North pole sea ice marginal area independent floating ice similarity identification method and related device

Abstract

The invention provides a similarity identification method for independent floating ice in an arctic sea ice marginal area and a related device, and relates to the field of meteorology. The method comprises the following steps: the electronic equipment acquires a first image and a second image which are sequentially shot for a target area; identifying a first independent floating ice in the first image; identifying at least one second independent floating ice in the second image; and determining a target floating ice most similar to the first independent floating ice from the at least one second independent floating ice according to the Hauschoff distance between the first independent floating ice and each second independent floating ice. Therefore, compared with a traditional algorithm which is easily influenced by shape change and position drift, the method has the advantages that the characteristic that the farthest point distance between the two sets can be effectively measured by using the Hauschoff distance is utilized, so that the similarity between the floating ice can be evaluated more accurately.

Description

Technical Field

[0001] The present application relates to the field of meteorology, and more specifically, to a method and a related device for identifying the similarity of independent floating ice in the Arctic sea ice edge zone. Background Art

[0002] The importance of studying the similarities between ice floes and their drift lies in their multiple impacts on climate research, maritime transportation, offshore activities and safety monitoring.

[0003] First, information on the similarity of floating ice is essential for understanding the climate system, including the exchange of floating ice within a region, the formation of channels and ice ridges through ice dispersion and shearing, and the impact of floating ice on sea-ice-ocean interactions (such as energy flux). Similarity analysis of floating ice can reveal the dynamic behavior and melting patterns of different floating ice, thus affecting the prediction of global climate models.

[0004] Secondly, studying the similarity of ice floes helps to understand the formation and maintenance mechanisms of multi-year ice, which is crucial for long-term climate prediction and model building. As Arctic sea ice continues to decrease and open water expands, maritime shipping and offshore activities in the Arctic are expected to increase steadily, especially in the marginal ice zone (MIZ). In the MIZ, the similarity between ice floes plays an important role in protecting the stable morphology of the interior ice, preventing wave penetration, and affecting the accessibility of human access to the Arctic Ocean.

[0005] Therefore, analyzing the similarity of floating ice not only provides an important basis for planning maritime transport routes, but also supports offshore resource development and ecological environmental protection. In addition, by monitoring the characteristics of floating ice such as icebergs and multi-year ice, potential dangers can be prevented and the safety of humans and equipment in the Arctic region can be guaranteed. In summary, deepening the research on the dynamic characteristics of floating ice, especially its similarity analysis, is of great significance for responding to climate change, promoting Arctic economic activities and ensuring security.

[0006] During the research, it was found that traditional algorithms (for example, AKAZE, Disk and other methods) have significant shortcomings when processing sea ice data from two periods. First, when calculating shape similarity, traditional methods often rely on fixed shape features (such as boundaries, corners, etc.), the shape changes, and the changes in sea ice in the time series (such as breakage, melting) are not considered. The shape of sea ice may change significantly due to environmental factors, and traditional methods are prone to deviations in similarity assessment. Secondly, traditional algorithms usually assume that the direction of the object is fixed, while sea ice may experience rotation and displacement (angle changes) during drifting. This change in angle makes the contour-based similarity calculation invalid, and it is difficult to effectively identify the similarity of independent ice floes before and after the two periods. Summary of the invention

[0007] In order to overcome at least one of the shortcomings of the prior art, the present application provides a method and a related device for identifying the similarity of independent floating ice in the Arctic sea ice edge area, specifically comprising:

[0008] In a first aspect, the present application provides a method for identifying similarity of independent floating ice in the Arctic sea ice edge region, the method comprising:

[0009] Acquire a first image and a second image taken successively of a target area;

[0010] identifying a first independent ice floe located in the first image;

[0011] identifying at least one second independent ice floe located in the second image;

[0012] A target ice floe that is most similar to the first independent ice floe is determined from the at least one second independent ice floe according to the Haustoff distance between the first independent ice floe and each of the second independent ice floes.

[0013] In combination with an optional implementation manner of the first aspect, determining, from the at least one second independent ice floe, a target ice floe that is most similar to the first independent ice floe according to the Haustoff distance between the first independent ice floe and each of the second independent ice floes, includes:

[0014] Obtaining the shortest Haustov distance between the first independent ice floe and each of the second independent ice floes;

[0015] taking the shortest Haustof distance between the first independent ice floe and each of the second independent ice floes as a reference distance of each of the second independent ice floes;

[0016] The target ice floe is selected from the reference distances of each of the second independent ice floes, wherein the target ice floe has the shortest reference distance.

