Sea ice outer edge line extraction method and device, electronic equipment and storage medium

Abstract

The application provides a sea ice outer edge line extraction method and device, electronic equipment and a storage medium, and relates to the technical field of ocean remote sensing. The method comprises the following steps: acquiring an optical remote sensing image of a preset ocean area; performing preliminary sea ice extraction processing on the optical remote sensing image to obtain a sea ice extraction matrix (used for representing a plurality of connected regions meeting a preset range); performing ice fragment identification processing on the plurality of connected regions to obtain an ice fragment region, and removing the ice fragment region to obtain a target matrix; converting the target matrix after removing the ice fragment region into a target image, performing raster-to-vector processing on the target image, and obtaining a vector surface file; removing background vector surfaces in the vector surface file, and performing vector surface-to-line processing to obtain a sea ice outer edge line. The application improves the accuracy of sea ice outer edge line extraction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ocean remote sensing, and in particular to a sea ice outer edge line extraction method and device, electronic equipment and a storage medium. BACKGROUND

[0002] Large-area sea ice can affect the safety of various production activities such as sea transportation, marine aquaculture, oil platforms, etc. In order to ensure timely and effective sea ice condition acquisition, in related technologies, remote sensing images are used for sea ice edge line detection. The sea ice outer edge line is represented as the line of the outermost pixels of the main body of sea ice on a remote sensing image, which can reflect the overall condition of the sea ice and is an important indicator of the development trend of sea ice. In related technologies, the sea ice outer edge line extraction method needs to be modified by manual visual interpretation, which cannot meet the needs of business sea ice monitoring. SUMMARY

[0003] The purpose of the present application is to provide a sea ice outer edge line extraction method, device, electronic equipment and storage medium, which improves the accuracy of sea ice outer edge line extraction.

[0004] In a first aspect, the present application provides a sea ice outer edge line extraction method, which comprises: acquiring an optical remote sensing image of a preset sea area; performing preliminary sea ice extraction processing on the optical remote sensing image to obtain a sea ice extraction matrix; the sea ice extraction matrix is used to represent a plurality of connected regions that meet a preset range; performing ice fragment identification processing on the plurality of connected regions to obtain an ice fragment region, and removing the ice fragment region to obtain a target matrix; converting the target matrix after removing the ice fragment region into a target image, performing raster-to-vector processing on the target image, and obtaining a vector surface file; removing the background vector surface in the vector surface file, and performing vector surface-to-line processing to obtain the sea ice outer edge line.

[0005] In an optional implementation, the preliminary sea ice extraction processing on the optical remote sensing image to obtain the sea ice extraction matrix comprises: performing sea-land mask processing on the optical remote sensing image to obtain a mask matrix after masking; performing threshold segmentation processing on the mask matrix to obtain a first binary matrix after segmentation; performing dilation and erosion processing on the binary matrix based on a preset convolution kernel to obtain a region filling matrix; performing small area removal processing on the region filling matrix to obtain the sea ice extraction matrix.

[0006] In an optional implementation, the ice fragment identification processing on the plurality of connected regions to obtain the ice fragment region comprises: performing connected domain labeling processing on the sea ice extraction matrix to obtain a first connected domain labeling matrix; performing binary negation on the sea ice extraction matrix to obtain a second binary matrix opposite to the sea ice extraction matrix, and performing connected domain labeling processing on the second binary matrix to obtain a second connected domain labeling matrix; calculating a connected domain difference matrix based on the first connected domain labeling matrix and the second connected domain labeling matrix; the connected domain difference matrix is used to represent the ice fragment region.

[0007] In an optional embodiment, the connected domain marking process comprises: sequentially traversing the to-be-marked matrix according to a preset traversal order, when a first outer contour point that has not been marked is identified, marking the outer contour point with a first mark; taking the first outer contour point as a starting point, tracking based on an outer contour where the first outer contour point is located until returning to the first outer contour point, and marking all points on the tracking path with the first mark; if a second outer contour point that has been marked is identified on the preset traversal order, marking all points on the preset traversal order after the second outer contour point as a second mark corresponding to the second outer contour point; if an inner contour point is identified on the preset traversal order starting from the second outer contour point, marking points on the path on the preset traversal order after the inner contour point as the second mark.

[0008] In an optional embodiment, the removing of the ice fragment region to obtain the target matrix comprises: taking the second connected domain marking matrix as a base matrix, counting the number of pixels corresponding to each pixel value in the connected domain difference value matrix; finding a first position index where the number of pixels of each pixel value in the connected domain difference value matrix is greater than a preset threshold, and marking the pixel value at the corresponding first position index in the second connected domain marking matrix with a first mark; finding a second position index where the number of pixels of each pixel value in the connected domain difference value matrix is less than or equal to the preset threshold, and marking the pixel value at the corresponding second position index in the second connected domain marking matrix with a second mark, to obtain the target matrix after removing the ice fragment region.

