Land utilization change detection method and system based on remote sensing image

Abstract

The invention discloses a land utilization change detection method and system based on a remote sensing image, and belongs to the technical field of remote sensing images. Adding label attributes to the collected multi-temporal remote sensing image, wherein the label attributes comprise a time label attribute and a ground area label attribute; based on label attributes, adding image feature marks to the multi-temporal remote sensing images, selecting ground area label attributes as image stream guidance, and sorting and combing all image features to obtain an image stream cluster; generating a feature state based on the image features, and representing the feature state through a feature capture function; based on the image stream cluster and the feature capture function, analyzing and calculating a change state value of land utilization; based on the change state value of the land utilization, analyzing and detecting the relevancy of the land utilization characteristics in different territorial ranges to generate a detection group, and uploading the detection group to a detection log; and furthermore, land utilization behavior perception in the aspect of linkage planning adjustment of multiple ground areas is realized, so that an effective land utilization data association detection strategy is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing images, and specifically to a method and system for detecting land use changes based on remote sensing images. Background Art

[0002] Multi-temporal remote sensing image technology can use satellite or aerial remote sensing platforms to obtain image data of the same area at different time points. These image data cover various characteristic information such as the spectrum, texture, and shape of the earth's surface. By comparing and analyzing the changes in these characteristic information over time, the conversion of land use types can be identified, such as the conversion of cultivated land into construction land, and the conversion of forest land into grassland;

[0003] In the prior art, multi-temporal remote sensing image technology can be used to capture and accurately reflect the subtle changes in land use in real time to make up for traditional land use monitoring methods, such as on-site manual surveys and cadastral surveys;

[0004] However, with the acceleration of the urbanization process and the adjustment of agricultural land, the changes in land use types are becoming increasingly frequent and complex. Multi-temporal remote sensing image technology can only detect single ground areas and cannot cope with the perception of land use modes in the aspect of coordinated planning and adjustment of multiple ground areas. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for detecting land use changes based on remote sensing images to solve the problems raised in the above background art.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] A land use change detection system based on remote sensing images, the system includes: a remote remote sensing module, an image data management module, and a cloud data analysis module;

[0008] The remote remote sensing module is used to remotely control an unmanned aerial vehicle and collect multi-temporal remote sensing images of a geographical area;

[0009] The image data management module is used to attach tag attributes to the collected multi-temporal remote sensing images, perform image feature processing to generate an image stream cluster, and is also used to characterize the feature state corresponding to the image feature through a feature capture function;

[0010] The cloud data analysis module is used to analyze and calculate the change state value of land use, and is also used to analyze and detect the land use feature correlation of different geographical areas to generate a detection group and upload it to the detection log.

[0011] Further, the way the remote remote sensing module is used to collect the multi-temporal remote sensing images is as follows: The multi-temporal remote sensing images of different geographical ranges are collected through a remote sensing platform carried on a drone.

[0012] Further, the tag attributes include a time tag attribute and a ground area tag attribute. The time tag is the acquisition time node of the multi-temporal remote sensing image, and the ground area tag is the geographical range shown by the multi-temporal remote sensing image. The geographical range is set by pre-dividing the surface demarcation area, and one surface demarcation area corresponds to one geographical range; the image feature processing includes time tag dimension processing, ground area tag dimension processing, and crop type dimension processing, and respectively generates a time tag serial number, a ground area tag serial number, and a crop type number; based on the order of the crop type numbers from small to large, the initialization arrangement of each image feature is performed. After the initialization arrangement is completed, based on the order of the time tag serial numbers from small to large, the optimized arrangement is performed on the result of the initialization arrangement. Through the two methods of initialization arrangement and optimized arrangement, the image stream cluster is generated.

