Abandoned land block identification method and system based on crop type change

Abstract

The embodiment of the invention provides an abandoned land block identification method and system based on crop type change, and belongs to the technical field of image processing. The method comprises the following steps: preprocessing a multi-temporal remote sensing image to obtain a preprocessed image, and generating plot time sequence samples corresponding to plots on the basis of cadastre vector boundaries; extracting a multi-dimensional feature vector; identifying a crop type label, constructing a crop type change sequence, and obtaining an operation state initial judgment result based on a land parcel judgment model; and correcting the operation state initial judgment result based on a preset confusion resolution rule set, and outputting an abandoned land block recognition result. According to the scheme of the invention, the crop type change sequence is constructed, the multi-dimensional feature vector is combined, and the discrimination model and the confusion resolution rule are combined for processing, so that high-precision recognition of the abandoned land parcel is realized, and misjudgment of fallow, multiple cropping and disaster damage situations is effectively avoided.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and more specifically to a method and system for identifying abandoned land plots based on crop type changes. Background Technology

[0002] With the development of remote sensing monitoring methods, using multi-temporal satellite imagery to determine farmland use status has become an important method for land resource management and agricultural production supervision. In existing technologies, vegetation indices or time-series variation curves are typically calculated from remote sensing data acquired at different farming seasons to identify whether farmland is in a normal planting state. However, methods based on single spectral indicators or simple thresholds have significant shortcomings in practical applications.

[0003] Existing methods have limitations in distinguishing between abandoned land and policy-mandated fallow land. Abandoned land often exhibits low vegetation cover or bare land characteristics due to abandonment, while policy-mandated fallow land will also show low vegetation cover for a period of time. The two are highly similar in spectral characteristics and temporal variation curves. If only vegetation index thresholds are relied upon for judgment, fallow land can easily be misidentified as abandoned land, thereby affecting the accuracy of land use statistics and potentially causing deviations in the implementation of agricultural management policies.

[0004] Existing methods also carry the risk of misjudgment when dealing with anomalies caused by single-season disasters. For example, natural disasters such as floods or droughts can lead to reduced or even total crop yields in the current season, which is reflected in remote sensing imagery as vegetation indices failing to reach their peak or declining midway. In traditional time-series monitoring methods, such damaged areas are often directly classified as abandoned land, ignoring the fact that they may be able to resume normal planting in the next season. This not only reduces the accuracy of the identification results but may also mislead the assessment of agricultural production potential and post-disaster recovery capacity.

[0005] Therefore, how to effectively distinguish between abandoned and fallow land during remote sensing image monitoring, and avoid misjudging single-season disaster-damaged plots as abandoned land, is a technical problem that urgently needs to be solved in the field of farmland use status identification. Summary of the Invention

[0006] The purpose of this invention is to provide a method and system for identifying abandoned land based on crop type changes, so as to at least solve the problems in the prior art of difficulty in distinguishing abandoned and fallow land, and the easy misjudgment of single-season disaster-damaged land as abandoned land.

[0007] To achieve the above objectives, the first aspect of the present invention provides a method for identifying abandoned land parcels based on crop type changes. The method includes: acquiring multi-temporal remote sensing images and cadastral vector boundaries of a target area; performing preprocessing on the multi-temporal remote sensing images to obtain preprocessed images; and performing spatial registration and vector masking cropping on the preprocessed images based on the cadastral vector boundaries to generate land parcel time series samples corresponding to each parcel; extracting multi-dimensional feature vectors of the land parcels, including spectral features, temporal features, and spatial structural features, from the land parcel time series samples within a preset phenological window; identifying crop type labels for each temporal phase in the land parcel time series samples based on a temporal segmentation network, constructing a crop type change sequence, and inputting the crop type change sequence and the land parcel multi-dimensional feature vectors into a land parcel discrimination model to obtain a preliminary judgment result of the management status; and correcting the preliminary judgment result of the management status based on a preset confusion resolution rule set to output the abandoned land parcel identification result.

[0008] Optionally, the preprocessing rules for the multi-temporal remote sensing images are as follows: radiometric calibration, atmospheric correction, and geometric correction are performed sequentially on the multi-temporal remote sensing images to obtain preprocessed images with spectral comparability and spatial consistency between images of different times; wherein, radiometric calibration is used to convert the original pixel values ​​into physical reflectance; atmospheric correction is used to eliminate the interference of atmospheric scattering and absorption on the spectral curve; and geometric correction is used to spatially align each temporal image with the cadastral vector boundary.

[0009] Optionally, spatial registration and vector mask cropping are performed on the preprocessed image based on the cadastral vector boundary to generate land parcel time series samples corresponding to each parcel. This includes: performing coordinate system and geometric registration between the cadastral vector boundary and the preprocessed image to ensure a one-to-one correspondence between the parcel boundary and image pixels; applying the cadastral vector boundary to the registered image to perform vector masking operations, removing non-parcel region pixels, and retaining only the set of pixels consistent with the parcel boundary range; and grouping the pixel set according to the parcel identifier of the cadastral vector boundary to form land parcel time series samples corresponding to each parcel.

[0010] Optionally, within a preset phenological window, a multidimensional feature vector of the land parcel, including spectral features, temporal features, and spatial structure features, is extracted from the temporal samples of the land parcel. This includes: calculating a spectral index curve based on the pixel reflectance sequence of the temporal samples of the land parcel within the phenological window, and using the spectral index curve as a spectral feature; extracting trend information and key node information of crop growth stages based on the temporal series changes of the temporal samples of the land parcel within the phenological window, and using the trend information and the node information as temporal features; extracting boundary compactness and internal spatial texture parameters based on the image texture distribution and cadastral vector boundary morphology of the temporal samples of the land parcel, and using the boundary compactness and the internal spatial texture parameters as spatial structure features; and fusing the spectral features, the temporal features, and the spatial structure features to obtain a multidimensional feature vector.

[0011] Optionally, a multidimensional feature vector is obtained by fusing the spectral features, the temporal features, and the spatial structure features, including: performing normalization processing on the spectral features, the temporal features, and the spatial structure features respectively; concatenating or weighting the normalized features according to preset weights along the feature dimension to form a fused feature matrix; and extracting key feature components from the fused feature matrix using a dimensionality reduction algorithm or feature selection method to obtain the final multidimensional feature vector.