[0017] In combination with an optional implementation manner of the first aspect, obtaining the shortest Haustoff distance between the first independent ice floe and each of the second independent ice floes includes:

[0018] For each piece of the second independent ice floe, calculating a plurality of Haustoff distances between the second independent ice floe and the first independent ice floe at a plurality of rotation angles;

[0019] The shortest Haustoff distance of the second independent ice floe is determined from the plurality of Haustoff distances.

[0020] In combination with an optional implementation manner of the first aspect, the calculating a plurality of Haustoff distances between the second independent ice floe and the first independent ice floe at a plurality of rotation angles includes:

[0021] Rotating the second independent ice floe by a preset angle based on the current angle;

[0022] calculating a Haustof distance between the second independent ice floe and the first independent ice floe after the second independent ice floe is rotated;

[0023] If the second independent ice floe has not rotated one circle, the process returns to the step of rotating the second independent ice floe by a preset angle based on the current angle until the second independent ice floe rotates one circle, thereby obtaining a plurality of Haustoff distances between the second independent ice floe and the first independent ice floe at a plurality of rotation angles.

[0024] In combination with an optional implementation manner of the first aspect, calculating the Haustof distance between the second independent ice floe and the first independent ice floe after the second independent ice floe rotates includes:

[0025] Sampling the edge contour of the first independent ice floe rotation to obtain positions of a plurality of first edge points;

[0026] Sampling the edge contour of the second independent ice floe rotation to obtain positions of a plurality of second edge points;

[0027] According to the positions of the plurality of first edge points and the positions of the plurality of second edge points, a Haustof distance between the second independent ice floe and the first independent ice floe after rotation is obtained.

[0028] In combination with the optional implementation manner of the first aspect, the method further includes:

[0029] Calculating an area ratio and an area difference between the first independent ice floe and the target ice floe;

[0030] The degree of change of the floating ice is determined based on the area proportion and the area difference.

[0031] In combination with the optional implementation manner of the first aspect, the identifying at least one second independent ice floe located in the second image includes:

[0032] Separating at least one piece of primary screening ice from the second image by a threshold method;

[0033] Identifying the at least one initially screened floating ice by using random forest and support vector to obtain at least one preferred floating ice;

[0034] Morphological processing and connected domain analysis are performed on the at least one preferred floating ice to identify the at least one second independent floating ice.

[0035] In a second aspect, the present application further provides a device for identifying similarity of independent floating ice in the edge area of ​​Arctic sea ice, the device comprising:

[0036] An image acquisition module, used to acquire a first image and a second image taken successively of a target area;

[0037] An ice floe identification module, configured to identify a first independent ice floe located in the first image;

[0038] The ice floe identification module is further configured to identify at least one second independent ice floe located in the second image;

[0039] The ice floe matching module is used to determine, from the at least one second independent ice floe, a target ice floe that is most similar to the first independent ice floe according to the Haustoff distance between the first independent ice floe and each of the second independent ice floes.

[0040] In conjunction with the optional implementation manner of the second aspect, the floating ice matching module is further specifically used for:

[0041] Obtaining the shortest Haustov distance between the first independent ice floe and each of the second independent ice floes;

[0042] taking the shortest Haustof distance between the first independent ice floe and each of the second independent ice floes as a reference distance of each of the second independent ice floes;

[0043] The target ice floe is selected from the reference distances of each of the second independent ice floes, wherein the target ice floe has the shortest reference distance.

[0044] In conjunction with the optional implementation manner of the second aspect, the floating ice matching module is further specifically used for:

[0045] For each piece of the second independent ice floe, calculating a plurality of Haustoff distances between the second independent ice floe and the first independent ice floe at a plurality of rotation angles;

[0046] The shortest Haustoff distance of the second independent ice floe is determined from the plurality of Haustoff distances.

[0047] In conjunction with the optional implementation manner of the second aspect, the floating ice matching module is further specifically used for:

[0048] Rotating the second independent ice floe by a preset angle based on the current angle;

[0049] calculating a Haustof distance between the second independent ice floe and the first independent ice floe after the second independent ice floe is rotated;

[0050] If the second independent ice floe has not rotated one circle, the process returns to the step of rotating the second independent ice floe by a preset angle based on the current angle until the second independent ice floe rotates one circle, thereby obtaining a plurality of Haustoff distances between the second independent ice floe and the first independent ice floe at a plurality of rotation angles.

