66 results about "Boundary precision" patented technology

The invention provides an aluminum alloy surface oxidation spot defect identification method and device based on machine vision, and relates to the field of intelligent manufacturing and industrial automation, and the method comprises the steps: obtaining an aluminum alloy surface color image, and carrying out the preprocessing of the image, so as to extract a brightness component image; self-adaptive threshold segmentation of local contrast enhancement is carried out on the brightness component image, a defect area binary mask is generated, morphological connected domains are extracted according to the mask, and three basic feature indexes of the area pixel value, the contour Fourier descriptor complexity and the area gray scale standard deviation contrast of each connected domain are calculated; and extracting and marking a connected domain boundary, verifying a boundary closed topological structure, and dynamically generating a curvature-driven self-adaptive sampling point through multi-scale B-spline curvature extreme value detection. Through optical-algorithm-process three-level collaborative innovation, the curved surface reflection false alarm rate is reduced, the pinhole detection rate is increased, and the boundary precision is + / -0.2 pixel.

The invention relates to a medical image segmentation method based on wavelet boundary enhancement and multi-scale perception, and the method comprises the steps: firstly carrying out the preprocessing of an input medical image, including size standardization, intensity normalization and data enhancement; then, inputting the processed image into a deep fusion segmentation network, extracting high-frequency boundary features through wavelet transform and generating a boundary attention map, and capturing global context information in combination with a multi-scale dynamic sparse attention mechanism; and finally, fusing the multi-scale features through a boundary enhancement up-sampling module in a decoder stage, and optimizing a segmentation result by adopting multi-scale supervision and a mixed loss function. According to the method, the boundary precision and the detail retention capability of medical image segmentation are effectively improved, and the segmentation performance under a fuzzy boundary, a multi-scale structure and a complex background is remarkably improved.

The invention relates to the technical field of agricultural remote sensing information processing, and particularly discloses a crop planting pattern spot intelligent extraction system based on remote sensing information, which constructs a multi-scale feature vector by fusing pattern spot area, compactness, time sequence vegetation index fluctuation and field ridge slope variation coefficient, and combines dynamic threshold adjustment and spatial semantic verification to obtain a multi-scale feature vector. According to the method, automatic correction of abnormal fragments, giant spots and topological conflicts is achieved, in complex scenes such as Yunnan terraced fields, through vertical field and ridge error response suppression and dynamic graph reconstruction, the pattern spot boundary precision and topological rationality are remarkably improved, and a classification result in a GeoJSON format is output.

The invention discloses a single tree trunk structure extraction method and system based on deep learning, and the method comprises the steps: obtaining two-dimensional image data of a single tree, marking the two-dimensional image data, and constructing a single tree trunk segmentation data set; constructing a spatial domain and frequency domain double-branch network based on the segmented data set, respectively extracting spatial domain features and frequency domain features, and fusing the double-branch features to generate a coding feature map; the coding feature map is decoded, in the decoding process, coordinate convolution CoordConv is adopted to enhance position perception, and mask segmentation and semantic label extraction are respectively carried out through a dynamic mask reconstruction branch DRMask Branch and an instance branch Inst Branch; based on a bipartite graph matching strategy, associating results of the mask segmentation and instance branches, and realizing segmentation of a single tree trunk and matching of instance-level labels; according to the method, the boundary precision and the detail reconstruction capability of trunk segmentation are remarkably improved, and the problem of feature loss of a traditional method in a complex under-forest environment is solved.

The invention discloses a medical image segmentation method based on a lightweight visual basis model, and the method comprises the steps: achieving the cross-modal and cross-anatomical region universal feature extraction through introducing a multi-scale token aggregation and a lightweight decoder; interlayer tokens are fused in a layered mode, global semantics and local textures are considered, and small target and boundary precision is remarkably improved. According to the multi-stage field adaptive pre-training, firstly, a fine-grained structure is captured by self-distillation, reconstruction and regularization composite loss, then, teacher-student distribution is aligned by Gram matrix anchoring loss, and finally, field migration and representation enhancement under the non-labeling condition are realized through high-resolution data refining. The lightweight compression selectively removes part of self-attention and retains MLP, and reduces parameter quantity and calculation quantity on the premise of almost no precision loss, so that the model can perform real-time reasoning on edge equipment. The end-to-end process reduces the annotation dependence, shortens the fine adjustment period, can support multi-organ and multi-focus segmentation through a unified frame, and improves the clinical deployment efficiency and generalization ability.