[0009] In an optional embodiment, the optical remote sensing image of the preset sea area is a Landsat8 remote sensing image of the Bohai Sea area.

[0010] In a second aspect, the present application provides a device for extracting an ice edge line, which comprises: an image acquisition module, configured to acquire an optical remote sensing image of a preset sea area; an extraction module, configured to perform a preliminary sea ice extraction process on the optical remote sensing image to obtain a sea ice extraction matrix; the sea ice extraction matrix is used to represent a plurality of connected regions that meet a preset range; an ice fragment processing module, configured to perform ice fragment identification processing on the plurality of connected regions to obtain an ice fragment region, and remove the ice fragment region to obtain a target matrix; a conversion module, configured to convert the target matrix after removing the ice fragment region into a target image, perform raster-to-vector processing on the target image, and obtain a vector surface file; and an edge line extraction module, configured to remove background vector surfaces in the vector surface file, and perform vector surface-to-line processing to obtain an ice edge line.

[0011] In an optional embodiment, the extraction module is further configured to: perform a sea-land mask processing on the optical remote sensing image to obtain a masked mask matrix; perform a threshold segmentation processing on the mask matrix to obtain a segmented first binary matrix; perform an inflation corrosion processing on the binary matrix based on a preset convolution kernel to obtain a region filling matrix; and perform a small area removal processing on the region filling matrix to obtain the sea ice extraction matrix.

[0012] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, the memory storing computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to implement the method for extracting the sea ice edge line according to any one of the preceding embodiments.

[0013] In a fourth aspect, the present application provides a computer readable storage medium, the computer readable storage medium storing computer executable instructions, and the computer executable instructions, when invoked and executed by a processor, cause the processor to implement the method for extracting the sea ice edge line according to any one of the preceding embodiments.

[0014] The method for extracting the sea ice edge line, the device, the electronic device and the storage medium provided by the present application first acquire an optical remote sensing image of a preset sea area, perform a preliminary sea ice extraction processing on the optical remote sensing image to obtain a sea ice extraction matrix (wherein the sea ice extraction matrix is used to represent a plurality of connected regions satisfying a preset range), perform a broken ice identification processing on the plurality of connected regions to obtain a broken ice region, and remove the broken ice region to obtain a target matrix. The target matrix after the broken ice region is removed is converted into a target image, a raster-to-vector processing is performed on the target image to obtain a vector surface file, the background vector surface in the vector surface file is removed, and a vector surface-to-line processing is performed to obtain the sea ice edge line. In this way, through a series of processing such as sea-land mask, fixed threshold segmentation, dilation and corrosion processing, small area removal processing, and broken ice region inspection removal, the purpose of identifying the main sea ice is achieved, and then through raster-to-vector, removal of the vector surface background value, and vector surface-to-line processing, the accuracy of the sea ice edge line identification is improved. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed in the description of the embodiments or the prior art will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0016] Figure 1 A flowchart of a method for extracting a sea ice edge line provided by an embodiment of the present application;

[0017] Figure 2 A flowchart of a specific method for extracting a sea ice edge line provided by an embodiment of the present application;

[0018] Figure 3 A Landsat8 third band Bohai Bay sea ice remote sensing image schematic diagram provided by an embodiment of the present application;

[0019] Figure 4 A binary image after threshold segmentation of a Landsat8 third band remote sensing image provided by an embodiment of the present application;

[0020] Figure 5 A binary image after closed operation and small area removal processing of a threshold segmentation binary image provided by an embodiment of the present application;

[0021] Figure 6 A binary image after ice fragment removal by connected domain labeling provided by an embodiment of the present application;

[0022] Figure 7 A schematic diagram of a sea ice outer edge line superimposed on a Landsat8 third band remote sensing image provided by an embodiment of the present application;

[0023] Figure 8 A structural diagram of a sea ice outer edge line extraction device provided by an embodiment of the present application;

[0024] Figure 9 A structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in connection with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative labor are within the scope of protection of the present application.

[0027] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0028] Bohai Sea is the highest latitude and nearly closed inland sea in China, affected by the river into the sea, the sea water salinity is lower, combined with the winter cold invasion, every winter will appear large area of ice phenomenon; the region is also an important marine economic zone, large area of sea ice seriously affected the safety of marine transportation, marine aquaculture, oil platform and other production activities, so timely and effective ice conditions, for the prevention and mitigation of ice disaster in Bohai Sea has important significance.