[0012] Optionally, the crop type labels of each time phase in the temporal samples of the land parcels are identified based on a temporal segmentation network, and a crop type change sequence is constructed. This includes: inputting the temporal samples of the land parcels into a trained temporal segmentation network, performing pixel-by-pixel classification on the pixels of each time phase image, and outputting the corresponding crop type labels; aggregating the crop type labels according to the cadastral vector boundaries to generate crop type results corresponding to each land parcel; and encoding the crop type results of each time phase in chronological order to form a crop type change sequence used to characterize the crop evolution process.

[0013] Optionally, the crop type change sequence and the plot multidimensional feature vector are jointly input into the plot discrimination model to obtain a preliminary judgment result of the management status. This includes: performing time-series encoding on the crop type change sequence to generate a time-series embedding vector representing the crop evolution process; performing feature mapping on the plot multidimensional feature vector to generate a comprehensive feature embedding representing the plot's spectral information, time-series information, and spatial structure information; fusing the time-series embedding vector and the comprehensive feature embedding in a unified feature space and passing it as input to the plot discrimination model; and the plot discrimination model outputs a preliminary judgment result of the management status based on the fused input.

[0014] Optionally, the training rules for the land parcel discrimination model are as follows: collect historical land parcel time-series samples with land parcel management status labels, wherein the historical land parcel time-series samples simultaneously contain the corresponding crop type change sequence and the land parcel multi-dimensional feature vector; use the crop type change sequence and the land parcel multi-dimensional feature vector as input, and use the land parcel management status label as a supervision signal to perform supervised learning training on the land parcel discrimination model; introduce boundary constraint loss and temporal consistency loss during the training process, and obtain the land parcel discrimination model after training convergence.

[0015] Optionally, the preliminary judgment result of the management status is corrected based on a preset confusion resolution rule set, and the result of the abandoned land identification is output. This includes: the confusion resolution rule set predefines multiple cropping discrimination rules, fallow discrimination rules, and disaster damage detection rules, and stores them in a rule base; the preliminary judgment result of the management status is compared with the crop type change sequence and the multidimensional feature vector of the land plot, and the confusion resolution rule set is called to verify them one by one; if the multiple cropping discrimination rule is satisfied, the preliminary judgment result of the management status is corrected to multiple cropping status; if the fallow discrimination rule is satisfied, the preliminary judgment result of the management status is corrected to fallow status; if the disaster damage detection rule is satisfied, the preliminary judgment result of the management status is corrected to disaster damage status; if none of the multiple cropping discrimination rules, fallow discrimination rules, and disaster damage detection rules are satisfied, the preliminary judgment result of the management status is confirmed as abandoned status, and the result of the abandoned land identification is output.

[0016] A second aspect of the present invention provides a system for identifying abandoned land parcels based on crop type changes. The system includes: an acquisition unit, configured to acquire multi-temporal remote sensing images and cadastral vector boundaries of a target area, perform preprocessing on the multi-temporal remote sensing images to obtain preprocessed images, and perform spatial registration and vector mask cropping on the preprocessed images based on the cadastral vector boundaries to generate land parcel time-series samples corresponding to each parcel; a feature extraction unit, configured to extract multi-dimensional feature vectors of land parcels, including spectral features, temporal features, and spatial structural features, from the land parcel time-series samples within a preset phenological window; a judgment unit, configured to identify crop type labels for each temporal phase in the land parcel time-series samples based on a temporal segmentation network, construct a crop type change sequence, and input the crop type change sequence and the land parcel multi-dimensional feature vectors into a land parcel discrimination model to obtain a preliminary judgment result of the management status; and an output unit, configured to correct the preliminary judgment result of the management status based on a preset confusion resolution rule set and output the abandoned land parcel identification result.

[0017] Through the above technical solution, this invention achieves accurate acquisition of plot-level temporal samples by registering and cropping multi-temporal remote sensing images with cadastral vector boundaries, ensuring the consistency of data spatial positioning. By comprehensively extracting spectral, temporal, and spatial structural features within a phenological window, the growth status of plots can be fully characterized, providing multi-dimensional evidence for subsequent analysis. Combining crop type labels output by the temporal segmentation network to form a crop type change sequence, and inputting it along with multi-dimensional feature vectors into the plot discrimination model, effectively improves the accuracy of identifying plot management status. Finally, by correcting the initial management status judgment results through a set of confusion resolution rules, it avoids misjudging fallow, replanting, or disaster-damaged land as abandoned land, thereby achieving accurate identification of abandoned plots and ensuring the reliability and practicality of monitoring results.

[0018] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0019] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of the steps of a method for identifying abandoned land plots based on crop type changes provided in one embodiment of the present invention; Figure 2 This is a schematic diagram of generating a set of land parcel pixels by clipping cadastral vector boundaries according to one embodiment of the present invention; Figure 3 This is a system structure diagram of an abandoned land identification system based on crop type changes provided in one embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0021] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0022] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0023] Figure 1 This is a flowchart of a method for identifying abandoned land plots based on crop type changes, provided by one embodiment of the present invention. Figure 1 As shown, this invention provides a method for identifying abandoned land plots based on crop type changes, the method comprising: Step S1: Acquire multi-temporal remote sensing images and cadastral vector boundaries of the target area, perform preprocessing on the multi-temporal remote sensing images to obtain preprocessed images, and perform spatial registration and vector mask cropping on the preprocessed images based on the cadastral vector boundaries to generate land parcel time series samples corresponding to each land parcel.

[0024] Specifically, the preprocessing rules for the multi-temporal remote sensing images are as follows: radiometric calibration, atmospheric correction, and geometric correction are performed sequentially on the multi-temporal remote sensing images to obtain preprocessed images with spectral comparability and spatial consistency between images of different times; wherein, radiometric calibration is used to convert the original pixel values ​​into physical reflectance; atmospheric correction is used to eliminate the interference of atmospheric scattering and absorption on the spectral curve; and geometric correction is used to spatially align each temporal image with the cadastral vector boundary.