The invention provides a multi-mode nuclear magnetic resonance image glioma segmentation method and application thereof, and belongs to the field of medical image processing. The invention provides an M2ES-UNet network aiming at the problems of insufficient utilization of spatial features, single multi-modal fusion mechanism and cross-level semantic loss of an existing segmentation method. According to the method, multi-view anatomical information is extracted through a multi-plane feature collaboration module; utilizing an orthogonal dimension fusion convolution and modal introspection-collaboration module to respectively realize differential fusion of shallow and deep features; and the progressive jump transmission of the features is realized through a coding information smooth transmission module. According to the method, multi-plane and multi-mode complementary information can be effectively mined, the boundary precision and robustness of brain glioma segmentation are remarkably improved, and clinical diagnosis is assisted.

The invention discloses an intelligent road extraction method based on occlusion perception, and the method comprises the steps: firstly obtaining a remote sensing image of a to-be-extracted road region, and obtaining a feature map integrating global and local information through multi-level deep analysis; for the feature map obtained by coding, utilizing strip convolution operation in horizontal, vertical and double-diagonal directions to establish relevance between cross channels, and generating attention weight to obtain optimized features by combining the multi-direction features and the cross channel relevance; finally, depth features are generated through a decoder, the optimization features and the depth features are fused through jump connection, the reasonability of a morphological structure perception constraint prediction result is obtained through combination of segmentation basic loss, structural continuity loss and boundary precision loss, and automatic road extraction is completed based on multi-level supervision. The method is suitable for automatic road information extraction in the fields of automatic driving, urban planning, geographic information system construction and the like.

The invention discloses an SAM medical image segmentation method based on QR-KAN and MSMDA feature enhancement, and relates to the technical field of medical image segmentation. The method comprises the following steps: carrying out data preprocessing operation of normalization and data enhancement on an image; designing a QR-KAN feature enhancement module and an MSMDA attention mechanism module to transform an SAM image encoder to obtain an encoder, and performing feature extraction and enhancement on the preprocessed image by the encoder; and the decoder decodes the features output by the encoder by using the multi-head self-attention module and the deformable attention module, and the decoded feature sequence is input to the prediction head to output a prediction result. According to the invention, the QR-KAN feature enhancement module, the MSMDA multi-scale and multi-dimensional attention mechanism and the Gaussian noise injection module are designed, so that the boundary precision and detail recovery capability of medical image segmentation can be effectively improved, and the method has strong advantages especially when low-contrast and blurred images are processed.

The invention discloses an optical remote sensing image salient target detection method based on Mama dynamic clustering and bidirectional calibration, and belongs to the field of computer vision. The method comprises the following steps: preprocessing an original data set; inputting the preprocessed image into a lightweight encoder, capturing multi-scale features and refining local textures and edges; the multi-scale features output by the lightweight encoder are input into a dynamic clustering module based on Mamba, and interaction enhancement of global semantic modeling and dynamic local feature capture is achieved; inputting the output features of the Mama-based dynamic clustering module into a bidirectional cross-scale calibration module to realize cross-scale feature bidirectional complementation and semantic detail enhancement; inputting the output features of the bidirectional cross-scale calibration module into an edge attention combined repair module to realize attention hole repair and boundary precision enhancement; and finally, realizing feature aggregation and spatial resolution recovery through a decoder, and finally generating a saliency map. The method is used for solving the problems of target scale inconsistency and boundary blur in the remote sensing image.

The invention belongs to the technical field of shared vehicle management, and particularly relates to a method and a system for counting vehicles in a shared vehicle electronic fence, in a fence modeling stage, encrypted boundary points are adaptively generated, the boundary precision of a polygonal fence model is ensured, misjudgment caused by GPS drifting is effectively reduced, and in a coordinate unification stage, the calculation efficiency is improved. Multi-source vehicle positioning data are converted, a coordinate system is unified, statistical accuracy is guaranteed, in the vehicle screening stage, vehicle-candidate fence mapping is established, a foundation is laid for improving boundary judgment precision, in the fence judgment stage, accurate point position judgment is conducted through a ray method, buffer area judgment and directional drifting processing are introduced, and the accuracy of boundary judgment is improved. And the accuracy of fence judgment is further improved, so that the real-time performance of vehicle statistics is ensured, multi-platform data is compatible, and the management efficiency of shared vehicles and the parking specification level are improved.

