water body determination result to obtain the target glacier determination result corresponding to the study area.

[0095] The above-mentioned device respectively utilizes the prediction part of other objects to eliminate the influence of different landforms on glacier extraction, and utilizes the water body determination result to eliminate the influence of water body on glacier extraction, which significantly improves the accuracy of glacier determination results; in addition, the glacier index determination model provided by the embodiment of the present invention has high versatility. When glacier determination is performed on different regions, the generated glacier index can be compared with the fixed threshold to obtain the initial glacier determination result. Compared with the threshold selection problem faced by the prior art, the embodiment of the present invention can realize glacier extraction more universally and quickly.

[0096] In one embodiment, the glacier determination module 404 is further configured to:

[0097] Input the target multi-band data into the glacier prediction division to obtain the first calculation result of the glacier prediction division, and the first calculation result is positively correlated with the possibility that the pixel point is a glacier pixel point;

[0098] and inputting the target multi-band data into the other object prediction division to obtain a second calculation result of the other object prediction division, wherein the positivity of the second calculation result is related to the possibility that the pixel point is a vegetation, bare soil or cloud pixel point;

[0099] Based on the first calculation results and the second calculation results, the glacier index corresponding to each pixel point in the study area is determined.

[0100] In one embodiment, the target multi-band data includes green band surface reflectance, red band surface reflectance, near infrared band surface reflectance, first short infrared band surface reflectance, and second short infrared band surface reflectance; the expression of the glacier index determination model is as follows:

[0101]

[0102] Among them, NDGI is the glacier index, For the Glacier Prediction Division, For the predicted divisions of other objects, B2 is the surface reflectance of the green band, B3 is the surface reflectance of the red band, B4 is the surface reflectance of the near-infrared band, B5 is the surface reflectance of the first short infrared band, and B6 is the surface reflectance of the second short infrared band.

[0103] In one embodiment, the glacier determination module 404 is further configured to:

[0104] For each pixel point in the study area, if the glacier index corresponding to the pixel point is greater than 0, the pixel point is determined to be a glacier pixel point; if the glacier index corresponding to the pixel point is less than or equal to 0, the pixel point is determined to be a non-glacier pixel point, so as to obtain the initial glacier determination result corresponding to the study area.

[0105] In one embodiment, the water body determination module 406 is further configured to:

[0106] For each pixel point in the study area, if the surface reflectance in the near-infrared band corresponding to the pixel point is less than the preset threshold, the pixel point is determined to be a water body pixel point; if the surface reflectance in the near-infrared band corresponding to the pixel point is greater than or equal to the preset threshold, the pixel point is determined to be a non-water body pixel point, so as to obtain the water body judgment result corresponding to the study area.

[0107] In one embodiment, the mask module 408 is further configured to:

[0108] For each glacier pixel point in the initial glacier determination result, if the glacier pixel point is identified as a water body pixel point in the water body determination result, the glacier pixel point is removed from the initial glacier determination result to obtain the target glacier determination result corresponding to the study area.

[0109] In one implementation, the data acquisition module 402 is further configured to:

[0110] Extract multi-band data from meteorological satellite remote sensing data according to the specified multiple bands;

[0111] The multi-band data are resampled to unify the spatial resolution of the multi-band data and obtain the target multi-band data.

[0112] 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.

[0113] 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.

[0114] Figure 5 A structural diagram of an electronic device provided in an embodiment of the present invention, the electronic device 100 includes: a processor 50, a memory 51, a bus 52 and a communication interface 53, wherein the processor 50, the communication interface 53 and the memory 51 are connected via the bus 52; the processor 50 is used to execute an executable module stored in the memory 51, such as a computer program.

[0115] The memory 51 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 53 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0116] The bus 52 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 5 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.

[0117] Among them, the memory 51 is used to store programs, and the processor 50 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 embodiment of the present invention can be applied to the processor 50 or implemented by the processor 50.

[0118] The processor 50 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 50. The above processor 50 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 embodiments of the present invention can be directly embodied as a hardware decoding processor to be executed, 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 51, and the processor 50 reads the information in the memory 51 and completes the steps of the above method in combination with its hardware.

[0119] 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.

[0120] 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 for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment 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.