[0025] Furthermore, based on the cadastral vector boundary, spatial registration and vector mask cropping are performed on the preprocessed image to generate temporal samples of land parcels corresponding to each parcel. This includes: performing coordinate system and geometric registration between the cadastral vector boundary and the preprocessed image to ensure a one-to-one correspondence between the parcel boundary and image pixels; applying the cadastral vector boundary to the registered image to perform vector masking operations, removing non-parcel region pixels, and retaining only the set of pixels consistent with the parcel boundary range; grouping the pixel set according to the parcel identifier of the cadastral vector boundary to form temporal samples of land parcels corresponding to each parcel.

[0026] In the specific implementation process, the first step is to acquire multi-temporal remote sensing images of the target area and the corresponding cadastral vector boundaries. Multi-temporal remote sensing images refer to remote sensing data covering the same area acquired at different time points; these images reflect the dynamic changes of land parcels with seasons and agricultural periods. Cadastral vector boundaries are vectorized boundary data that precisely delineates the extent of each land parcel within the target area. To ensure consistency between the temporal images and the land parcel boundaries in subsequent analysis, these two types of data must be combined to form a temporal sample that can be directly mapped to each land parcel.

[0027] Before converting raw remote sensing images into usable data, preprocessing is required. The preprocessing rules are as follows: radiometric calibration, atmospheric correction, and geometric correction are sequentially performed on the multi-temporal remote sensing images to obtain preprocessed images with spectral comparability and spatial consistency. Radiometric calibration transforms the pixel values ​​in the original images from digitally quantized values ​​recorded by the sensor into physically meaningful reflectance values. This processing ensures that images acquired at different times are comparable on a spectral scale; otherwise, differences in sensor imaging conditions will lead to deviations in vegetation indices and spectral curves. Atmospheric correction eliminates the interference of atmospheric scattering and absorption on spectral curves, especially in the shortwave and near-infrared bands, where atmospheric conditions have a significant impact on remote sensing data. Without atmospheric correction, images of the same area on different dates may exhibit spectral curve drift due to differences in water vapor content or aerosol concentration, severely affecting subsequent time-series-based change analysis. Geometric correction is a crucial step in ensuring that images from different time periods are strictly aligned in space. By referencing cadastral vector boundaries and control points for geometric registration, the pixel positions of images from different times can be corrected to a unified geographic coordinate system, avoiding misalignment between the plot boundaries and the pixel set due to positional deviations.

[0028] After obtaining the preprocessed image, it needs to be spatially registered and clipped using vector masks with the cadastral vector boundaries to generate temporal samples of land parcels corresponding to each parcel. Specifically, the cadastral vector boundaries are first registered with the preprocessed image using coordinate system one and geometric registration. Here, coordinate system one refers to unifying data from different sources to the same spatial reference system, ensuring that the boundaries and images can be superimposed in the same coordinate system; geometric registration uses control point matching and geometric transformation to precisely align the cadastral boundaries with the preprocessed image, ensuring that the parcel boundaries and image pixels correspond one-to-one.

[0029] After completing the registration process, a vector mask operation needs to be performed on the preprocessed image using the cadastral vector boundaries. The vector mask operation uses the vector boundaries as a mask to remove all pixels in the image that do not belong to the boundary range, retaining only the set of pixels that perfectly match the boundary range. The purpose of this process is to eliminate interference from background areas or adjacent land parcels, ensuring that the subsequently extracted spectral curves, texture features, and other information strictly originate from within the target land parcel's area.

[0030] like Figure 2 This paper presents a schematic diagram of a vector masking operation. The left side illustrates the state of overlaying cadastral vector boundaries onto a preprocessed image, where the parcel area is defined by the cadastral vector boundaries, and the image simultaneously includes the parcel area and the background area outside the parcel. By performing a vector masking operation, all pixels outside the parcel can be removed, retaining only the set of pixels within the parcel that conforms to the cadastral vector boundaries. The right side illustrates the cropped result, which only contains the set of pixels within the parcel area. This result serves as the input data for subsequent parcel time-series sample generation and feature extraction. This processing method ensures that the time-series image data used in subsequent recognition processes strictly originates from within the parcel, thereby avoiding misjudgments caused by interference from neighboring parcels or background areas.

[0031] After the masking operation is completed, the pixel set needs to be grouped according to the block identifiers of the cadastral vector boundaries. Each block typically has a unique identifier in the cadastral data. This identifier is used to match pixel sets belonging to the same block one-to-one in different temporal images, thus forming a complete block time-series sample. The block time-series samples generated in this way retain the spectral and spatial information of each block at different time points, while ensuring the consistency between the data and the block boundaries, laying a data foundation for subsequent feature extraction and crop type change sequence construction.

[0032] The above steps address two major issues that arise when directly using existing remote sensing imagery: first, the incomparability between images from different time periods due to differences in radiometric, atmospheric, and geometric factors; and second, the impurity of samples caused by misalignment or contamination between plot boundaries and image pixels. By employing preprocessing and vector cropping rules, the resulting plot time-series samples exhibit consistent spectral curves across time phases, accurate spatial correspondence, and clear plot boundary segmentation, thus ensuring reliable data input for subsequent land abandonment assessment based on time-series characteristics.

[0033] Step S2: Extract multidimensional feature vectors of the land parcels from the temporal samples of the land parcels within a preset phenological window, including spectral features, temporal features, and spatial structure features.

[0034] Specifically, a spectral index curve is calculated based on the pixel reflectance sequence of the plot's time-series samples within the phenological window, and the spectral index curve is used as a spectral feature; trend information and key node information of crop growth stages are extracted based on the time-series changes of the plot's time-series samples within the phenological window, and the trend information and the node information are used as temporal features; boundary compactness and internal spatial texture parameters are extracted based on the image texture distribution and cadastral vector boundary morphology of the plot's time-series samples, and the boundary compactness and the internal spatial texture parameters are used as spatial structure features; a multidimensional feature vector is obtained by fusing the spectral features, the temporal features, and the spatial structure features.