[0051] In conjunction with the optional implementation manner of the second aspect, the floating ice matching module is further specifically used for:

[0052] Sampling the edge contour of the first independent ice floe rotation to obtain positions of a plurality of first edge points;

[0053] Sampling the edge contour of the second independent ice floe rotation to obtain positions of a plurality of second edge points;

[0054] According to the positions of the plurality of first edge points and the positions of the plurality of second edge points, a Haustof distance between the second independent ice floe and the first independent ice floe after rotation is obtained.

[0055] In conjunction with the optional implementation manner of the second aspect, the floating ice matching module is further used for:

[0056] Calculating an area ratio and an area difference between the first independent ice floe and the target ice floe;

[0057] The degree of change of the floating ice is determined based on the area proportion and the area difference.

[0058] In conjunction with the optional implementation manner of the second aspect, the floating ice identification module is further specifically used for:

[0059] Separating at least one piece of primary screening ice from the second image by a threshold method;

[0060] Identifying the at least one initially screened floating ice by using random forest and support vector to obtain at least one preferred floating ice;

[0061] Morphological processing and connected domain analysis are performed on the at least one preferred floating ice to identify the at least one second independent floating ice.

[0062] In a third aspect, the present application further provides a storage medium storing a computer-readable program, which, when executed by a processor, implements the method for identifying the similarity of independent floating ice in the Arctic sea ice edge zone.

[0063] In a fourth aspect, the present application further provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for identifying the similarity of independent floating ice in the edge zone of Arctic sea ice is implemented.

[0064] Compared with the prior art, this application has the following beneficial effects:

[0065] The present application provides a method and related device for identifying the similarity of independent floating ice in the edge of the Arctic sea ice. In the method, an electronic device obtains a first image and a second image taken successively of a target area; identifies a first independent floating ice in the first image; identifies at least one second independent floating ice in the second image; and determines the target floating ice that is most similar to the first independent floating ice from at least one second independent floating ice according to the Haustoff distance between the first independent floating ice and each second independent floating ice. In this way, compared with the traditional algorithm that is easily affected by shape changes and position drift, the Haustoff distance can effectively measure the distance between the farthest points of the two sets, thereby more accurately evaluating the similarity between the floating ice. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0067] Figure 1 A schematic diagram of a process for identifying similarity of independent floating ice in the Arctic sea ice edge region provided in an embodiment of the present application;

[0068] Figure 2 A schematic diagram of the effect of the floating ice identification method provided in an embodiment of the present application;

[0069] Figure 3A One of the comparison schematic diagrams of ice floe contours provided in the embodiment of the present application;

[0070] Figure 3B The second comparison diagram of ice floe contours provided in the embodiment of the present application;

[0071] Figure 4 A schematic diagram of the relationship between the rotation angle and the Haustoff distance provided in an embodiment of the present application;

[0072] Figure 5 A schematic diagram of the calculation principle of the Haustoff distance provided in an embodiment of the present application;

[0073] Figure 6 A schematic diagram of the structure of an independent ice floe similarity recognition device in the Arctic sea ice edge region provided in an embodiment of the present application;

[0074] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part 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 here can be arranged and designed in various different configurations.

[0076] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0077] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0078] In the description of the present application, it should be noted that the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. In addition, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0079] Based on the above statement, as introduced in the background technology, traditional algorithms often rely on fixed shape features and assume that the orientation of the object is fixed. However, the shape of sea ice may change significantly due to environmental factors, and sea ice may experience rotation and displacement (angle changes) during drifting. Therefore, it is difficult for traditional algorithms to effectively identify the similarities of independent ice floes before and after.

[0080] Based on the discovery of the above technical problems, the inventors have proposed the following technical solutions to solve or improve the above problems through creative work. It should be noted that the defects in the solutions in the above prior art are the results obtained by the inventors after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the embodiments of the present application for the above problems below should all be the contributions made by the inventors to the present application in the process of invention and creation, and should not be understood as technical contents known to those skilled in the art.

