88results about How to "Good segmentation effect" patented technology

The invention discloses a multi-modal semi-supervised medical image segmentation method based on SAM adaptive fine tuning, and the method comprises the steps: obtaining an original multi-modal image, adjusting the original multi-modal image to a preset size, and carrying out the image preprocessing, thereby obtaining a multi-modal image pair; simultaneously inputting the multi-modal image pair into a student branch model and a teacher branch model which are completely identical in structure, wherein each of the student branch model and the teacher branch model comprises a fusion module, an SAM encoder and a layered decoder; the multi-modal image pair passes through a fusion module formed by a convolutional network to obtain fusion features, the fusion features are input to the SAM encoder, and output features of different Transform layers are obtained; and inputting the plurality of output features into a hierarchical decoder, performing similarity calculation by the hierarchical decoder according to the plurality of output features to obtain prototype classification, and obtaining a prediction mask through a linear layer. According to the method, the multi-level features can be well utilized to realize fine-grained segmentation, and a good segmentation effect is realized.

The invention relates to the field of image segmentation, in particular to a multi-modal nuclear medicine image segmentation method and system and a storage medium. Comprising the steps that image type classification is carried out on multi-modal medical examination images, focus area positioning is carried out, and CT (computed tomography) focus images and PET (positron emission tomography) focus images are obtained respectively; carrying out lesion geometric mutation form prediction on the CT fault lesion image, and carrying out multi-modal image fusion boundary correction on the CT fault lesion image and the PET lesion image to obtain multi-modal lesion image fusion boundary correction data; according to the multi-modal lesion image fusion boundary correction data, performing multi-modal lesion region segmentation combination optimization on the CT image and the PET image to obtain a lesion region segmentation combination optimization strategy; and carrying out image segmentation model construction on the lesion region segmentation combination optimization strategy based on a strategy gradient algorithm to obtain a lesion image segmentation model. According to the method, the image segmentation technology is optimized, so that the image segmentation technology is more perfect.

The invention discloses a multi-task blood vessel segmentation model construction method based on a hybrid encoder. The encoder is a Swin Transform path multi-layer encoder based on a Mamform module, and the Mamform multi-layer encoder carries out data processing in combination with a W-MSA and an improved Mamba module; the decoder is a multi-task decoder and consists of three independent decoding paths which are respectively used for blood vessel segmentation, contour edge segmentation and blood vessel connectivity segmentation, and each decoding path adopts Swin Transformblock as a construction block and is used for generating feature mapping with the same size as an input image; an attention mechanism is shared, learned features are shared among decoders, the number of model parameters can be reduced, and overfitting is prevented; in the training process, a total loss function is formed through a loss function of a vascular connectivity decoding path, a self-distillation loss function and the like, the total loss function is calculated, model parameters are updated by using a back propagation algorithm, the segmentation performance of the model is gradually optimized, and after training is completed, the model can carry out precision on a vascular image.

The invention belongs to the technical field of medical image processing, and particularly relates to a double-encoder semi-supervised heart MRI double-ventricle segmentation method based on improved SAM. A teacher model and a student model which are used both comprise double encoders, prompt encoders and mask decoders, each double encoder comprises a ViT branch and a CNN-Mama branch which are parallel, parameter fine tuning of the ViT branch is realized through a position adapter and a feature adapter, the CNN-Mama branch mainly comprises a convolution fusion Mama block and a second-order dimension attention block, and the CNN-Mama branch is used for realizing fine tuning of parameters of the CNN-Mama block. The convolution fusion Mama block introduces an enhanced convolution block on the basis of a VSS block, and the second-order dimension attention block uses a covariance matrix to mine second-order statistical information of data; carrying out weighted summation on the output features of the ViT branch and the CNN-Mama branch to obtain the output features of the double encoders; the output features of the double-encoder and the prompt encoder are input into a mask decoder to be decoded, and a segmentation result is obtained; and performing joint training on the teacher model and the student model based on interpolation consistency regularization semi-supervision, and using the trained student model as a segmentation model for double-ventricle segmentation of heart MRI. The segmentation model has strong feature extraction capability, can effectively extract the edge information of the ventricles and the boundary information of the double-ventricle connection region, and improves the segmentation precision.

