81results about How to "Accurate segmentation" patented technology

The invention discloses a rice seedling leaf age intelligent identification system based on a depth camera, and belongs to the technical field of agricultural intelligent equipment and machine vision. Comprising a monitoring point gridding path planning module, a mechanical arm cooperative positioning data acquisition module, an RGB-D data preprocessing module, a dynamic foreground seedling accurate extraction module, a leaf age recognition confidence evaluation module, a leaf age data visualization presentation module and an integrated control strategy feedback module. RGB color features and connected domain analysis are combined to optimize a mask, a front single seedling is accurately segmented, background interference is eliminated, the confidence coefficient is dynamically calibrated through a deep learning model and image quality features, texture definition and edge continuity features are combined to generate calibrated confidence coefficient, confidence coefficient evaluation is directly associated with an agricultural decision, and the accuracy of the agricultural decision is improved. The leaf age result is generated only based on reliable data, the personnel rechecking demand is reduced, and the decision-making efficiency is improved.

This invention discloses a 3D scene segmentation and interaction method based on 3D Gaussian, comprising: Step 1, instance discovery: inputting 3D Gaussian scene data, dividing the 3D Gaussian points into structurally coherent instance-level Gaussian groups to obtain refined instances; Step 2, instance and scene semantic assignment: selecting representative viewpoint images of refined instances and inputting them into a visual-language model to generate semantic description labels for the instances; filtering instance pairs in the scene through spatial geometric relationships, and clarifying the spatial relationship description of instance pairs through a large model, constructing a static scene graph that integrates geometric proximity relationships and instance semantic relationships, forming a structured description of all instances; Step 3, natural language-driven instance localization and interaction: receiving user input commands, combining the instance semantic description, the static scene graph, and the real-time viewpoint direction relationship during the query to perform multi-dimensional matching, determining the target instance ID, and executing interactive operations.

The utility model belongs to medical apparatus and instruments, concretely relates to a kind of pathological auxiliary material taking tool of endoscopic mucosal resection specimen, including total connecting plate and comb plate;The side of total connecting plate is connected comb plate;Comb plate is composed of several parallel straight boards, the width of each straight board is less than target material taking width;The distance between the upper edge of the n-1th straight board to the upper / lower edge of the nth straight board is equal to the distance between the upper / lower edge of the nth straight board to the upper / lower edge of the n+1th straight board, and the distance between the upper / lower edge of the n-1th straight board to the upper / lower edge of the nth straight board is equal to target material taking width, wherein, n is natural number greater than 1 and less than total number N.Compared with prior art, the utility model solves the problem that it is difficult to control the cutting size and easy to cause specimen contamination when cutting specimen into mucosal strips in prior art.The tool of the present scheme can effectively assist cutting positioning and control the cutting size.

The application discloses a complex specification multi-modal understanding method and system based on YOLO two-stage segmentation, comprising the following steps: performing pre-processing on an input specification image; inputting the pre-processed image into a coarse-grained detection stage of an improved YOLOv8 network to generate a coarse-grained candidate region set; inputting the coarse-grained candidate region set into a fine-grained segmentation network based on an improved YOLOv8 feature extraction structure; constructing a layout hierarchical relationship structure based on an accurate layout segmentation result; according to the layout hierarchical relationship structure, performing multi-modal feature extraction on the accurate layout segmentation result, and calculating a matching weight; inputting a graphic-text semantic alignment result and the layout hierarchical relationship structure into a logical structure modeling module together to construct a layout element graph; and generating a knowledge graph semantic output result according to a structured logical reasoning result. The application realizes automatic structured understanding of a complex specification by adopting YOLO two-stage segmentation and multi-modal semantic alignment.

The invention discloses a semi-supervised medical image segmentation method based on dynamic ambiguity perception, and designs a dynamic ambiguity perception framework which comprises a heterogeneous feature extraction module, a dynamic ambiguity bootstrap module and an ambiguity perception module. Firstly, an original medical image enters a heterogeneous feature extraction module, and two competitive subnets extract high-level semantic features and generate different pseudo tags. The pseudo labels generated by the two competitive subnets enter a dynamic ambiguity bootstrap module, and the competitive subnets are divided into a strong network and a weak network by calculating the quality scores of the two pseudo labels. After a strong network and a weak network are divided, prediction generated by the weak network focuses on mutual ambiguity perception which biases to targeted learning of pseudo label knowledge, and prediction generated by the strong network focuses on self-ambiguity perception of self-ambiguity examination. The medical image segmentation accuracy is improved, the diagnosis time of doctors can be effectively shortened, and the efficiency is improved. Meanwhile, missed diagnosis or misdiagnosis caused by different diagnosis levels or fatigue of doctors is reduced.

