Method and device for screening remote sensing image data

Abstract

The application relates to a screening method and device for remote sensing image data. The method comprises the following steps: acquiring remote sensing image data sets meeting preset conditions in a to-be-covered area, and performing spatial self-intersection on all remote sensing image data to form a plurality of image blocks; calculating the occurrence frequency of each image block, and the global coverage rate and the essential degree of each remote sensing image; constructing a heuristic function, and initializing the solution by using the heuristic function construction algorithm to determine a first global approximate feasible image in the to-be-covered area; iteratively deleting remote sensing images in a preset proportion from the first global approximate feasible image, and covering the deleted gaps by using the heuristic function or a greedy algorithm to generate a plurality of second global approximate feasible images in the to-be-covered area, which form a feasible image solution set; simulating the force of electric quantity on electric charge to build a kind of electromagnetic moving mechanism, so as to select the least number of target remote sensing images capable of covering the to-be-covered area from the feasible image solution set.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method and apparatus for screening remote sensing image data. Background Technology

[0002] Existing technologies use a greedy algorithm to filter data, which overlays all eligible spatial data (such as images) onto the area to be covered, selects the spatial data with the largest intersection area, erases the area covered by that data, and repeats the overlay process until coverage is complete.

[0003] The drawback of existing technologies is that the minimum cover problem is NP-hard, meaning it cannot be solved in polynomial time; only approximate solutions can be calculated. Greedy algorithms solve for approximate solutions by selecting the current optimal solution at each step, substituting the global optimal solution for the local optimum. Therefore, cover selection algorithms based on this principle will ultimately select spatial datasets influenced by the selection order, resulting in the minimum cover under that selection order. Literature has shown that, in the worst case, the approximate solution selected by this method is ln(n / k)+1 times the theoretical optimal solution. Summary of the Invention

[0004] To overcome the problems existing in related technologies, the present invention provides a method and apparatus for screening remote sensing image data, which can select the minimum number of target remote sensing images that can cover the area from all remote sensing image data in the area to be covered, thereby avoiding getting trapped in local optima and improving algorithm efficiency.

[0005] According to a first aspect of the present invention, a method for filtering remote sensing image data is provided, the method comprising:

[0006] Acquire a dataset of remote sensing images that meet preset conditions within the area to be covered, and perform spatial self-intersection on all remote sensing image data in the dataset to form multiple image blocks;

[0007] Calculate the frequency of occurrence of each image block, as well as the global coverage and selectability of each remote sensing image;

[0008] A heuristic function is constructed based on the global coverage and selectivity of each remote sensing image, and the solution is initialized using the heuristic function construction algorithm to determine the first globally approximate feasible image within the area to be covered.

[0009] Iteratively delete a preset proportion of remote sensing images from the first global approximate feasible image, and then use the heuristic function or greedy algorithm to cover the deleted vulnerabilities to generate multiple second global approximate feasible images within the area to be covered, forming a feasible image solution set;

[0010] By simulating the force of electric charge on electric charge, an electromagnetic-like movement mechanism is constructed to select the minimum number of target remote sensing images from the feasible image solution set that can cover the area to be covered.

[0011] In one embodiment, preferably, calculating the occurrence frequency of each image block, as well as the global coverage and selectability of each remote sensing image, includes:

[0012] Determine the area containing each image block x i The number of remote sensing images, wherein the number is defined as x for each image block. i The frequency of occurrence q i ;

[0013] Each remote sensing image s is calculated based on the occurrence frequency of each image block. i global coverage c i And required degree d i ;

[0014] Wherein, global coverage c i Equal to remote sensing images s i The minimum frequency of occurrence across all included image blocks;

[0015] Required degree d i This is equivalent to deleting remote sensing images. i The number of other remote sensing images with a global coverage of 1 that appear later.

[0016] In one embodiment, preferably, the heuristic function includes:

[0017] f=(1+d) / (c-1)+1 / (|S|-|s i |)

[0018] Where f represents the heuristic function, d represents the selectivity, c represents the global coverage, S represents the remote sensing image dataset, and s i Represents remote sensing images.