The invention discloses a remote sensing image ground object segmentation method based on hierarchical feature extraction and decoding, which relates to the technical field of remote sensing image processing, and comprises the following steps: step 1, collecting and preprocessing a remote sensing image, and constructing a training sample set; 2, constructing an image segmentation network, wherein the image segmentation network comprises a hierarchical encoder, a receptive field module unit and a network decoder which are connected in sequence; 3, training and optimizing the image segmentation network by adopting the training sample set to obtain a remote sensing image ground object segmentation model; and 4, collecting a remote sensing image to be segmented, and inputting the remote sensing image to the remote sensing image ground object segmentation model to obtain a ground object segmentation result. According to the method, the advantages of the advanced visual basic model and the U-shaped network architecture are combined, so that rapid and accurate segmentation of the ground target is realized.

The invention provides a domain adaptation cross-modal medical image segmentation method and device based on boundary comparison, equipment and a medium, and relates to the technical field of medical image segmentation. The method comprises the following steps: respectively acquiring a source sample and a target domain image from a source domain data set and a target domain data set; the first image segmentation model is used as a teacher model, and weights are distributed for the pseudo labels of the target domain images; a training sample is obtained through bidirectional cross-domain cutmix; performing supervision and self-training by taking a weight learnable first model as a student model; combining supervision loss and comparison loss during training to pull a query sample to a prototype positive sample and push a boundary negative sample as a target optimization parameter, and obtaining a second image segmentation model; and finally, segmenting a second modal medical image by using the model. The method has significant advantages in cross-modal medical image segmentation, and the segmentation performance can be effectively improved.

An underwater in-situ sea cucumber volume measurement method based on binocular vision and electronic equipment belong to the field of image processing, are used for solving the problem of keeping in-situ sea cucumber volume measurement, and are technically characterized in that a sea cucumber image is detected in underwater images collected by a binocular camera to obtain a sea cucumber image detection frame; segmenting a sea cucumber image detected in the image according to the sea cucumber image detection frame, and calculating mask information of the sea cucumber on an image plane; mapping the mask information to a global point cloud constructed by binocular information, and obtaining point cloud data of the sea cucumber; performing grid reconstruction on the point cloud data of the sea cucumber to obtain a continuous triangular grid; according to the method, the continuous triangular grids are converted into voxel representation, the number of non-zero elements in the voxel grids and the volume of each element are counted, the volume of the grids is estimated, and the volume of the sea cucumbers is obtained, so that the volume of the in-situ sea cucumbers can be accurately evaluated, and more accurate data support is provided for scientific cultivation of the sea cucumbers.

The invention discloses an improved tissue ultrasonic image segmentation system, and the system comprises an improved image segmentation network model FSwinNet which achieves the efficient segmentation of an image in a resource-constrained environment. The image segmentation network model comprises one or more encoder modules, one or more decoder modules and one or more bottleneck blocks; the Swin Transformer of the encoder module uses an SFFN (Sandwich Forward Neural Network) sand clock feedforward neural network module, and the decoder module uses an MBDW (Multimedia Broadcast Downlink Weight) lightweight operator. The invention further discloses a method for carrying out tissue ultrasound image lightweight segmentation by using the image segmentation system, and the method has a wide application prospect.