[0029] Traditional site reconnaissance cannot obtain macro ice distribution information, time-consuming and laborious. Since 1985, scholars have used remote sensing technology to monitor sea ice in Bohai Sea. Remote sensing technology has the ability to obtain electromagnetic wave reflection, radiation or scattering of sea ice in a large range and quickly. Based on remote sensing images, sea ice monitoring has become the main means of sea ice monitoring. Unlike polar sea ice, the thickness of Bohai Bay sea ice is thin, which belongs to one-year ice. Polar sea ice monitoring is mainly based on active remote sensing data such as microwave remote sensing data and laser radar remote sensing data, while Bohai Sea ice monitoring mainly uses passive remote sensing data such as optical remote sensing, thermal infrared remote sensing and microwave remote sensing, for example, Landsat series data, Sentinel 2 data, marine 1C satellite data and so on. Most of these data can be obtained free of charge, with short revisit period and wide coverage, which can meet the demand of Bohai Sea ice monitoring.

[0030] Sea ice monitoring elements include sea ice classification, sea ice outer edge line, sea ice area, sea ice thickness, sea ice drift, sea ice density, sea ice temperature and so on. The sea ice outer edge line is represented as the connection line of the outermost pixels of the main sea ice in the remote sensing image, which can reflect the whole sea ice condition and is an important indicator of the development trend of sea ice. The existing sea ice outer edge line extraction method needs to be modified by manual visual interpretation, which cannot meet the demand of business sea ice monitoring.

[0031] Therefore, the embodiment of the present application provides a sea ice outer edge line extraction method, device, electronic equipment and storage medium, which improves the accuracy of sea ice outer edge line extraction.

[0032] The embodiment of the present application provides a sea ice outer edge line extraction method, as shown in Figure 1 The method mainly includes the following steps:

[0033] Step S110, acquiring an optical remote sensing image of a preset marine area.

[0034] The optical remote sensing image of the preset marine area is a Landsat8 remote sensing image of Bohai Sea area. In an embodiment, a Landsat8 third band optical remote sensing image can be acquired.

[0035] In step S120, the optical remote sensing image is subjected to preliminary sea ice extraction processing to obtain a sea ice extraction matrix. The sea ice extraction matrix is used to represent a plurality of connected regions that meet a preset range.

[0036] In an embodiment, the preliminary sea ice extraction processing includes land-sea mask processing, threshold segmentation processing, dilation erosion processing, and small area removal processing. In an embodiment, the preliminary sea ice extraction processing can include the following steps 2-1 to 2-4:

[0037] In step 2-1, the optical remote sensing image is subjected to land-sea mask processing to obtain a mask matrix after masking.

[0038] In step 2-2, the mask matrix is subjected to threshold segmentation processing to obtain a first binary matrix after segmentation.

[0039] In step 2-3, the binary matrix is subjected to dilation erosion processing based on a preset convolution kernel to obtain a region filling matrix.

[0040] In step 2-4, the region filling matrix is subjected to small area removal processing to obtain a sea ice extraction matrix.

[0041] In an embodiment, a pre-configured land-sea mask vector file is first obtained, and the obtained optical remote sensing image is subjected to land-sea mask processing, with the land pixel value being set to 0 to obtain a sea ice extraction mask matrix T1 after masking. Threshold segmentation is performed with a preset threshold, with the pixel value of the mask matrix T1 greater than the preset threshold being set to 1, and otherwise being set to 0, to obtain a binary matrix T2 after threshold segmentation. A convolution kernel of a preset size is set, and the binary image matrix T2 is subjected to dilation erosion processing to obtain a region filling matrix T3. The region filling matrix T3 is subjected to small area removal processing, a minimum connected region size is set, that is, if the size of a connected region is smaller than the minimum connected region size, the value of the connected region is set to the same value as the value of the surrounding background, and the small connected region is removed to obtain a sea ice extraction matrix T4.

[0042] In step S130, the plurality of connected regions is subjected to ice fragment identification processing to obtain an ice fragment region, and the ice fragment region is removed to obtain a target matrix.

[0043] In an embodiment, the ice fragment identification processing of the plurality of connected regions to obtain the ice fragment region can include the following steps 3-1 to 3-3:

[0044] In step 3-1, the sea ice extraction matrix is subjected to connected region labeling processing to obtain a first connected region labeling matrix.