[0019] In one embodiment, preferably, a heuristic function construction algorithm is used to initialize the solution to determine a first globally approximate feasible image within the area to be covered, including:

[0020] Determine the global coverage corresponding to each remote sensing image;

[0021] The first remote sensing image with a global coverage rate of 1 is determined as the first globally approximate feasible image within the area to be covered;

[0022] Calculate the heuristic function of the other second remote sensing images besides the first remote sensing image, and delete the remote sensing image with the smallest heuristic function.

[0023] In one embodiment, preferably, an electromagnetic-like movement mechanism is constructed by simulating the force of electric charge on electric charge to select the minimum number of target remote sensing images from the feasible image solution set that can cover the area to be covered, including:

[0024] The electromagnetic movement mechanism is constructed by simulating the force of electric charge on electric charge. When the number of images in the feasible image solution set is greater than a preset value, other feasible image solutions are rejected. When the number of images in the feasible image solution set is less than or equal to the preset value, other feasible image solutions are attracted, so that each feasible image solution moves in a better direction and undergoes random mutation after each movement.

[0025] According to a second aspect of the present invention, a remote sensing image data filtering device is provided, the device comprising:

[0026] The processing module is used to acquire a remote sensing image dataset that meets preset conditions within the area to be covered, and to perform spatial self-intersection on all remote sensing image data in the remote sensing image dataset to form multiple image blocks.

[0027] The calculation module is used to calculate the occurrence frequency of each image block, as well as the global coverage and selectivity of each remote sensing image.

[0028] The determination module is used to construct a heuristic function based on the global coverage and necessity of each remote sensing image, and to initialize the solution using a heuristic function construction algorithm, so as to determine the first globally approximate feasible image within the area to be covered;

[0029] The generation module is used to iteratively delete a preset proportion of remote sensing images from the first global approximate feasible image, and then use the heuristic function or greedy algorithm to cover the deleted vulnerabilities to generate multiple second global approximate feasible images within the area to be covered, forming a feasible image solution set.

[0030] A selection module is used to simulate the force of electric charge on electric charge and construct an electromagnetic-like movement mechanism to select the minimum number of target remote sensing images that can cover the area to be covered from the feasible image solution set.

[0031] In one embodiment, preferably, the computing module is used for:

[0032] Determine the area containing each image block x i The number of remote sensing images, wherein the number is defined as x for each image block. i The frequency of occurrence q i ;

[0033] Each remote sensing image s is calculated based on the occurrence frequency of each image block. i global coverage ci And required degree d i ;

[0034] Wherein, global coverage c i Equal to remote sensing images s i The minimum frequency of occurrence across all included image blocks;

[0035] Required degree d i This is equivalent to deleting remote sensing images. i The number of other remote sensing images with a global coverage of 1 that appear later.

[0036] In one embodiment, preferably, the heuristic function includes:

[0037] f=(1+d) / (c-1)+1 / (|S|-|s i |)

[0038] Where f represents the heuristic function, d represents the selectivity, c represents the global coverage, S represents the remote sensing image dataset, and s i Represents remote sensing images.

[0039] In one embodiment, preferably, the determining module includes:

[0040] The first determining unit is used to determine the global coverage corresponding to each remote sensing image;

[0041] The second determining unit is used to determine the first remote sensing image with a global coverage rate of 1 as the first globally approximate feasible image within the area to be covered.

[0042] The calculation unit is used to calculate the heuristic function of the other second remote sensing images besides the first remote sensing image, and delete the remote sensing image with the smallest heuristic function.

[0043] In one embodiment, preferably, the selection module is used for:

[0044] The electromagnetic movement mechanism is constructed by simulating the force of electric charge on electric charge. When the number of images in the feasible image solution set is greater than a preset value, other feasible image solutions are rejected. When the number of images in the feasible image solution set is less than or equal to the preset value, other feasible image solutions are attracted, so that each feasible image solution moves in a better direction and undergoes random mutation after each movement.