[0013] A method for detecting land use change based on remote sensing images, the method comprising the following steps:

[0014] S1. Add tag attributes to the collected multi-temporal remote sensing images, and the tag attributes include a time tag attribute and a ground area tag attribute;

[0015] S2. Based on the tag attributes, add image feature markers to the multi-temporal remote sensing images, and select the ground area tag attribute as the image stream guide to sort and comb each image feature to obtain an image stream cluster;

[0016] S3. Generate a feature state based on the image features, and characterize the feature state through a feature capture function;

[0017] S4. Analyze and calculate the land use change state value based on the image stream cluster and the feature capture function;

[0018] S5. Analyze and detect the land use feature correlation of different geographical ranges based on the land use change state value to generate a detection group and upload it to the detection log.

[0019] Further, the specific implementation process of adding the tag attributes includes:

[0020] Collect multi-temporal remote sensing images of different geographical ranges through a remote sensing platform carried on a drone, and the multi-temporal remote sensing images have time tag attributes and ground area tag attributes. The time tag is the acquisition time node of the multi-temporal remote sensing images, and the ground area tag is the geographical range shown by the multi-temporal remote sensing images. The geographical range is set by pre-dividing the surface demarcation area, and one surface demarcation area corresponds to one geographical range.

[0021] Further, the generation method of the image stream cluster is as follows:

[0022] Based on the order of the time tag serial numbers, compile the serial numbers of the multi-temporal remote sensing images, and denote the i-th multi-temporal remote sensing image as RS i ; when the a-th ground area tag G a the type of crop planted under the i-th time tag is C e then add an image feature mark to the multi-temporal remote sensing image RS i and denote it as RS i (G a , C e ), where e represents the number of the crop type;

[0023] Based on the image features, with the ground area tag G a as the image stream guide, sort and arrange each image feature to obtain an image stream cluster, denoted as FL(G a ) = {RS i (G a , C e )|i ∈ [1, I], e ∈ [1, E]}; the sorting and arranging method includes initialization sorting and optimization sorting, and the optimization sorting responds after the initialization sorting is completed; the initialization sorting is: initialize and arrange each image feature in ascending order of the crop type number, and the optimization sorting is: based on the result of the initialization sorting, optimize and arrange each image feature in ascending order of the time tag serial number.

[0024] Further, the specific implementation process of characterizing the feature state through the feature capture function includes:

[0025] Capture the features of the image feature RS i (G a , C e ) and generate a feature state, denoted as i:e. Based on the feature state, construct a feature capture function, denoted as f(y:x) = y, where x is the independent variable, and the value of x corresponds to the number of the crop type, y is the dependent variable, and the value of y corresponds to the time tag serial number. When the feature state is i:e, then f(y:x) = f(i:e) = i.

[0026] Furthermore, the specific implementation process of analyzing and calculating the change status value of land use includes:

[0027] Based on the image stream cluster and the feature capture function, analyze and calculate the change status value of land use

[0028]

[0029] SV(G a ) represents the change status value of the land use of the ground area label G a , j:(e + 1) represents the feature status corresponding to the image feature RS j (G a , C e+1 ). RS j represents the j-th multi-temporal remote sensing image, C e+1 represents the (e + 1)-th crop type, NUM[FL(G a )] represents the total number of image features included in the image stream cluster FL(C a );

[0030] According to the above method, the land use change detection in the present invention includes the perception of two types of underlying data. One is the crop type, and the other is the time node. In particular, the change of the crop type is subjectively affected by the change of the time node. The essence of this subjective influence comes from policy adjustment or human farming behavior. Therefore, under the influence of the two dimensions of the change of the crop type and the change of the time node, the multi-temporal remote sensing image features collected show an irregular phenomenon. This phenomenon makes it difficult for traditional land use change detection to cope with the perception of land use behavior in the aspect of the linkage planning adjustment of multiple ground areas; the present invention simplifies the recording of the feature status by capturing the multi-temporal remote sensing image features in the same ground range, and constructs a feature capture function based on this. The essence of the feature capture function is to capture the jump degree of the farming time caused by the change of the crop type, that is, the change status value of the land use. The larger the change status value, the greater the jump degree of the farming time caused by the change of the crop type, and the more obvious the change of the land use behavior.