[0081] In view of this, the present embodiment provides a method for identifying the similarity of independent ice floes in the edge of the Arctic sea ice. In the method, the electronic device obtains a first image and a second image taken successively of the target area; identifies the first independent ice floe in the first image; identifies at least one second independent ice floe in the second image; and determines the target ice floe that is most similar to the first independent ice floe from at least one second independent ice floe based on the Haustoff distance between the first independent ice floe and each second independent ice floe. In this way, compared with the traditional algorithm that is easily affected by shape changes and position drift, the Haustoff distance can effectively measure the distance between the farthest points of the two sets, thereby more accurately evaluating the similarity between the ice floes.

[0082] In this embodiment, the electronic device implementing the method may be, but is not limited to, a mobile terminal, a tablet computer, a laptop computer, a desktop computer, a server, and the like. When it is a server, the server may be a single server or a server group. The server group may be centralized or distributed (for example, the server may be a distributed system). In some embodiments, the server may be local or remote relative to the user terminal. In some embodiments, the server may be implemented on a cloud platform; as an example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, and the like, or any combination thereof. In some embodiments, the server may be implemented on an electronic device having one or more components.

[0083] To make the solution provided by this embodiment clearer, Figure 1 Each step of the method is described in detail. However, it should be understood that the operations of the flowchart may not be implemented in order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowchart, or remove one or more operations from the flowchart under the guidance of the content of this application. Figure 1 As shown, the method includes:

[0084] S1, acquiring a first image and a second image taken successively of a target area.

[0085] In this embodiment, the first image and the second image may be remote sensing images of the target area taken by a satellite; in addition, the target area may be a local area within the Arctic Circle, or other water surface areas where ice may form. It should also be noted that the first image may be taken earlier than the second image, or the second image may be taken earlier than the first image.

[0086] S2: Identify a first independent ice floe located in the first image.

[0087] In this embodiment, the number of the first independent ice floes may be one or more. For each first independent ice floe, this embodiment adopts the same method to determine the most similar target ice floe from at least one second independent ice floe in the second image.

[0088] S3: Identify at least one second independent ice floe located in the second image.

[0089] It should be noted that this embodiment adopts the same method for the first image and the second image to identify the first independent floating ice and the second independent floating ice. Therefore, the second image is taken as an example to describe the method for identifying floating ice in detail. Therefore, as an optional implementation of step S3, it may include:

[0090] S3-1, distinguishing at least one piece of primary screening floating ice from the second image by using a threshold method.

[0091] In this regard, the server first uses the threshold method to perform preliminary image segmentation, that is, by setting a suitable threshold, the floating ice and seawater are quickly separated from the second image. For example, the area with a grayscale lower than the threshold is determined as seawater, and the area with a grayscale greater than or equal to the threshold is determined as floating ice. Since the results identified only based on the threshold have certain limitations, the floating ice identified by the threshold method is called the initial screening floating ice.

[0092] S3-2, identifying at least one piece of initially screened floating ice by using random forest and support vector, and obtaining at least one piece of preferred floating ice.

[0093] In this embodiment, two classification algorithms, random forest and support vector machine, are also introduced to further improve the classification accuracy and robustness. These algorithms can comprehensively consider the multi-dimensional features of the image and accurately identify sea ice and seawater by learning the features of existing samples. Therefore, at least one piece of preliminary screening floating ice is identified by random forest and support vector, and the identification result of the threshold method is optimized, so as to obtain at least one piece of preferred floating ice.

[0094] As an optional implementation, in order to facilitate subsequent processing, the present embodiment further performs binarization processing on the second image according to at least one preferred floating ice, for example, setting the brightness of the area corresponding to the preferred floating ice to 255 and setting the brightness of the area outside the preferred floating ice to 0.

[0095] S3-3, performing morphological processing and connected domain analysis on at least one preferred ice floe, and identifying at least one second independent ice floe.

[0096] In this way, in order to solve the problem that the contours of ice floes cannot be completely extracted when the distance between them is small, the above-mentioned threshold method, random forest and support vector are used to comprehensively process the image. Among them, morphological operations (such as expansion and erosion) can improve the shape and connectivity of ice floes, so that adjacent ice floes can be relatively independent; at the same time, connected component analysis technology is used to accurately mark ice floes at close range. In this way, the edge information of ice floes is extracted, and the accuracy and smoothness of the extracted contour can be improved through contour optimization technology.

