Large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening-fine detection

Abstract

The invention discloses a large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening-fine detection, and the algorithm comprises the following steps: S1, collecting two large-scale cultivated land remote sensing images at the same position at different times, and carrying out the preprocessing of the images; cutting the preprocessed image to obtain a front time phase subimage group and a rear time phase subimage group; s2, selecting a histogram specification method to perform style unification on the front time phase subimage group and the rear time phase subimage group; s3, performing coarse screening on cultivated land change images to obtain a new image data set, wherein the cultivated land change images are a front time phase sub-image group and a rear time phase sub-image group; and S4, finely detecting and positioning the cultivated land change area in the new image data set to obtain the cultivated land change state. The problems that when an existing change detection method is used for detecting cultivated land changes, label information is difficult to obtain, cultivated land change areas are few, detection is difficult, and images are complex from collection to landing application are solved.

Description

[Technical field]

[0001] The present invention belongs to the technical field of cultivated land change detection, and in particular relates to a large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening and fine inspection. [Background technology]

[0002] Land resources are the material basis for human survival and development. Studying cultivated land and its temporal and spatial changes, and gaining an in-depth understanding of the current status of regional cultivated land resources and the causes of cultivated land changes, play an important role in revealing the laws of cultivated land changes, ensuring food security, and promoting social stability. As a highly practical remote sensing analysis technology, the purpose of change detection is to find interesting change information and filter out irrelevant change information as interference factors. It has been widely used in various fields such as land cover and land use change analysis, urban planning, forest status monitoring, and disaster assessment.

[0003] With the continuous development of convolutional neural networks, many deep learning-based methods have been applied to the field of change detection in recent years. Depending on whether the training data contains label information, it can be divided into supervised change detection methods and unsupervised change detection methods. Supervised methods have achieved accurate change detection in urban planning, environmental monitoring and other fields with their high-precision classification capabilities; while unsupervised methods have shown strong practicality in scenarios such as remote sensing image processing and anomaly detection due to their advantage of not requiring label information. However, both methods face challenges such as data acquisition and computational complexity in their applications, and need to be selected and improved based on specific needs to promote the further development of change detection technology.

[0004] In recent years, remote sensing technology is developing towards multi-sensor, multi-platform, multi-angle, high spatial resolution, high spectral resolution, and high temporal resolution. The image data available every day is increasing in TB units. For the current large-scale and large-scale cultivated land detection, the above methods have the following disadvantages:

[0005] (1) Difficulty in obtaining label information: Due to the diversity and complexity of land cover types, it is particularly difficult to obtain sufficient and representative label information. This not only involves the investment of manpower and material resources, but also involves the guarantee of labeling quality and consistency. At the same time, due to the seasonal changes of cultivated land and the differences between different regions, the acquisition of labeled samples also needs to consider temporal and spatial factors, which further increases the difficulty and cost of labeling.

[0006] (2) There are few areas of farmland change and detection is difficult: The relative stability and periodic changes of farmland make the number of areas that actually change relatively small. This results in the number of positive samples (i.e., changed areas) being far less than the number of negative samples (i.e., unchanged areas) when training deep learning models, making it difficult for the model to effectively learn the characteristics of the changes. In addition, due to the subtlety and complexity of farmland changes, even if there are changes, they may be difficult to detect accurately due to the influence of multiple factors (such as climate, crop types, planting methods, etc.).

[0007] (3) The image acquisition and application process are complex: Remote sensing images usually have high resolution and contain a large amount of geographic information. For specific application scenarios, the original images often need to go through a series of processing steps before they can be applied to extract the geographic area of ​​interest and focus on the detailed features of the area of ​​interest. [Summary of the invention]

[0008] The purpose of the present invention is to provide a large-scale remote sensing fragmented farmland change detection algorithm based on coarse screening and fine inspection, so as to solve the problems of difficulty in obtaining label information, small number of farmland change areas and difficulty in detection, and complex image acquisition and application when existing change detection methods are used to detect farmland changes.

[0009] The present invention adopts the following technical solution: a large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening and fine inspection, comprising the following steps:

[0010] Step S1, collecting two large-scale remote sensing images of cultivated land at the same location at different times, the two large-scale remote sensing images of cultivated land being a front phase image and a back phase image respectively; pre-processing the front phase image and the back phase image respectively;

[0011] Then the pre-processed front-phase image and the back-phase image are cropped according to the selected size to obtain two groups of small-sized cultivated land remote sensing images; the two groups of small-sized cultivated land remote sensing images are respectively the front-phase sub-image group and the back-phase sub-image group;

[0012] Step S2, selecting a histogram normalization method to unify the styles of the front-phase sub-image group and the back-phase sub-image group;

[0013] Step S3, roughly screening the cultivated land change image to obtain a new image data set, wherein the cultivated land change image comprises a pre-phase sub-image group and a post-phase sub-image group;

[0014] Step S4: finely detect and locate the cultivated land change area in the new image data set to obtain the cultivated land change status.