[0045] The connected region labeling processing can include the following steps 3-1.1 to 3-1.4:

[0046] Step 3-1.1. According to the preset traversal order, the to-be-labeled matrix is traversed in sequence, and when a first outer contour point that has not been labeled is identified, the outer contour point is labeled with a first identification mark;

[0047] Step 3-1.2. Starting from the first outer contour point, tracking is performed based on the outer contour where the first outer contour point is located until the first outer contour point is returned, and all points on the tracking path are labeled with the first identification mark;

[0048] Step 3-1.3. If a second outer contour point that has been labeled is identified in the preset traversal order, all points in the subsequent preset traversal order are labeled as a second identification corresponding to the second outer contour point.

[0049] Step 3-1.4. If an inner contour point is identified in the preset traversal order starting from the second outer contour point, the points on the path in the subsequent preset traversal order are labeled as the second identification.

[0050] In an embodiment, the above connected domain labeling processing can be performed on the sea ice extraction matrix T4 to obtain a first connected domain labeled matrix L1.

[0051] Step 3-2. A second binary matrix opposite to the sea ice extraction matrix is obtained by binary negation of the sea ice extraction matrix, and connected domain labeling processing is performed on the second binary matrix to obtain a second connected domain labeled matrix.

[0052] In an embodiment, a second binary matrix T4_Ant opposite to the sea ice extraction matrix T4 can be obtained by a binary negation calculation method, and the binary negation calculation formula is as follows: T4_Ant = 1-T4.

[0053] Further, the second binary matrix T4_Ant is subjected to connected domain labeling processing, which is the same as described above and will not be repeated here.

[0054] Step 3-3. A connected domain difference matrix is calculated based on the first connected domain labeled matrix and the second connected domain labeled matrix; the connected domain difference matrix is used to represent a broken ice region.

[0055] In an embodiment, the connected domain difference matrix DV can be calculated from the first connected domain labeled matrix and the second connected domain labeled matrix, and the calculation formula is: DV = L1-(1-L2).

[0056] Further, the target matrix can be obtained by excluding the broken ice region, which can include the following steps 4-1 to 4-3:

[0057] Step 4-1. Based on the second connected domain labeled matrix as a base matrix, the number of pixels corresponding to each pixel value in the connected domain difference matrix is counted.

[0058] In an embodiment, the number of pixels corresponding to each pixel value in the connected domain difference value matrix DV (except for the 0 value) can be counted to determine the number of pixels corresponding to each pixel value.

[0059] In step 4-2, the first position index in the connected domain difference value matrix, in which the number of pixels corresponding to each pixel value is greater than a preset threshold, is found, and the pixel value at the first position index in the second connected domain marking matrix is marked first.

[0060] In an embodiment, the position index P1(x, y) in the connected domain difference value matrix DV, in which the number of pixels corresponding to each pixel value is greater than 30000, is found, and the pixel value at the position index P1(x, y) in the connected domain marking matrix L2 is set to 1.

[0061] The selection of the above-mentioned preset threshold is determined through multiple experiments. If the threshold is too small, a part of the broken ice will be identified as the main sea ice, affecting the extraction of the outer edge line; if the threshold is too large, a large area of seawater region in the main sea ice will be missed, resulting in incomplete main sea ice.

[0062] In step 4-3, the second position index in the connected domain difference value matrix, in which the number of pixels corresponding to each pixel value is less than or equal to a preset threshold, is found, and the pixel value at the second position index in the second connected domain marking matrix is marked second to obtain a target matrix in which the broken ice region is removed.

[0063] In actual application, the position index P2(x, y) in the connected domain difference value matrix DV, in which the number of pixels corresponding to each pixel value is less than or equal to 30000, is found, and the pixel value at the position index P2(x, y) in the connected domain marking matrix L2 is set to 0, that is, the target matrix L3 after the removal of the broken ice region is obtained.

[0064] In step S140, the target matrix after the removal of the broken ice region is converted into a target image, and the target image is subjected to raster-to-vector processing to obtain a vector surface file.

[0065] In an embodiment, the target matrix L3 is saved as a target image I in the geotiff format, and the target image I is subjected to raster-to-vector processing to obtain a vector surface file S.

[0066] In step S150, the background vector surface in the vector surface file is removed, and vector surface-to-line processing is performed to obtain a sea ice outer edge line.

[0067] In an embodiment, the removal of the vector surface file can delete the surface elements with an attribute value of 0 in the vector surface file S.

[0068] The embodiment of the application provides an embodiment of a specific sea ice outer edge line extraction method, as shown in Figure 2 The embodiment of the application provides an embodiment of a specific sea ice outer edge line extraction method, as shown in The embodiment of the application provides an embodiment of a specific sea ice outer edge line extraction method, as shown in

[0069] Step 1: input a Landsat8 optical remote sensing image A of the third band, wavelength range 530nm-590nm, the imaging time in this embodiment is January 24, 2016, see Figure 3 .