[0045] According to a third aspect of the present invention, a remote sensing image data filtering apparatus is provided, the apparatus comprising:

[0046] processor;

[0047] Memory used to store processor-executable instructions;

[0048] The processor is configured as follows:

[0049] Acquire a dataset of remote sensing images that meet preset conditions within the area to be covered, and perform spatial self-intersection on all remote sensing image data in the dataset to form multiple image blocks;

[0050] Calculate the frequency of occurrence of each image block, as well as the global coverage and selectability of each remote sensing image;

[0051] A heuristic function is constructed based on the global coverage and selectivity of each remote sensing image, and the solution is initialized using the heuristic function construction algorithm to determine the first globally approximate feasible image within the area to be covered.

[0052] Iteratively delete a preset proportion of remote sensing images from the first global approximate feasible image, and then use the heuristic function or greedy algorithm to cover the deleted vulnerabilities to generate multiple second global approximate feasible images within the area to be covered, forming a feasible image solution set;

[0053] By simulating the force of electric charge on electric charge, an electromagnetic-like movement mechanism is constructed to select the minimum number of target remote sensing images from the feasible image solution set that can cover the area to be covered.

[0054] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method as described in any one of the embodiments of the second aspect.

[0055] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0056] In this embodiment of the invention, the minimum number of target remote sensing images that can cover the area can be selected from all remote sensing image data in the area to be covered, avoiding getting trapped in a local optimum and improving algorithm efficiency.

[0057] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0058] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0059] Figure 1 This is a flowchart illustrating a method for filtering remote sensing image data according to an exemplary embodiment.

[0060] Figure 2This is a flowchart of step S102 in a method for filtering remote sensing image data according to an exemplary embodiment.

[0061] Figure 3 This is a flowchart of step S103 in a method for filtering remote sensing image data according to an exemplary embodiment.

[0062] Figure 4 This is a block diagram illustrating a remote sensing image data filtering device according to an exemplary embodiment.

[0063] Figure 5 This is a block diagram of a determining module in a remote sensing image data filtering apparatus according to an exemplary embodiment. Detailed Implementation

[0064] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0065] Figure 1 This is a flowchart illustrating a method for filtering remote sensing image data according to an exemplary embodiment.

[0066] like Figure 1 As shown, according to a first aspect of the present invention, a method for filtering remote sensing image data is provided, the method comprising:

[0067] Step S101: Obtain a remote sensing image dataset that meets preset conditions within the area to be covered, and perform spatial self-intersection on all remote sensing image data in the remote sensing image dataset to form multiple image blocks; the preset conditions may be a preset time period, a preset cloud cover range, etc.

[0068] Spatial data that meets the criteria, such as images (referred to as set S, with each image scene referred to as s), are then processed. i The algorithm performs spatial self-intersection, generating a large number of non-intersecting small blocks (referred to as set X). A thinning scheme can be employed to further improve algorithm efficiency.

[0069] Step S102: Calculate the occurrence frequency of each image block, as well as the global coverage and selectability of each remote sensing image;

[0070] Step S103: Construct a heuristic function based on the global coverage and mandatory degree of each remote sensing image, and use the heuristic function construction algorithm to initialize the solution to determine the first globally approximate feasible image within the area to be covered; construct a heuristic function based on the global coverage and mandatory degree of each remote sensing image as a dynamically adjusted global evaluation index.

[0071] Step S104: Iteratively delete a preset proportion of remote sensing images from the first global approximate feasible images, and then use the heuristic function or greedy algorithm to cover the deleted vulnerabilities to generate multiple second global approximate feasible images within the area to be covered, forming a feasible image solution set.

[0072] Step S105: Simulate the force of electric charge on electric charge to construct an electromagnetic-like movement mechanism, so as to select the minimum number of target remote sensing images that can cover the area to be covered from the feasible image solution set.