The invention discloses a remote sensing image segmentation method based on local consistency and pseudo label filtering. The method comprises the following steps: acquiring an optical remote sensing data set; constructing a remote sensing image segmentation model, wherein the remote sensing image segmentation model comprises a local consistency loss calculation module and a pseudo label filtering module; and inputting the optical remote sensing data set into the remote sensing image segmentation model to obtain a remote sensing image segmentation result graph. A local consistency loss and pseudo label filtering strategy is provided, local consistency features are effectively learned, pseudo label noise is removed, a good remote sensing image segmentation effect is obtained, more label-free remote sensing images are utilized to improve remote sensing image segmentation precision, remote sensing images acquired by satellites can be segmented, and remote sensing image segmentation efficiency is improved. The problems that in a remote sensing image, objects are dense, the background difference is large, the size change range is large, the color and texture difference is large, local consistency features are difficult to obtain, and a large amount of noise inevitably exists in a pseudo tag are solved.

The invention discloses a heart AI system based on deep learning, and relates to the technical field of medical image processing, and the heart AI system comprises a two-dimensional fully-supervised left atrium segmentation algorithm module, a three-dimensional semi-supervised left atrium segmentation algorithm module, and a whole heart segmentation algorithm module. Meanwhile, through combination of Transform and a residual network, semantic information in the image is captured in a larger visual field, so that the segmentation precision of the network is improved; a two-dimensional fully-supervised left atrium segmentation algorithm module based on axial attention is provided from a two-dimensional angle by taking UNet as a basic model, the algorithm module firstly constructs a double-layer residual error convolution module, gradient information is transmitted through a plurality of paths, then a task-driven feature enhancement module is introduced to optimize feature representation, and finally, a task-driven left atrium segmentation algorithm is constructed. A multivariate feature fusion module is designed to integrate features, and finally a feature coupling module is designed, so that the limitation of traditional convolution operation is overcome.

The invention discloses a medical image automatic segmentation method based on a dual-aggregation hybrid neural network, and the method comprises the steps: inputting a to-be-segmented medical image into a pre-trained medical image segmentation network, and outputting a medical image segmentation result; according to the medical image segmentation network, a dual-polymerization mixed U-shaped network is adopted, the dual-polymerization mixed U-shaped network comprises two parallel encoders and a single decoder, and the two parallel encoders are a convolutional neural network and a Transformer respectively; local features and global features of the medical image are extracted at the same time through a convolutional neural network and a Transform; performing multi-scale feature fusion on the extracted local features and global features through a collaborative feature aggregation module CFA and a non-collaborative feature aggregation module NCFA; and inputting the features subjected to multi-scale feature fusion into a decoder, and outputting a medical image segmentation result. According to the invention, multi-scale feature fusion can be realized, the segmentation precision of a medical image segmentation result is enhanced, and the performance of a medical image segmentation network is improved.

The invention relates to the technical field of iPSCs colony pluripotency evaluation, in particular to an iPSCs colony pluripotency evaluation method based on hierarchical Transform attention feature fusion, and the method comprises the following steps: collecting images in an iPSCs culture process, and establishing a mapping relation between stem cell pluripotency and cell colony morphology; constructing an iPSCs image data set, enabling each pixel in the image to correspond to a pluripotent state category, and marking a pixel level; building an evaluation model based on Transform attention feature fusion, wherein the evaluation model comprises a Gabor edge feature enhancement module, a layered Transform trunk feature extraction module and an attention feature fusion module; the obtained feature layers are fused after being subjected to up-sampling and normalization, and then a prediction image, namely an evaluation result, is obtained after decoding; training the model by using the iPSCs image data set; and carrying out pluripotency evaluation on the image in the iPSCs culture process by using the model obtained by training. According to the method, human factor interference can be prevented, and the precision of iPSCs set pluripotency evaluation is high.

The invention relates to the technical field of machine vision, in particular to an image segmentation method and system for liquid crystal screen display. The method comprises the following steps: acquiring basic data of the liquid crystal screen; performing screen response characteristic analysis according to the basic data of the liquid crystal screen to obtain screen response characteristic data; performing multi-scale image acquisition according to the basic data of the liquid crystal screen to generate multi-scale image data; performing characteristic classification on the liquid crystal display according to the screen response characteristic data, and performing edge compensation analysis on the multi-scale image data to obtain edge characteristic compensation data; acquiring real-time data of the touch screen; and performing touch interference identification analysis on the real-time data of the touch screen according to the edge feature compensation data to generate touch interference mask data. By analyzing the screen response characteristics and performing edge compensation analysis, the phenomenon of edge blurring caused by liquid crystal response time limitation is reduced, and the accuracy of edge detection is improved.