[0015] Furthermore, the specific method of step S3 is:

[0016] Step 311: by adopting a feature extraction algorithm, under the same algorithm, extracting features of the same dimension from all sub-images in the new front-phase sub-image group and the back-phase sub-image group, the features of the front-phase image and the back-phase image can be expressed as an N×K matrix, wherein N is the feature dimension and K is the number of sub-images;

[0017] Step 312: Take the i-th sub-image feature in the later-phase sub-image group as the object to be reconstructed, and select k sub-image features around the previous-phase sub-image feature at the position corresponding to the i-th sub-image feature in the later-phase group. 2 The image features are used to construct a dictionary to achieve sparse reconstruction;

[0018] Step 313: Calculate the reconstruction error according to formula (1), and sort the reconstruction errors from large to small. The larger the error, the higher the possibility of change. That is, sort according to the reconstruction error and discard the image pairs with an error less than the error threshold. The remaining images are the new image data set.

[0019]

[0020] Among them, ||·||2 is the l2-norm, ε is the error threshold. If the error threshold is less than the error threshold, it can be considered as no change. The number of words in the dictionary M = k 2 ≤K, K is the number of sub-images obtained after cropping each large-scale farmland remote sensing image, k is the width of the surrounding neighborhood, x i is a sparse representation matrix.

[0021] Furthermore, the specific method of step S3 is:

[0022] Step 321: grayscale all sub-images in the new front-phase sub-image group and the back-phase sub-image group, and then form a front-phase sub-image group matrix and a back-phase sub-image group matrix accordingly;

[0023] Step 322: using PCA to reduce the dimensions of the matrix of the front-phase sub-image group and the matrix of the back-phase sub-image group to the same N-dimension, and obtaining the front-phase sub-image group key feature matrix A and the back-phase sub-image group key feature matrix B after the dimension reduction;

[0024] Step 323: According to formulas (2) to (4), the corresponding positions of the key feature matrix A of the previous phase sub-image group and the key feature matrix B of the next phase sub-image group are subtracted to obtain the key feature difference matrix C;

[0025] Then, the key features are made into a difference matrix C, and the absolute values ​​are summed up by column to obtain the key feature difference threshold matrix D. The matrix is ​​sorted according to the absolute value sum results, and the image pairs whose absolute value sum results are less than the difference threshold are removed; the remaining images are the new image data set;

[0026]

[0027] in, δ is the difference threshold, below which the change is negligible; A and B are the key feature matrices of the pre-phase sub-image group and the post-phase sub-image group, respectively; C is the key feature difference matrix; D is the key feature difference threshold matrix; N is the pre-phase sub-image group matrix and the post-phase sub-image group matrix, the two image matrices are reduced to the same dimension respectively; K is the number of sub-images obtained after cropping each pre-phase image or post-phase image; δ is the difference threshold.

[0028] Furthermore, the specific method of step S2 is:

[0029] Firstly, the grayscale histograms of the front-phase sub-image group and the back-phase sub-image group are analyzed to obtain the brightness and contrast distribution of the front-phase sub-image group and the back-phase sub-image group;

[0030] Secondly, according to the histogram of the subsequent phase sub-image group and the histogram of the previous phase sub-image group, the pixel value of the previous phase sub-image group is mapped to a new value through a mapping function, so that the new value is within the dynamic range of the histogram of the subsequent phase sub-image group;

[0031] Finally, the mapping function is applied to each pixel of the previous phase sub-image group to generate a new previous phase sub-image group.

[0032] Furthermore, the specific method of step S4 is:

[0033] Step 4.1: Feature extraction

[0034] The paired image data in the new image data obtained after the rough screening in step 2 is used as input, and the spatial features of the image are extracted through a series of convolutional layers; the maximum pooling or average pooling layer is used to downsample the features to retain the main feature information; activation functions such as ReLU are used to increase the nonlinearity of the features; and the feature map of the front phase sub-image and the feature map of the back phase sub-image are obtained;

[0035] Step 4.2: Change Extraction

[0036] Align the feature map of the front phase sub-image and the feature map of the back phase sub-image obtained in step 4.1; calculate the difference between the feature map of the front phase sub-image and the feature map of the back phase sub-image to obtain a change feature map; perform threshold processing on the change feature map;

[0037] Step 4.3: Generate a change graph

[0038] The change feature map is input into a classification network to generate a probability map of changed and unchanged areas; and the probability map is threshold segmented to obtain a binary change map.