[0073] In this embodiment, a heuristic function is constructed using a dynamically adjusted global evaluation index, and the influence of a certain remote sensing image data on the global scope is used as the selection criterion. The method of replacing local solutions is adopted in multiple stages to avoid getting trapped in local optima. At the same time, an electromagnetic-like mechanism is introduced to make the solution always move in the optimal direction. In this way, the minimum number of target remote sensing images that can cover the area can be selected from all remote sensing image data in the area to be covered, avoiding getting trapped in local optima and improving the efficiency of the algorithm.

[0074] Figure 2 This is a flowchart of step S102 in a method for filtering remote sensing image data according to an exemplary embodiment.

[0075] like Figure 2 As shown, in one embodiment, preferably, step S102 includes:

[0076] Step S201, determine the area containing each image block x i The number of remote sensing images, wherein the number is defined as x for each image block. i The frequency of occurrence q i ;

[0077] Step S202: Calculate the occurrence frequency of each remote sensing image s based on the occurrence frequency of each image block. i global coverage c i And required degree d i ;

[0078] Wherein, global coverage c i Equal to remote sensing images s i The minimum frequency of occurrence across all included image blocks;

[0079] Required degree di This is equivalent to deleting remote sensing images. i The number of other remote sensing images with a global coverage of 1 that appear later.

[0080] In one embodiment, preferably, the heuristic function includes:

[0081] f=(1+d) / (c-1)+1 / (|S|-|s i |)

[0082] Where f represents the heuristic function, d represents the selectivity, c represents the global coverage, S represents the remote sensing image dataset, and s i Represents remote sensing images.

[0083] Heuristic functions are a method of evaluating the quality of different solutions by calculating function values. Heuristic functions cannot directly provide the optimal solution, but they can help researchers choose a better solution.

[0084] The construction method of the heuristic function can be adjusted, or even a greedy algorithm can be used directly to improve the efficiency of the algorithm.

[0085] Figure 3 This is a flowchart of step S103 in a method for filtering remote sensing image data according to an exemplary embodiment.

[0086] like Figure 3 As shown, in one embodiment, preferably, step S103 includes:

[0087] Step S301: Determine the global coverage corresponding to each remote sensing image;

[0088] Step S302: The first remote sensing image with a global coverage rate of 1 is determined as the first globally approximate feasible image within the area to be covered;

[0089] Step S303: Calculate the heuristic function of the other second remote sensing images besides the first remote sensing image, and delete the remote sensing image with the smallest heuristic function.

[0090] Repeating steps S301-S303 above generates a globally approximate feasible solution. Based on this solution, a portion of remote sensing image data is randomly deleted at a certain ratio. Then, a heuristic function or greedy algorithm is used to cover the deleted vulnerabilities, which to some extent avoids getting trapped in local optima and can generate multiple different feasible solutions. After the above steps form a solution set consisting of multiple feasible solutions, in each iteration, a portion of the images in the solution set is randomly replaced at a certain ratio using a greedy algorithm or heuristic function. That is, after random deletion, a greedy algorithm or heuristic function is used to cover the deleted vulnerabilities, avoiding getting trapped in local optima.

[0091] In one embodiment, preferably, an electromagnetic-like movement mechanism is constructed by simulating the force of electric charge on electric charge to select the minimum number of target remote sensing images from the feasible image solution set that can cover the area to be covered, including:

[0092] The electromagnetic movement mechanism is constructed by simulating the force of electric charge on electric charge. When the number of images in the feasible image solution set is greater than a preset value, other feasible image solutions are rejected. When the number of images in the feasible image solution set is less than or equal to the preset value, other feasible image solutions are attracted, so that each feasible image solution moves in a better direction and undergoes random mutation after each movement.

[0093] In this embodiment, the force of electric charge on electric charge is simulated to construct an electromagnetic movement mechanism. The number of images, n, in the solution is used as the criterion for whether the solution is better. Solutions with smaller n will attract other solutions, while those with larger n will repel other solutions, causing each solution to move towards a better direction. After each movement, random mutation is performed to avoid getting trapped in local optima. Theoretically, the above process can produce the theoretically optimal solution after a sufficient number of iterations. Experiments show that the present invention can achieve results superior to the greedy algorithm after 10 iterations. The calculation method for charge movement can be adjusted according to specific application scenarios, such as increasing weights or adding attenuation.

