A method and apparatus for determining the security classification of remote sensing images

Abstract

This invention provides a method and apparatus for classifying the security level of remote sensing images, relating to the technical field of remote sensing image processing. The method includes: acquiring a remote sensing image to be classified; determining whether the remote sensing image to be classified contains classified targets based on the remote sensing image to be classified, a reference image, and corresponding classified target vector data; if the remote sensing image to be classified contains classified targets, determining first target data for the remote sensing image to be classified, and determining the image security level of the remote sensing image to be classified based on the first target data, wherein the first target data includes: planar precision, sensitive labeling information, and ground resolution; if the remote sensing image to be classified does not contain classified targets, determining second target data for the remote sensing image to be classified, and determining the image security level of the remote sensing image to be classified based on the second target data, wherein the second target data includes: planar precision, coverage area, and ground resolution. This invention solves the technical problem of low classification efficiency in existing remote sensing image security level classification methods.

Description

Technical Field

[0001] This invention relates to the technical field of remote sensing image processing, and in particular to a method and apparatus for identifying the security classification of remote sensing images. Background Technology

[0002] Traditional image classification assessment mainly involves manual use of multiple geographic information software programs. This process involves examining the image's spatial resolution, planar accuracy, identifying ground features, and searching for sensitive annotations, ultimately determining the classification level based on relevant confidentiality regulations.

[0003] Classification identification involves the detection of classified targets. Current research on image target recognition mainly focuses on improving recognition efficiency and accuracy by refining algorithms.

[0004] While manual identification has a high accuracy rate, it suffers from two main problems. First, identifying classified targets in images requires a high level of professional expertise from the personnel involved; those without extensive training cannot accurately identify them. Second, manual identification necessitates switching between multiple geographic information systems (GIS) software programs, making it complex, inefficient, and difficult to process large volumes of data.

[0005] No effective solutions have yet been proposed to address the above problems. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide a method and apparatus for identifying the security level of remote sensing images, so as to alleviate the technical problem of low identification efficiency of existing remote sensing image security level identification methods.

[0007] In a first aspect, embodiments of the present invention provide a method for classifying the security level of remote sensing images, comprising: acquiring a remote sensing image to be classified; determining whether the remote sensing image to be classified contains a classified target based on the remote sensing image to be classified, a reference image, and classified target vector data corresponding to the reference image; if the remote sensing image to be classified contains a classified target, determining first target data of the remote sensing image to be classified, and determining the image security level of the remote sensing image to be classified based on the first target data, wherein the first target data includes: planar precision, sensitive annotation information, and ground resolution; if the remote sensing image to be classified does not contain a classified target, determining second target data of the remote sensing image to be classified, and determining the image security level of the remote sensing image to be classified based on the second target data, wherein the second target data includes: planar precision, coverage area, and ground resolution; wherein the image security level includes: confidential, secret, and unclassified.

[0008] Further, based on the remote sensing image to be identified, the reference image, and the classified target vector data corresponding to the reference image, determining whether the remote sensing image to be identified contains classified targets includes: registering the remote sensing image to be identified using the reference image to obtain a registered remote sensing image to be identified; identifying the classified target vector data that overlaps with the registered remote sensing image to be identified in the classified target vector data corresponding to the reference image; determining the target region in the remote sensing image to be identified based on the classified target vector data that overlaps with the registered remote sensing image to be identified; and using a deep learning algorithm to identify whether the target region contains classified targets.

[0009] Further, based on the classified target vector data overlapping with the registered remote sensing image to be identified, the target region in the remote sensing image to be identified is determined, including: extending the classified target vector data overlapping with the registered remote sensing image to be identified by a preset distance to obtain an initial region; and determining the region in the remote sensing image to be identified that corresponds to the initial region as the target region.

[0010] Further, the classified target vector data overlapping with the registered remote sensing image to be identified is extended by a preset distance to obtain an initial region, including: if the classified target vector data overlapping with the remote sensing image to be identified is a surface layer, then the surface layer is extended by a first preset distance to obtain the initial region; if the classified target vector data overlapping with the remote sensing image to be identified is a point layer, then the initial region is extended by a second preset distance with the center of the point layer as the center.

[0011] Furthermore, the method also includes: after determining that the target area contains classified targets, manually verifying the classified targets.