The invention discloses a lightweight 3D heart MRI segmentation algorithm based on 3D efficient partial attention and three-dimensional sparse MLP, and the algorithm obtains an MRI pixel block with a detailed target region feature through a 3D efficient deformable attention module EDA, and fits the edge distribution of a segmented region with lower calculation complexity through reference point translation. Efficient attention calculation ensures feature information extraction and greatly reduces resource consumption; the method comprises the following steps: constructing a cross-shaped receptive field at extremely low cost through information in transverse, longitudinal and depth directions of a three-dimensional sparse MLP module (triSMLP) mixed voxel block, and outputting a fine characteristic spectrum with a global receptive field through three-time superposition; the feature maps output by the EDA and the triSMLP recover down-sampling lost detail features at an encoder through a partial convolution feature fusion decoder. Compared with most of the leading edge 3D segmentation algorithms at present, the method has the advantage that a better segmentation effect is obtained with extremely small computing resources.

The invention discloses an NIR-II video lymphatic vessel segmentation method based on Frangi and multi-frame accumulation, and belongs to the field of computer vision, and the method comprises the following steps: converting a video into a frame image; preprocessing the frame image by using a contrast limited adaptive histogram equalization algorithm and neighborhood mean filtering; performing top-hat transformation on the preprocessed image to obtain a rough foreground image; taking a mean value of non-zero pixels as a threshold value, and performing adaptive segmentation frame by frame; accumulating the output binary image, and enhancing a tubular structure in the image by using Frangi filtering; and performing certain morphological processing on the image after Frangi filtering to obtain a final lymphatic vessel segmentation result. According to the NIR-II video lymphatic vessel segmentation method based on Frangi and multi-frame accumulation, the detection capability of low-contrast lymphatic vessels with tiny disturbance in the video is improved.

The invention provides an instance segmentation detection method and application based on improved YOLOv8s. The method comprises the following steps: collecting a to-be-segmented data set, preprocessing the to-be-segmented data set, constructing an improved YOLOv8s model, and training the preprocessed data set; the method is applied to target detection of images and / or videos, such as segmentation detection of second-phase particles of nickel-based superalloy. According to the improved model, an SPDConv layer and a small target detection layer are added, and an SIoU loss function is adopted, so that the small target detection performance of the model is greatly improved, and the omission ratio is reduced; second-phase particle dispersion calculation is updated and embedded into the second-phase particle identification process, batch detection is achieved, and indexes such as the average area fraction, the average number, the average size and the dispersion of the second-phase particles can be directly calculated; the model segmentation performance is good, the operation speed is high, the target detection process is opened, and the method can also be applied to other processes, intelligent recognition of macroscopic objects and online recognition and calculation of videos.

The invention discloses a blood vessel segmentation method based on perceptual tissue rules, and belongs to the field of image processing. Comprising the following steps: establishing perceptual organization rules; establishing a neural network based on a perceptual organization rule; establishing a semi-supervised learning method based on a covariant rate; setting a 3D image mode; and defining a loss function and setting an experiment. The method is inspired by a human visual system and comprises two key parts: a neural network based on a perceptual organization rule and a semi-supervised learning method based on a covariant rate. And by calculating perceptual tissue rules such as similarity, proximity and continuity, expression of vascular coherence structure features is enhanced, so that the segmentation effect is improved. The blood vessel segmentation method disclosed by the invention shows excellent diagnostic ability in assisting doctors in clinical diagnosis and treatment, and can be used for quickly analyzing and processing the condition of a patient.

