Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

51 results about "Boundary refinement" patented technology

Remote sensing image semantic segmentation method and system based on dynamic attention mechanism

The invention discloses a remote sensing image semantic segmentation method and system based on a dynamic attention mechanism, and relates to the technical field of remote sensing image processing, and the method comprises the following steps: carrying out the labeling and enhancement processing of a multi-scene remote sensing image, and generating a standardized data set; processing the data set through an encoder, and extracting a multi-scale high-dimensional feature map; decoding the multi-scale high-dimensional feature map, and fusing a decoding result with scale features to generate an optimized feature map; based on the optimized feature map, adopting a joint loss function to synchronously optimize segmentation, detection and classification tasks; performing dynamic up-sampling and boundary refinement on the optimized feature map, and outputting a structured analysis result; according to the method, the boundary information of the ground objects in the remote sensing image is accurately extracted through a dynamic processing flow and introduction of a double-flow decoder network and a multi-task joint optimization strategy, accurate segmentation and classification of the ground objects in a complex scene are achieved, and the overall effect of analysis and processing of the remote sensing image is improved.
Owner:ECONOMIC TECH RES INST OF STATE GRID ANHUI ELECTRIC POWER

Vanishing point determination, symmetry-based boundary refinement, and component detection for vehicle object detection or other applications

A method includes obtaining, using at least one processing device, image data associated with a scene. The method also includes identifying, using the at least one processing device, multiple line segments based on the image data. The method further includes identifying, using the at least one processing device, one or more boundaries around one or more objects detected in the image data. In addition, the method includes estimating, using the at least one processing device, a position of a vanishing point associated with the image data based on multiple collections of the line segments while excluding, from the multiple collections, one or more of the line segments that overlap with or that are included within the one or more boundaries.
Owner:WHS ENERGY SOLUTIONS LLC

Vanishing point determination, symmetry-based boundary refinement, and component detection for vehicle object detection or other applications

A method includes obtaining, using at least one processing device, a vanishing point and a boundary based on image data associated with a scene, where the boundary is associated with a detected object within the scene. The method also includes repeatedly, during multiple iterations and using the at least one processing device, (i) identifying multiple patches within the boundary and (ii) determining a similarity of the image data contained within the multiple patches. The method further includes identifying, using the at least one processing device, a modification to be applied to the boundary based on the identified patches and the determined similarities. In addition, the method includes generating, using the at least one processing device, a refined boundary based on the modification, where the refined boundary identifies a specified portion of the detected object.
Owner:WHS ENERGY SOLUTIONS LLC

Image target recognition system based on convolutional neural network and feature fusion technology

The invention relates to the field of computer vision and image processing, and discloses an image target recognition system based on a convolutional neural network and a feature fusion technology. Comprising a quality evaluation and alignment unit, a reversible decoupling and gating recharge unit, a multi-branch feature extraction unit, an evidence fusion unit, a marginal contribution gating unit, a topology consistency and boundary refinement unit, a detection and positioning unit and a linkage control unit. Reversible decoupling of contents and degradation components is realized in a feature domain, and bitwise gating recharge is implemented in a candidate region according to a quality map, so that small target and weak texture features are enhanced. The system fuses multi-branch output based on an evidence theory, determines weight distribution by combining marginal contribution calculation, triggers gating enhancement and local refinement when a conflict or deviation exceeds a threshold value, and realizes cooperative control of feature suppression and structure correction. According to the method, the recognition stability can be kept in complex scenes such as weak light, blurring and shielding, and the target recognition precision and the system interpretability are improved.
Owner:HENAN UNIVERSITY

Image semantic segmentation method based on self-supervised learning

The invention discloses an image semantic segmentation method based on self-supervised learning, and the method comprises the following steps: obtaining a label-free image data set, and carrying out the calculation to generate a structure agent set; inputting the structure agent set into a structure coding network, and executing multi-scale convolution extraction and interlayer down-sampling; inputting the label-free image data set into a semantic coding network, and executing layer-by-layer feature extraction and jumper fusion; an improved BYOL algorithm is adopted to execute a structure-semantic alignment self-supervision task, and a structure alignment embedding set and a semantic alignment embedding set are generated; mapping the structure alignment embedding set to a segmentation decoding module to form a boundary refining branch, and performing up-sampling and cascade fusion on the semantic alignment embedding set; and executing an alternating training process. According to the method, high-precision semantic segmentation under the label-free condition is realized, and boundary consistency and feature alignment performance are improved.
Owner:OCEAN UNIV OF CHINA

