582 results about "Boundary detection" patented technology

Automatic generation of in-store product information and navigation guidance, using Augmented Reality (AR) and a Vision-and-Language Model (VLM) and multi-modal Artificial Intelligence (AI). An automated method includes: providing to the VLM images that are captured within a retailer venue by an electronic device that is a smartphone or an AR device or smart glasses; (b) automatically feeding into the VLM those images, or pre-sliced or pre-cropped image-portions of those images that were sliced or cropped using Machine Learning that performs object boundaries detection and not product recognition; (c) invoking the VLM to generate outputs of VLM analysis of content of those fed images or image-portions. The VLM outputs can be: VLM-based product recognition, VLM-based product-related information, VLM-generated virtual shopping assistance, VLM-generated in-store navigation guidance, or other VLM-generated outputs. Based on the VLM-generated outputs, the electronic device provides real-time information about products depicted in the images, VLM-generated shopping assistance, and VLM-generated in-store navigation guidance.

The invention relates to a display screen backlight brightness adjusting method and system based on a Mini QLED technology. The method comprises the following steps: dividing a display image signal into a brightness signal, a chrominance signal and a saturation signal, and generating image feature data; performing sub-pixel-level boundary detection to obtain a plurality of initial backlight sub-regions, and calculating region brightness distribution data; executing region clustering operation and region merging to obtain a plurality of target backlight sub-regions and calculating backlight partition mapping data; carrying out nonlinear feature transformation, and calculating backlight unit control data of the Mini LED backlight unit; outputting the backlight compensation amount of each target backlight sub-region by adopting a deep Q network; and performing real-time feedback correction, calculating a deviation value between an actual display parameter and a target parameter of each target backlight sub-region, and outputting a backlight optimization control signal. According to the invention, the backlight brightness is accurately adjusted, and the consistency of the display effect is improved.

The invention belongs to the technical field of artificial intelligence, and relates to an artificial intelligence-based electric energy quality disturbance identification and positioning method, which comprises the steps of constructing an electric energy quality disturbance signal data set, performing segmented preprocessing on electric energy quality disturbance voltage data, enhancing time-frequency joint features and encoding disturbance sensitive areas. And constructing a deep learning model for power quality disturbance identification and positioning, and identifying and positioning the power quality disturbance. According to the invention, through adaptive denoising processing, boundary detection and multi-resolution time-frequency feature extraction, the identification precision and positioning precision of power quality disturbance are significantly improved; self-adaptive wavelet denoising and dynamic segmentation are combined, noise interference is effectively suppressed, and the edge characteristics of voltage sudden change points are kept; according to the dual-task sharing network, disturbance identification and positioning tasks are cooperatively optimized, so that the network can consider disturbance classification and time positioning at the same time; and through Bayesian reasoning, the system can output confidence estimation, provides credibility quantification of identification and positioning results, and effectively improves the reliability of the system.

The invention belongs to the technical field of document content extraction, and particularly discloses a document content extraction method and system based on multimodal model collaboration, a terminal and a medium. Comprising the following steps: identifying the type of an input to-be-processed document, and judging the document type; on the basis of the type identification result, calling a multi-modal model to analyze the document content, and outputting space coordinates, visual features and semantic features of document elements; generating a content sequence according with a reading habit through a semantic sequence reconstruction algorithm; paragraph boundary detection, paragraph recombination and semantic association modeling of charts and texts are completed based on the multilayer attention network and the graph neural network; grammar error correction, format optimization and title hierarchy generation are carried out by using a large language model and a hierarchical classification network; and converting the identification result into a structured output file. According to the method, the processing requirements of different types of documents can be considered, and high-precision analysis and efficient output are realized under the scenes of complex layouts, multiple languages and formula tables.

The invention relates to the technical field of industrial production intelligent process control, in particular to an AI-based electrolytic manganese process production quality intelligent prediction method and system, and the system comprises a drift calibration module, a structure matching module, a process parameter inversion module, a path correction module and a deviation verification module. According to the method, dynamic compensation of deviation between input parameter drift and output parameters is achieved through the response relation between input and output of all links, the actual influence degree of fluctuation of all the parameters on the target control parameters and product quality is effectively recognized according to correlation matching of the periodic change of the production process and the fluctuation frequency of the target control parameters, and the accuracy of the product quality is improved. Potential interference of key process parameters on stability of each process is locked in time, diffusion starting time and space of impurities are clearly traced through path judgment of residual liquid concentration trend and raw material adding position, and migration path parameters are further adjusted based on ion retention behaviors of boundary detection points.