[0097] For example, Figure 2 As shown, it is still assumed that the second image is the original remote sensing image, and after it is processed by image classification methods such as threshold method, random forest and support vector machine, at least one preferred ice floe is identified therefrom, and then, the at least one preferred ice floe is morphologically processed and connected domain analyzed to identify at least one second independent ice floe in the original remote sensing image.

[0098] Based on the introduction of the first independent ice floe and the second independent ice floe in the above embodiment, see Figure 1 , the method provided in this embodiment also includes:

[0099] S4, determining a target ice floe that is most similar to the first independent ice floe from at least one second independent ice floe according to the Haustoff distance between the first independent ice floe and each second independent ice floe.

[0100] It should be understood that Hausdorff distance is currently often used to evaluate the similarity of contours in images and measure the deviation between object boundaries. In particular, in the field of remote sensing image processing, Hausdorff distance is used for change detection of object boundaries, especially contour extraction and change tracking of objects such as buildings, roads, ports, and forests. However, despite its mature application in ordinary image processing, the objects it evaluates usually have unchanged shapes and angles, while the randomness, fragmentation, and drift of ice floes make the Hausdorff distance relatively less used in ice floe similarity recognition in natural environments.

[0101] In this embodiment, the larger the Haustoff distance value, the more significant the change in the independent ice floe contour is, and the lower the similarity between the independent ice floes is; the smaller the distance value, the smaller the change in the independent ice floe contour is, and the higher the similarity between the independent ice floes is. Therefore, this embodiment also provides the following optional implementation of step S4:

[0102] S4-1, obtaining the shortest Haustov distance between the first independent ice floe and each second independent ice floe.

[0103] In practice, it is found that independent ice floes generally rotate during drifting. Figure 3A , Figure 3BAs shown in the figure, the same independent ice floe is shown in two remote sensing images. Figure 3A The remote sensing images corresponding to the independent ice floes shown were collected earlier than Figure 3B The independent floating ice shown corresponds to the acquisition time of the remote sensing image. It is not difficult to see that after a period of drift, the shape and angle of the independent floating ice have changed to a certain extent. In this regard, this embodiment also designs an experiment of rotation matching of independent floating ice based on Haustoff distance. In this experiment, Figure 3A The independent floating ice pattern rotates, and the counterclockwise rotation is defined as the positive direction. The rotation range is 0-360°, and the amplitude of each rotation of the graphic is defined as 5°. Every 5° rotation, the calculation is performed once. Figure 3B The Haustov distance between the corresponding patterns of the independent ice floes shown in the figure. Finally, the relationship between the statistical rotation angle and the Haustov distance is as follows: Figure 4 As shown. Figure 4 It can be seen that when the rotation angle is 214°, the Haustoff distance reaches a maximum value of 165.002, and when the rotation angle is 308°, the Haustoff distance reaches a minimum value of 2.83.

[0104] Therefore, the angle change of the independent ice floes will have a serious impact on the length of the Haustoff distance between the independent ice floes. However, through the above experiments, it can be found that the rotation matching method can ensure that the calculation of the Haustoff distance is not affected by the angle rotation during the drift of the ice floes. Based on this finding, this embodiment also provides the following optional implementation of step S4-1:

[0105] S4-1-1, for each second independent ice floe, calculating a plurality of Haustoff distances between the second independent ice floe and the first independent ice floe at a plurality of rotation angles.

[0106] In this regard, the server may rotate the second independent ice float by a preset angle based on the current angle; calculate the Haustoff distance between the second independent ice float and the first independent ice float after the rotation; if the second independent ice float has not rotated one circle, return to the step of rotating the second independent ice float by a preset angle based on the current angle, until the second independent ice float rotates one circle, and obtain multiple Haustoff distances between the second independent ice float and the first independent ice float at multiple rotation angles.

[0107] In this way, the shape characteristics of ice cubes in different orientations can be fully captured, thus overcoming the limitation of traditional distance calculation methods that are sensitive to angles. This algorithm effectively improves the accuracy of assessing the similarity of floating ice cubes and enhances the ability to monitor and analyze floating ice in complex environments.

[0108] As a specific implementation method of calculating the Haustof distance between the second independent ice floe and the first independent ice floe after rotation, the server may sample the edge contour of the first independent ice floe to obtain the positions of multiple first edge points; sample the edge contour of the second independent ice floe to obtain the positions of multiple second edge points; and obtain the Haustof distance between the second independent ice floe and the first independent ice floe after rotation based on the positions of the multiple first edge points and the positions of the multiple second edge points.