[0070] Step 2: input a land-sea mask vector file, which is a shape format face file containing the land around Bohai Bay;

[0071] Step 3: land-sea mask processing is performed on image A, first, the vector raster processing is performed on the land-sea mask vector file with image A as the template to obtain a mask matrix with land area as 0 and other areas as 1; then the mask matrix is multiplied by image A to obtain a masked matrix T1;

[0072] Step 4: fixed threshold segmentation processing is performed on matrix T1, through multi-scene image analysis, it is found that the optimal ice water segmentation threshold of Landsat8 third band image is 8000; the pixel value greater than 8000 in matrix T1 is set to 1, otherwise 0, to obtain the ice water binary matrix T2 after threshold segmentation;

[0073] Step 5: set the convolution kernel as 15x15, and perform dilation and erosion processing on the binary image matrix T2 to obtain matrix T3. The processing method of dilation first and then erosion can fill small holes and bridge small cracks, and the overall shape and position remain unchanged.

[0074] Let the input image be T, the convolution kernel (structure element) be J, and the dilation operation formula be:

[0075]

[0076] The formula means that T is dilated with structure element J, and the origin of structure element J is shifted to the position of image pixel (x, y). If the intersection at image pixel (x, y) with T is not empty (that is, at least one of the image values corresponding to the element position of 1 in J is 1), then the corresponding pixel (x, y) of the output image is assigned a value of 1, otherwise 0.

[0077] Erosion is opposite to dilation, and its formula is:

[0078]

[0079] The formula means that when the origin of J is shifted to the pixel (x, y) of image T, if J is completely contained in the overlapping area of image T at (x, y) (that is, all image values corresponding to the element position of 1 in J are 1), then the corresponding pixel (x, y) of the output image is assigned a value of 1, otherwise 0.

[0080] Step 6: Small area removal processing is performed on the image matrix T3. The minimum connected domain size is set to 2000, that is, if the size of a connected domain is less than 2000, the value of the connected domain is set to the same value as the value of the surrounding background, and small connected domains are removed to obtain matrix T4;

[0081] Step 7: After the expansion and erosion processing and the removal of small areas, the cracks of the main sea ice are basically filled (see Figure 4 and Figure 5 for details), but there is still broken ice on the outer edge of the sea ice, which affects the extraction of the sea ice outer edge line. Therefore, the present application uses a contour-based connected domain labeling and binary inversion calculation method to identify the broken ice.

[0082] The contour-based connected domain labeling algorithm process is as follows:

[0083] 1) Traverse the image from top to bottom and from left to right, and when an outer contour point A (white pixel) is encountered and has not been labeled, label A with a new label number;

[0084] 2) Starting from A, all the outer contour points in A are tracked, and then A is returned, and all the points on the path are labeled as the label number of A;

[0085] 3) If an already labeled outer contour point A' is encountered, then from A' to the right, all the points to the right of A' are labeled as the label number of A', until a black pixel is encountered;

[0086] 4) If an inner contour point B is encountered when traversing from A' point, then starting from B, the inner contour is tracked to the right, and all the points on the path are labeled as the same label number as A', until a black pixel is encountered.

[0087] Step 7.1: Perform connected domain labeling on matrix T4 to obtain connected domain labeling matrix L1;

[0088] Step 7.2: Use the binary inversion calculation method to obtain the binary matrix T4_Ant opposite to T4, and the binary inversion calculation formula is as follows:

[0089] T4_Ant = 1-T4

[0090] Step 7.3: Perform connected domain labeling on T4_Ant to obtain connected domain labeling matrix L2;

[0091] Step 7.4: Calculate the connected domain difference value matrix DV, and the calculation formula is:

[0092] DV = L1-(1-L2)

[0093] Step 8: Take the connected domain labeling matrix L2 as the base matrix, and remove the broken ice based on the calculation result of the connected domain difference value matrix DV, and the steps are as follows.

[0094] Step 8.1: Count how many pixels have each pixel value (except 0) in the connected domain difference value matrix DV;

[0095] Step 8.2: Find the position index P1(x, y) of each pixel value in the connected domain difference value matrix DV whose pixel number is greater than 30000, and set the pixel value at the position index P1(x, y) in the connected domain label matrix L2 to 1;

[0096] Step 8.3: Find the position index P2(x, y) of each pixel value in the connected domain difference value matrix DV whose pixel number is less than or equal to 30000, and set the pixel value at the position index P2(x, y) in the connected domain label matrix L2 to 0, that is, obtain the matrix L3 after removing the broken ice area. As shown in Figure 6