The invention provides a rail turnout foreign matter detection and type analysis method and system, and the method comprises the steps: arranging a first camera group at the front end of a train, recognizing the position of a turnout through a preset target detection model, and calibrating foreign matters in the turnout through a preset foreign matter detection model; shooting an image calibrated to the foreign matter in the turnout through a second camera group as a to-be-analyzed image; extracting a second boundary region rolled by a wheel on the foreign matter from the to-be-analyzed image through a preset wheel rolling track detection model, performing coarse classification on the foreign matter in the to-be-analyzed image to obtain a coarse classification result, and selecting a boundary detection strategy to identify the first boundary region according to the coarse classification result in the foreign matter image; and respectively extracting corresponding texture features in the first boundary region and the second boundary region through a deep learning network, performing one-to-one mapping on the extracted texture features to obtain a mapping relation group, performing analysis through the mapping relation group to obtain a feature change rate, and performing analysis through a multi-feature analysis strategy to obtain a specific foreign matter type.

The invention relates to a distributed trajectory planning method and system for an unmanned aerial vehicle cluster in an obstacle environment. The method comprises the steps of initializing a system, constructing a local Euclidean symbol distance site map, and realizing real-time interaction of state information of the unmanned aerial vehicle. An initial collision-free path is generated using jump point search. And solving an optimal control point through an L-BFGS algorithm through multi-constraint trajectory optimization in combination with a load swing dynamics model, four-rotor dynamics limitation, cluster collision avoidance and environment obstacle avoidance requirements. And a dynamic time redistribution strategy is adopted, and the track time interval is adjusted according to speed and acceleration overrun conditions. The method further comprises an adaptive re-planning mechanism, and local target points are updated in real time and adjacent aircraft collaborative optimization is triggered based on local map boundary detection and quadrotor track safety detection. According to the method, efficient, safe and stable trajectory planning of the hanging load quad-rotor unmanned aerial vehicle cluster in a complex environment is realized, the requirement of autonomously and efficiently completing tasks is met, and the task execution efficiency and safety are improved.

A road boundary detection device is a road boundary detection device that acquires a set of lines corresponding to a road boundary from point cloud data as road boundary information. The road boundary detection device includes: a candidate point detection unit that detects each point of road boundary candidates corresponding to candidates of a road boundary from the point cloud data; a candidate point clustering unit that clusters each point of the road boundary candidates; an adjacent cluster reduction unit that reduces a cluster from a distribution of points in clusters in an adjacency relationship by using a predetermined cluster reduction method; a line fitting unit that fits one or more straight lines or curved lines to one or more of the clusters and output fitted lines as road boundary candidates; a line connecting unit that connects some of the fitted lines by using a predetermined analysis method; and an information output unit that outputs a calculated line as the road boundary information.

The invention relates to the technical field of table information updating, in particular to a table information updating method and system based on an intelligent recognition text. The method comprises the following steps: associating at least one table to be updated, and preprocessing an input table image; identifying the pre-processed table image by using an OCR identification technology and a deep learning convolutional neural network, and extracting table content in the table image; a semantic relation in the table content is understood through a pre-trained language model, and relation association is conducted on the table content; according to the method, the content of the table is input into the to-be-updated table according to the semantic relation and correspondingly updated, the whole process can be automated by combining OCR, CNN, a pre-training language model and an image processing technology, boundary detection, content extraction, semantic analysis and data association of the table are automatically completed through algorithms, and the processing efficiency is greatly improved.

The invention provides a farmland plot extraction method based on a multi-type double-branch convolutional neural network, and the method comprises the steps: creating a double-branch multi-task network DBMNet based on a multi-type convolution module, and designing a double-branch feature extraction module DBFE to replace a convolution layer of an original network, a dynamic linear constraint convolution module LCDC and a multi-scale deformable convolution feature extraction module MDFE are used to comprehensively extract edge features of an image and field block region features of different sizes and shapes, the perception ability of a network to information of different scales is improved, and thus the segmentation precision of the network is improved. The network uses boundary detection and distance regression tasks to improve the precision extraction of the farmland plot masks, so that the network has a better generalization effect. According to the method, the multi-type convolutional network is applied to the farmland plot extraction task, the experimental result shows that compared with other most advanced algorithms, the method has the best segmentation performance, discriminative features of the farmland plot can be effectively extracted, the segmentation precision is remarkably improved, the farmland plot is accurately extracted, and the method has great application potential and prospect.