[0035] Furthermore, the multidimensional feature vector is obtained by fusing the spectral features, temporal features, and spatial structure features, including: performing normalization processing on the spectral features, temporal features, and spatial structure features respectively; concatenating or weighting the normalized features according to preset weights along the feature dimension to form a fused feature matrix; and extracting key feature components from the fused feature matrix using a dimensionality reduction algorithm or feature selection method to obtain the final multidimensional feature vector.

[0036] In the specific implementation process, multi-dimensional feature vectors, including spectral features, temporal features, and spatial structure features, are extracted from the plot time series samples within a preset phenological window. This ensures that the subsequent discrimination model obtains complete and multi-dimensional plot feature information at the input end. A phenological window is a pre-defined time range based on the crop phenological patterns of the target area, such as the stages from sowing to jointing, jointing to grain filling, and grain filling to harvest. The corresponding remote sensing observation data within this time range can relatively completely reflect the crop growth trend. Therefore, limiting the plot time series samples formed by preprocessing and masking multi-temporal remote sensing images to this phenological window can minimize noise interference from redundant time points while retaining the key growth information necessary for crop type identification.

[0037] Specifically, the first step is to calculate the spectral index curve based on the pixel reflectance sequence of the plot's time-series samples within the phenological window. Spectral indices are indicators composed of combinations of different bands, such as the common Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SDI), and Moisture Index, all constructed through band operations to amplify the differences between vegetation and soil, and between vegetation and water bodies. During the calculation, the reflectance sequence of pixels within each plot within the phenological window is combined temporally to form a continuous spectral index time curve. This curve is then smoothed or interpolated to remove gaps and abnormal fluctuations caused by clouds and fog, thus obtaining a continuous spectral index curve. This spectral index curve serves as the spectral feature input to the plot's multidimensional feature vector, characterizing features such as vegetation cover, photosynthetic activity, and moisture status within the phenological window. Those skilled in the art will understand that the shape of this spectral curve is closely related to crop type; different crops will exhibit different curve shapes within the same phenological window. For example, wheat shows a significant rapid rise during the greening stage, while corn reaches its peak after jointing.

[0038] Furthermore, it is necessary to extract trend information and key node information of crop growth stages based on the time series changes of the plot's time series samples within the phenological window. The extraction rules for trend information can be defined as follows: by fitting the spectral index curve or directly calculating the slope of change based on the reflectance sequence, characteristic parameters of upward trend, plateau trend, or downward trend are obtained. For example, in the early stage, a slope close to zero indicates a dormant period, while a significantly positive slope corresponds to the greening or rapid growth period. The extraction rules for key node information include determining the inflection point position, peak position, and the starting point of decline. By comparing the numerical changes of continuous time phases, when the growth rate changes from positive to zero, it can be identified as an inflection point; when the value reaches a maximum value, it can be identified as a peak value; and when the value begins to decline, it is the starting point of decline. The temporal positions of these nodes directly correspond to the phenological stages of the crop and are important bases for determining crop type and plot management status. The extracted trend information and key node information are collectively referred to as temporal features and are input as independent features into the plot's multidimensional feature vector.

[0039] Furthermore, it is necessary to extract boundary compactness and internal spatial texture parameters based on the image texture distribution and cadastral vector boundary morphology of the plot's time-series samples. The extraction rule for texture distribution is as follows: select typical temporal images within the phenological window, calculate texture statistics such as the gray-level co-occurrence matrix, local binary pattern, or directional gradient histogram of pixels within the plot, thereby quantifying the uniformity and directionality of the spatial distribution within the plot. The extraction rule for boundary compactness is as follows: calculate the continuity and closure of boundary pixels based on the matching degree between the cadastral vector boundary and the actual image boundary. If there are obvious intrusions or gaps in the boundary extension area, the compactness is low. The extraction of internal spatial texture parameters is used to reflect the neatness and consistency of crop planting within the plot, for example, by statistically analyzing the internal texture entropy value of the block to characterize whether the crop rows are uniform. The aforementioned boundary compactness and texture parameters, as spatial structural features, are input into the plot's multi-dimensional feature vector alongside spectral and temporal features, ensuring that the model relies not only on spectral and temporal dimensions but also utilizes spatial dimension information.

[0040] After obtaining spectral features, temporal features, and spatial structure features, these three types of features need to be fused to obtain a complete multidimensional feature vector. The specific rules include three steps: 1. Normalize the spectral features, temporal features, and spatial structure features respectively. Since different features have different value ranges and dimensions—for example, spectral indices are between 0 and 1, while texture entropy values ​​may be between 0 and 10—direct splicing would lead to excessively large differences in feature scales. Normalization transforms various features into the same numerical range, improving the effectiveness of subsequent fusion.

[0041] 2. After normalization, the various features are concatenated or weighted and summed according to preset weights along the feature dimension to form a fused feature matrix. The concatenation rule directly combines different feature vectors in dimensional order to obtain a higher-dimensional comprehensive feature vector. The weighted summation rule assigns a weight coefficient to each type of feature; for example, spectral features account for 0.5, temporal features for 0.3, and spatial structure features for 0.2, resulting in a lower-dimensional comprehensive feature through linear weighting. The weights can be set empirically or determined through previous training processes.

[0042] 3. Extract key feature components from the fused feature matrix using dimensionality reduction algorithms or feature selection methods to obtain the final multidimensional feature vector. Dimensionality reduction algorithms may include principal component analysis, linear discriminant analysis, or nonlinear manifold learning, while feature selection methods may include feature importance based on information gain, LASSO regularization, or tree models. These methods effectively remove redundant features, retaining the feature components that best distinguish different crop types and land management statuses, resulting in a final multidimensional feature vector with appropriate dimensionality and strong discriminative power.

[0043] The multi-dimensional feature vectors obtained through the above rules encompass not only the changing shape of the spectral curve, but also the trend and key node information over time, as well as the texture and boundary features of spatial distribution, thus forming a relatively comprehensive descriptive system at the data input level. Relying solely on a single feature, such as spectral indices, can easily lead to difficulties in distinguishing between fallow and abandoned land; similarly, relying solely on temporal trends may result in misjudging single-season disaster damage as long-term abandonment. Multi-dimensional fusion can minimize such confusion and improve the discriminative power of the model's input data.