[0097] Step 9: Save the matrix L3 as a geotiff image I, and perform raster-to-vector processing on the image I to obtain a vector face file S;

[0098] Step 10: Delete the face elements with attribute value 0 in the vector face file S to remove the background vector face;

[0099] Step 11: Perform vector face-to-line processing on the vector face file S to obtain the sea ice outer edge line, as shown in Figure 7

[0100] The embodiments of the present application have the following advantages:

[0101] 1. Continuous and stable monitoring. Landsat8 data resources are stable, can be obtained for free, and have a high revisit period. At least two images of the Bohai Sea can be obtained per month. The use of Landsat8 data for outer edge line extraction can continuously and stably monitor the monthly variation trend of sea ice growth and decay;

[0102] 2. High automation. The method can automatically extract the sea ice outer edge line. Compared with the traditional visual interpretation of drawing the sea ice outer edge line, the method is simpler and more effective, and can greatly save labor costs;

[0103] 3. High precision. Compared with the method of directly extracting the sea ice outer edge line from a binary image, the method solves the problem of interference of the broken ice area during extraction of the outer edge line, and the extracted sea ice outer edge line has high precision.

[0104] Based on the above method embodiments, the embodiments of the present application also provide an extraction device for a sea ice outer edge line, as shown in Figure 8 The device mainly includes the following parts:

[0105] An image acquisition module 810 is configured to acquire an optical remote sensing image of a preset marine area;

[0106] ​​The extraction module 820 is configured to perform preliminary sea ice extraction processing on the optical remote sensing image to obtain a sea ice extraction matrix. The sea ice extraction matrix is configured to represent a plurality of connected regions that meet a preset range.

[0107] The broken ice processing module 830 is configured to perform broken ice identification processing on the plurality of connected regions to obtain a broken ice region, and to remove the broken ice region to obtain a target matrix.

[0108] The conversion module 840 is configured to convert the target matrix after the broken ice region is removed into a target image, perform raster-to-vector processing on the target image, and obtain a vector surface file.

[0109] The outer edge line extraction module 850 is configured to remove background vector surfaces in the vector surface file, and perform vector surface-to-line processing to obtain a sea ice outer edge line.

[0110] In an implementation, the extraction module 820 is further configured to:

[0111] perform sea-land mask processing on the optical remote sensing image to obtain a mask matrix after the mask processing;

[0112] perform threshold segmentation processing on the mask matrix to obtain a first binary matrix after the segmentation processing;

[0113] perform dilation and erosion processing on the binary matrix based on a preset convolution kernel to obtain a region filling matrix;

[0114] perform small area removal processing on the region filling matrix to obtain the sea ice extraction matrix.

[0115] In an implementation, the broken ice processing module 830 is configured to:

[0116] perform connected region labeling processing on the sea ice extraction matrix to obtain a first connected region labeling matrix;

[0117] perform binary inversion on the sea ice extraction matrix to obtain a second binary matrix opposite to the sea ice extraction matrix, and perform connected region labeling processing on the second binary matrix to obtain a second connected region labeling matrix;

[0118] calculate a connected region difference matrix based on the first connected region labeling matrix and the second connected region labeling matrix. The connected region difference matrix is configured to represent a broken ice region.

[0119] In an implementation, the connected region labeling processing includes:

[0120] iterating through the to-be-labeled matrix in a preset iteration order, and when a first outer contour point that has not been labeled is identified, the outer contour point is labeled with a first label;

[0121] Taking the first outer contour point as a starting point, tracking based on the outer contour where the first outer contour point is located to return to the first outer contour point, and marking all points on the tracking path with the first mark;

[0122] If a second outer contour point that has been marked is identified on the preset traversal order, then mark all points on the subsequent preset traversal order as the second mark corresponding to the second outer contour point.

[0123] If an inner contour point is identified on the preset traversal order starting from the second outer contour point, then mark the points of the path on the subsequent preset traversal order as the second mark.

[0124] In an implementable embodiment, the ice crushing processing module 830 is configured to:

[0125] Take the second connected domain marking matrix as a basis matrix, and count the pixel number corresponding to each pixel value in the connected domain difference value matrix;

[0126] Find a first position index in the connected domain difference value matrix, where the pixel number of each pixel value is greater than a preset threshold, and mark the pixel value at the first position index in the second connected domain marking matrix with the first mark;

[0127] Find a second position index in the connected domain difference value matrix, where the pixel number of each pixel value is less than or equal to the preset threshold, and mark the pixel value at the second position index in the second connected domain marking matrix with the second mark to obtain a target matrix for removing the ice crushing region.

[0128] In an implementable embodiment, the optical remote sensing image of the preset sea area is a Landsat8 remote sensing image of the Bohai Sea area.