[0109] For example, assume that the coordinates of multiple points are collected from the edge of the first independent ice floe to obtain a set A{a0, a1, ...an}; and the coordinates of multiple points are collected from the edge of the second independent ice floe to obtain a set B{b0, b1, b2, ...bn}. Figure 5 The 6 steps shown in Figure 5 take two points a0 and a1 from set A and three points b0, b1 and b2 from set B, and use them to calculate the Haustoff distance. The following is a detailed description of the 6 calculation steps in Figure 5:

[0110] In step 1 of the diagram, it is mainly shown that two points a0 and a1 are taken from set A, and three points b0, b1, and b2 are taken from set B;

[0111] In step 2 of the diagram, it is shown that based on a point a0 in set A, the distance from a0 to all points in set B is calculated, and the shortest distance d1 is retained. In step 3 of the diagram, it is shown that from a point a1 in set A, the distance from a1 to all points in set B is calculated, and the shortest distance d2 is retained.

[0112] As shown in steps 2, 3, and 4, we traverse the two points a0 and a1 in set A, calculate the distances between all points in set A and set B, d1 and d2 are the closest distances among all the points, and then select the longest distance d2 from the closest distances.

[0113] In step 5 of the diagram, the longest distance is taken as h, which is the one-way Haustoff distance from set A to set B, denoted as h(A,B).

[0114] In step 6 shown in the figure, for any point an in set A, it can be determined that the nearest point in set B must be inside the circle with point an as the center and h as the radius.

[0115] Finally, we need to swap the roles of set A and set B, calculate the one-way Haustoff distance h(B,A) from set B to set A, and select the longest distance between h(A,B) and h(B,A) as the two-way Haustoff distance between set A and set B.

[0116] Based on the above implementation of the introduction of the Haustoff distance under multiple rotation angles and the introduction of the Haustoff distance calculation method, step S4-1 further includes:

[0117] S4-1-2, determine the shortest Haustov distance of the second independent ice floe from multiple Haustov distances.

[0118] In this way, at each rotation angle, the Haustoff distance between the first independent ice floe and the second independent ice floe at the current rotation angle can be calculated. For multiple rotation angles, multiple Haustoff distances can be obtained, from which the shortest Haustoff distance is selected. The shortest Haustoff distance indicates that the first independent ice floe and the second independent ice floe have a high similarity at this rotation angle.

[0119] Through the above implementation, the shortest Haustoff distance between the first independent ice floe and each second independent ice floe can be obtained. Step S4 provided in this embodiment also includes:

[0120] S4-2, taking the shortest Haustov distance between the first independent ice floe and each second independent ice floe as the reference distance of each second independent ice floe.

[0121] S4-3, selecting a target ice floe from the reference distances of each second independent ice floe, wherein the target ice floe has the shortest reference distance.

[0122] Thus, through the above implementation, the target ice floe that is most similar to the first independent ice floe is determined from at least one second independent ice floe in the second image, thereby establishing a corresponding relationship between the first independent ice floe and the target ice floe. Since the first independent ice floe and the corresponding target ice floe are derived from images collected successively, the dynamic behavior and melting pattern of the ice floe can be revealed by analyzing the change information between the first independent ice floe and the target ice floe. Therefore, the independent ice floe similarity identification method in the Arctic sea ice edge area provided by this implementation also includes:

[0123] S5, calculating an area ratio and an area difference between the first independent ice floe and the target ice floe.

[0124] S6, determine the degree of change of floating ice based on the area proportion and area difference.

[0125] For the above embodiment, it can be understood that, according to the value range of the area difference and the area ratio, the original floating ice blocks are analyzed and grouped, and the floating ice data are divided into three types, including:

[0126] (1) The area difference is less than 0.1 km 2 The ice floes with an area ratio of 0.99 to 1.01 are defined as the type with unchanged contours; that is, the contours of the ice floes do not change during the drift process, but the position and angle change;

[0127] (2) The area difference is 0.1 km 2 ~0.9km 2 Within this range, floating ice with an area ratio less than 0.98 or between 1.01 and 1.38 is defined as a type of slightly deformed contour, that is, the contour, position, and angle have all changed, with the contour change being relatively small.