[0044] Step S3: Based on the temporal segmentation network, identify the crop type labels of each time phase in the temporal samples of the plot, construct the crop type change sequence, and input the crop type change sequence and the multi-dimensional feature vector of the plot into the plot discrimination model to obtain the preliminary judgment result of the operation status.

[0045] Specifically, the method for identifying crop type labels for each time phase in the temporal samples of the land parcels based on a temporal segmentation network and constructing a crop type change sequence includes: inputting the temporal samples of the land parcels into a trained temporal segmentation network, performing pixel-by-pixel classification on the pixels of each time phase image, and outputting the corresponding crop type labels; aggregating the crop type labels according to the cadastral vector boundaries to generate crop type results corresponding to each land parcel; and encoding the crop type results of each time phase in chronological order to form a crop type change sequence for characterizing the crop evolution process.

[0046] Furthermore, the crop type change sequence and the plot multidimensional feature vector are jointly input into the plot discrimination model to obtain a preliminary judgment result of the management status. This includes: performing time-series encoding on the crop type change sequence to generate a time-series embedding vector representing the crop evolution process; performing feature mapping on the plot multidimensional feature vector to generate a comprehensive feature embedding representing the plot's spectral information, time-series information, and spatial structure information; fusing the time-series embedding vector and the comprehensive feature embedding in a unified feature space and passing it as input to the plot discrimination model; and the plot discrimination model outputs a preliminary judgment result of the management status based on the fused input.

[0047] Specifically, the training rules for the land parcel discrimination model are as follows: historical land parcel time-series samples with land parcel management status labels are collected, and the historical land parcel time-series samples simultaneously contain the corresponding crop type change sequence and the land parcel multi-dimensional feature vector; the crop type change sequence and the land parcel multi-dimensional feature vector are used as inputs, and the land parcel management status labels are used as supervision signals to perform supervised learning training on the land parcel discrimination model; boundary constraint loss and temporal consistency loss are introduced during the training process, and the land parcel discrimination model is obtained after training convergence.

[0048] In the specific implementation process, it is necessary to identify crop type labels for each temporal phase in the temporal samples of the plots based on a temporal segmentation network, and then construct a crop type change sequence based on this. This crop type change sequence, along with the multi-dimensional feature vector of the plot, is then input into the plot discrimination model to obtain a preliminary judgment result on the operational status. This process is adopted because multi-temporal remote sensing image data inherently possesses both temporal and spatial dimensions, while crop growth and land use patterns naturally exhibit an evolutionary process over time. Classification results from a single temporal phase often only reflect the crop cover situation at a specific instant, lacking temporal continuity and overall consistency, and therefore insufficient to distinguish between multiple cropping, fallow, and abandoned states. However, by constructing a crop type change sequence and jointly modeling it with the multi-dimensional feature vector of the plot, both temporal evolution patterns and spatial spectral characteristics can be considered simultaneously, significantly improving the discrimination accuracy.

[0049] Specifically, the first step is to use a temporal segmentation network to identify the temporal samples of the land parcels and extract crop type labels for each time phase. The rule for this step is as follows: the temporal samples of the land parcels are used as input, and each time phase is fed into the already trained temporal segmentation network. Pixel-by-pixel classification is performed on each pixel of the image, and the corresponding crop type label is output. Pixel-by-pixel classification means individually determining the crop type corresponding to each pixel in the image at that time phase, such as wheat, corn, rice, or bare land. This process differs from traditional areal classification methods; it can capture subtle differences within the land parcel at the pixel level, thus ensuring more refined and accurate labeling results. With the development of deep learning technology, temporal segmentation networks often adopt a structure combining convolutional neural networks and recurrent neural networks to simultaneously capture spatial and temporal features. During the training phase, they are based on a large amount of labeled historical data, thus enabling reliable pixel classification results to be output during the inference phase.

[0050] After obtaining the crop type labels for each pixel, these pixel-level labels need to be further aggregated according to the cadastral vector boundaries. The rule is as follows: first, identify the cadastral plot number corresponding to each pixel; then, statistically or weightedly integrate all pixel labels under the same plot number to obtain a unified crop type result corresponding to that plot. This is because the plot is the basic unit of agricultural management, while the pixel is merely a technical division at the observation scale. If pixel labels are used directly as the basis for judgment, noise or boundary interference may cause local anomalies, thus affecting the overall judgment. Therefore, it is necessary to aggregate the pixel results based on the cadastral vector boundaries so that the final crop type result corresponds one-to-one with the actual plot unit.

[0051] After extracting the crop type results for each time phase, the results from each time phase need to be encoded chronologically to construct a crop type change sequence characterizing the crop evolution process. The rule is as follows: the crop type labels corresponding to the same plot on different dates are arranged sequentially according to time, forming a discretized sequence. For example, the labels for a plot throughout the four seasons might be "wheat—bare land—corn—bare land," directly reflecting the crop succession and land use changes of that plot during the phenological cycle. In this way, the originally independent single-time phase labels are linked into a continuous evolutionary process, significantly improving the explanatory power of subsequent analyses on operational status.

[0052] Furthermore, the crop type change sequence and the plot multidimensional feature vector need to be input into the plot discrimination model to obtain a preliminary judgment result of the operating status. In this step, feature encoding and mapping need to be performed on the crop type change sequence and the plot multidimensional feature vector respectively. The rules are as follows: First, the crop type change sequence is temporally encoded to generate a temporal embedding vector representing the crop evolution process. Temporal encoding refers to the process of converting discrete crop label sequences into continuous numerical vectors through methods such as recurrent neural networks, attention mechanisms, or positional encoding, thereby maintaining the time order and evolution characteristics in the vector space. For example, independent embedding vectors can be set for different crop types, and then the sequence can be processed through a long short-term memory network to capture the sequential relationship and periodic pattern in the sequence, and output a fixed-length temporal embedding vector.

[0053] Feature mapping is performed on the multidimensional feature vectors of the land parcels to generate comprehensive feature embeddings representing the spectral, temporal, and spatial structural information of the land parcels. The feature mapping rules include fully connected mapping or convolutional mapping, which compress or expand the original multidimensional features to the same dimensional space as the temporal embedding vector through a series of nonlinear transformations, thus facilitating subsequent feature fusion. These multidimensional features include spectral exponential curves, trend information and key nodes, texture statistics and boundary parameters, etc., which, after mapping, can be better aligned with the temporal information to form a unified embedding representation.