[0094] Figure 4 This is a block diagram illustrating a remote sensing image data filtering device according to an exemplary embodiment.

[0095] like Figure 4 As shown, according to a second aspect of the present invention, a remote sensing image data filtering device is provided, the device comprising:

[0096] Processing module 41 is used to acquire a remote sensing image dataset that meets preset conditions within the area to be covered, and to perform spatial self-intersection on all remote sensing image data in the remote sensing image dataset to form multiple image blocks.

[0097] The calculation module 42 is used to calculate the occurrence frequency of each image block, as well as the global coverage and selectivity of each remote sensing image;

[0098] The determination module 43 is used to construct a heuristic function based on the global coverage and necessity of each remote sensing image, and to initialize the solution using the heuristic function construction algorithm, so as to determine the first globally approximate feasible image in the area to be covered;

[0099] The generation module 44 is used to iteratively delete a preset proportion of remote sensing images from the first global approximate feasible image, and then use the heuristic function or greedy algorithm to cover the deleted vulnerabilities to generate multiple second global approximate feasible images within the area to be covered, forming a feasible image solution set.

[0100] Module 45 is selected to simulate the force of electric charge on electric charge and construct an electromagnetic movement mechanism to select the minimum number of target remote sensing images that can cover the area to be covered from the feasible image solution set.

[0101] In one embodiment, preferably, the computing module is used for:

[0102] Determine the area containing each image block x i The number of remote sensing images, wherein the number is defined as x for each image block. i The frequency of occurrence q i ;

[0103] Each remote sensing image s is calculated based on the occurrence frequency of each image block. i global coverage c i And required degree d i ;

[0104] Wherein, global coverage c i Equal to remote sensing images s i The minimum frequency of occurrence across all included image blocks;

[0105] Required degree d i This is equivalent to deleting remote sensing images. i The number of other remote sensing images with a global coverage of 1 that appear later.

[0106] In one embodiment, preferably, the heuristic function includes:

[0107] f=(1+d) / (c-1)+1 / (|S|-|s i |)

[0108] Where f represents the heuristic function, d represents the selectivity, c represents the global coverage, S represents the remote sensing image dataset, and s i Represents remote sensing images.

[0109] Figure 5 This is a block diagram of a determining module in a remote sensing image data filtering apparatus according to an exemplary embodiment.

[0110] like Figure 5 As shown, in one embodiment, preferably, the determining module 43 includes:

[0111] The first determining unit 51 is used to determine the global coverage corresponding to each remote sensing image;

[0112] The second determining unit 52 is used to determine the first remote sensing image with a global coverage rate of 1 as the first globally approximate feasible image within the area to be covered.

[0113] The calculation unit 53 is used to calculate the heuristic function of the other second remote sensing images besides the first remote sensing image, and delete the remote sensing image with the smallest heuristic function.

[0114] In one embodiment, preferably, the selection module 45 is used for:

[0115] The electromagnetic movement mechanism is constructed by simulating the force of electric charge on electric charge. When the number of images in the feasible image solution set is greater than a preset value, other feasible image solutions are rejected. When the number of images in the feasible image solution set is less than or equal to the preset value, other feasible image solutions are attracted, so that each feasible image solution moves in a better direction and undergoes random mutation after each movement.

[0116] According to a third aspect of the present invention, a remote sensing image data filtering apparatus is provided, the apparatus comprising:

[0117] processor;

[0118] Memory used to store processor-executable instructions;

[0119] The processor is configured as follows:

[0120] Acquire a dataset of remote sensing images that meet preset conditions within the area to be covered, and perform spatial self-intersection on all remote sensing image data in the dataset to form multiple image blocks;

[0121] Calculate the frequency of occurrence of each image block, as well as the global coverage and selectability of each remote sensing image;

[0122] A heuristic function is constructed based on the global coverage and selectivity of each remote sensing image, and the solution is initialized using the heuristic function construction algorithm to determine the first globally approximate feasible image within the area to be covered.