[0039] The beneficial effects of the present invention are as follows: First, the present invention targets the non-change areas of interest that are widely present in remote sensing images of cultivated land. The present invention introduces two efficient coarse detection algorithms, which can quickly eliminate those areas that are irrelevant to the target of interest or have insignificant changes, thereby improving the overall analysis efficiency. Secondly, in view of the problem of insufficient unlabeled or labeled training samples that are prevalent in remote sensing image analysis, the coarse screening module of the present invention does not rely on sample labels, and the fine detection module adopts an unsupervised or weakly supervised learning model to complete the detection of change areas by extracting and learning the intrinsic features of the image. Finally, in view of the application complexity of images from acquisition to landing, the coarse screening module quickly identifies and screens images of non-cultivated land changes, and the fine detection module specifically extracts and locates the areas of interest. The cascade processing of the two modules realizes full-process change detection. This innovation not only solves the problem of lack of labeled data, but also makes the change detection algorithm more versatile and flexible, and can adapt to remote sensing image analysis tasks of different scenarios and needs.

Brief Description of the Drawings

[0040] Figure 1 A diagram of a rough screening method for characterizing changes by reconstructing characteristic errors according to the present invention;

[0041] Figure 2 A diagram of a coarse screening method for characterizing changes in key characteristic errors according to the present invention;

[0042] Figure 3 A diagram of the method for fine detection and positioning of cultivated land change areas according to the present invention. [Specific implementation method]

[0043] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] The present invention provides a large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening and fine inspection, comprising the following steps:

[0045] Step S1, collecting two large-scale remote sensing images of cultivated land at the same location at different times, the two large-scale remote sensing images of cultivated land being a front phase image and a back phase image respectively; preprocessing the front phase image and the back phase image respectively; the preprocessing includes geometric correction and image registration;

[0046] Then the pre-processed front-phase image and the back-phase image are cropped according to the selected size to obtain two groups of small-sized cultivated land remote sensing images; the two groups of small-sized cultivated land remote sensing images are respectively the front-phase sub-image group and the back-phase sub-image group;

[0047] Step S2, selecting a histogram normalization method to unify the styles of the front-phase sub-image group and the back-phase sub-image group;

[0048] Step S3, roughly screening the cultivated land change image to obtain a new image data set, wherein the cultivated land change image comprises a pre-phase sub-image group and a post-phase sub-image group;

[0049] Step S4: finely detect and locate the cultivated land change area in the new image data set to obtain the cultivated land change status.

[0050] The present invention aims to detect changes in cultivated land using a strategy of "rough screening" followed by "fine inspection". The differences between the sub-image groups of the previous and next phases are analyzed and quantified using traditional machine methods, and the sub-image pairs with relatively small differences are discarded. The purpose is to quickly identify areas with obvious changes, reduce the amount of data for subsequent processing, and improve efficiency; in the fine inspection stage, the reserved image pairs are carefully inspected using deep learning methods, and changes in the damaged areas of cultivated land are located.

[0051] The proposed change detection method based on dual modules of "rough screening" followed by "fine inspection" makes it possible to use the original remote sensing images (large-size before and after phase images) directly for detection. The rough screening module first acts on the original remote sensing images (large-size before and after phase images), using efficient algorithms to quickly identify and screen images of non-arable land changes. This step effectively reduces the amount of data for subsequent processing and preliminarily excludes a large amount of irrelevant information. Subsequently, the fine detection module conducts in-depth analysis of the candidate change areas in the rough screening results, and uses a deep learning model to carefully classify and verify the candidate areas to ensure the accuracy and reliability of the detection results.

[0052] Guided by practical application needs, regarding the problem of difficulty in obtaining sample change labels in images, the coarse screening module uses traditional methods to analyze and quantify the differences between the previous and subsequent phase images, completely abandoning the dependence on labels; while the fine detection module can consider adopting an unsupervised or weakly supervised learning model, using a small amount of incomplete or noisy label information to guide model learning, thereby reducing dependence on labels while achieving good change detection effects.