[0128] (3) The area difference is greater than 0.9 km 2 For ice floes with an area ratio greater than 1.38 or less than 0.9, the ice floes are defined as those with significant contour deformation, that is, the contour, position, and angle have all changed, among which the contour has changed significantly.

[0129] Based on the same inventive concept as the method for identifying the similarity of independent floating ice in the edge of the Arctic sea ice provided in this embodiment, this embodiment also provides a device for identifying the similarity of independent floating ice in the edge of the Arctic sea ice, the device comprising at least one software function module that can be stored in a memory or fixed in an electronic device in the form of software. The processor in the electronic device is used to execute the executable module stored in the memory. For example, the software function module and computer program included in the device. Please refer to Figure 6 , functionally speaking, the device may include:

[0130] An image acquisition module 11 is used to acquire a first image and a second image taken successively of a target area;

[0131] An ice floe identification module 12, configured to identify a first independent ice floe located in the first image;

[0132] The ice floe identification module 12 is further configured to identify at least one second independent ice floe located in the second image;

[0133] The ice floe matching module 13 is used to determine the target ice floe most similar to the first independent ice floe from at least one second independent ice floe according to the Haustoff distance between the first independent ice floe and each second independent ice floe.

[0134] In this embodiment, the image acquisition module 11 is used to implement Figure 1 In step S1, the floating ice recognition module 12 is used to implement Figure 1 In steps S2 and S3, the ice floe matching module 13 is used to implement Figure 1Therefore, for the detailed introduction of each of the above models, please refer to the specific implementation of the corresponding step. In addition, it should be noted that since the method for identifying the similarity of independent floating ice in the edge of the Arctic sea ice has the same inventive concept, the device for identifying the similarity of independent floating ice in the edge of the Arctic sea ice can also implement other steps or sub-steps of the method through the above modules or other modules, and this implementation will not be repeated.

[0135] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0136] It should also be understood that if the above implementation is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, 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, which is stored in a storage medium and includes 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 method described in each embodiment of the present application.

[0137] Therefore, this embodiment also provides a storage medium, which is a computer-readable storage medium. The storage medium stores a computer program, and when the computer program is executed by the processor, the method for identifying the similarity of independent floating ice in the Arctic sea ice edge area provided by this embodiment is implemented. Among them, the storage medium can be a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, etc., which can store program codes.

[0138] This embodiment also provides an electronic device for implementing the method for identifying the similarity of independent floating ice in the Arctic sea ice edge area. Figure 7 As shown, the electronic device may include a processor 22 and a memory 21. In addition, the memory 21 stores a computer program, and the processor implements the independent floating ice similarity identification method in the Arctic sea ice edge area provided in this embodiment by reading and executing the computer program corresponding to the above implementation in the memory 21.

[0139] Continue to see Figure 7 The electronic device further includes a communication unit 23. The memory 21, the processor 22 and the communication unit 23 are electrically connected to each other directly or indirectly through a system bus 24 to achieve data transmission or interaction.

[0140] The memory 21 may be an information recording device based on any electronic, magnetic, optical or other physical principle, used to record execution instructions, data, etc. In some embodiments, the memory 21 may be, but is not limited to, a volatile memory, a non-volatile memory, a storage drive, etc.

[0141] In some embodiments, the volatile memory may be a random access memory (RAM); in some embodiments, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), a flash memory, etc.; in some embodiments, the storage drive may be a disk drive, a solid-state drive, any type of storage disk (such as a CD, a DVD, etc.), or a similar storage medium, or a combination thereof, etc.

[0142] The communication unit 23 is used to send and receive data through a network. In some embodiments, the network may include a wired network, a wireless network, a fiber optic network, a telecommunication network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a wide area network (WAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include a wired or wireless network access point, such as a base station and / or a network switching node, through which one or more components of the service request processing system may be connected to the network to exchange data and / or information.

[0143] The processor 22 may be an integrated circuit chip having a signal processing capability, and the processor may include one or more processing cores (e.g., a single-core processor or a multi-core processor). By way of example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), or a microprocessor, or any combination thereof.

[0144] Understandably, Figure 7 The structure shown is for illustration only. The electronic device may also have Figure 7 More or fewer components than shown, or with Figure 7 Different configurations are shown. Figure 7 The components shown may be implemented in hardware, software or a combination thereof.