[0012] Further, determining whether the remote sensing image to be identified is a classified image based on the first target data includes: if the planar accuracy of the remote sensing image to be identified is greater than or equal to 10 meters, then the remote sensing image to be identified is classified as confidential; if the planar accuracy of the remote sensing image to be identified is less than 10 meters and the remote sensing image to be identified contains sensitive information, then the remote sensing image to be identified is classified as confidential; if the planar accuracy of the remote sensing image to be identified is less than 10 meters, the remote sensing image to be identified does not contain sensitive information, and the ground resolution of the remote sensing image to be identified is greater than or equal to 0.5 meters, then the remote sensing image to be identified is classified as secret; if the planar accuracy of the remote sensing image to be identified is less than 10 meters, the remote sensing image to be identified does not contain sensitive information, and the ground resolution of the remote sensing image to be identified is less than 0.5 meters, then the remote sensing image to be identified is classified as unclassified.

[0013] Further, the image security level of the remote sensing image to be identified is determined based on the second target data, including: if the planar resolution of the remote sensing image to be identified is greater than or equal to 10 meters and the coverage area of ​​the remote sensing image to be identified is greater than or equal to 25 square kilometers, then the remote sensing image to be identified is classified as secret; if the planar resolution of the remote sensing image to be identified is greater than or equal to 10 meters and the coverage area of ​​the remote sensing image to be identified is less than 25 square kilometers, then the remote sensing image to be identified is classified as non-secret; if the planar resolution of the remote sensing image to be identified is less than 10 meters and the ground resolution of the remote sensing image to be identified is less than 10 square kilometers, then the remote sensing image to be identified is classified as non-secret. If the planar accuracy of the remote sensing image to be identified is less than 0.5 meters, then the image is classified as non-classified; if the planar accuracy of the remote sensing image to be identified is less than 10 meters, the ground resolution is greater than or equal to 0.5 meters, and the coverage area is less than 25 square kilometers, then the image is classified as non-classified; if the planar accuracy of the remote sensing image to be identified is less than 10 meters, the ground resolution is greater than or equal to 0.5 meters, and the coverage area is greater than or equal to 25 square kilometers, then the image is classified as secret.

[0014] Secondly, embodiments of the present invention also provide a remote sensing image classification identification device, comprising: an acquisition unit for acquiring a remote sensing image to be identified; a determination unit for determining whether the remote sensing image to be identified contains a classified target based on the remote sensing image to be identified, a reference image, and classified target vector data corresponding to the reference image; a first identification unit for determining first target data of the remote sensing image to be identified, and determining the image classification level of the remote sensing image to be identified based on the first target data, wherein the first target data includes: planar precision, sensitive annotation information, and ground resolution; and a second identification unit for determining second target data of the remote sensing image to be identified, and determining the image classification level of the remote sensing image to be identified based on the second target data, wherein the second target data includes: planar precision, coverage area, and ground resolution; wherein the image classification level includes: confidential, secret, and unconfidential.

[0015] Thirdly, embodiments of the present invention also provide an electronic device, including a memory and a processor, wherein the memory is used to store a program that supports the processor in executing the method described in the first aspect above, and the processor is configured to execute the program stored in the memory.

[0016] Fourthly, embodiments of the present invention also provide a computer-readable storage medium on which a computer program is stored.

[0017] In this embodiment of the invention, a remote sensing image to be identified is acquired; based on the remote sensing image to be identified, a reference image, and the classified target vector data corresponding to the reference image, it is determined whether the remote sensing image to be identified contains classified targets; if the remote sensing image to be identified contains classified targets, first target data of the remote sensing image to be identified is determined, and the image classification level of the remote sensing image to be identified is determined based on the first target data, wherein the first target data includes: planar accuracy, sensitive annotation information, and ground resolution; if the remote sensing image to be identified does not contain classified targets, second target data of the remote sensing image to be identified is determined, and the image classification level of the remote sensing image to be identified is determined based on the second target data, wherein the second target data includes: planar accuracy, coverage area, and ground resolution; wherein the image classification level includes: confidential, secret, and unconfidential, thereby reducing the need for manual classification of remote sensing images and solving the technical problem of low efficiency in existing remote sensing image classification methods, thus achieving the technical effect of improving the efficiency of remote sensing image classification.