The landslide image recognition method provided by the invention comprises the following steps: performing multiple times of residual processing on a target image to extract high-order and low-order semantic features; performing multi-scale feature extraction on the high-order features, dynamically modulating branch features through adaptive channel attention, and performing channel splicing to generate high-order fusion features; edge features are extracted from the high-order fusion features and the low-order features through depth separable convolution, height / width dimension aggregation is decoupled through a direction sensitive attention mechanism, direction weights are generated and cross enhancement is carried out, and high-order and low-order direction enhancement features are obtained; after the two are spliced, an output feature map is generated through two-way pooling aggregation and space attention enhancement, and a landslide division result is obtained through segmentation of a classifier. According to the method, the problems of insufficient feature fusion and weak boundary perception are solved, and the boundary precision and region consistency of landslide segmentation in a complex terrain are remarkably improved.

This invention discloses an adaptive edge-aware 3D medical image segmentation method, with the following specific steps: S1, constructing an adaptive edge-aware network, which includes an encoder and a decoder, with a skip connection between the encoder and decoder; S2, acquiring and processing a 3D medical image; S3, inputting the preprocessed image from step S2 into the encoder of the adaptive edge-aware network through a patch partitioning layer, then into the decoder through residual blocks and adaptive weight matching blocks. The decoder output and the original input image are skip-connected through adaptive weight matching blocks, and finally, the image segmentation result is output through residual blocks and Fourier convolution. This invention exhibits stronger robustness and boundary accuracy in multi-organ 3D segmentation tasks, providing an efficient and scalable solution for medical image segmentation.

The invention provides a mining area surface water area mining influence evaluation method and device, equipment and a medium, and the method comprises the steps: obtaining remote sensing images of a target mining area before and after mining, and carrying out the spectral feature enhancement of the remote sensing images to obtain a normalized water body index; performing rough identification on the surface water area based on the normalized water body index to obtain a suspected water body area; performing fine identification on the suspected water body area to obtain a high-precision surface water area classification result; performing post-processing on the high-precision surface water area classification result; according to the total area of the surface water area before mining and the total area of the surface water area after mining, indexes of the surface water area influenced by mining of the target mining area are calculated, a quantitative evaluation result is output, the spatial integrity and boundary precision of water body recognition are improved, and the defects that a traditional remote sensing method is prone to noise interference and the extraction result is rough are effectively overcome; the evaluation method which is low in cost, automatic, quantitative and high in safety is realized, and powerful decision support is provided for protection of the surface water area of the mining area.

The invention discloses a real-time polyp segmentation system based on a multi-domain hierarchical attention network, and relates to the field of medical image processing and computer vision, and the system comprises a dynamic region guide block which is used for partitioning an input image and selecting key region features through a two-stage routing attention mechanism; the potential entropy quantization channel space attention module is used for carrying out channel and space information entropy quantization calculation on the feature map and highlighting fine organization differences; the spatial frequency fusion module is used for performing pixel-level fusion on the spatial domain features and frequency domain features extracted through fast Fourier convolution, and capturing a periodic mode and global structure information; and the patch extension layer and the linear projection are used for layer-by-layer up-sampling and executing quadruple up-sampling in the final stage to recover to the input resolution, and pixel-level segmentation prediction is generated. The boundary precision and the pixel classification performance are both improved, and the real-time performance of polyp segmentation and the clinical application reliability are remarkably improved.

The application discloses a kind of semi-supervised medical image segmentation method and system, it is related to image segmentation technical field, method includes: through the foreground probability graph of student network output, calculate its three-dimensional gradient amplitude and the space average weighted sum of discrete three-dimensional Laplace operator, obtain global boundary roughness scalar;Combining voxel level entropy and soft boundary indicator constructs roughness perception consistency loss, realizes adaptive course learning;Drive scaling factor to carry out residual modulation to geometric contrast loss, enhance the structure discriminant of boundary region;Guide boundary gradient alignment, curvature smoothing and pseudo-supervised threshold, through the weighted joint optimization student network of three, teacher network is updated with exponential moving average.The application introduces global boundary roughness scalar, cooperates and controls entropy consistency, geometric boundary contrast and gradient-curvature-pseudo-supervised joint regularization, significantly improves the boundary precision and robustness of medical image segmentation under semi-supervised condition.