The invention relates to the technical field of weld joint detection, in particular to a CO2 welding automatic trolley weld joint recognition method. According to the method, by measuring current signals and magnetic conductivity parameters in real time and combining comparison of dynamic change amplitudes, the initial position of a weld joint is accurately recognized, the initial accuracy of weld joint detection is improved, meanwhile, a displacement characteristic curve is extracted, weld joint form data is dynamically adjusted, the continuity and accuracy of weld joint path recognition are ensured, and the path tracking effect is improved; the welding seam boundary and width range are accurately judged in combination with electromagnetic parameter differences, the reliability of welding seam boundary detection is facilitated, irrelevant parameters are removed through frequency selection, edge contours are captured, welding seam surface features are marked, feature point layered clustering and normalization processing are conducted through a Gaussian mixture model, welding seam feature point data are comprehensively integrated, and the accuracy of welding seam boundary detection is improved. The generated feature point model provides an important basis for high efficiency and accuracy of weld joint recognition, and the performance of weld joint detection in the aspects of paths, forms and boundaries is integrally optimized.

The invention belongs to the technical field of remote sensing image intelligent processing and agricultural information extraction, and particularly relates to a remote sensing large model pre-training and multi-granularity boundary supervision natural field type extraction method, which comprises the following steps: firstly, pre-training a model on a large-scale space-time spectrum remote sensing data set, and combining anchor point sensing mask and geographic information coding; secondly, inputting the multi-scale features into a multi-branch structure sensing network, and outputting a semantic segmentation prediction map through high and low resolution double input and dynamic attention fusion; generating a multi-scale field boundary label through morphological operation, and outputting a boundary prediction map through multi-task supervision after domain enhancement of features by a frequency space double-domain enhancement module; and finally, aligning the two images and performing pixel-level operation to obtain a high-precision extraction result. Through the method, the global classification error during cross-region migration is greatly reduced, the method is adaptive to a low-pixel wide ridge, the boundary detection value and the closure rate of a small-scale field are improved, and the extraction precision of a large field and a small field is considered.

The invention provides a low-load tomato fruit detection method oriented to complex shielding of a facility environment, and belongs to the field of target detection. The method comprises the following steps: firstly, combining a plurality of self-adaptive convolution kernels by using a dynamic convolution so as to better extract rich features of fruits; besides, a D-KLA attention mechanism is designed at the end stage of the neck network, and irregular deformation and shielding problems of tomatoes are focused through adaptive adjustment of a receptive field. Then, a WIoU boundary regression loss function based on a scale factor is constructed, and the accuracy and convergence of boundary detection are improved; and finally, optimizing the detection model by adopting a knowledge distillation method based on semantic frequency prompt, and realizing light weight of the model. And detecting the verification set through the trained tomato target detection model, and evaluating the performance of the verification set. Compared with other methods, the method has the advantages that the optimal performance of tomato fruit detection is realized in a complex shielding environment, the problems of pipeline shielding, leaf shielding and mutual shielding among fruits in a facility environment are effectively relieved, the detection precision is remarkably improved, and the parameter quantity and the calculation complexity of the model are greatly reduced.

The invention relates to a light blanket projection control method and device, computer equipment and a readable storage medium. The method comprises the steps of obtaining a road image collected by a vehicle camera at a current time step under the condition that a vehicle projects a light blanket; performing lane line detection and light blanket boundary detection on the road image, and determining deviation information between a lane line and a light blanket boundary in the road image according to a detection result; based on a perspective transformation matrix between an image coordinate system and a light blanket projection coordinate system, mapping the deviation information from the image coordinate system to the light blanket projection coordinate system to obtain mapped deviation information; adjusting light blanket projection control information corresponding to the next time step of the current time step according to the mapped deviation information; and the vehicle is controlled to perform light blanket projection at the next time step according to the light blanket projection control information, so that the light blankets projected under various road conditions are accurately matched with the lane lines, the road perception ability of a driver is improved, and the driving safety of the vehicle is ensured.