[0018] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a method for determining the security level of remote sensing images, provided as an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a remote sensing image security classification device provided in an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Example 1:

[0026] According to an embodiment of the present invention, an embodiment of a method for identifying the security level of remote sensing images is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 1 This is a flowchart of a method for determining the security level of remote sensing images according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0028] Step S102: Acquire the remote sensing image to be identified;

[0029] It should be noted that the aforementioned remote sensing images to be identified are generally visible light images.

[0030] Step S104: Based on the remote sensing image to be identified, the reference image, and the classified target vector data corresponding to the reference image, determine whether the remote sensing image to be identified contains classified targets.

[0031] Step S106: If the remote sensing image to be identified contains classified targets, the first target data of the remote sensing image to be identified is determined, and the image security level of the remote sensing image to be identified is determined based on the first target data. The first target data includes: planar precision, sensitive annotation information and ground resolution.

[0032] Step S108: If the remote sensing image to be identified does not contain classified targets, then the second target data of the remote sensing image to be identified is determined, and the image security level of the remote sensing image to be identified is determined based on the second target data. The second target data includes: planar accuracy, coverage area and ground resolution.

[0033] The image classification includes: confidential, secret, and unclassified.

[0034] In this embodiment of the invention, a remote sensing image to be identified is acquired; based on the remote sensing image to be identified, a reference image, and the classified target vector data corresponding to the reference image, it is determined whether the remote sensing image to be identified contains classified targets; if the remote sensing image to be identified contains classified targets, first target data of the remote sensing image to be identified is determined, and the image classification level of the remote sensing image to be identified is determined based on the first target data, wherein the first target data includes: planar accuracy, sensitive annotation information, and ground resolution; if the remote sensing image to be identified does not contain classified targets, second target data of the remote sensing image to be identified is determined, and the image classification level of the remote sensing image to be identified is determined based on the second target data, wherein the second target data includes: planar accuracy, coverage area, and ground resolution; wherein the image classification level includes: confidential, secret, and unconfidential, thereby reducing the need for manual classification of remote sensing images and solving the technical problem of low efficiency in existing remote sensing image classification methods, thus achieving the technical effect of improving the efficiency of remote sensing image classification.

[0035] Classified remote sensing images usually contain location information, and according to regulations, only images within my country are considered classified. Generally, publicly released images have undergone declassification processing as required (e.g., the location has been shifted, and classified texture information in the image has been removed). However, some remote sensing images have not undergone declassification processing or have not been declassified completely. Therefore, it is necessary to use the above methods to identify the classification level of remote sensing images.

[0036] In this embodiment of the invention, step S104 includes the following steps:

[0037] Step S11: Register the remote sensing image to be identified using the reference image to obtain the registered remote sensing image to be identified.

[0038] Step S12: Identify the classified target vector data that overlaps with the registered remote sensing image to be identified in the classified target vector data corresponding to the reference image;

[0039] Step S13: Based on the classified target vector data that overlaps with the registered remote sensing image to be identified, determine the target area in the remote sensing image to be identified.

[0040] Step S14: Using a deep learning algorithm, identify whether the target area contains classified targets.

[0041] Specifically, step S13 includes the following steps:

[0042] The vector data of classified targets that overlap with the registered remote sensing image to be identified are extended by a preset distance to obtain an initial region.

[0043] The region in the remote sensing image to be identified that corresponds to the initial region is determined as the target region.

[0044] Current research on image target recognition mainly focuses on improving algorithms to enhance recognition efficiency and accuracy. However, in this embodiment of the invention, the target being identified is a remote sensing image with location information, and the location of the classified information is basically fixed. Therefore, the scope of target recognition can be narrowed down using location information to improve the efficiency and accuracy of target recognition.

[0045] First, the remote sensing image to be identified is registered with the reference image. Since quantitative calculation is not required in this embodiment of the invention, only approximate registration is needed.

[0046] Then, the vector data of the classified target is overlaid with the registered image of the unclassified target.