[0053] In some embodiments, Figure 1 As shown, the first rough screening method in step S3 is to characterize the change by reconstruction error, and the specific process is as follows:

[0054] Step 311: by adopting a feature extraction algorithm, under the same algorithm, extracting features of the same dimension from all sub-images in the new front-phase sub-image group and the back-phase sub-image group, the features of the front-phase image and the back-phase image can be expressed as an N×K matrix, wherein N is the feature dimension and K is the number of sub-images;

[0055] Step 312: Take the i-th sub-image feature in the later-phase sub-image group as the object to be reconstructed, and select k sub-image features around the previous-phase sub-image feature at the position corresponding to the i-th sub-image feature in the later-phase group. 2 The dictionary is constructed based on the features of each image to achieve sparse reconstruction of the features of the i-th sub-image in the subsequent phase sub-image group.

[0056] Step 313: Calculate the reconstruction error according to formula (1) and sort the reconstruction errors from large to small. The larger the error, the higher the possibility of change. That is, sort according to the reconstruction error, and discard the image pairs with an error less than the error threshold. The remaining images are the new image data set.

[0057]

[0058] Among them, ||·||2 is the l2-norm, ε is the error threshold. If the error threshold is less than the error threshold, it can be considered as no change. The number of words in the dictionary M = k 2 ≤K, K is the number of sub-images obtained after cropping each original image, k is the width of the surrounding neighborhood, x i is a sparse representation matrix.

[0059] This method focuses on identifying features that are sparsely distributed in the data set but may have significant significance. It can quickly determine the situation where the sparse characteristics in the cultivated land image have changed significantly, so as to quickly screen out the cultivated land images that need further analysis. The advantage of this method is that it is highly efficient and suitable for processing large-scale data sets. It can preliminarily screen out areas of potential changes in a short time, saving a lot of computing resources for subsequent fine analysis. In addition, sparse features are often associated with anomalies or special phenomena in the data. In cultivated land monitoring, significant changes in sparse features may indicate changes in land use and degradation of soil quality. This method is usually insensitive to noise, helps to reduce misjudgments, and has a high sensitivity for timely detection of cultivated land problems.

[0060] In some embodiments, Figure 2 As shown, the second rough screening method in step S3 is to characterize the change based on the key feature difference, and the specific process is as follows:

[0061] Step 321: grayscale all sub-images in the new front-phase sub-image group and the back-phase sub-image group, and then form a front-phase sub-image group matrix and a back-phase sub-image group matrix accordingly;

[0062] Step 322: PCA is used to reduce the dimensions of the matrix of the front-phase sub-image group and the matrix of the back-phase sub-image group to the same N-dimension, and the front-phase sub-image group key feature matrix A and the back-phase sub-image group key feature matrix B after the dimension reduction are obtained, so as to highlight the key information and exclude the interference information; PCA is a principal component analysis method; PCA is a principal component analysis method;

[0063] Step 323: According to formulas (2) to (4), the corresponding positions of the key feature matrix A of the previous phase sub-image group and the key feature matrix B of the next phase sub-image group are subtracted to obtain the key feature difference matrix C;

[0064] Then, the key features are made into a difference matrix C, and the absolute values ​​are summed up by column to obtain the key feature difference threshold matrix D. The matrix is ​​sorted according to the absolute value sum results, and the image pairs whose absolute value sum results are less than the difference threshold are removed; the remaining images are the new image data set;

[0065]

[0066] in, δ is the difference threshold, below which the change is negligible; A and B are the key feature matrices of the pre-phase sub-image group and the post-phase sub-image group, respectively; C is the key feature difference matrix; D is the key feature difference threshold matrix; N is the pre-phase sub-image group matrix and the post-phase sub-image group matrix, the two image matrices are reduced to the same dimension respectively; K is the number of sub-images obtained after cropping each pre-phase image or post-phase image; δ is the difference threshold.

[0067] The second method focuses on the extraction of key features, which can identify features that have a significant impact on the surface morphology or structural changes of cultivated land. These features are usually closely related to factors such as crop growth conditions, soil quality, topography, and landforms. This method is suitable for detailed analysis of physical or morphological changes in cultivated land and can capture small but important surface changes. Compared with sparse feature analysis, this method pays more attention to details, so it is more reliable for judging image changes.