AI complex scene image semantic segmentation and recognition method based on deep learning

The invention relates to the technical field of artificial intelligence, and discloses an AI complex scene image semantic segmentation and recognition method based on deep learning. The method comprises the following steps: carrying out illumination invariance preprocessing on an original image; multi-level space-semantic joint features are obtained through a multi-scale context sensing feature extraction network; generating semantic probability distribution by using a global semantic consistency constraint module; and outputting a pixel-level segmentation result in combination with a dynamic boundary refinement decoder. According to the method, through illumination normalization, semantic prototype memory bank, category attention mechanism and edge detail fusion, the definition and semantic consistency of the segmentation boundary are improved, and the method is superior to an existing mainstream method.
Owner:LUZHOU VOCATIONAL & TECHN COLLEGE

Live broadcast long video editing method and device based on memory perception collaboration

The invention provides a live broadcast long video editing method and device based on memory perception collaboration, and relates to the technical field of image processing and video editing. Voice, subtitles and picture actions are analyzed in a linkage mode on a unified time grid, low-complexity characterization of a long video is achieved through an efficient perception module, and the effect of editing the long video is achieved. Cross-fragment core characters, events and semantic clues are precipitated through long-term memory of an entity center, and current perception is fed back through memory retrieval so as to enhance consistency and robustness; on the basis, a three-mode fusion wonderness score is generated, interval optimization and boundary refinement with duration budget constraint are executed, and finally, an editing decision list is output and quickly spliced into a high-quality finely-cut video. According to the invention, the problems of large quantity of long-time live broadcast materials, low efficiency of manual reviewing and editing and easy leakage of wonderful fragments are solved, and the later production efficiency and the quality of the live broadcast content are remarkably improved.
Owner:LETIAN ZHIZUO (HUNAN) FILM & TELEVISION TECH SERVICE CO LTD

Automatic segmentation method for pulmonary fibrosis image lesions based on multi-scale feature fusion

This invention relates to the field of medical image processing technology, specifically to an automatic segmentation method for pulmonary fibrosis lesions based on multi-scale feature fusion. The method includes: acquiring and preprocessing lung images to generate a standardized dataset; decomposing the dataset into multiple scales to extract feature groups at different scales; optimizing the feature groups using a specially constructed feature selection rule library based on lesion separability and feature redundancy analysis to obtain a key lesion representation feature set; achieving collaborative integration of cross-scale features through a designed feature interaction mapping mechanism combining spatial and frequency mappings to generate a multi-scale fused feature volume; inputting this feature volume into a lesion region discrimination model incorporating spatial attention and boundary refinement modules to calculate pixel assignment probabilities and generate an initial segmentation atlas; and finally, outputting the final segmentation result after morphological post-processing and fine-tuning calibration. This method effectively improves the accuracy of segmentation and its robustness to complex lesions.
Owner:GUANGDONG MEDICAL UNIV

Lightweight head and neck lymph node segmentation method and system

The application discloses a lightweight head and neck lymph node image segmentation method and system, and relates to the technical field of image processing. The application comprises the following steps: receiving a lymph node image for preprocessing, and dividing the image data into a training set and a test set; constructing a segmentation network structure based on a U-Net network, wherein the segmentation network structure comprises an encoder, a volume partial convolution layer, a convolution block and a decoder; adding a lightweight boundary refinement output module at the output end of the segmentation network structure for further refining the edge; training the segmentation network structure by using the training set, taking the minimization of the overall loss function as the network optimization objective function, and optimizing the segmentation network structure. The application adds the volume partial convolution, the convolution block and the lightweight boundary refinement output module between the encoder and the decoder, which can effectively reduce the calculation amount and the parameter amount while enhancing the accuracy of the segmentation result, and improve the calculation efficiency and the model performance.
Owner:SUZHOU UNIV

Live long video clipping method and device based on memory perception collaboration