[0129] The implementation principle and the technical effects of the sea ice outer edge line extraction device provided in the embodiments of the present application are the same as those of the aforementioned method embodiments. For brevity of description, the embodiments of the sea ice outer edge line extraction device are not mentioned in the foregoing method embodiments of the sea ice outer edge line extraction method. Please refer to the corresponding content in the foregoing method embodiments.

[0130] The embodiments of the present application also provide an electronic device, as shown in the accompanying drawings, which is a structural schematic diagram of the electronic device. The electronic device 100 includes a processor 91 and a memory 90. The memory 90 stores computer executable instructions that can be executed by the processor 91. The processor 91 executes the computer executable instructions to implement any of the aforementioned sea ice outer edge line extraction methods. Figure 9

[0131] In the embodiments shown in the accompanying drawings, the electronic device further includes a bus 92 and a communication interface 93. The processor 91, the communication interface 93 and the memory 90 are connected through the bus 92. Figure 9 In the embodiments shown in the accompanying drawings, the electronic device further includes a bus 92 and a communication interface 93. The processor 91, the communication interface 93 and the memory 90 are connected through the bus 92.​

[0132] The memory 90 can include a high-speed random access memory (RAM), and can 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 93 (which can be wired or wireless), and the Internet, a wide area network, a local network, a metropolitan area network, etc. can be used. The bus 92 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 92 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 9 Only one bidirectional arrow is used in the figure to represent only one bus or one type of bus.

[0133] The processor 91 can be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor 91 or the instructions in the form of software. The processor 91 described above 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 device, a discrete gate or transistor logic device, a discrete hardware component. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, or other mature storage media in the art. The storage medium is located in the memory, and the processor 91 reads the information in the memory and combines the hardware to complete the steps of the sea ice edge line extraction method of the above embodiments.

[0134] The embodiment of the present application further provides a computer readable storage medium storing computer executable instructions, when the computer executable instructions are invoked and executed by a processor, the computer executable instructions cause the processor to implement the method for extracting the sea ice outer edge line, and specific implementation can be referred to the foregoing method embodiments, and details are not described herein again.

[0135] The method for extracting the sea ice outer edge line, the device, the electronic device and the computer program product of the storage medium provided by the embodiment of the present application include a computer readable storage medium storing program codes, the instructions included in the program codes can be used to execute the method described in the foregoing method embodiments, and specific implementation can be referred to the method embodiments, and details are not described herein again.

[0136] Unless specifically stated, the relative arrangement of the components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present application.

[0137] If the functions are realized in the form of software function units and sold or used as independent products, the functions can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on such understanding, the technical solutions of the present application or parts of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0138] In the description of the present application, it should be noted that the terms "upper", "lower", "left", "right", and the like indicate the orientation or positional relationship shown in the drawings, or the orientation or positional relationship commonly used when the product is used, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", and the like are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0139] Furthermore, the terms "horizontal," "vertical," "overhang," and the like, do not mean that the components must be absolutely horizontal or overhanging, but can be slightly tilted. As "horizontal" merely means that it is more horizontal than "vertical," it does not mean that the structure must be perfectly horizontal, but can be slightly tilted.

[0140] Finally, it should be noted that the above embodiments are merely used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for extracting the outer edge of sea ice, characterized in that, The method includes: Acquire optical remote sensing images of a predefined ocean area; The optical remote sensing image is subjected to preliminary sea ice extraction processing to obtain a sea ice extraction matrix; the sea ice extraction matrix is ​​used to characterize multiple connected regions that satisfy a preset range; Multiple connected regions are subjected to ice fragmentation identification processing to obtain ice fragmentation regions, and the target matrix is ​​obtained by removing the ice fragmentation regions. The target matrix after removing the ice fragments is converted into a target image, and the target image is then processed by raster-to-vector conversion to obtain a vector surface file. Remove the background vector planes from the vector plane file and perform vector plane to line conversion to obtain the outer edge line of the sea ice; Ice fragmentation is identified by performing ice fragmentation processing on multiple connected regions, resulting in ice fragmentation regions, including: The sea ice extraction matrix is ​​processed by connected component labeling to obtain the first connected component labeling matrix; The sea ice extraction matrix is ​​inverted to obtain a second binary matrix that is the opposite of the sea ice extraction matrix. The second binary matrix is ​​then subjected to connected component labeling to obtain a second connected component labeling matrix. A connected component difference matrix is ​​calculated based on the first connected component labeling matrix and the second connected component labeling matrix; the connected component difference matrix is ​​used to characterize the ice fragmentation region; The connected component labeling process includes: The matrix to be marked is traversed sequentially according to the preset traversal order. When an unmarked first outer contour point is identified, the outer contour point is marked with the first identifier. Starting from the first outer contour point, the tracking path is traced back to the first outer contour point based on the outer contour where the first outer contour point is located, and all points on the tracking path are marked with the first identifier. If a marked second outer contour point is identified in the preset traversal order, then all points in the subsequent preset traversal order will be marked as the second identifier corresponding to the second outer contour point. If an inner contour point is identified starting from the second outer contour point in the preset traversal order, then the points on the path in the subsequent preset traversal order are marked as the second identifier.