[0054] Furthermore, the temporal embedding vector and the comprehensive features are embedded in a unified feature space and fused together, then passed as input to the land parcel discrimination model. The fusion rule can be vector concatenation, weighted summation, or attention weighting; the specific method chosen can be adjusted based on experimental results. Through fusion, the model input can simultaneously contain the temporal patterns of crop evolution and the spatial information of land parcel characteristics, providing a comprehensive basis for discrimination. Finally, based on the fused input, the land parcel discrimination model outputs a preliminary judgment result on the management status. This preliminary judgment result may include categories such as abandoned, fallow, replanting, and normal planting, which are used for subsequent correction rules to further eliminate confusion.

[0055] During training, the land parcel discrimination model requires supervised learning training using labeled historical land parcel time-series samples to ensure accurate output of operational status. The training rules are as follows: collect historical land parcel time-series samples labeled with operational status. These samples simultaneously contain corresponding crop type change sequences and multi-dimensional feature vectors of the land parcels. Use these as inputs, and use operational status labels provided by manual surveys or authoritative databases as supervisory signals to train the land parcel discrimination model. To enhance the model's performance in complex scenarios, boundary constraint loss and temporal consistency loss are introduced during training. The boundary constraint loss rule is: when calculating the classification loss, pixels or regions close to the cadastral vector boundary are assigned higher weights to reduce errors caused by contamination between land parcels. The temporal consistency loss rule is: constrain the temporal continuity of crop type change sequences within the same land parcel, requiring that the model's prediction results do not exhibit unreasonable jumps between adjacent time phases, such as jumping directly from rice to wheat without any bare land or transitional stages in between. By introducing these constraints, the robustness of the model in scenarios with complex boundaries and temporal breaks can be significantly improved. After multiple rounds of training iterations, when the loss function converges, the final land parcel discrimination model that can be used for inference is obtained.

[0056] The above rules form a complete data link: starting from the time series samples of the plots, the crop type labels are obtained pixel by pixel through the time series segmentation network, aggregated and encoded into crop type change sequences, and then fused with multi-dimensional feature vectors and input into the discrimination model, finally outputting the preliminary judgment result of the management status.

[0057] Step S4: Based on the preset confusion resolution rule set, the preliminary judgment result of the operating status is corrected, and the result of the abandoned land identification is output.

[0058] Specifically, the confusion resolution rule set predefines multiple cropping discrimination rules, fallow discrimination rules, and disaster damage detection rules, and stores them in a rule base. The initial judgment result of the management status is compared with the crop type change sequence and the multi-dimensional feature vector of the plot, and the confusion resolution rule set is called to verify them one by one. If the multiple cropping discrimination rule is satisfied, the initial judgment result of the management status is corrected to multiple cropping status; if the fallow discrimination rule is satisfied, the initial judgment result of the management status is corrected to fallow status; if the disaster damage detection rule is satisfied, the initial judgment result of the management status is corrected to disaster damage status; if none of the multiple cropping discrimination rule, fallow discrimination rule, and disaster damage detection rule are satisfied, the initial judgment result of the management status is confirmed as abandoned status, and the abandoned plot identification result is output.

[0059] In this embodiment of the invention, after completing the inference of the plot discrimination model based on crop type change sequences and multi-dimensional feature vectors of plots, the preliminary judgment results of the management status often still have certain ambiguity and uncertainty. This is because actual agricultural production scenarios are complex, and plots in different states may have high similarity in spectral performance and temporal evolution. For example, multiple-cropping plots, due to multiple sowing and harvesting throughout the year, may appear as empty land or low-coverage states at certain times, very similar to abandoned plots in surface features; fallow plots, although temporarily unplanted, often show some traces of artificial covering or irrigation, and their spectral performance partially overlaps with abandoned plots; disaster-damaged plots may suddenly lose their normal crop growth curves when subjected to natural disasters, but may resume planting in subsequent seasons. If identification is based solely on images from a single season, it is highly likely to be misjudged as abandoned. Therefore, based on the preliminary judgment results of the model's management status, an additional set of confusion resolution rules needs to be introduced to verify and correct the preliminary judgment results item by item, in order to eliminate confusion between multiple similar states.

[0060] Specifically, the confusion resolution rule set is a set of discrimination rules that are predefined and stored in the rule base, including three categories: multiple cropping discrimination rules, fallow discrimination rules, and disaster damage detection rules.

[0061] The criteria for determining multiple cropping are based on the multi-peak structure of crop type change sequences. The rule is as follows: if two or more distinct vegetation peaks appear in the crop type change sequence within the same phenological cycle, and the temporal characteristics of the corresponding multidimensional feature vectors show a recurring growth trend, then the plot can be determined to be in a multiple cropping state. If the initial assessment of the management status is abandonment, but the above criteria for multiple cropping are met, then it is revised to multiple cropping.

[0062] The fallow classification rules primarily rely on cover indexes and irrigation / drainage characteristics within the spatial structural features. The rules are as follows: if a typical crop growth curve does not appear in the crop type change sequence, but the plot's multidimensional feature vector shows spectral characteristics of surface cover crop residues or straw returned to the field, and the boundary density and irrigation / drainage traces maintain high integrity, then it indicates that although the plot has not been planted with a major crop, it is still under artificial management and can be corrected to a fallow state. If the initial assessment of the management status is marked as abandoned, but it conforms to the above fallow rules, it is corrected.

[0063] The disaster damage assessment rules primarily rely on cross-seasonal recoverability and proximity consistency. The rules state: if an abnormal decline or interruption occurs in the crop type variation sequence of a given season, resulting in an incomplete growth curve for that season, but a normal crop peak is observed in subsequent seasons, and similar anomalies are observed in surrounding plots during the same period, then the plot can be determined to be disaster-damaged rather than abandoned. If the initial assessment of the operational status is abandonment, but the disaster damage assessment rules are met, the status is revised to disaster-damaged.