[0047] The aforementioned classified target vector data and the aforementioned reference imagery can be perfectly overlaid. Its attribute information includes the name and address of the classified target. It may include two types of graphics: one is point data of the classified target, which can show the actual location of the classified target; the other is area data of the classified target, which can show not only the actual location of the classified target, but also the shape and outline of the classified target.

[0048] If no vector features fall into the registered image of the pending classification, then the image of the pending classification is considered to contain no classified targets.

[0049] If any vector features fall into the registered remote sensing image to be identified, then the registered remote sensing image to be identified will be used to identify classified targets.

[0050] It should be noted that if the classified target vector data is a polygon layer, then the target area is directly defined by extending 100 meters outward from the polygon layer; if the classified target vector data is a point layer, then the target area is defined by a radius of two kilometers centered on the point.

[0051] Finally, deep learning algorithms are used to determine whether the target area contains classified targets.

[0052] Since target identification is performed only within the target area, the efficiency of target identification can be greatly improved, as can the accuracy of identification. However, since some classified targets may be just a building, they cannot be distinguished from ordinary buildings if identified directly. Therefore, after obtaining the identification results, the identification results in the second step are manually checked. Since the accuracy of machine identification depends on the quality of the sample library, the identification cannot be completely correct. Therefore, manual intervention is required in this step to verify the data.

[0053] In this embodiment of the invention, determining whether the remote sensing image to be identified is a classified image based on the first target data includes:

[0054] If the planar accuracy of the remote sensing image to be identified is greater than or equal to 10 meters, then the remote sensing image to be identified is classified as confidential.

[0055] If the planar accuracy of the remote sensing image to be identified is less than 10 meters and the remote sensing image to be identified contains sensitive information, then the remote sensing image to be identified is classified as confidential.

[0056] If the planar accuracy of the remote sensing image to be identified is less than 10 meters, the remote sensing image to be identified does not contain sensitive information, and the ground resolution of the remote sensing image to be identified is greater than or equal to 0.5 meters, then the remote sensing image to be identified is classified as secret.

[0057] If the planar accuracy of the remote sensing image to be identified is less than 10 meters, the remote sensing image to be identified does not contain sensitive information, and the ground resolution of the remote sensing image to be identified is less than 0.5 meters, then the remote sensing image to be identified is classified as non-classified.

[0058] In this embodiment of the invention, the planar accuracy of the remote sensing image to be identified is determined by finding corresponding points on the remote sensing image to be identified and the reference image, and then calculating the distance between the two corresponding points.

[0059] Specifically, based on the multiple sets of corresponding points found, the average distance between these points is calculated. If the average distance is less than 10 meters, the accuracy is considered better than 10 meters; if the average distance is greater than 10 meters, the accuracy is considered less than 10 meters. Assume n corresponding points are found, x′ i Let y′ be the x-coordinate of the reference image of the i-th corresponding point. i Let x be the ordinate of the reference image of the i-th corresponding point. i Let y be the x-coordinate of the undetermined dense image of the i-th point with the same name. i Let be the ordinate of the undetermined dense image of the i-th point with the same name.

[0060] The formula for calculating planar accuracy is as follows:

[0061]

[0062] First, the annotation information in the remote sensing image to be identified is extracted. Then, by setting specific sensitive words, such as "military" or "nuclear power plant", the extracted annotation information is searched to determine the sensitive annotation information in the remote sensing image to be identified.

[0063] In this embodiment of the invention, after the security classification of the remote sensing image to be identified is completed, an identification report is generated. The identification report includes the image number (the image is numbered before the image is detected), identification date, identification personnel, target recognition results, manual inspection results, image location accuracy, annotation information extraction results, image spatial resolution, and coverage area.

[0064] Example 2:

[0065] This invention also provides a remote sensing image security classification identification device, which is used to perform the remote sensing image security classification identification method provided in the above-described embodiments of this invention. The following is a detailed description of the remote sensing image security classification identification device provided in this invention.

[0066] like Figure 2 As shown, Figure 2 The diagram shows a remote sensing image security classification identification device, which includes:

[0067] Acquisition unit 10 is used to acquire remote sensing images to be identified;

[0068] The determining unit 20 is used to determine whether the remote sensing image to be identified contains a classified target based on the remote sensing image to be identified, the reference image, and the classified target vector data corresponding to the reference image.