This invention proposes a three-dimensional glioma image segmentation method, electronic device, and storage medium. The method includes: acquiring three-dimensional volume data from multimodal magnetic resonance imaging; fusing the three-dimensional volume data with prior information on orientation boundaries to obtain orientation-boundary-enhanced three-dimensional volume data; decomposing the orientation-boundary-enhanced three-dimensional volume data into a two-dimensional slice sequence and performing inter-slice context modeling to aggregate information from adjacent slices to generate a target feature volume; dynamically inferring discrete token combinations based on the target feature volume using a discrete token vocabulary and an attribute predictor to generate high-level semantic cue features; inputting the target feature volume into an orientation-aware dual-domain enhancement branch to obtain enhanced features; and inputting the enhanced features and high-level semantic cue features together into a sparse hybrid expert decoder to output segmentation probability maps of three nested tumor regions. This invention significantly improves the boundary accuracy and small target recognition capability of glioma subregion segmentation, thereby enhancing the accuracy of image segmentation.

The invention relates to the technical field of image semantic segmentation, in particular to a small sample image semantic segmentation optimization method fusing an attention mechanism, which comprises the following steps of: constructing a double-branch feature extraction network to respectively process a support set and a query image, and generating a multi-granularity category prototype; based on a channel attention and space attention mechanism, performing dynamic re-calibration and region enhancement on the features; and based on joint attention feature fusion and edge perception loss, boundary segmentation precision and semantic consistency are improved. According to the method, the segmentation performance can be remarkably improved under the condition that only 1-5 annotation samples exist in each class, dependence on large-scale annotation data is reduced, and the method is suitable for high-cost annotation scenes.

This invention relates to a flood inundation monitoring method and apparatus based on multi-level cross-modal fusion of optical and SAR images. The method first acquires and preprocesses pre-disaster optical images and post-disaster SAR images to construct training samples. Through three core modules—cross-modal adaptive interactive fusion, frequency-domain adaptive dual-stream fusion, and hierarchical multi-interactive fusion—it achieves complementary deep features and modeling of optical and SAR images, improving feature robustness and boundary accuracy. The cross-modal adaptive interactive fusion module enhances inter-modal complementarity, the frequency-domain adaptive dual-stream fusion module balances consistency and boundary accuracy through high- and low-frequency modeling, and the hierarchical multi-interactive fusion module considers both global semantics and local details, further improving the model's adaptability to different scenarios. This invention can effectively improve the accuracy of flood monitoring, enhance extraction performance in complex scenarios, and provide reliable methodological support for flood inundation monitoring, emergency response, and disaster assessment, with broad application prospects.

The invention discloses a cerebrovascular segmentation method and device based on physical guidance and pyramid vision Transform, and relates to the field of medical image data, and the method comprises the steps: constructing a cerebrovascular segmentation model, and enabling loss functions used during training to comprise boundary intersection-to-union ratio loss, focus Tversky loss and Dice loss; the method comprises the following steps: acquiring an optical coherence tomography image of a brain to be processed, inputting the optical coherence tomography image into a trained cerebrovascular segmentation model, enabling the optical coherence tomography image to pass through an encoder module of pyramid vision Transform, and inputting an output feature of a first Transform encoding layer into a radial strength module to obtain a radial enhancement feature; wherein the output features of the second Transform coding layer, the third Transform coding layer and the fourth Transform coding layer are input into a deformable cross-scale fusion module to obtain enhanced fusion features, and the radial enhanced features and the enhanced fusion features are input into a boundary perception attention module to obtain a corresponding cerebrovascular prediction segmentation mask and a cerebrovascular prediction segmentation image. The problems of low segmentation accuracy and boundary precision in the prior art are solved.

The application discloses a deep image inpainting tampering detection method based on adaptive tampering trace learning, and belongs to the technical field of digital image forensics. The method first processes the input image by using an adaptive differential convolution module to suppress image content and enhance tampering traces; then, multi-scale and fine-grained features are extracted in parallel by a multi-scale hollow convolution module and a dense connection network; next, a neural network structure search module is used to automatically optimize the feature extraction path to adapt to diversified tampering types; then, a global and local double-branch attention enhancement module is used to fuse multi-level features and simultaneously improve the internal consistency and boundary accuracy of the tampering area; finally, a decoder module is used to output a pixel-level tampering area mask. The application can adaptively learn tampering features and maintain high precision and strong robustness under post-processing conditions such as JPEG compression, scaling, noise addition and the like, and is suitable for fields such as digital forensics and media content security.