[0145] It should be understood that the apparatus and method disclosed in the above-mentioned embodiments can also be implemented in other ways. The apparatus embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the apparatus, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0146] The above are only various implementations of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for identifying independent floating ice similarity in the Arctic sea ice edge area, characterized in that: The method comprises: Acquire a first image and a second image taken successively of a target area; identifying a first independent ice floe located in the first image; identifying at least one second independent ice floe located in the second image; A target ice floe that is most similar to the first independent ice floe is determined from the at least one second independent ice floe according to the Haustoff distance between the first independent ice floe and each of the second independent ice floes.

2. The method for identifying independent floating ice similarity in the Arctic sea ice edge area according to claim 1, characterized in that: The step of determining, from the at least one second independent ice floe, a target ice floe that is most similar to the first independent ice floe according to the Haustov distance between the first independent ice floe and each of the second independent ice floes, comprises: Obtaining the shortest Haustov distance between the first independent ice floe and each of the second independent ice floes; taking the shortest Haustof distance between the first independent ice floe and each of the second independent ice floes as a reference distance of each of the second independent ice floes; The target ice floe is selected from the reference distances of each of the second independent ice floes, wherein the target ice floe has the shortest reference distance.

3. The method for identifying independent floating ice similarity in the Arctic sea ice edge area according to claim 2, characterized in that: The obtaining of the shortest Haustof distance between the first independent floating ice and each of the second independent floating ice comprises: For each piece of the second independent ice floe, calculating a plurality of Haustoff distances between the second independent ice floe and the first independent ice floe at a plurality of rotation angles; The shortest Haustoff distance of the second independent ice floe is determined from the plurality of Haustoff distances.

4. The method for identifying independent floating ice similarity in the Arctic sea ice edge region according to claim 3 is characterized in that: The calculating a plurality of Haustoff distances between the second independent ice floe and the first independent ice floe at a plurality of rotation angles comprises: Rotating the second independent ice floe by a preset angle based on the current angle; calculating a Haustof distance between the second independent ice floe and the first independent ice floe after the second independent ice floe is rotated; If the second independent ice floe has not rotated one circle, the process returns to the step of rotating the second independent ice floe by a preset angle based on the current angle until the second independent ice floe rotates one circle, thereby obtaining a plurality of Haustoff distances between the second independent ice floe and the first independent ice floe at a plurality of rotation angles.

5. The method for identifying independent floating ice similarity in the Arctic sea ice edge region according to claim 4, characterized in that: The calculating the Haustof distance between the second independent ice floe after rotation and the first independent ice floe comprises: Sampling the edge contour of the first independent ice floe rotation to obtain positions of a plurality of first edge points; Sampling the edge contour of the second independent ice floe rotation to obtain positions of a plurality of second edge points; According to the positions of the plurality of first edge points and the positions of the plurality of second edge points, a Haustof distance between the second independent ice floe and the first independent ice floe after rotation is obtained.

6. The method for identifying independent floating ice similarity in the Arctic sea ice edge area according to claim 1, characterized in that: The method further comprises: Calculating an area ratio and an area difference between the first independent ice floe and the target ice floe; The degree of change of the floating ice is determined based on the area proportion and the area difference.

7. The method for identifying independent floating ice similarity in the Arctic sea ice edge region according to claim 1, characterized in that: The identifying at least one second independent ice floe located in the second image comprises: Separating at least one piece of primary screening ice from the second image by a threshold method; Identifying the at least one initially screened floating ice by using random forest and support vector to obtain at least one preferred floating ice; Morphological processing and connected domain analysis are performed on the at least one preferred floating ice to identify the at least one second independent floating ice.

8. An independent floating ice similarity recognition device in the Arctic sea ice edge area, characterized in that: The device comprises: An image acquisition module, used to acquire a first image and a second image taken successively of a target area; An ice floe identification module, configured to identify a first independent ice floe located in the first image; The ice floe identification module is further configured to identify at least one second independent ice floe located in the second image; The ice floe matching module is used to determine, from the at least one second independent ice floe, a target ice floe that is most similar to the first independent ice floe according to the Haustoff distance between the first independent ice floe and each of the second independent ice floes.

9. A storage medium, characterized in that: The storage medium stores a computer-readable program, and when the computer-readable program is executed by a processor, the method for identifying the similarity of independent floating ice in the Arctic sea ice edge area according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for identifying the similarity of independent floating ice in the Arctic sea ice edge area according to any one of claims 1 to 7 is implemented.

Images