[0031] Furthermore, the specific implementation process of generating the detection group includes:

[0032] Based on the change status value of the land use, analyze and detect the correlation of the land use features in different geographical ranges

[0033]

[0034] FC(G a →G b ) represents the ground area label G aand the land use feature correlation with the ground area label G b The land use feature correlation between

[0035] SV(G b ) represents the change status value of the land use of the ground area label G b where b is the number of the ground area label, and a≠b, μ represents the average value of the change status values of the land use, and A represents the total number of ground ranges, and σ 2 represents the variance of the change status values of the land use, and

[0036] For a preset correlation threshold, if the land use feature correlation is greater than or equal to the correlation threshold, a detection group is formed between the ground area label G a and the ground area label G b and is uploaded to the detection log, and the staff conducts on-site inspections according to the detection group;

[0037] According to the above method, the essence of the analysis of the land use feature correlation is an embodiment of a correlation probability. Transforming the formula SV(G a ) + SV(G b ) - 2μ gives SV(G a ) - μ + SV(G b ) - μ, that is, the sum of the differences between the change status value SV(G a ) and the average value, and the sum of the differences between the change status value SV(G b ) and the average value. The smaller the sum of the differences, the more similar the land use behaviors of the two ground ranges are, or the more complementary benefits can be generated.

[0038] An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, is used to make the processor execute the computer program by means of computer-executable instructions to implement a land use change detection method based on remote sensing images according to the present invention.

[0039] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: In a method and system for detecting land use changes based on remote sensing images provided by the present invention, time-series remote sensing images collected are attached with tag attributes, including time tag attributes and ground area tag attributes; based on the tag attributes, image feature markers are attached to the time-series remote sensing images, and the ground area tag attributes are selected as the image stream orientation, and each image feature is sorted and sorted to obtain an image stream cluster; based on the image features, a feature state is generated, and the feature state is characterized by a feature capture function; based on the image stream cluster and the feature capture function, the change state value of land use is analyzed and calculated; based on the change state value of land use, the correlation degree of land use features in different geographical ranges is analyzed and detected to generate a detection group and uploaded to the detection log; furthermore, the perception of land use behavior in the aspect of linkage planning adjustment of multiple ground areas is realized to provide an effective land use data association detection strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification, and are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention.

[0041] In the drawings: Figure 1 is a schematic diagram of the steps of a method for detecting land use changes based on remote sensing images according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] In the first embodiment: A system for detecting land use changes based on remote sensing images is provided, and the system includes: a remote remote sensing module, an image data management module, and a cloud data analysis module;

[0044] The remote remote sensing module is used to remotely control the unmanned aerial vehicle and collect time-series remote sensing images of a geographical range;

[0045] Preferably, time-series remote sensing images of different geographical ranges are collected through a remote sensing platform carried on the unmanned aerial vehicle;

[0046] The image data management module is used to attach tag attributes to the collected time-series remote sensing images, perform image feature processing to generate an image stream cluster, and is also used to characterize the feature state corresponding to the image features through a feature capture function;

[0047] Preferably, the tag attributes include a time tag attribute and a ground area tag attribute. The time tag is the acquisition time node of the multi-temporal remote sensing image, and the ground area tag is the geographical range shown in the multi-temporal remote sensing image. The geographical range is set by pre-dividing the surface demarcation area, and one surface demarcation area corresponds to one geographical range. The image feature processing includes time tag dimension processing, ground area tag dimension processing, and crop type dimension processing, and respectively generates a time tag serial number, a ground area tag serial number, and a crop type number. Based on the order of the crop type numbers from small to large, the initialization arrangement of each image feature is performed. After the initialization arrangement is completed, based on the order of the time tag serial numbers from small to large, the optimization arrangement is performed on the result of the initialization arrangement. Through the two methods of initialization arrangement and optimization arrangement, the image stream cluster is generated.