The embodiment of the present application provides a parcel image segmentation method, device, system and image processing equipment, the method is applied to the image processing equipment in the security inspection system, the security inspection system further includes a security inspection equipment, the security inspection equipment has a detector and a detection unit, the detection unit includes multiple groups of detectors, the detection range of the multiple groups of detectors covers the space of the preset height perpendicular to the conveying belt transmission direction of the security inspection equipment, and the method comprises the following steps: obtaining parcel data detected by the detector in the operation process of the security inspection equipment and a detection result of the detection unit; in the case that the detection result indicates that there is no parcel on the conveying belt, determining parcel data in the parcel data based on the difference between the parcel data and reference data; and based on the parcel data, the parcel data is segmented to obtain a parcel image. The embodiment of the present application can improve the accuracy of parcel image segmentation and reduce the loss of parcel data.

The application discloses an optical remote sensing image semantic segmentation method and relates to the technical field of optical remote sensing image processing. The method is composed of a progressive context aggregation mechanism and a dynamic wavelet transform attention module, query-key-value features are generated in a hierarchical manner, and progressive fusion of low-level spatial details and high-level semantic information is realized; and grouping multi-level wavelet decomposition is adopted to adaptively and weightedly enhance low-frequency semantic features and high-frequency detail features, and dynamic frequency filtering is realized in combination with query guidance. Compared with the prior art, the application can effectively capture multi-scale features and fine spatial details of remote sensing images, fully model global context and long-distance dependency, and is compatible with mainstream encoders, so that more accurate and robust semantic segmentation can be realized on public data sets.

The application discloses a kind of for the method, device, equipment and medium of tab abnormality detection in battery cell production process, comprising: the tab area image collected in battery cell production process is segmented to generate tab mask;Based on the tab mask extraction multi-scale pixel-level feature vector, and the multi-scale pixel-level feature vector is input into unsupervised probability GMM model to identify pixel-level abnormal point;The pixel-level abnormal point is analyzed to obtain candidate abnormal area, and the parameter index of the candidate abnormal area is obtained;Determine whether the parameter index meets the set tab abnormality judgment rule, if meet, it is judged as tab abnormality, and tab abnormality result is output.Therefore, the application can be widely applied to the detection of tab folding, crease, fracture, misplacement and other abnormalities on battery cell production line.

This invention provides a method and system for accurate tumor segmentation in CT images, relating to the field of image processing technology. The method includes: determining the region to be identified in a CT image containing a tumor using an image segmentation model; determining the boundary line, center position, and nearest reference pixels of the region to be identified, along with their probability information; and then selecting correction pixels from the nearest reference pixels to obtain a correction region, thereby updating the trained image segmentation model. According to this invention, after obtaining the region to be identified in the CT image of each slice using the image segmentation model, the boundary line of the region to be identified can be mutually verified based on the nearest pixels on the boundary line and the pixels of adjacent slices. This allows for the selection of pixels that better represent the tumor edge from the nearest pixels on the boundary line, thereby achieving more accurate segmentation of the region containing the tumor.

The present application belongs to the technical field of ground laser radar forestry data processing, and discloses a broad-leaved forest single tree segmentation method and system based on branch information guidance, taking ground-based laser radar broad-leaved forest point cloud as a processing object, using RANSAC cylindrical fitting to combine the growth characteristics of the tree trunk to detect the tree trunk; starting from the top of the tree trunk in the low vegetation area, the tree branches are extracted by segmenting and growing the branches and combining the thickness changes of the branch segments; starting from the end of the branch, the tree crown leaf point cloud is segmented by layer-by-layer growth. The present application has stronger trunk detection capability under the conditions of lush low vegetation and complex terrain; on the other hand, the present application can accurately segment the tree crown when the large and small crowns are intertwined and the multiple crowns are closely surrounded. The algorithm is efficient, simple and easy to use, and has great practical significance for improving the semantic understanding ability of forest scenes, assisting forest resource investigation, vegetation ecological research, and satellite remote sensing product calibration and verification.