[0068] In some embodiments, the specific method of step S2 is:

[0069] Firstly, the grayscale histograms of the front-phase sub-image group and the back-phase sub-image group are analyzed to obtain the brightness and contrast distribution of the front-phase sub-image group and the back-phase sub-image group;

[0070] Secondly, according to the histogram of the subsequent phase sub-image group and the histogram of the previous phase sub-image group, the pixel value of the previous phase sub-image group is mapped to a new value through a mapping function, so that the new value is within the dynamic range of the histogram of the subsequent phase sub-image group;

[0071] Finally, the mapping function is applied to each pixel of the previous phase sub-image group to generate a new previous phase sub-image group.

[0072] In some embodiments, Figure 3 As shown, the specific method of step S4 is:

[0073] Step 4.1: Feature extraction

[0074] The paired image data in the new image data set obtained after the rough screening in step 2 is used as input, and the paired image data is the front phase sub-image and the back phase sub-image, and the spatial features of the image are extracted through a series of convolutional layers;

[0075] Use the maximum pooling or average pooling layer to downsample features and retain the main feature information;

[0076] Use activation functions such as ReLU to increase the nonlinearity of features; obtain feature maps of the previous phase sub-image and feature maps of the next phase sub-image for subsequent change extraction;

[0077] Step 4.2: Change Extraction

[0078] Align the feature map of the front-phase sub-image and the feature map of the back-phase sub-image obtained in step 4.1 to ensure the consistency of corresponding pixel positions; calculate the difference between the feature map of the front-phase sub-image and the feature map of the back-phase sub-image to obtain a change feature map; perform threshold processing on the change feature map to extract significant change areas; and use an attention mechanism to strengthen attention to change areas and improve the accuracy of change detection.

[0079] Step 4.3: Generate a change graph

[0080] The change feature map is input into a classification network to generate a probability map of changed and unchanged areas; the probability map is threshold segmented to obtain a binary change map, from which the change status of the cultivated land can be known.

[0081] Example

[0082] The effects of the present invention can be further illustrated by the following experimental results and analysis:

[0083] 1. Experimental data: The experimental data of the present invention are 2 pairs of optical remote sensing images located in Shangyu District, Shaoxing City, Zhejiang Province. The acquisition satellites are Gaofen 1B and Beijing 2 respectively. The sizes of the experimental areas are 40598×35178 and 21243×19041 respectively. During the experiment, they are uniformly cropped to 512×512 size to form their respective sub-image groups.

[0084] 2. Experimental methods

[0085] Two methods proposed by the present invention:

[0086] (1) A coarse screening method that uses reconstruction feature errors to characterize changes;

[0087] (2) A coarse screening method that uses key feature errors to characterize changes.

[0088] Table 1 Comparison of the results of rough screening methods of optical remote sensing images of Shangyu District (taken by Gaofen 1B)

[0089]

[0090]

[0091] Table 2 Comparison of the results of rough screening methods of optical remote sensing images of Shangyu District (photographed by Beijing No. 2)

[0092]

[0093] As can be seen from Tables 1 and 2, as the number of words k in the dictionary increases 2 Or the image removal rate of the two coarse screening methods increases as the value of the dimension N is increased. In the ShangYu-GF1b dataset, when k 2 =7×7 or N=512, the image removal rate reaches the maximum, which is 37.07% and 46.59% respectively. In the ShangYu-BJ2 dataset, when k 2 When N=9×9 and N=1024, the image removal rates are 15.79% and 19.80%.

[0094] Therefore, the above analysis shows that the two coarse screening methods proposed in the present invention can both screen out sub-images without any cultivated land changes, which indicates that the method proposed in the present invention is effective and can provide a suitable new image data set for subsequent change detection to achieve precise detection and positioning of cultivated land change areas, thereby obtaining the cultivated land change status.

Claims

1. A large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening and fine inspection, characterized by: The following steps are involved: Step S1, collecting two large-scale remote sensing images of cultivated land at the same location at different times, the two large-scale remote sensing images of cultivated land being a front phase image and a back phase image respectively; pre-processing the front phase image and the back phase image respectively; Then the pre-processed front-phase image and the back-phase image are cropped according to the selected size to obtain two groups of small-sized cultivated land remote sensing images; the two groups of small-sized cultivated land remote sensing images are respectively the front-phase sub-image group and the back-phase sub-image group; Step S2, selecting a histogram normalization method to unify the styles of the front-phase sub-image group and the back-phase sub-image group; Step S3, roughly screening the cultivated land change image to obtain a new image data set, wherein the cultivated land change image comprises a pre-phase sub-image group and a post-phase sub-image group; Step S4: finely detect and locate the cultivated land change area in the new image data set to obtain the cultivated land change status.