[0123] Iteratively delete a preset proportion of remote sensing images from the first global approximate feasible image, and then use the heuristic function or greedy algorithm to cover the deleted vulnerabilities to generate multiple second global approximate feasible images within the area to be covered, forming a feasible image solution set;

[0124] By simulating the force of electric charge on electric charge, an electromagnetic-like movement mechanism is constructed to select the minimum number of target remote sensing images from the feasible image solution set that can cover the area to be covered.

[0125] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method as described in any one of the embodiments of the second aspect.

[0126] Furthermore, it can be understood that in this invention, "multiple" refers to two or more, and other quantifiers are similar. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. The singular forms "a," "the," and "the" are also intended to include the plural forms unless the context clearly indicates otherwise.

[0127] It is further understood that the terms "first," "second," etc., are used to describe various types of information, but this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another, and do not indicate a specific order or degree of importance. In fact, the expressions "first," "second," etc., are completely interchangeable. For example, without departing from the scope of this invention, first information can also be referred to as second information, and similarly, second information can also be referred to as first information.

[0128] It is further understood that although the operations are described in a specific order in the accompanying drawings in the embodiments of the present invention, this should not be construed as requiring these operations to be performed in the specific order or serial order shown, or requiring all the operations shown to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0129] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0130] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method of screening remote sensing image data, characterized in that, The method comprises: acquiring a remote sensing image data set meeting preset conditions in a region to be covered, and performing spatial self-intersection on all remote sensing image data in the remote sensing image data set to form a plurality of image blocks; calculating the occurrence frequency of each image block, and the global coverage rate and the mandatory degree of each remote sensing image; constructing a heuristic function according to the global coverage rate and the mandatory degree of each remote sensing image, and initializing a solution by using the heuristic function to construct an algorithm to determine a first global approximate feasible image in the region to be covered; iteratively deleting a preset proportion of remote sensing images from the first global approximate feasible image, and covering the deleted gaps by using the heuristic function or a greedy algorithm to generate a plurality of second global approximate feasible images in the region to be covered, which constitute a feasible image solution set; simulating the force of electric quantity on electric charge, and constructing a quasi-electromagnetic moving mechanism to select a minimum number of target remote sensing images that can cover the region to be covered from the feasible image solution set; wherein the calculation of the occurrence frequency of each image block, and the global coverage rate and the mandatory degree of each remote sensing image comprises: determining a number of remote sensing images containing each image block x i , the number being determined as a frequency q i of occurrence of the each image block x i ; calculating a global coverage c i and a degree of obligation d i of each remote sensing image s i based on the frequency of occurrence of each image block wherein the global coverage c i is equal to the remote sensing image s i contains the minimum value of the frequency of occurrence in all image tiles. Mandatory degree d i Equal to delete remote sensing image s i The number of other remote sensing images with global coverage of 1 that appear later the heuristic function comprises: f = (1 + d) / (c - 1) + 1 / (|S| - |s i |) wherein f denotes the heuristic function, d denotes the degree of obligation, c denotes the global coverage, S denotes the remote sensing image dataset, s i denotes a remote sensing image.

2. The method of claim 1, wherein, initializing a solution by using the heuristic function to construct an algorithm to determine a first global approximate feasible image in the region to be covered comprises: determining the global coverage rate corresponding to each remote sensing image; determining a first remote sensing image with a global coverage rate of 1 as the first global approximate feasible image in the region to be covered; calculating the heuristic function of other second remote sensing images except the first remote sensing image, and deleting the remote sensing image with the minimum heuristic function.

3. The method of claim 1, wherein, simulating the force of electric quantity on electric charge, and constructing a quasi-electromagnetic moving mechanism to select a minimum number of target remote sensing images that can cover the region to be covered from the feasible image solution set comprises: simulating the force of electric quantity on electric charge, and constructing a quasi-electromagnetic moving mechanism, wherein when the number of images in a feasible image solution in the feasible image solution set is greater than a preset value, other feasible image solutions are repelled, and when the number of images in the feasible image solution is less than or equal to the preset value, other feasible image solutions are attracted, so that each feasible image solution moves in a more optimal direction, and random mutation is performed after each movement.