The invention discloses a defect feature recognition method based on a clothing visual image and a quality inspection system, and aims to solve the problems that traditional manual quality inspection is low in efficiency and poor in precision and an existing automatic system is insufficient in robustness and generalization ability. The method comprises the following steps: after image preprocessing, segmenting by using an SAM network to obtain a clothes main body and an initial flaw; constructing multi-scale features by the FPN, inputting the multi-scale features into the improved YOLOv11 network, and outputting an initial candidate box; correcting the candidate frame according to IoU / Dice to obtain a refined frame; extracting texture and morphological characteristics and calculating abnormal scores; carrying out weighted fusion on multiple indexes to obtain a comprehensive confidence coefficient to identify flaws; and carrying out secondary training to update the model after manually annotating the low-confidence sample. The system comprises eight corresponding modules, realizes full-process automatic detection, can significantly improve the precision, robustness and automation level of garment defect identification, and has important practical application value.

The invention provides a color feature extraction and correction method and system for drug sensitive plate MIC value interpretation and a computer readable storage medium. The method comprises the following steps: acquiring a to-be-processed drug sensitive plate image; performing visual preprocessing such as exposure, contrast and white balance on the image according to the configuration file; high-precision alignment correction of the image is realized by using ORB feature detection and a BFMatcher matching algorithm; generating a transparent mask with an Alpha channel based on predefined hole position contour data, and performing non-destructive target segmentation on the aligned image; and converting the target region to an HSV color space, extracting H-channel hue features, executing cyclic correction, eliminating the problem of numerical value jump of the red region, and obtaining stable color feature data. The method has the advantages of being high in image registration precision, accurate in segmentation, stable in color feature, high in robustness and the like, and automatic and standardized interpretation of the MIC value of the drug sensitive plate can be achieved under different shooting conditions.

In order to solve the problems of limited labeled data, differences between blood vessels and interference of lesion area, the present application discloses a retinal blood vessel image segmentation method based on a multi-scale dilated convolution residual network, which is still a challenge problem for accurately segmenting retinal blood vessels, especially fine blood vessels, on a retinal fundus image. The present application designs a multi-scale residual input and output module to make up for the loss of part of the blood vessel structure information due to down-sampling, combines the advantages of dilated convolution and DropBlock to relieve network overfitting and reduce the influence of the lesion area on blood vessel feature extraction, and further introduces a multi-scale mean pooling module to obtain high-level features and retain context information. Finally, by improving the way of jump connection, the dilated convolution is effectively used to improve the information transmission capacity of the jump connection. Compared with other algorithms, the present application can more accurately segment the fine blood vessels in the retinal image under complex conditions and has better robustness.

This invention discloses a non-contact tire deformation recognition method based on a fine-tuned large-scale visual model. The method includes calibrating a monocular high-speed camera, fine-tuning the parameters of the mask decoder of the large-scale visual model using a tire image dataset, generating a point coordinate cue sequence based on pixel calculation using OpenCV, inputting the cue sequence into the fine-tuned large-scale model for segmentation, further processing the pixel matrix using OpenCV to generate a point cue sequence, and post-processing using iterative geometric fitting and region growing algorithms to obtain the mechanical deformation parameters of the target sample tire. This invention can achieve accurate and rapid tire deformation recognition, reaching pixel-level precise segmentation. It solves the problems of large errors, limited measurement environments, nonlinear image distortion caused by cameras, weak generalization ability, and high training costs in existing computer vision-based vehicle tire recognition methods.

The application discloses a rape whole growth cycle monitoring method and system based on three-dimensional point cloud reconstruction, relates to the field of intelligent agriculture and computer vision technology, collects three-dimensional point cloud data at multiple key growth periods of rape, constructs a semantic growth graph after pretreatment; the graph is input into a pre-trained time sequence model, the energy flow among source nodes, library nodes and channel nodes is simulated based on the energy dynamic balance principle, the future growth state of the plant is deduced, and growth monitoring data is finally output. The application realizes nondestructive monitoring of rape from the bud stage to the silique stage through three-dimensional point cloud technology, and overcomes the problems of low efficiency and strong destructiveness of traditional methods. Through the construction of the semantic growth graph, the organ recognition and segmentation problem is solved. Further, a calculable model is constructed by combining the source-library theory, photosynthetic product flow and organ competition are simulated, the biomass is accurately predicted before the silique forms, and the phenomenon of abortion is recognized, so that the leap from morphological monitoring to growth mechanism deduction is realized.