[0048] The cloud data analysis module is used to analyze and calculate the change state value of land use, and is also used to analyze and detect the land use feature correlation of different geographical ranges to generate detection groups and upload them to the detection log.

[0049] Please refer to Figure 1 , in the second embodiment: A method for detecting land use change based on remote sensing images is provided. The method includes the following steps:

[0050] S1. Add tag attributes to the acquired multi-temporal remote sensing images. The tag attributes include a time tag attribute and a ground area tag attribute;

[0051] Exemplarily, multi-temporal remote sensing images of different geographical ranges are acquired through a remote sensing platform carried on a drone, and the multi-temporal remote sensing images have a time tag attribute and a ground area tag attribute. The time tag is the acquisition time node of the multi-temporal remote sensing image, and the ground area tag is the geographical range shown in the multi-temporal remote sensing image. The geographical range is set by pre-dividing the surface demarcation area, and one surface demarcation area corresponds to one geographical range;

[0052] S2. Based on the tag attributes, add image feature markers to the multi-temporal remote sensing images, and select the ground area tag attribute as the image stream guide to sort and arrange each image feature to obtain an image stream cluster;

[0053] Exemplarily, based on the order of the time tag serial numbers, the serial numbers of the multi-temporal remote sensing images are compiled, and the i-th multi-temporal remote sensing image is denoted as RS i ; when the a-th ground area tag G a The crop type planted under the i-th time tag is C e At this time, for the multi-temporal remote sensing image RS iAdditional image feature markers, denoted as RS i (G a , C e ), where e represents the number of the crop type;

[0054] Based on the image features, with the ground area label G a as the image stream guide, sort and arrange each image feature to obtain an image stream cluster, denoted as FL(G a ) = {RS i (G a , C e )|i ∈ [1, I], e ∈ [1, E]}; The sorting and arranging method includes initial sorting and optimization sorting, and the optimization sorting responds after the initial sorting is completed; The initial sorting is: initially arrange each image feature in ascending order of the crop type number, and the optimization sorting is: based on the result of the initial sorting, optimize the arrangement of each image feature in ascending order of the time label sequence number;

[0055] S3. Based on the image features, generate a feature state and characterize the feature state through a feature capture function;

[0056] Exemplarily, perform feature capture on the image feature RS i (G a , C e ) to generate a feature state, denoted as i:e, and based on the feature state, construct a feature capture function, denoted as f(y:x) = y, where x is the independent variable and its value corresponds to the number of the crop type, y is the dependent variable and its value corresponds to the time label sequence number. When the feature state is i:e, then f(y:x) = f(i:e) = i;

[0057] S4. Based on the image stream cluster and the feature capture function, analyze and calculate the change state value of land use;

[0058] Exemplarily, based on the image stream cluster and the feature capture function, analyze and calculate the change state value of land use

[0059] SV(G a ) represents the change state value of land use of the ground area label G a , j:(e + 1) represents the feature state corresponding to the image feature RS j (G a , C e+1 ), RS j represents the j-th multi-temporal remote sensing image, C e+1 represents the (e + 1)-th crop type, NUM[FL(G a) represents the total number of image features included in the image stream cluster FL(G a )

[0060] S5. Analyze and detect the correlation of land use features in different geographical ranges based on the change status value of land use to generate detection groups, and upload them to the detection log;

[0061] Exemplarily, analyze and detect the correlation of land use features in different geographical ranges based on the change status value of land use In the formula, FC(G a →G b ) represents the correlation of land use features between the ground area label G a and the ground area label G b , SV(G b ) represents the change status value of the land use of the ground area label G b , b is the number of the ground area label, and a≠b, μ represents the average value of the change status value of land use, and A represents the total number of ground ranges, σ 2 represents the variance of the change status value of land use, and