[0121] 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 glacier extraction method based on meteorological satellite remote sensing data, characterized in that: include: Acquire meteorological satellite remote sensing data corresponding to the study area, and generate target multi-band data based on the meteorological satellite remote sensing data; The glacier index corresponding to each pixel point in the study area is determined based on the target multi-band data through a pre-constructed glacier index determination model, so as to determine the initial glacier determination result corresponding to the study area using the glacier index; wherein the glacier index determination model includes a glacier prediction section and other object prediction sections; Determine the water body determination result corresponding to each pixel point in the study area based on the target multi-band data; Masking the initial glacier determination result using the water body determination result to obtain a target glacier determination result corresponding to the study area; The step of determining the glacier index corresponding to each pixel point in the study area based on the target multi-band data by using a pre-constructed glacier index determination model comprises: inputting the target multi-band data into the glacier prediction section to obtain a first calculation result of the glacier prediction section, wherein the first calculation result is positively correlated with the possibility that the pixel point is a glacier pixel point; and inputting the target multi-band data into the other object prediction section to obtain a second calculation result of the other object prediction section, wherein the positivity of the second calculation result is correlated with the possibility that the pixel point is a vegetation, bare soil or cloud pixel point; determining the glacier index corresponding to each pixel point in the study area based on the first calculation result and the second calculation result; The target multi-band data includes green band surface reflectivity, red band surface reflectivity, near infrared band surface reflectivity, first short infrared band surface reflectivity, and second short infrared band surface reflectivity; the expression of the glacier index determination model is as follows: ;in, is the glacier index, For the Glacier Prediction Division, Predict distributions for other objects, is the surface reflectance of the green band, is the surface reflectance of the red band, is the surface reflectivity in the near-infrared band, is the surface reflectivity in the first short infrared band, is the surface reflectivity in the second shortest infrared band; The step of determining the water body determination result corresponding to each pixel point in the study area based on the target multi-band data includes: for each pixel point in the study area, if the surface reflectance of the near-infrared band corresponding to the pixel point is less than a preset threshold, then the pixel point is determined to be a water body pixel point; if the surface reflectance of the near-infrared band corresponding to the pixel point is greater than or equal to the preset threshold, then the pixel point is determined to be a non-water body pixel point, so as to obtain the water body determination result corresponding to the study area.

2. The glacier extraction method based on meteorological satellite remote sensing data according to claim 1 is characterized in that: The step of using the glacier index to determine the initial glacier determination result corresponding to the study area includes: For each pixel point in the study area, if the glacier index corresponding to the pixel point is greater than 0, the pixel point is determined to be a glacier pixel point; if the glacier index corresponding to the pixel point is less than or equal to 0, the pixel point is determined to be a non-glacier pixel point, so as to obtain the initial glacier determination result corresponding to the study area.

3. The glacier extraction method based on meteorological satellite remote sensing data according to claim 1 is characterized in that: The step of masking the initial glacier determination result by using the water body determination result to obtain the target glacier determination result corresponding to the study area includes: For each glacier pixel point in the initial glacier determination result, if the glacier pixel point is identified as a water body pixel point in the water body determination result, the glacier pixel point is removed from the initial glacier determination result to obtain the target glacier determination result corresponding to the study area.

4. The glacier extraction method based on meteorological satellite remote sensing data according to claim 1 is characterized in that: The step of generating target multi-band data based on the meteorological satellite remote sensing data includes: Extracting multi-band data from the meteorological satellite remote sensing data according to the specified multiple bands; The multi-band data is resampled to unify the spatial resolution of the multi-band data to obtain target multi-band data.

5. A glacier extraction device based on meteorological satellite remote sensing data, characterized in that: include: A data acquisition module is used to acquire meteorological satellite remote sensing data corresponding to the study area, and generate target multi-band data based on the meteorological satellite remote sensing data; A glacier determination module is used to determine the glacier index corresponding to each pixel point in the study area based on the target multi-band data through a pre-constructed glacier index determination model, so as to determine the initial glacier determination result corresponding to the study area using the glacier index; wherein the glacier index determination model includes a glacier prediction section and other object prediction sections; A water body determination module, used to determine the water body determination result corresponding to each pixel point in the study area based on the target multi-band data; A masking module, used to mask the initial glacier determination result using the water body determination result to obtain a target glacier determination result corresponding to the study area; The glacier determination module is specifically used for: inputting the target multi-band data into the glacier prediction section to obtain a first calculation result of the glacier prediction section, wherein the first calculation result is positively correlated with the possibility that the pixel point is a glacier pixel point; and inputting the target multi-band data into the other object prediction section to obtain a second calculation result of the other object prediction section, wherein the positivity of the second calculation result is correlated with the possibility that the pixel point is a vegetation, bare soil or cloud pixel point; based on the first calculation result and the second calculation result, determining the glacier index corresponding to each pixel point in the study area; The target multi-band data includes green band surface reflectivity, red band surface reflectivity, near infrared band surface reflectivity, first short infrared band surface reflectivity, and second short infrared band surface reflectivity; the expression of the glacier index determination model is as follows: ;in, is the glacier index, For the Glacier Prediction Division, Predict distributions for other objects, is the surface reflectance of the green band, is the surface reflectance of the red band, is the surface reflectivity in the near-infrared band, is the surface reflectivity in the first short infrared band, is the surface reflectivity in the second shortest infrared band; The water body determination module is specifically used for: for each pixel point in the study area, if the surface reflectance in the near-infrared band corresponding to the pixel point is less than a preset threshold, then the pixel point is determined to be a water body pixel point; if the surface reflectance in the near-infrared band corresponding to the pixel point is greater than or equal to the preset threshold, then the pixel point is determined to be a non-water body pixel point, so as to obtain the water body determination result corresponding to the study area.

6. 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 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 4.

Images