2. The large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening and fine inspection as claimed in claim 1 is characterized in that: The specific method of step S3 is: Step 311: by adopting a feature extraction algorithm, under the same algorithm, extracting features of the same dimension from all sub-images in the new front-phase sub-image group and the back-phase sub-image group, the features of the front-phase image and the back-phase image can be expressed as an N×K matrix, wherein N is the feature dimension and K is the number of sub-images; Step 312: Take the i-th sub-image feature in the later-phase sub-image group as the object to be reconstructed, and select k sub-image features around the previous-phase sub-image feature at the position corresponding to the i-th sub-image feature in the later-phase group. 2 The image features are used to construct a dictionary to achieve sparse reconstruction; Step 313: Calculate the reconstruction error according to formula (1), and sort the reconstruction errors from large to small. The larger the error, the higher the possibility of change. That is, sort according to the reconstruction error and discard the image pairs with an error less than the error threshold. The remaining images are the new image data set. Among them, ||·||2 is -norm, ε is the error threshold. If the error threshold is less than the error threshold, it can be considered as no change. The number of words in the dictionary M = k 2 ≤K, K is the number of sub-images obtained after cropping each large-scale farmland remote sensing image, k is the width of the surrounding neighborhood, x i is a sparse representation matrix.

3. The large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening and fine inspection as claimed in claim 1 is characterized in that: The specific method of step S3 is: Step 321: grayscale all sub-images in the new front-phase sub-image group and the back-phase sub-image group, and then form a front-phase sub-image group matrix and a back-phase sub-image group matrix accordingly; Step 322: using PCA to reduce the dimensions of the matrix of the front-phase sub-image group and the matrix of the back-phase sub-image group to the same N-dimension, and obtaining the front-phase sub-image group key feature matrix A and the back-phase sub-image group key feature matrix B after the dimension reduction; Step 323: According to formulas (2) to (4), the corresponding positions of the key feature matrix A of the previous phase sub-image group and the key feature matrix B of the next phase sub-image group are subtracted to obtain the key feature difference matrix C; Then, the key features are made into a difference matrix C, and the absolute values ​​are summed up by column to obtain the key feature difference threshold matrix D. The matrix is ​​sorted according to the absolute value sum results, and the image pairs whose absolute value sum results are less than the difference threshold are removed; the remaining images are the new image data set; in, δ is the difference threshold, below which the change is negligible; A and B are the key feature matrices of the pre-phase sub-image group and the post-phase sub-image group, respectively; C is the key feature difference matrix; D is the key feature difference threshold matrix; N is the pre-phase sub-image group matrix and the post-phase sub-image group matrix, the two image matrices are reduced to the same dimension respectively; K is the number of sub-images obtained after cropping each pre-phase image or post-phase image; δ is the difference threshold.

4. The large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening and fine inspection as claimed in claim 2 or 3, characterized in that: The specific method of step S2 is: Firstly, the grayscale histograms of the front-phase sub-image group and the back-phase sub-image group are analyzed to obtain the brightness and contrast distribution of the front-phase sub-image group and the back-phase sub-image group; Secondly, according to the histogram of the subsequent phase sub-image group and the histogram of the previous phase sub-image group, the pixel value of the previous phase sub-image group is mapped to a new value through a mapping function, so that the new value is within the dynamic range of the histogram of the subsequent phase sub-image group; Finally, the mapping function is applied to each pixel of the previous phase sub-image group to generate a new previous phase sub-image group.

5. The large-scale remote sensing fragmented cultivated land change detection algorithm based on coarse screening and fine inspection as claimed in claim 2 or 3, characterized in that: The specific method of step S4 is: Step 4.1: Feature extraction The paired image data in the new image data obtained after the rough screening in step 2 is used as input, and the spatial features of the image are extracted through a series of convolutional layers; the maximum pooling or average pooling layer is used to downsample the features to retain the main feature information; activation functions such as ReLU are used to increase the nonlinearity of the features; and the feature map of the front phase sub-image and the feature map of the back phase sub-image are obtained; Step 4.2: Change Extraction Align the feature map of the front phase sub-image and the feature map of the back phase sub-image obtained in step 4.1; calculate the difference between the feature map of the front phase sub-image and the feature map of the back phase sub-image to obtain a change feature map; perform threshold processing on the change feature map; Step 4.3: Generate a change graph The change feature map is input into a classification network to generate a probability map of changed and unchanged areas; and the probability map is threshold segmented to obtain a binary change map.

Images