2. The method for extracting the outer edge of sea ice according to claim 1, characterized in that, The optical remote sensing image is subjected to preliminary sea ice extraction processing to obtain a sea ice extraction matrix, including: The optical remote sensing image is subjected to land and sea masking to obtain the masked mask matrix; The mask matrix is ​​subjected to threshold segmentation to obtain the segmented first binary matrix; The binary matrix is ​​subjected to dilation and erosion processing based on a preset convolution kernel to obtain a region filling matrix; The region filling matrix is ​​subjected to small area removal processing to obtain the sea ice extraction matrix.

3. The method for extracting the outer edge of sea ice according to claim 1, characterized in that, The target matrix is ​​obtained by removing the ice fragments, including: Using the second connected component label matrix as the base matrix, count the number of pixels corresponding to each pixel value in the connected component difference matrix; Find the first position index in the connected component difference matrix where the number of pixels in each pixel value is greater than a preset threshold, and mark the pixel value at the corresponding first position index in the second connected component marking matrix. Find the second position index in the connected component difference matrix where the number of pixels in each pixel value is less than or equal to a preset threshold, and then mark the pixel value at the corresponding second position index in the second connected component marking matrix to obtain the target matrix for removing the ice fragment area.

4. The method for extracting the outer edge of sea ice according to claim 2, characterized in that, The optical remote sensing image of the preset marine area is the Landsat 8 remote sensing image of the Bohai Sea area.

5. A device for extracting the outer edge of sea ice, characterized in that, The device includes: The image acquisition module is used to acquire optical remote sensing images of a preset ocean area; An extraction module is used to perform preliminary sea ice extraction processing on the optical remote sensing image to obtain a sea ice extraction matrix; the sea ice extraction matrix is ​​used to represent multiple connected regions that satisfy a preset range; The ice crushing module is used to perform ice crushing processing on multiple connected regions to obtain ice crushing regions, and then remove the ice crushing regions to obtain the target matrix. The conversion module is used to convert the target matrix after removing the ice fragments into a target image, and to perform raster-to-vector conversion on the target image to obtain a vector surface file; The outer edge extraction module is used to remove the background vector planes in the vector plane file and perform vector plane to line conversion to obtain the outer edge of the sea ice. The ice crushing module is also used to: perform connected component labeling processing on the sea ice extraction matrix to obtain a first connected component labeling matrix; The sea ice extraction matrix is ​​inverted to obtain a second binary matrix that is the opposite of the sea ice extraction matrix. The second binary matrix is ​​then subjected to connected component labeling to obtain a second connected component labeling matrix. A connected component difference matrix is ​​calculated based on the first connected component labeling matrix and the second connected component labeling matrix; the connected component difference matrix is ​​used to characterize the ice fragmentation region; The connected component labeling process includes: The matrix to be marked is traversed sequentially according to the preset traversal order. When an unmarked first outer contour point is identified, the outer contour point is marked with the first identifier. Starting from the first outer contour point, the tracking path is traced back to the first outer contour point based on the outer contour where the first outer contour point is located, and all points on the tracking path are marked with the first identifier. If a marked second outer contour point is identified in the preset traversal order, then all points in the subsequent preset traversal order will be marked as the second identifier corresponding to the second outer contour point. If an inner contour point is identified starting from the second outer contour point in the preset traversal order, then the points on the path in the subsequent preset traversal order are marked as the second identifier.

6. The sea ice outer edge extraction device according to claim 5, characterized in that, The extraction module is also used for: The optical remote sensing image is subjected to land and sea masking to obtain the masked mask matrix; The mask matrix is ​​subjected to threshold segmentation to obtain the segmented first binary matrix; The binary matrix is ​​subjected to dilation and erosion processing based on a preset convolution kernel to obtain a region filling matrix; The region filling matrix is ​​subjected to small area removal processing to obtain the sea ice extraction matrix.

7. An electronic device, characterized in that, The device includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the sea ice outer edge extraction method according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the sea ice outer edge extraction method according to any one of claims 1 to 4.

Images