The invention discloses a railway construction protection method and system, and the method comprises the steps: firstly, setting hyper-parameters based on a construction operation position; secondly, acquiring video stream data of a construction scene in real time based on an unmanned aerial vehicle; secondly, segmenting a railway in the obtained video stream data by adopting an instance segmentation algorithm, and obtaining pixel point coordinates of an uplink track and pixel point coordinates of a downlink track; then, based on the pixel point coordinates of the uplink track and the pixel point coordinates of the downlink track, a fitting straight line of the uplink track and the downlink track is calculated; then, based on the fitting straight line of the uplink track and the downlink track, an electronic fence is automatically generated; and finally, based on the coordinate position of the constructor and the electronic fence, whether the constructor breaks into the dangerous area is judged. According to the method, the instance segmentation algorithm is adopted to segment the railway, the segmentation effect is good, manual drawing of an electronic fence is not needed, and only the unmanned aerial vehicle needs to be carried to a designated construction site without external cooperation.

The invention relates to the technical field of image processing, in particular to a training method of a semantic segmentation model and a semantic segmentation method and device. Comprising the following steps: acquiring and preprocessing tree-containing images, and constructing an image set; carrying out image segmentation based on a U-Net architecture, wherein the U-Net architecture comprises an encoder, a decoder and a jump connection; based on Dice coefficient loss and weighted cross entropy loss, determining a total loss function to optimize image background and tree category imbalance; the learning rate is adjusted in each training step through an Adam optimizer in combination with gradient first-order moment estimation and gradient second-order moment estimation, and learning rate attenuation adjustment of the Adam optimizer is achieved in combination with cosine annealing scheduling; and training the semantic segmentation model based on the configured Adam optimizer and cosine annealing scheduling until the semantic segmentation model is obtained through convergence. Therefore, based on the obtained semantic segmentation model, subsequent image segmentation processing application in an education robot can be facilitated.

The invention relates to the field of image processing, in particular to a water area ecological environment pollution monitoring system which comprises a water area ecological image acquisition module, an edge image acquisition module, an adhesion rate acquisition module, a segmentation module and a water area ecological environment monitoring module. Obtaining the number of edge pixel points under different gradient thresholds according to the gradient amplitudes of all pixel points in the water area ecological image so as to obtain the mutation degree of each gradient threshold, obtaining an optimal edge image according to the mutation degree so as to obtain an aquatic product binary image, obtaining the adhesion rate of each pixel point in a connected domain of the aquatic product binary image, and obtaining the adhesion rate of each pixel point in the connected domain of the aquatic product binary image. And obtaining the size of a structural element of the pixel point according to the adhesion rate, carrying out morphological corrosion on each pixel point in the connected domain to obtain a segmented image, and carrying out water area ecological environment monitoring. The method has a good segmentation effect on the overlapped aquatic products, facilitates dynamic tracking of the aquatic products, and ensures the accuracy of water area ecological environment monitoring.

The invention discloses a pathological image segmentation method based on a U-Net model of an improved encoder and decoder, and the method comprises the following steps: carrying out the preprocessing of data, and improving the generalization capability of a model; a U-Net model encoder and a U-Net model decoder are improved, and an EEDU-Net model is established; training the model by using the training set data; optimal model parameters are obtained, test set data are input, and a prediction result of the model is subjected to visualization processing. According to the invention, each layer of encoder is changed into a multi-branch form, so that the capability of encoding to extract information of different scales is improved. And meanwhile, semantic differences are eliminated through channel attention and axial attention processing on the feature map subjected to jump connection, and the effectiveness of each jump connection is ensured. The robustness and precision of pathological image segmentation are improved by using the EEDU-Net model, and a segmentation effect superior to that of an existing model is shown.