[0062] For a preset correlation threshold, if the land use feature correlation is greater than or equal to the correlation threshold, then a detection group is formed between the ground area label G a and the ground area label G b , and it is uploaded to the detection log, and the staff conducts on-site inspections according to the detection groups;

[0063] For example, the average value is 5. If the change status values SV(G a ) and SV(G b ) are 10 and 3 respectively, then SV(G a ) + SV(G b ) - 2μ is equal to 3. If the change status values SV(G a ) and SV(G a ) are 7 and 6 respectively, then SV(G a ) + SV(G b ) - 2μ is equal to 3, indicating that the land use behaviors of the two ground ranges are complementary or similar.

[0064] An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, is used to make the processor execute the computer program to implement a method for detecting land use changes based on remote sensing images according to the present invention;

[0065] Exemplarily, a computer storage medium may adopt any combination of one or more computer-readable media. The computer-readable media may be computer-readable signal media or computer-readable storage media. The computer-readable storage media may, for example, but not be limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, the computer-readable storage media may be any tangible medium that contains or stores a program, and this program may be used by or in conjunction with an instruction execution system, device, or component.

[0066] The computer-readable signal media may include data signals propagated in a baseband or as part of a carrier wave, in which computer-readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal media may also be any computer-readable media other than the computer-readable storage media, and this computer-readable media may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component.

[0067] The program codes contained on the computer-readable media may be transmitted by any suitable media, including but not limited to wireless, wire, optical cable, etc., or any suitable combination of the above. The computer program codes for performing the operations of the present invention may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages - such as Java, Smalltalk, C++, and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program codes may be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0068] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0069] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacement of some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for detecting land use changes based on remote sensing images, characterized in that, The method includes the following steps: S1. Add label attributes to the collected multi-temporal remote sensing images, where the label attributes include time label attributes and ground area label attributes; S2. Based on the label attributes, add image feature markers to the multi-temporal remote sensing images, and select the ground area label attribute as the image flow orientation to sort and arrange each image feature to obtain an image flow cluster; S3. Generate a feature state based on the image features, and characterize the feature state through a feature capture function; S4. Analyze and calculate the change state value of land use based on the image flow cluster and the feature capture function; S5. Analyze and detect the relevance of land use features in different geographical ranges based on the change state value of land use to generate a detection group, and upload it to the detection log.

2. The method for detecting land use change based on remote sensing images according to claim 1, wherein The specific implementation process of adding the label attributes includes: Collect multi-temporal remote sensing images of different geographical ranges through a remote sensing platform carried on a drone, and the multi-temporal remote sensing images have time label attributes and ground area label attributes. The time label is the acquisition time node of the multi-temporal remote sensing image, and the ground area label is the geographical range shown by the multi-temporal remote sensing image. The geographical range is set by pre-dividing the surface demarcation area, and one surface demarcation area corresponds to one geographical range.

3. A method for detecting land use changes based on remote sensing images according to claim 1, characterized in that, The generation method of the image flow cluster is: Based on the order of the time tag sequence numbers, sequence numbers of the multi-temporal remote sensing images are compiled, and the i-th multi-temporal remote sensing image is denoted as RS i ; when the a-th ground area tag G a the type of crop planted under the i-th time tag is C e , then an image feature mark is added to the multi-temporal remote sensing image RS i , denoted as RS i (G a , C e ), where e represents the number of the crop type; Based on the image features, with the ground area label G a as the image stream guide, sort and arrange each image feature to obtain an image stream cluster, denoted as FL(G a ) = {RS i (G a C e )|i ∈ [1, I], e ∈ [1, E]}; The sorting and arranging method includes initial sorting and arranging and optimized sorting and arranging, and the optimized sorting and arranging responds after the initial sorting and arranging is completed; The initial sorting and arranging is: initialize and arrange each image feature in ascending order of the crop type number, and the optimized sorting and arranging is: based on the result of the initial sorting and arranging, optimize and arrange each image feature in ascending order of the time label sequence number.