The invention relates to the technical field of rock mass fracture recognition, in particular to a rock mass fracture recognition method based on a boundary detection neural network model. According to the method, an innovative deep learning framework is provided for boundary recognition, the characteristics of a refinement strategy and sub-pixel convolution are combined, and a leading result is obtained on a data set. The research shows that the CED model can improve the performance of middle-level and high-level visual tasks including optical flow estimation, target suggestion generation, semantic segmentation and the like. According to the method, a novel architecture is provided to solve the precision problem of a CED algorithm, a reverse refining path is supplemented for an HED network to improve the recognition precision, and the path uses efficient sub-pixel convolution to merge features step by step; the CED provided by the invention can generate an edge image which is well aligned with an image boundary.

Systems and methods for imaging, such as with an intravascular ultrasound (IVUS) imaging device are employed with components and accessories, such as for example, catheters, a catheter interface module, mounts, a workstation, a tablet, a display, and cart. The components may be controlled or interacted with via hands-free commands, voice control, gestures, and may be enhanced with artificial intelligence and / or machine learning. Real time measurements and border detection with enhanced imaging are provided.

The invention relates to a three-stage tooth intelligent accurate segmentation method based on a shape distance field, and the method comprises the following steps: S1, obtaining a tooth image, and carrying out the preprocessing; s2, extracting a region of interest, and determining a foreground region; s3, calculating the distance and direction from each foreground pixel in the foreground region to the centroid of the corresponding tooth to form a centroid offset vector; s4, generating a tooth centroid density map, and performing clustering identification on centroids of the teeth; s5, designing a segmentation mask loss function and a segmentation boundary loss function of the model; s6, designing a shape loss function based on a distance field; and the trained tooth segmentation model comprises a multi-label mask segmentation sub-network, a multi-label boundary segmentation sub-network and a shape sub-network based on a distance field, which are respectively used for executing a mask image generation task, a boundary detection task and a boundary fine description task, and outputting a final segmentation result. Compared with the prior art, the method has the advantages of improving the accuracy of tooth segmentation and the like.

The invention discloses an intelligent road roller trajectory planning method, electronic equipment and a storage medium. The method comprises the following steps: acquiring a road boundary detection result and the category, speed and distance information of an obstacle by adopting a target detection and semantic segmentation network; calculating the relative pose of the road roller and the road boundary based on the road boundary detection result; using a multi-sensor data fusion method to fuse the obstacle information, the road boundary information and the road roller global positioning information obtained from the integrated navigation equipment to obtain the global positioning information of the road roller and the obstacle; establishing a global path planning model; constructing a multi-objective function considering the compaction quality and a multi-constraint condition considering a construction time window, and optimally solving the working speed and the compaction times of the road roller based on a dynamic programming method; coupling of the speed and the path of the road roller is achieved through a spline curve interpolation method, and an intelligent compaction global track is generated. The optimal compaction quality can be achieved under complex construction, and meanwhile high efficiency and economical efficiency of operation are guaranteed.

The invention discloses a bladder tumor image segmentation method and system based on FEBE-Net, which are applied to the technical field of image processing, and adopt a PVTv2 encoder to learn multi-scale feature representation so as to adapt to the change of the size and shape of a bladder tumor; secondly, a feature exploration attention module is provided to fully mine potential local detail information in shallow features extracted by a PVTv2 encoder, noise is eliminated, missing fine-grained details are supplemented for a decoding stage, and the network segmentation performance is improved; meanwhile, a boundary enhancement and refinement module (BER) is provided, the boundary of the bladder tumor is additionally learned through a boundary detection operator to enhance a boundary region in input features of a decoder end, and a final prediction feature map is refined and adjusted; an efficient self-attention calibration decoder module is provided, and global context information and local detail information are gradually and effectively recovered from high-level features and low-level features with the help of boundary clues provided by a BER module.

The invention discloses an image edge cutting method and device based on boundary detection, equipment and a storage medium, and relates to the technical field of image boundary detection, and the method comprises the steps: carrying out the preprocessing of an original image, and obtaining a target image; determining a scene type of the target image; based on an edge detection strategy corresponding to the scene type, performing edge detection on the target image to obtain an edge image; performing straight line detection on the edge image to obtain a plurality of candidate straight line segments; and based on a boundary positioning rule, determining a target boundary line segment from the plurality of candidate straight line segments, so as to carry out edge cutting on the original image according to the target boundary line segment. According to the invention, a more reliable image edge cutting effect can be generated.