The invention relates to the technical field of data processing, in particular to an image material processing method and system. The method comprises the following steps: acquiring a to-be-processed image material, and performing semantic analysis on the image material by utilizing a preset visual language model to obtain a text prompt corresponding to each element; inputting the text prompt and the image material into a preset target detection model to obtain a detection result; for a hierarchy corresponding to each text prompt or bounding box, determining an interaction matching threshold value of the hierarchy; screening the bounding box according to a comparison result of the confidence of the bounding box and a corresponding interaction matching threshold to obtain a target bounding box; and inputting the target bounding box and the corresponding text prompt into a preset segmentation model, and generating a segmentation mask corresponding to each element. According to the method provided by the invention, automatic positioning, separation, filling and repairing of elements of different levels in the image material can be realized, and the efficiency and precision of image material processing are improved.

The application discloses a kind of automatic prompting ultrasound image segmentation method and system based on SAM, the method of the present application includes using ultrasound image segmentation network model to carry out ultrasound image segmentation, including CNN encoder, classification head module, low-level feature refining module, SAM's Transform encoder, cross-branch attention module, high-level feature enhancement module, pixel decoder, prompt encoder and mask decoder, pixel decoder decodes and generates preliminary segmentation prediction map, and mask decoder is based on the point, mask embedding vector generated by prompt encoder and the image embedding obtained by CNN encoder and Transform encoder Decoding obtains the final segmentation prediction map.The present application aims to solve the problem that most of the existing segmentation methods based on SAM rely on artificial prompting and have poor adaptability to ultrasound images, reduce the false segmentation affected by ultrasound noise and shadow, and improve the segmentation performance and generalization performance of the network.

The application discloses a method for realizing dynamic visualization of non-heritage pictures, and belongs to the cross field of computer vision and digital cultural heritage protection. The method comprises the following steps: collecting non-heritage pictures and text instructions containing dynamic requirements and respectively preprocessing; completing semantic labeling and image segmentation based on a hierarchical labeling system combined with a ResBlock-CBAM enhanced U-Net; detecting key points according to non-heritage object types; introducing a cultural constraint mechanism, selecting a GANs model to fuse features to generate dynamic data; previewing and iteratively optimizing, and the method can also integrate style picture features. The method can improve labeling and segmentation accuracy, guarantee the cultural authenticity of dynamic effects, improve generation efficiency, adapt to various non-heritage scenes, and optimize user experience, and is suitable for non-heritage digital inheritance.

This invention relates to a method, apparatus, and medium for rapid sorting of poultry meat percentage based on X-ray imaging. The method includes: Step S1: acquiring X-ray images of the poultry to be tested; Step S2: identifying the sternal region and skin boundary based on the X-ray image; Step S3: drawing a normal at the sternal apex, obtaining the intersection of the normal at the sternal apex and the skin boundary as the first surface point, and obtaining the initial bone-skin distance based on the distance from the sternal apex to the first surface point; Step S4: obtaining the angle between the X-ray machine's visual axis direction and the normal direction of the first surface point as the consistency difference angle, obtaining the sternal integrity ratio and sternal principal axis attitude angle based on the sternal region, and correcting the initial bone-skin distance based on the consistency difference angle, sternal integrity ratio, and sternal principal axis attitude angle to obtain the corrected bone-skin distance; Step S5: obtaining the meat percentage grading result based on the corrected bone-skin distance. Compared with the prior art, this invention can achieve poultry meat percentage sorting based on X-ray imaging.

The invention relates to the technical field of fuel cell production, in particular to a fuel cell bipolar plate adhesive tape segmentation method, system, medium and equipment based on gradient attention and a multi-scale void residual structure, a MobileNetV3-U-Net fusion architecture is adopted, lightweight MobileNetV3 is used as an encoder, high-level semantic features of an image are extracted step by step through a multi-layer inverse residual block, and the high-level semantic features of the image are extracted through a multi-scale void residual block. Meanwhile, a DG Attention module is embedded in the bottommost layer of the encoding stage, the DG Attention module guides attention weight calculation by extracting gradient features and long-strip-shaped features and strengthens feature capture of the edge and the slender structure of the adhesive tape, a decoder reserves multi-layer jump connection of U-Net, meanwhile, a traditional convolution operation is replaced with a Res2DilatedConv module, and therefore the decoding efficiency is improved. Multi-scale feature extraction is realized through channel grouping, multi-voidage convolution and cross-group feature fusion, the structural difference of the adhesive tape under different widths and bending degrees is adapted, and efficient and accurate segmentation of the adhesive tape region in the fuel cell bipolar plate is realized.