The invention provides a fine-grained segmentation method for extremely small defects in a welding seam of a spiral steel pipe, and relates to the technical field of nondestructive testing based on machine vision. According to the method, a fine-grained minimum defect segmentation network model is constructed under the condition that minimum defects in a spiral steel pipe welding seam are difficult to distinguish in a static scene, the model comprises a feature extraction network, a semantic discrimination encoder, a comparison conversion mechanism, a progressive iterative decoding strategy and a plurality of convolution modules, and a semantic discrimination system structure is designed. Features are self-adaptively initialized with semantics as guidance, and defect scale differences are relieved; introducing a comparison conversion mechanism to dynamically optimize defect features; and finally, performing fine-grained pixel-level segmentation on the fused feature map by adopting a progressive iterative decoding strategy. According to the method, a good segmentation effect can still be achieved in adverse scenes such as unbalanced sample category distribution, dense minimum defect distribution, pixel redundancy and background interference, and the segmentation performance of the network is effectively improved.

The invention discloses a method and a system for automatically intercepting a high-frequency signal in a constant-speed operation section of mechanical equipment. The method comprises the following steps: acquiring signal data of the mechanical equipment; determining the size and the step length of a first sliding window processing window; performing sliding window processing on the original signal, calculating the variance of each window signal, and performing data compression to obtain a first signal; visually judging whether signals in different operation states in the first signals are in the same order of magnitude or not; determining the window size and step length of second-time window sliding processing; performing sliding window processing on the compressed first signal, calculating the variance of each window signal, and performing data compression to obtain a second signal; determining a threshold magnitude order of data distinguishing of the operation section and the non-operation section; finding out a starting point and an ending point of the operation section, and restoring to original signals to obtain operation section signals; calculating a central point of an operation section, calculating constant-speed operation time according to an actual working condition, and restoring to an original signal; and error analysis is carried out through a starting point and end point signal interception mode and a midpoint signal interception mode.

The application relates to a liver cancer CT image segmentation method based on channel attention, a segmentation network for liver and tumor regions is constructed, residual modules are used to replace ordinary convolution layers on the basis of a U-Net encoding-decoding structure, the training speed and precision of the network are improved, an attention mechanism is added in the decoder stage, the importance and mutual dependence of different channels in a feature map are fully considered, feature maps output by each stage of the decoder are up-sampled to the size of an original image through a deep supervision module and are spliced with the feature map output in the last stage, feature loss is prevented, two same segmentation networks are used for segmenting a liver region of interest and segmenting tumor cells respectively. The method has good segmentation effect without significantly increasing the parameter amount; from the clinical point of view, liver and tumor regions in an abdominal CT image are accurately segmented, a good auxiliary role is provided for doctor diagnosis, and the diagnosis efficiency is improved.

The utility model provides a kind of cut fresh steak machine, belong to meat cutting machine technical field.It solves the problem of slicer how to ensure the stable operation of machine when cutting fresh steak.The machine includes panel, cutter assembly and meat clamping assembly are provided on panel, meat clamping assembly includes the steel rope that middle part is upturned, the both ends of steel rope are connected with cylinder one and cylinder two respectively, cylinder one and cylinder two can drive the both ends of steel rope to be close to each other, at least one end of steel rope is configured to be slidable and is connected with driving element for pulling steel rope to make the middle part of steel rope arching contract.The both ends of steel rope can be moved towards the both sides of meat strip under the driving of cylinder one and cylinder two, so that steel rope can be embraced on meat block by fitting the contour of meat block, and after cutting is completed, cylinder one and cylinder two reset can drive the both ends of steel rope to be away from meat block, avoid sticking to meat block, affect subsequent cutting, so that the stability of continuously cutting out steak can be ensured.

The invention relates to an efficient medical image ROI region extraction method and system with lower parameters based on a deep learning network, and belongs to the technical field of medical image processing. The method comprises the following steps: firstly, acquiring medical image data, and preprocessing an image; inputting the preprocessed medical image into a constructed deep learning model, wherein a feature extraction module LGFE is used for extracting detail and contour information in the medical image; compressing the information in the encoding process through an information compression module; extracting features of different scales from the compressed medical image by using a decoder; the features of different scales are fused through an efficient feature aggregation module; and inputting the fused feature map into a convolution module, and performing final medical image segmentation processing. According to the invention, by combining the lightweight module and adjusting the calculation ratio of the encoding and decoding stages, the segmentation precision is effectively improved, the model complexity is reduced, and the efficiency and accuracy of medical image segmentation are improved.