The invention discloses a semi-supervised medical image segmentation method and system, and relates to the technical field of image segmentation, and the method comprises the steps: calculating the spatial average weighted sum of the three-dimensional gradient magnitude and a discrete three-dimensional Laplacian operator through a foreground probability graph outputted by a student network, and obtaining a global boundary roughness scalar; the voxel-level entropy and the soft boundary indicator are combined to construct the consistency loss of roughness perception, and adaptive course learning is realized; carrying out residual modulation on geometric contrast loss by driving a scaling factor, and enhancing the structural discrimination force of a boundary region; boundary gradient alignment, curvature smoothing and a pseudo-supervision threshold are guided, and the student network and the teacher network are optimized through weighted joint of the three so as to perform index moving average updating. According to the method, the global boundary roughness scalar is introduced, entropy consistency, geometric boundary comparison and gradient-curvature-pseudo supervision joint regularization are cooperatively regulated, and the boundary precision and robustness of medical image segmentation are remarkably improved under the semi-supervised condition.

The invention discloses a breast ultrasound image segmentation method and device based on semantic perception, and the method comprises the steps: obtaining an ultrasound image of a patient, constructing a semantic perception breast tumor segmentation network of the ultrasound image, employing an encoder to capture the global structure information of the ultrasound image, employing a semantic perception block to extract low-level features from the global structure information, and carrying out the segmentation of a breast tumor. A plurality of decoders combine the global structure information with the low-level features to generate an optimized breast tumor segmentation result, and the decoders combine the global structure information extracted by the encoders with the low-level detail features acquired by the semantic perception module to finally generate an optimized segmentation result. An output result is ensured to have context accuracy and keep boundary accuracy, the network adopts an efficient U-shaped network architecture and fuses deep convolution and jump connection, different scale changes can be flexibly coped with, meanwhile, additional calculation overhead is avoided, and the method is suitable for large-scale application. Therefore, the effectiveness and robustness of breast tumor segmentation of the breast ultrasound image are improved.

The invention discloses a depth image restoration tampering detection method based on adaptive tampering trace learning, and belongs to the technical field of digital image forensics. The method comprises the following steps: firstly, processing an input image by using a self-adaptive differential convolution module so as to inhibit image contents and enhance tampering traces; then, multi-scale and fine-grained features are extracted in parallel through a multi-scale cavity convolution module and a dense connection network; then, automatically optimizing a feature extraction path by using a neural network structure search module to adapt to diversified tampering types; then, through an attention enhancement module containing global and local double branches, fusing multi-level features and simultaneously improving internal consistency and boundary precision of a tampered region; finally, a pixel-level tampered region mask is output by the decoder module. According to the method, tampering features can be adaptively learned, high precision and high robustness are kept under post-processing conditions such as JPEG compression, zooming and noise adding, and the method is suitable for the fields of digital forensics, media content security and the like.

The invention discloses a wafer bonding defect detection method and device, computer equipment and a storage medium, and belongs to the technical field of wafer detection. The method comprises the following steps: inputting an original acquisition image into an instance segmentation model for segmentation processing, identifying a defect object of a wafer bonding interface and generating a boundary segmentation mask; carrying out supplementary verification on the boundary segmentation mask, correcting a mistakenly segmented region and optimizing boundary precision to obtain an optimized segmentation result; based on the optimized segmentation result, geometric feature information and morphological feature information of the defect object are extracted; and performing defect judgment processing based on the geometrical characteristic information and the morphological characteristic information, and outputting a defect detection report of the wafer bonding interface. According to the technical scheme provided by the invention, high-accuracy and high-efficiency defect detection can be carried out on the wafer bonding interface.

The invention discloses an edge attention enhanced double-branch frame field building contour extraction method and device, and belongs to the technical field of computer vision and remote sensing image processing. According to the method, an edge-aware double-branch framework field network (EA-DBFFN) is adopted, and end-to-end building contour extraction is realized through image input, feature extraction, double-task decoding, mask framework field fusion and polygularization. Wherein the dual-task decoding comprises a mask branch and an edge branch, the feature expression capability is enhanced through a dynamic receptive field module and a multi-direction convolution module, and feature interaction and collaborative optimization between the two branches are realized by adopting dual-task mutual guidance. According to the method, boundary feature learning is enhanced through an edge attention mechanism, and geometric constraints of a frame field vector field are combined, so that the structural integrity and boundary precision of building contour extraction are remarkably improved.