[0064] In practical applications, the preliminary judgment result of the management status is compared with the crop type change sequence and the multi-dimensional feature vector of the plot, and the confusion resolution rule set is called to verify each one. The execution order can be as follows: multiple cropping discrimination, fallow discrimination, and disaster damage inspection. When a certain rule condition is detected, the preliminary judgment result of the management status is corrected; if none of the above three rules are met, the preliminary judgment result of the management status is confirmed as a fallow state, and the fallow plot identification result is finally output.

[0065] By conducting secondary screening and correction of the initial assessment results of the operational status, the potential for misjudgment in the direct output of the model was effectively resolved. The multiple cropping discrimination rule ensures that areas with intermittent bare land are not mistakenly labeled as abandoned; the fallow discrimination rule ensures that policy-mandated fallow land is not incorrectly counted as abandoned land; and the disaster damage verification rule prevents short-term anomalies caused by natural disasters from being misinterpreted as long-term abandonment. The introduction of these rules makes the final abandonment identification results more consistent with actual agricultural production conditions, providing land management departments with more reliable data support and facilitating subsequent policy formulation and resource allocation.

[0066] In one possible implementation, during a farmland monitoring exercise in a plain area, multi-temporal remote sensing images of the area for a given year are acquired. After preprocessing and masking / cropping, a temporal sample of 1200 plots is formed. Taking plot A101 as an example, this plot has an area of ​​6.2 hectares. Based on the identification results of the temporal segmentation network, this plot is labeled as "wheat" in spring (March to May) images, appears as "bare land" in summer (June to July), is identified as "corn" again in autumn (August to October), and is vacant land in winter (November to December) images. If relying solely on the initial model judgment, this plot would be classified as "abandoned" due to the continuous bare land appearance in summer.

[0067] The initial assessment of the land's operational status was input into the confusion resolution rule set for verification. First, the multiple cropping discrimination rule was invoked: comparing the crop type change sequence of plot A101, it was observed that two complete crop growth peaks (wheat and corn) occurred within the same year. The spectral index curves reached peak values ​​of 0.72 and 0.69 in April and September, respectively, both exceeding the preset multiple cropping threshold of 0.6. Simultaneously, the temporal feature extraction of this plot showed two distinct growth trend segments, corresponding to the wheat greening stage and the corn jointing stage. After meeting the multiple cropping discrimination criteria, the system revised the initial operational status assessment from "abandoned" to "multiple cropping."

[0068] Plot B305, with an area of ​​4.8 hectares, showed no significant crop cover in the year-round imagery, with a spectral index below 0.25 throughout the year. However, further examination of the plot's multidimensional feature vector revealed that the boundary compactness in the spatial structure remained at 0.91, and there was persistent straw cover reflection in the red band. Based on the fallow criteria, although no major crop was grown, there were clear signs of human management, therefore the initial assessment of the management status was revised to "fallow."

[0069] Plot C512, covering an area of ​​5.5 hectares, showed a spectral index peak of only 0.32 in June during summer imagery, while similar anomalies were observed in neighboring plots (C510, C511, and C513). By September, the spectral index of C512 had recovered to 0.71. According to the disaster damage assessment rules, this anomaly was interpreted as a temporary reduction in yield due to summer flooding, with subsequent replanting. Therefore, the initial assessment of the operational status was revised from "abandoned" to "disaster damaged."

[0070] If the initial operational status assessment from the discriminant model were used directly, A101, B305, and C512 would all be classified as abandoned land. However, after correction using the confusion resolution rule, they were accurately identified as replanted, fallow, and disaster-damaged land, respectively. This rule effectively avoids misjudgments under different circumstances, improving the accuracy and reliability of the abandoned land identification results.

[0071] Figure 3 This is a system structure diagram of an abandoned land identification system based on crop type changes, provided in one embodiment of the present invention. Figure 3 As shown, this invention provides a system for identifying abandoned land parcels based on crop type changes. The system includes: an acquisition unit for acquiring multi-temporal remote sensing images and cadastral vector boundaries of a target area, performing preprocessing on the multi-temporal remote sensing images to obtain preprocessed images, and performing spatial registration and vector mask cropping on the preprocessed images based on the cadastral vector boundaries to generate land parcel time-series samples corresponding to each parcel; a feature extraction unit for extracting multi-dimensional feature vectors of land parcels, including spectral features, temporal features, and spatial structure features, from the land parcel time-series samples within a preset phenological window; a judgment unit for identifying crop type labels for each temporal phase in the land parcel time-series samples based on a temporal segmentation network, constructing a crop type change sequence, and inputting the crop type change sequence and the land parcel multi-dimensional feature vectors into a land parcel discrimination model to obtain a preliminary judgment result of the management status; and an output unit for correcting the preliminary judgment result of the management status based on a preset confusion resolution rule set and outputting the abandoned land parcel identification result.

[0072] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0073] The optional embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details described above. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe the various possible combinations.

[0074] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the embodiments of the present invention, they should also be regarded as the content disclosed by the embodiments of the present invention.

Claims

1. A method for identifying abandoned land plots based on crop type changes, characterized in that, The method includes: Acquire multi-temporal remote sensing images and cadastral vector boundaries of the target area, perform preprocessing on the multi-temporal remote sensing images to obtain preprocessed images, and perform spatial registration and vector mask cropping on the preprocessed images based on the cadastral vector boundaries to generate land parcel time series samples corresponding to each land parcel. Within a preset phenological window, extract multidimensional feature vectors of the land parcels from time-series samples, including spectral features, temporal features, and spatial structure features; Based on the temporal segmentation network, crop type labels for each phase in the temporal samples of the plot are identified, a crop type change sequence is constructed, and the crop type change sequence and the multi-dimensional feature vector of the plot are input into the plot discrimination model to obtain the preliminary judgment result of the operation status. The preliminary judgment result of the operating status is corrected based on the preset confusion resolution rule set, and the result of the abandoned land plot identification is output.

2. The method for identifying abandoned land plots based on crop type changes according to claim 1, characterized in that, The rules for preprocessing the multi-temporal remote sensing images are as follows: Radiometric calibration, atmospheric correction, and geometric correction are sequentially performed on the multi-temporal remote sensing images to obtain preprocessed images with spectral comparability and spatial consistency between images of different time periods; wherein, Radiometric calibration is used to convert raw pixel values ​​into physical reflectance; Atmospheric correction is used to eliminate the interference of atmospheric scattering and absorption on the spectral curve; Geometric correction is used to spatially align each temporal image with the cadastral vector boundary.