This invention relates to the field of high-pressure internal gear pump technology, and discloses a method for predicting the multi-axis fatigue life of a high-pressure internal gear pump. The method involves performing typical full-cycle operations on the target gear pump within its expected lifespan, and acquiring the flow parameters of the target gear pump's discharge port at fixed time intervals. The flow parameters are then segmented based on the discharge tooth cavity to form M flow characteristic sequences. For the m-th flow characteristic sequence, the first peak, valley, and second peak are extracted to calculate the m-th bimodal index, where 1 ≤ m ≤ M, and m is a positive integer. The M bimodal indices are used to determine the characteristic time of the target gear pump through change point detection, and the cumulative number of cycles corresponding to the characteristic time is taken as the first cycle life. The characteristic time represents the transition time between the stable period and the period of significant change of the target gear pump. The cumulative number of cycles of the target gear pump within its expected lifespan is taken as the second cycle life.

This invention discloses a polyp segmentation method based on edge guidance and deep-supervised PVT. For colonoscopy images containing polyps, this method utilizes a constructed polyp segmentation network to output the location and shape of the polyps. The polyp segmentation network uses PVT-v2 as the backbone network for feature extraction and also includes a context fusion decoding branch, a boundary extraction branch, a boundary awareness module, and a cascaded feature fusion branch. The context fusion decoding branch acts as an image decoder, receiving the semantic feature map output by the PVT-v2 backbone network. The boundary extraction branch uses a thinning module to enrich the content of the detail feature map, obtaining edge prediction results. The boundary awareness module fuses the thinned features with the output feature map of the context fusion decoding to obtain a boundary-aware prediction result. The cascaded feature fusion branch fuses features at different scales layer by layer in a deep-to-shallow order, outputting the final polyp segmentation prediction result P5.

The invention relates to the technical field of petroleum geological exploration and geophysical data processing, and discloses a fault rod extraction method and system based on a morphological erosion algorithm, which can be used for removing noise in low signal-to-noise ratio data and accurately segmenting a fault fracture zone, and carrying out erosion operation based on a directional anisotropic structural element customized by a tectonic stress field. The erosion operation is carried out along the dominant direction of the fault, the fracture zone is compressed towards the core axis of the fault by using the iterative erosion and feedback correction means constrained by the fault trend model, and the artificial limb on the fault rod is eliminated and the missing part on the fault rod is complemented by using the multi-attribute fusion verification and topological optimization method. According to the fault rod extraction method, a fault rod has higher authenticity and spatial continuity, a generated data body is input into a three-dimensional Kriging interpolation gap filling and then is converted through a coordinate system, so that the output fault rod data body can directly meet the precision required by tectonic framework modeling, and the fault rod extraction method suitable for low-signal-to-noise-ratio data is provided.

The application provides a depth image acquisition method, an electronic device and a storage medium. The method comprises the following steps: acquiring a first image and a second image; processing the first image to obtain a predicted depth map, and calculating a first error value by using a first preset loss function; determining a first transformation matrix between the first image and the second image; performing instance segmentation and mask processing on the first image to obtain a first mask image and a second mask image; processing the first transformation matrix according to the first mask image and the second mask image to obtain a target transformation matrix; generating a third image based on the target transformation matrix; calculating a second error value by using a second preset loss function; adjusting a depth learning network model according to the first error value and the second error value to obtain a target depth learning network model; and inputting a to-be-detected image into the target depth learning network model to obtain a depth image corresponding to the to-be-detected image. The application can obtain a more accurate depth image.

The application provides an endoscope image enhancement method and device, electronic equipment and a storage medium. The method comprises the following steps: extracting a plurality of image features from an acquired endoscope image, fusing the image features, and performing segmentation processing on the fused feature image through a double-threshold method to determine a blood vessel region and a mucous membrane region in the image. In different image processing modes, the blood vessel region and the mucous membrane region in the endoscope are accurately segmented to obtain a target image. In this way, the contrast of the blood vessel region and the mucous membrane region in the endoscope image can be improved, and in different image processing modes, the image region corresponding to the image processing mode in the image can be enhanced to obtain an enhanced target image, improve the overall image clarity, reduce a large number of data processing steps, ensure the accuracy of image enhancement processing, and improve the image processing efficiency.