The present application relates to a kind of forest leaf instance segmentation method and system based on deep learning, method includes: obtaining vegetation image, vegetation image is input into leaf instance segmentation model, obtains leaf instance segmentation prediction result;Leaf instance segmentation model is trained using training set;Training set includes: vegetation original image;Feature extraction and enhancement are carried out using backbone module in leaf instance segmentation model, and adaptive spatial fusion mechanism in progressive feature pyramid network is integrated to dynamically adjust feature weight, generate dynamic fusion feature;Through the dynamic asymmetric spatial perception mechanism built-in in dynamic anomaly regression head module, the corresponding multi-source deformation feature layer of dynamic fusion feature is obtained, and the feature fusion strategy of top-down cascaded decoding module is used to optimize multi-scale feature, obtain multi-source fusion feature layer, further using multi-source fusion feature layer, generate leaf instance segmentation prediction result.The present application solves the problems of data scarcity, poor adaptability and low efficiency.

The application discloses a biomass pyrolysis system for co-production of tar and fuel gas, which comprises a casing, a crushing mechanism and a crushing cylinder, the crushing mechanism is rotatably installed in the casing, the crushing cylinder is fixedly installed on the bottom of the crushing mechanism, the crushing cylinder is coaxially arranged with the casing, a crushing space is formed between the outer wall of the crushing cylinder and the inner wall of the casing, a feeding port is formed in the top of the casing, and an outer discharging port is formed in the bottom of the casing; a driving assembly is installed on one side of the casing, the output end of the driving assembly is drivingly connected with the crushing mechanism, the driving assembly drives the crushing mechanism to rotate in the casing, and a fixed gear ring is coaxially and fixedly installed in the casing. The biomass raw material can be crushed through the crushing mechanism, the biomass raw material can be finely processed to the maximum extent during crushing, and the pyrolysis speed can be improved during pyrolysis.

This invention discloses a semantic segmentation method for ocean internal wave stripes in SAR images, relating to the field of semantic segmentation of remote sensing images. The method model consists of an encoder and a decoder. The encoder comprises four Transformer modules, each containing a self-attention layer, a feedforward neural network, and an overlap patch merging module. Within each module, the input image is processed N times through a multi-head self-attention mechanism, and then the merging module generates feature maps at four scales. The decoder consists of three modules: a serpentine convolution, an EVC module, and an expectation-maximization attention network. The advantages of this invention are: the model fully utilizes the multi-scale fusion module, improving performance and robustness; the use of serpentine convolution can better extract features of linear shapes; and the use of the expectation-maximization attention network improves model accuracy while reducing computational complexity.

The invention belongs to the technical field of photovoltaic module recovery, and particularly relates to a device for segmenting photovoltaic glass and an EVA adhesive layer and a segmentation process. A photovoltaic glass heating area is used for heating the segmented photovoltaic glass and conveying the heated photovoltaic glass to be segmented to a photovoltaic glass segmentation area; the photovoltaic glass dividing area comprises an unpowered conveying roller, a pushing mechanism, a conveying belt, a dividing mechanism and a recycling box, and the pushing mechanism is used for moving the photovoltaic glass to be divided from the input end to the output end and conveying the divided photovoltaic glass to the conveying belt; an included angle is formed between a cutter of the cutting mechanism and the photovoltaic glass to be cut during cutting, and the included angle is 0-30 degrees. The photovoltaic glass cutting device has the function of heating photovoltaic glass to be cut, meanwhile, the angle of the cutter when the photovoltaic glass to be cut is cut is controlled, and the effect of removing an EVA adhesive layer is improved.