The invention discloses a sign language translation model, a sign language translation system and a sign language translation method based on full-modal alignment. The sign language translation method comprises the steps of extracting multi-modal features of hand, face and body postures from an input video and performing preliminary fusion; deep secondary fusion and alignment are carried out through multi-scale time sequence coding and a cross-modal collaborative attention mechanism, and a spatial-temporal feature sequence of full-modal alignment is generated; performing boundary detection and dynamic segmentation on the feature sequence by using a CTC-based sequence prediction model, and outputting a discrete sign language word sequence with a timestamp; and finally, capturing a sign language grammar structure of the sequence through a graph structure enhanced Transform encoder, inputting the sign language grammar structure into a Transform decoder integrating grammar consistency loss, and generating a target text conforming to target natural language grammar and semantic rules. According to the method, the problems of continuous sign language action adhesion and grammar structure difference are effectively solved, and the sign language translation accuracy and the natural language generation fluency are greatly improved.

The invention discloses a complex environment lane line accurate detection method based on multi-scale cooperative enhancement and semantic compensation. The method comprises the following steps: obtaining a lane line data set, and inputting the lane line data set into a trained lane line accurate detection network; adopting a backbone network to obtain multi-level features; utilizing a multi-scale collaborative enhancement module to obtain features of spatial and semantic information interaction enhancement; a mixed scene semantic compensation module is utilized to obtain supplementary semantic features so as to enhance feature robustness in different scenes; a boundary correction guiding module is adopted, features are refined from space and channel dimensions, and the lane boundary detection effect is improved; and optimizing and adjusting the lane line anchor layer by layer through the enhanced features to obtain a final lane line coordinate prediction sequence. According to the method, multi-scale cooperative enhancement and semantic compensation are combined, the lane line detection precision is improved, and the detection robustness in a complex scene is enhanced.

The invention discloses a pulmonary nodule boundary detection method based on semantic segmentation. The method comprises the following steps: generating an edge prior image set; obtaining a multi-scale boundary alignment feature map set and a deformation offset parameter set; a post-gating deformation offset parameter set is obtained, the multi-scale boundary alignment feature image set is updated, cross-scale feature fusion is executed, and a fusion feature image set is generated; establishing a node set and an edge set by utilizing node features in the fusion feature graph set and a spatial adjacency relationship, and initializing a node feature vector set; forming a fusion feature map set enhanced by multi-hop reasoning; and outputting a pulmonary nodule region mask prediction image set and a pulmonary nodule boundary probability prediction image set. According to the method, fracture between pseudo boundaries and slices is effectively inhibited, so that a three-dimensional structure prediction result is more coherent, and high-readability and high-consistency boundary segmentation output is provided for a clinical CAD (Computer Aided Design) system.

The invention discloses an erosion gully segmentation method based on multi-scale edge perception, and relates to the technical field of remote sensing image target extraction. The invention aims to solve the problem that the boundary extraction of the erosion gully by a common neural network algorithm is not clear due to the complicated geographical environment and characteristics of the erosion gully. According to the erosion gully segmentation method based on multi-scale edge perception, a boundary detection module and a multi-scale decoder are adopted, the edge detection module is used for extracting edge features of an erosion gully, the capability of extracting boundary details of the erosion gully is enhanced, and the segmentation precision of the whole erosion gully is improved; the multi-scale decoder decodes the features of the encoder and the boundary detection module, context feature information extracted by the encoder is fully utilized, the loss of detail feature information is inhibited, and the segmentation capability for fuzzy gullies and the overall segmentation precision are improved.

The invention belongs to the technical field of airport boundary security and protection, and discloses an airport boundary detection method and system based on multiple modes. According to the method, the environment around the enclosure is analyzed in real time through the video personnel detection module, and whether a person approaches the enclosure or not is observed; detecting whether the prompt word and the content of the image are illegal or not, and if yes, not processing; analyzing the content in the image through the image understanding capability, the text understanding capability and the analysis capability of the multi-modal visual large model, and returning an analysis result; judging whether the input text content has the intention of damaging and invading the enclosure or not; if there is no intention of invading and damaging the enclosure, the abnormal alarm module is directly used. According to the method, a large model and traditional deep learning are combined, so that the accuracy and the overall efficiency of a security system can be remarkably improved. The ever-increasing safety requirement of the civil aviation industry is met, and new powerful power is injected for continuous and healthy development of the unmanned aerial vehicle.