This invention discloses an iterative optimization method and related apparatus for single-tree crown segmentation based on confidence decoupling and prior-driven principles. The method includes: inputting remote sensing image data into a single-tree crown segmentation model to output a coarse segmentation result; performing confidence assessment on the coarse segmentation result to generate a confidence assessment result; generating prior information from the confidence assessment result using a prior encoder, and fusing the prior information with the original high-dimensional features to generate fused features; inputting the fused features into a neural network decoder for the next optimization segmentation process, outputting the next optimized single-tree crown segmentation result, and returning to the confidence assessment step, until the number of optimization iterations reaches a preset number, at which point the final optimized single-tree crown segmentation result is output. In this embodiment, the boundary precision and regional consistency of remote sensing image segmentation in complex forestry scenarios are significantly improved.

The application discloses a kind of unmanned ship path guidance and pollution area identification method based on unmanned aerial vehicle vision, it is related to image processing technical field;The method comprises the following steps: step one, controls unmanned aerial vehicle to obtain water surface image along the inspection route covering target water area above target water area, and generates the initial pollution area distribution diagram of target water area;Step two, determine the boundary uncertain area in the initial pollution area distribution diagram, update the initial pollution area distribution diagram for multiple rounds, obtain high-precision pollution area boundary map;Step three, high-precision pollution area boundary map is issued to unmanned ship control system, to realize the identification and guidance to pollution area contour and pollution area range.The application improves the boundary precision by multiple revisits, and realizes the cooperation of unmanned aerial vehicle and unmanned ship by dynamic path guidance, and the application significantly improves pollution identification accuracy and unmanned ship operation efficiency, with high reliability, high adaptability and high application value.

This invention discloses an intelligent road extraction method based on occlusion perception. The method first acquires remote sensing images of the road area to be extracted. Through multi-level depth analysis, a feature map integrating global and local information is obtained. The encoded feature map is then used with horizontal, vertical, and double diagonal strip convolution operations to establish the correlation between intersecting channels. Combining multi-directional features and intersecting channel correlations, attention weights are generated to obtain optimized features. Finally, a decoder produces deep features, which are fused with the optimized features using skip connections. The method then assesses the rationality of the morphological structure perception constraint prediction results obtained by combining segmentation base loss, structural continuity loss, and boundary accuracy loss, and completes automatic road extraction based on multi-level supervision. This invention is applicable to automatic road information extraction in fields such as autonomous driving, urban planning, and geographic information system construction.

The application provides a multi-modal nuclear magnetic resonance image brain glioma segmentation method and application thereof, and belongs to the field of medical image processing.The M2ES-UNet network is provided in view of the problems of insufficient space feature utilization, single multi-modal fusion mechanism and cross-level semantic loss of existing segmentation methods.The method extracts multi-view anatomical information through a multi-plane feature coordination module;orthogonal dimension fusion convolution and mode introspection-coordination modules are used to realize differentiated fusion of shallow and deep features;and the encoding information smooth transmission module is used to realize progressive jump transmission of features.The application can effectively mine multi-plane and multi-modal complementary information, significantly improve the boundary precision and robustness of brain glioma segmentation, and assist clinical diagnosis.

The application provides a landslide segmentation method and system fusing gravity-oriented scanning and state space, comprising: acquiring optical remote sensing images and corresponding digital elevation model DEM data of a region to be segmented; calculating gravity potential distribution and terrain gradient information based on the DEM data, and determining one-dimensional scanning priority of two-dimensional image features tokens according to the gravity potential distribution; reordering the two-dimensional image features tokens to form a gravity-oriented feature sequence; inputting the gravity-oriented feature sequence into a state space model to enable the features to be selectively scanned and state-evolved in a gravity potential descending direction; dynamically modulating evolution parameters of the state space model based on the terrain gradient information to establish long-range physical causal correlation between a landslide source area and a deposit area; and performing boundary feature enhancement and decoding on multi-scale features to obtain a landslide region segmentation result. The application improves the physical interpretability, boundary accuracy and calculation efficiency of landslide segmentation.