4. A method for detecting land use change based on remote sensing images according to claim 3, characterized in that The specific implementation process of characterizing the feature state through the feature capture function includes: For the image feature RS i (G a , C e ) perform feature capture and generate a feature state, denoted as i:e. Based on the feature state, construct a feature capture function, denoted as f(y:x) = y, where x is the independent variable and the value of x corresponds to the crop type number, y is the dependent variable and the value of y corresponds to the time tag serial number. When the feature state is i:e, then f(y:x) = f(i:e) = i.

5. A method for detecting land use change based on remote sensing images according to claim 4, characterized in that, The specific implementation process of analyzing and calculating the change state value of land use includes: Analyze and calculate the change status value of land use based on the image stream cluster and the feature capture function In the formula SV(G a ) represents the change status value of the land use of the ground area label G a , j:(e + 1) represents the image feature RS j (G a , C e+1 ) corresponding generated feature status, RS j represents the j-th multi-temporal remote sensing image, C e+1 represents the (e + 1)-th crop type, NUM[FL(G a )] represents the total number of image features included in the image stream cluster FL(G a ).

6. A method for detecting land use change based on remote sensing images according to claim 5, characterized in that The specific implementation process of generating the detection group includes: Based on the change status value of land use, analyze and detect the correlation of land use characteristics in different geographical ranges In the formula, FC(G a →G b ) represents the correlation of land use characteristics between ground area label G a and ground area label G b , SV(G b ) represents the change status value of the land use of ground area label G b , b is the number of the ground area label, and a≠b, μ represents the average value of the change status value of land use, and A represents the total number of ground ranges, σ 2 represents the variance of the change status value of land use, and Preset a correlation threshold. If the correlation of land use features is greater than or equal to the correlation threshold, then a detection group is formed between the ground area label G a and the ground area label G b and uploaded to the detection log. The staff conducts on-site inspections according to the detection group.

7. A land use change detection system based on remote sensing images, which executes a land use change detection method based on remote sensing images according to any one of claims 1-6, characterized in that, The system includes: a remote remote sensing module, an image data management module, and a cloud data analysis module; The remote remote sensing module is used to remotely control the drone and collect multi-temporal remote sensing images of the geographical range; The image data management module is used to add label attributes to the collected multi-temporal remote sensing images, perform image feature processing to generate an image flow cluster, and is also used to characterize the feature state corresponding to the image features through a feature capture function; The cloud data analysis module is used to analyze and calculate the change state value of land use, and is also used to analyze and detect the relevance of land use features in different geographical ranges to generate a detection group, and upload it to the detection log.

8. The land use change detection system based on remote sensing images according to claim 7, characterized in that: The method by which the remote remote sensing module is used to collect the multi-temporal remote sensing images is: collect multi-temporal remote sensing images of different geographical ranges through a remote sensing platform carried on a drone.

9. A land use change detection system based on remote sensing images according to claim 7, characterized in that: The label attributes include time label attributes and ground area label attributes. The time label is the acquisition time node of the multi-temporal remote sensing image, and the ground area label is the geographical range shown by the multi-temporal remote sensing image. The geographical range is set by pre-dividing the surface demarcation area, and one surface demarcation area corresponds to one geographical range; The image feature processing includes time label dimension processing, ground area label dimension processing, and crop type dimension processing, and respectively generates a time label serial number, a ground area label serial number, and a crop type number; Perform the initialization arrangement of each image feature in ascending order of the crop type numbers. After the completion of the initialization arrangement, perform the optimization arrangement on the result of the initialization arrangement in ascending order of the time tag sequence numbers. Generate the image stream clusters through the two methods of initialization arrangement and optimization arrangement.

10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, By means of computer-executable instructions, when the processor executes the computer program, implement a land use change detection method based on remote sensing images as described in any one of claims 1-6.

Images