The invention relates to the technical field of voice signal processing, and discloses a voice segmentation intelligent editing system based on deep learning. The system comprises a voice feature extraction module, a segmentation boundary detection module, a semantic content analysis module, an editing strategy generation module and a real-time quality evaluation module. The voice feature extraction module collects multi-dimensional voice features and timestamp information, and verifies feature integrity and timeliness; the segmentation boundary detection module identifies voice pause intervals and semantic turning nodes and divides segmentation units and boundary types; a semantic content analysis module extracts text content and emotion features of each segment, and analyzes semantic topic relevance and information density; an editing strategy generation module formulates a segmentation retention rule and a sequence adjustment scheme, and matches user preferences and scene demands; the real-time quality evaluation module monitors voice fluency and information integrity in the editing process and analyzes splicing errors and user feedback. According to the system, intelligent processing of the whole voice editing process is realized.

In various examples, object boundary detection for autonomous and semi-autonomous systems and applications is described. Systems and methods are disclosed that may use one or more machine learning models to process sensor data generated using a machine to generate one or more outputs indicating boundaries of objects surrounding the machine. In some examples, the output(s) may include confidence values (e.g., scores) associated with locations of an environment at least partially surrounding the machine, where the confidence values indicate whether an object boundary is located at the locations. In some examples, the output(s) (and / or an output from post-processing of the confidence values) may include an obstacle map indicating at least the boundaries of the objects. Additionally, in order for the machine learning model(s) to generate such outputs, systems and methods are further disclosed that train the machine learning model(s) using various types of ground truth data.

The invention provides an anti-collision method, device and equipment based on obstacle classification in a medical environment, a medium and a program product, and relates to the field of intelligent anti-collision. The anti-collision method comprises the following steps: acquiring point cloud data of a target body in a medical environment; carrying out clustering reconstruction processing on the point cloud data of the first dynamic obstacle in the target body to obtain a reconstructed cluster, and carrying out space division on the cluster to generate a high-dynamic convex boundary; performing recursive space division on the point cloud data of the second dynamic obstacle and the static obstacle in the target body to generate a low dynamic convex boundary, and performing recursive space division on the point cloud data of the to-be-controlled anti-collision body to generate a target convex boundary; and expanding the boundary of the target convex boundary based on the safety distance, detecting the position relationship between the expanded boundary and the low-dynamic convex boundary and the position relationship between the expanded boundary and the high-dynamic convex boundary, generating a control instruction according to the position relationship, and controlling the movement of the to-be-controlled anti-collision body.

The invention relates to a target detection method of a tactical AR helmet. Comprising the following steps: a head posture sensing and space positioning module: after a helmet is started, an inertial measurement unit IMU sensor acquires acceleration and angular velocity data of a head through a gyroscope, an accelerometer and a magnetometer; integrating the data of the multiple sensors by using a sensor fusion algorithm including Kalman filtering; creating space mapping between the virtual scene and the real scene; triggering of a target detection module: inputting a real-time video frame captured by a camera into a pre-trained convolutional neural network (CNN) model; the CNN model performs feature extraction according to different detection tasks including target classification and object boundary detection; performing multi-scale detection on a target through multi-layer convolution and pooling operation; generating a plurality of candidate boxes using a regional proposal network (RPN); real-time target tracking and calibration: a detected target position is transmitted to a target tracking algorithm, and tracking is initialized; the size and the position of the tracking frame are adjusted according to the visual angle change of a helmet wearer.

The invention discloses a remote sensing image semantic segmentation method and equipment based on an enhanced MambaVision architecture. The method comprises the following steps: performing initial feature extraction on a to-be-segmented high-resolution remote sensing image through a patch embedding module; the initial features are input into a MambaVision backbone network to extract multi-scale features, the backbone network comprises four layering stages, the stage 1 and the stage 2 adopt adaptive expansion convolution blocks to balance high and low frequency features, and the stage 3 and the stage 4 adopt two-dimensional selective scanning and a multi-head attention mechanism to capture global dependence; performing fusion and up-sampling on the multi-scale features through an MFMS decoder, and optimizing texture and boundary detection; the decoder comprises an MFMS attention module and a channel mixer; and performing multi-scale convolution fusion on the output of the MFMS attention module based on the channel mixer to generate a segmentation result. According to the method, through two-dimensional selective scanning, adaptive expansion convolution and a multi-frequency multi-scale MFMS decoder, the segmentation precision and efficiency are improved, and the method is suitable for high-resolution and large-size remote sensing images.