This invention discloses a passive visual weld seam tracking method based on deep learning semantic segmentation, comprising the following steps: establishing a vision system and acquiring weld seam images during PAW welding without the aid of external light; segmenting the weld seam images based on semantic segmentation to extract the arc light and weld seam components; labeling connected components in the segmented images to eliminate missegmented parts; determining the welding torch position based on the geometric features of the arc light and performing straight line fitting on the weld seam to calculate the offset between the two; and filtering the current result based on the previously calculated offset. The beneficial effects of this invention are: by constructing a BiseNetV2 network, accurate segmentation of the arc light and weld seam and accurate positioning of the welding torch are achieved; at the same time, the filtering method can obtain higher accuracy to meet the accuracy requirements of real-time weld seam tracking.

This invention proposes a multimodal driven and dynamically optimized method and system for power plant inspection image segmentation, belonging to the field of computer vision technology. The method includes: acquiring inspection sample images; generating initial pseudo-labels using a pre-trained visual language model and a multimodal large language model; inputting the inspection sample images into the visual model to obtain dense features, aligning them cross-modally with text semantic embeddings to obtain enhanced visual features; constructing a transition matrix based on image features and enhanced visual features, and inputting these features into a decoder to obtain a dual-path prediction mask, which is then fused to generate a segmentation probability map; optimizing the initial pseudo-labels based on the segmentation probability map and the transition matrix, and using the optimized pseudo-labels to construct a supervision signal to guide the generation of the transition matrix; iteratively optimizing until convergence to obtain a trained image segmentation network, which is then used as input to the inspection image to be segmented to obtain the segmentation result. This improves the segmentation accuracy and generalization ability of inspection images.

The application provides an intraoperative real-time optical coherence imaging guided laser ablation treatment system, which comprises an optical guiding module, a laser treatment module and a real-time monitoring and feedback module; high-resolution three-dimensional information and blood vessel function information obtained by the optical coherence imaging guiding module are used to accurately segment the region of a tumor site, and the power and irradiation time of a radiation laser light source are accurately controlled according to the information; meanwhile, a temperature sensor monitors the tissue temperature at any time, and the system pauses laser diagnosis and treatment when the temperature exceeds the set threshold range, so that precise laser ablation treatment is realized; the application aims to overcome the problems that the current laser ablation treatment lacks real-time and accurate segmentation of tumor regions and lacks real-time monitoring and feedback of the tissues around the tumor during the operation, so that real-time and accurate laser ablation treatment of the tumor site during the operation is realized.

The application discloses a multi-modal collaborative video sequence segmentation method, steps comprising: obtaining a multi-scale local feature matrix and a multi-scale global feature matrix of an image sequence; obtaining a multi-scale text feature matrix of a text sequence; obtaining a multi-scale local-global fusion feature matrix of the multi-scale local feature matrix and the multi-scale global feature matrix; obtaining a multi-modal fusion feature matrix of the multi-scale local-global fusion feature matrix and the multi-scale text feature matrix; using a decoder of a pre-trained large model to predict and generate a segmentation mask, and outputting a semantic segmentation map. The video sequence segmentation method is stable in the face of complex and variable scenes, does not need to rely on a large amount of labeled data, reduces training cost, and is suitable for various practical application fields, including intelligent monitoring, automatic driving and medical image analysis.

The present application relates to a kind of methods for training target segmentation model, comprising: obtaining training set, training set includes multiple frames of continuous original image, each frame original image is annotated with the real label of target;The original image in training set is input into convolutional neural network, obtains the feature map of multiple scales of each frame original image;First feature map of current frame original image and second feature map of previous frame original image are input into gated recurrent unit network, to obtain fusion feature map;Multiple scales of the feature map of current frame original image and fusion feature map are input into feature fusion decoding network, obtain the prediction label of target;Loss between real label and prediction label is calculated based on loss function, and target segmentation model is iteratively trained according to loss, until target segmentation model converges, and the trained target segmentation model is obtained.The target segmentation model obtained can accurately segment target, reduce the interference of complex background and the generation of artifact.