4. A screening device for remote sensing image data, characterized in that The device comprises: a processing module configured to acquire a remote sensing image data set meeting preset conditions in a region to be covered, and perform spatial self-intersection on all remote sensing image data in the remote sensing image data set to form a plurality of image blocks; a calculation module configured to calculate the occurrence frequency of each image block, and the global coverage rate and the mandatory degree of each remote sensing image; a determination module configured to construct a heuristic function according to the global coverage rate and the mandatory degree of each remote sensing image, and initialize a solution by using the heuristic function to construct an algorithm to determine a first global approximate feasible image in the region to be covered; a generation module configured to iteratively delete a preset proportion of remote sensing images from the first global approximate feasible image, and cover the deleted gaps by using the heuristic function or a greedy algorithm to generate a plurality of second global approximate feasible images in the region to be covered, which constitute a feasible image solution set; and a selection module configured to simulate the force of electric quantity on electric charge, and construct a quasi-electromagnetic moving mechanism to select a minimum number of target remote sensing images that can cover the region to be covered from the feasible image solution set. The selecting module is configured to simulate the force of electric quantity on electric charge, construct a mechanism similar to electromagnetic movement, and select, from the feasible image solution set, a minimum number of target remote sensing images that can cover the to-be-covered area; The calculation module is configured to calculate the appearance frequency of each image block, and the global coverage rate and the mandatory degree of each remote sensing image, including: determining a number of remote sensing images containing each image block x i , the number being determined as a frequency q i of occurrence of the each image block x i ; calculating a global coverage c of each remote sensing image s i and a degree of obligation d i based on the frequency of occurrence of each image block i ; wherein the global coverage c i is equal to the remote sensing image s i contains the minimum value of the frequency of occurrence in all image tiles. Mandatory degree d i Equal to delete remote sensing image s i The number of other remote sensing images with global coverage of 1 that appear later The heuristic function includes: f = (1 + d) / (c - 1) + 1 / (|S| - |s i |) wherein f denotes the heuristic function, d denotes the degree of obligation, c denotes the global coverage, S denotes the remote sensing image dataset, s i denotes a remote sensing image.

5. The apparatus of claim 4, wherein, The calculation module includes: determining a number of remote sensing images containing each image block x i , the number being determined as a frequency q i of occurrence of the each image block x i ; calculating a global coverage c of the remote sensing images s i based on the frequency of occurrence of each image tile i and a degree of obligation d i ; wherein the global coverage c i is equal to the remote sensing image s i contains the minimum value of the frequency of occurrence in all image tiles. Mandatory degree d i Equal to delete remote sensing image s i The number of other remote sensing images with global coverage of 1 that appear later.

6. The apparatus of claim 4, wherein, The heuristic function includes: f = (1 + d) / (c - 1) + 1 / (|S| - |s i |) wherein f denotes the heuristic function, d denotes the degree of obligation, c denotes the global coverage, S denotes the remote sensing image dataset, s i denotes a remote sensing image.

7. The apparatus of claim 6, wherein, The determining module includes: The first determining unit is configured to determine the global coverage rate corresponding to each remote sensing image. The second determining unit is configured to determine the first remote sensing image with a global coverage rate of 1 as the first global approximate feasible image in the to-be-covered area. The calculation unit is configured to calculate the heuristic function of the second remote sensing images other than the first remote sensing image, and delete the remote sensing image with the minimum heuristic function.

8. The apparatus of claim 6, wherein, The selecting module is configured to: simulate the force of electric quantity on electric charge, construct a mechanism similar to electromagnetic movement, wherein when the number of images in the feasible image solution is greater than a preset value, repel other feasible image solutions, and when the number of images in the feasible image solution is less than or equal to the preset value, attract other feasible image solutions, so that each feasible image solution moves in a more optimal direction, and after each movement, random mutation is performed.

Images