[0069] The first identification unit 30 is used to determine the first target data of the remote sensing image to be identified when the remote sensing image to be identified contains classified targets, and to determine the image security level of the remote sensing image to be identified based on the first target data. The first target data includes: planar accuracy, sensitive annotation information and ground resolution.

[0070] The second identification unit 40 is used to determine the second target data of the remote sensing image to be identified when the remote sensing image to be identified does not contain classified targets, and to determine the image security level of the remote sensing image to be identified based on the second target data. The second target data includes: planar accuracy, coverage area and ground resolution.

[0071] The image classification includes: confidential, secret, and unclassified.

[0072] In this embodiment of the invention, a remote sensing image to be identified is acquired; based on the remote sensing image to be identified, a reference image, and the classified target vector data corresponding to the reference image, it is determined whether the remote sensing image to be identified contains classified targets; if the remote sensing image to be identified contains classified targets, first target data of the remote sensing image to be identified is determined, and the image classification level of the remote sensing image to be identified is determined based on the first target data, wherein the first target data includes: planar accuracy, sensitive annotation information, and ground resolution; if the remote sensing image to be identified does not contain classified targets, second target data of the remote sensing image to be identified is determined, and the image classification level of the remote sensing image to be identified is determined based on the second target data, wherein the second target data includes: planar accuracy, coverage area, and ground resolution; wherein the image classification level includes: confidential, secret, and unconfidential, thereby reducing the need for manual classification of remote sensing images and solving the technical problem of low efficiency in existing remote sensing image classification methods, thus achieving the technical effect of improving the efficiency of remote sensing image classification.

[0073] Example 3:

[0074] This invention also provides an electronic device, including a memory and a processor. The memory is used to store a program that supports the processor in executing the method described in Embodiment 1 above, and the processor is configured to execute the program stored in the memory.

[0075] See Figure 3 The present invention also provides an electronic device 100, including: a processor 50, a memory 51, a bus 52 and a communication interface 53, wherein the processor 50, the communication interface 53 and the memory 51 are connected through the bus 52; the processor 50 is used to execute executable modules, such as computer programs, stored in the memory 51.

[0076] The memory 51 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 53 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0077] Bus 52 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0078] The memory 51 is used to store programs. After receiving an execution instruction, the processor 50 executes the programs. The method executed by the device for defining the flow process disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 50 or implemented by the processor 50.

[0079] Processor 50 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 50 or by instructions in software form. Processor 50 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 51. The processor 50 reads the information in memory 51 and, in conjunction with its hardware, completes the steps of the above method.

[0080] Example 4:

[0081] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method described in Embodiment 1 above.

[0082] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0083] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0085] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0086] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0087] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for determining the security classification of remote sensing images, characterized in that, include: Acquire remote sensing images to be identified; Based on the remote sensing image to be identified, the reference image, and the vector data of the classified target corresponding to the reference image, it is determined whether the remote sensing image to be identified contains a classified target. If the remote sensing image to be identified contains classified targets, then the first target data of the remote sensing image to be identified is determined, and the image security level of the remote sensing image to be identified is determined based on the first target data. The first target data includes: planar precision, sensitive annotation information and ground resolution. If the remote sensing image to be identified does not contain classified targets, then the second target data of the remote sensing image to be identified is determined, and the image security level of the remote sensing image to be identified is determined based on the second target data. The second target data includes: planar accuracy, coverage area and ground resolution. The image classification includes: confidential, secret, and unclassified.

2. The method according to claim 1, characterized in that, Based on the remote sensing image to be identified, the reference image, and the corresponding classified target vector data of the reference image, it is determined whether the remote sensing image to be identified contains classified targets, including: The reference image is used to register the remote sensing image to be identified, resulting in the registered remote sensing image to be identified. Identify the classified target vector data that overlaps with the registered remote sensing image to be identified in the classified target vector data corresponding to the reference image; Based on the classified target vector data that overlaps with the registered remote sensing image to be identified, the target area in the remote sensing image to be identified is determined. Using deep learning algorithms, it is determined whether the target area contains classified targets.

3. The method according to claim 2, characterized in that, Based on the classified target vector data overlapping with the registered remote sensing image to be identified, the target region in the remote sensing image to be identified is determined, including: The vector data of classified targets that overlap with the registered remote sensing image to be identified are extended by a preset distance to obtain an initial region. The region in the remote sensing image to be identified that corresponds to the initial region is determined as the target region.