3. The method for identifying abandoned land plots based on crop type changes according to claim 1, characterized in that, Based on the cadastral vector boundaries, spatial registration and vector mask cropping are performed on the preprocessed image to generate temporal samples of land parcels corresponding to each parcel, including: The cadastral vector boundary is registered with the preprocessed image using coordinate system and geometry to ensure that the land parcel boundary corresponds one-to-one with the image pixels; After registration, a vector mask operation is performed on the cadastral vector boundary to remove non-land parcel area pixels and retain only the set of pixels that are consistent with the land parcel boundary range. The pixel set is grouped according to the block identifier of the cadastral vector boundary to form a time series sample of each block.

4. The method for identifying abandoned land plots based on crop type changes according to claim 1, characterized in that, Within a preset phenological window, a multidimensional feature vector of the land parcel, including spectral features, temporal features, and spatial structure features, is extracted from the temporal samples of the land parcel. This includes: Spectral index curves are calculated based on the pixel reflectance sequence of the plot time series samples within the phenological window, and the spectral index curves are used as spectral features. Based on the temporal changes of the plot time series samples within the phenological window, trend information and key node information of crop growth stages are extracted, and the trend information and the node information are used as temporal features. Based on the image texture distribution and cadastral vector boundary morphology of the land parcel time series samples, the boundary compactness and internal spatial texture parameters are extracted, and the boundary compactness and internal spatial texture parameters are used as spatial structure features. A multidimensional feature vector is obtained by fusing the spectral features, the temporal features, and the spatial structure features.

5. The method for identifying abandoned land plots based on crop type changes according to claim 4, characterized in that, A multidimensional feature vector is obtained by fusing the spectral features, temporal features, and spatial structure features, including: Normalization processing is performed on the spectral features, the temporal features, and the spatial structure features respectively; The normalized features are concatenated or weighted and summed along the feature dimension according to preset weights to form a fused feature matrix. Key feature components are extracted from the fused feature matrix using dimensionality reduction algorithms or feature selection methods to obtain the final multidimensional feature vector.

6. The method for identifying abandoned land plots based on crop type changes according to claim 1, characterized in that, Based on a temporal segmentation network, crop type labels for each phase in the temporal samples of the land parcels are identified, and a crop type change sequence is constructed, including: The temporal samples of the plots are input into a trained temporal segmentation network, which performs pixel-by-pixel classification on the pixels of each temporal image and outputs the corresponding crop type label. The crop type labels are aggregated according to the cadastral vector boundaries to generate crop type results corresponding to each land parcel; The crop type results for each time phase are encoded in chronological order to form a crop type change sequence that characterizes the crop evolution process.

7. The method for identifying abandoned land plots based on crop type changes according to claim 1, characterized in that, The crop type change sequence and the multidimensional feature vector of the plot are input together into the plot discrimination model to obtain the preliminary judgment result of the management status, including: The crop type change sequence is temporally encoded to generate a temporal embedding vector characterizing the crop evolution process; Feature mapping is performed on the multidimensional feature vectors of the land parcels to generate comprehensive feature embeddings that characterize the spectral information, temporal information, and spatial structure information of the land parcels. The temporal embedding vector and the comprehensive feature are embedded in a unified feature space and fused, and then passed as input to the land parcel discrimination model; The land parcel discrimination model is based on the preliminary judgment results of the integrated input and output operating status.

8. The method for identifying abandoned land plots based on crop type changes according to claim 7, characterized in that, The training rules for the land parcel discrimination model are as follows: Collect historical land parcel time series samples with land parcel management status labels. The historical land parcel time series samples simultaneously contain the corresponding crop type change sequence and land parcel multidimensional feature vector. The crop type change sequence and the multidimensional feature vector of the plot are used as inputs, and the plot management status label is used as a supervision signal to perform supervised learning training on the plot discrimination model. Boundary constraint loss and temporal consistency loss are introduced during the training process, and the land parcel discrimination model is obtained after training convergence.

9. The method for identifying abandoned land plots based on crop type changes according to claim 1, characterized in that, The preliminary judgment result of the operating status is corrected based on a preset set of obfuscation resolution rules, and the result of the abandoned land identification is output, including: The confusion resolution rule set predefines multiple cropping discrimination rules, fallow discrimination rules, and disaster damage detection rules, and stores them in the rule base; The preliminary judgment result of the operating status is compared with the crop type change sequence and the multidimensional feature vector of the plot, and the confusion resolution rule set is called to verify them one by one; If the multiple cropping discrimination rule is met, the initial judgment result of the operating status is revised to multiple cropping status; if the fallow discrimination rule is met, the initial judgment result of the operating status is revised to fallow status; if the disaster damage inspection rule is met, the initial judgment result of the operating status is revised to disaster damage status. If none of the above rules for multiple cropping, fallow, and disaster damage verification are met, the initial assessment result of the operating status is confirmed as an abandoned state, and the abandoned land identification result is output.

10. A system for identifying abandoned land plots based on crop type changes, characterized in that, The system includes: The acquisition unit is used to acquire multi-temporal remote sensing images and cadastral vector boundaries of the target area, perform preprocessing on the multi-temporal remote sensing images to obtain preprocessed images, and perform spatial registration and vector mask cropping on the preprocessed images based on the cadastral vector boundaries to generate land parcel time series samples corresponding to each land parcel. The feature extraction unit is used to extract a multi-dimensional feature vector of the land parcel from the temporal samples of the land parcel within a preset phenological window, including spectral features, temporal features, and spatial structure features; The judgment unit is used to identify crop type labels for each phase in the temporal sample of the plot based on the temporal segmentation network, construct a crop type change sequence, and input the crop type change sequence and the multi-dimensional feature vector of the plot into the plot discrimination model to obtain the preliminary judgment result of the operation status; The output unit is used to correct the preliminary judgment result of the operating status based on a preset set of obfuscation resolution rules and output the identification result of abandoned land plots.

Images