4. The method according to claim 3, characterized in that, The vector data of classified targets overlapping with the registered remote sensing image to be identified are extended by a preset distance to obtain an initial region, including: If the vector data of the classified target that overlaps with the remote sensing image to be identified is a surface layer, then the surface layer is extended by a first preset distance to obtain the initial region; If the classified target vector data overlapping with the remote sensing image to be identified is a point layer, then the initial area is obtained by extending the point layer as the center by a second preset distance.

5. The method according to claim 2, characterized in that, After using deep learning algorithms to identify whether the target area contains classified targets, the method further includes: The identification results are manually verified.

6. The method according to claim 1, characterized in that, Determining whether the remote sensing image to be identified is a classified image based on the first target data includes: If the planar accuracy of the remote sensing image to be identified is greater than or equal to 10 meters, then the remote sensing image to be identified is classified as confidential. If the planar accuracy of the remote sensing image to be identified is less than 10 meters and the remote sensing image to be identified contains sensitive information, then the remote sensing image to be identified is classified as confidential. If the planar accuracy of the remote sensing image to be identified is less than 10 meters, the remote sensing image to be identified does not contain sensitive information, and the ground resolution of the remote sensing image to be identified is greater than or equal to 0.5 meters, then the remote sensing image to be identified is classified as secret. If the planar accuracy of the remote sensing image to be identified is less than 10 meters, the remote sensing image to be identified does not contain sensitive information, and the ground resolution of the remote sensing image to be identified is less than 0.5 meters, then the remote sensing image to be identified is classified as non-classified.

7. The method according to claim 1, characterized in that, Determining whether the remote sensing image to be identified is a classified image based on the second target data includes: If the planar accuracy of the remote sensing image to be identified is greater than or equal to 10 meters and the coverage area of ​​the remote sensing image to be identified is greater than or equal to 25 square kilometers, then the remote sensing image to be identified is classified as secret. If the planar accuracy of the remote sensing image to be identified is greater than or equal to 10 meters and the coverage area of ​​the remote sensing image to be identified is less than 25 square kilometers, then the remote sensing image to be identified is classified as non-classified. If the planar accuracy of the remote sensing image to be identified is less than 10 meters and the ground resolution of the remote sensing image to be identified is less than 0.5 meters, then the remote sensing image to be identified is classified as non-classified. If the planar accuracy of the remote sensing image to be identified is less than 10 meters, the ground resolution of the remote sensing image to be identified is greater than or equal to 0.5 meters, and the coverage area of ​​the remote sensing image to be identified is less than 25 square kilometers, then the remote sensing image to be identified is classified as non-classified. If the planar accuracy of the remote sensing image to be identified is less than 10 meters, the ground resolution of the remote sensing image to be identified is greater than or equal to 0.5 meters, and the coverage area of ​​the remote sensing image to be identified is greater than or equal to 25 square kilometers, then the remote sensing image to be identified is classified as secret.

8. A device for identifying the security classification of remote sensing images, characterized in that, include: The acquisition unit is used to acquire the remote sensing image to be identified. The determining unit is used to determine whether the remote sensing image to be identified contains a classified target based on the remote sensing image to be identified, the reference image, and the classified target vector data corresponding to the reference image. The first identification unit is used to determine the first target data of the remote sensing image to be identified when the remote sensing image to be identified contains classified targets, and to determine the image security level of the remote sensing image to be identified based on the first target data. The first target data includes: planar accuracy, sensitive annotation information and ground resolution. The second identification unit is used to determine the second target data of the remote sensing image to be identified when the remote sensing image to be identified does not contain classified targets, and to determine the image security level of the remote sensing image to be identified based on the second target data. The second target data includes: planar accuracy, coverage area and ground resolution. The image classification includes: confidential, secret, and unclassified.

9. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a program that supports the processor in executing the method of any one of claims 1 to 7, and the processor being configured to execute the program stored in the memory.

10. A computer-readable storage medium storing a computer program thereon, characterized in that, When a computer program is run by a processor, it performs the steps of the method described in any one of claims 1 to 7.

Images