The application provides a live long video clip method and device based on memory perception cooperation, relates to the technical field of image processing and video clip, and the application links and analyzes voice, subtitles and picture action on a unified time grid, realizes low complexity representation of the long video through an efficient perception module, deposits core characters, events and semantic clues across segments through entity-centered long-term memory, and enhances consistency and robustness through memory retrieval feedback to current perception; On the basis, the application generates a three-module fusion wonderful degree score, executes interval optimization and boundary refinement with time length budget constraints, and finally outputs an editing decision list and quickly splices into a high-quality refined video; The application solves the problems of large long-time live material quantity, low efficiency and easy-to-miss wonderful segment of manual review and editing, and significantly improves the post-production efficiency and finished film quality of live content.
Owner:LETIAN ZHIZUO (HUNAN) FILM & TELEVISION TECH SERVICE CO LTD

A general dense instance segmentation method and system based on prompt driving and pixel-level supervision

The application discloses a general dense instance segmentation method and system based on prompt driving and pixel-level supervision, and relates to the technical field of computer vision. The method comprises the following steps: extracting shared image features of an input image; determining a target domain query vector matched with the shared image features from a plurality of preset text domain query vectors; inputting the shared image features and the target domain query vector into a semantic branch module for pixel-level geometric modeling to obtain an instance-level semantic prediction mask; extracting instance spatial position information according to the semantic prediction mask and generating instance prompt information; inputting the shared image features and the instance prompt information into an instance branch module for prompt-driven segmentation to obtain an instance-level segmentation mask; and finally, performing boundary refinement and error screening on the two types of segmentation results through an instance perception fusion module to output a final instance segmentation result. The application effectively improves the precision, discrimination ability and cross-domain generalization performance of instance segmentation in a dense scene.
Owner:SUZHOU UNIV

Image super-resolution reconstruction method and device based on anchor point guidance and boundary refinement cooperation

The application relates to an image super-resolution reconstruction method and device based on anchor point guidance and boundary refinement cooperation, and belongs to the field of computer vision. The method comprises the following steps: performing shallow feature extraction on an input low-resolution image to obtain initial features; a deep feature enhancement network comprising multiple series cooperative reconstruction units is constructed, the initial features are input, and the initial features are sequentially enhanced by each unit; each unit performs anchor point routing global interaction and boundary perception region refinement on the input features to obtain global enhanced features and local refined features, the global enhanced features and the local refined features are fused through adaptive gating, and then the input features are fused through residual fusion, current cooperative enhanced features are output and are transmitted to the next unit, and finally, deep enhanced features are obtained; upsampling and pixel reconstruction are performed on the deep enhanced features, and a super-resolution image is output. The application considers long-distance structure dependence modeling and local boundary detail recovery, and realizes the cooperative optimization of global structure consistency and local detail fidelity under the constraint of lightweight deployment.
Owner:HUNAN POLICE ACAD

A muscle segmentation method based on state space model and boundary-aware attention

The present application relates to a kind of muscle segmentation methods based on state space model and boundary perception attention, belong to medical image segmentation technical field.It includes the following steps: obtaining lumbar MRI image, constructs lumbar muscle data set;Lumbar muscle data set is preprocessed, and standardized training set and test set are obtained;Segmentation network model is constructed;The segmentation network model is based on LightMU-Net network and is constructed, including depth separable convolution layer, encoder, bottleneck layer, decoder, boundary refining module BRM;Boundary perception Mamba attention module EMAM is added in decoder;Training set after pre-processing is used to train model;In the training process, the model is optimized using combined loss function, and the trained model is obtained;The image to be detected in test set is input into the trained model, and muscle segmentation result is obtained.The present application can improve the segmentation accuracy of the adhesion boundary between muscle groups.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) +1

Muscle segmentation method based on state space model and boundary perception attention

The invention relates to a muscle segmentation method based on a state space model and boundary perception attention, and belongs to the technical field of medical image segmentation. The method comprises the following steps: acquiring a waist MRI image, and constructing a waist muscle data set; preprocessing the waist muscle data set to obtain a standardized training set and a test set; constructing a segmentation network model; the segmentation network model is constructed based on a LightMU-Net network and comprises a depth separable convolutional layer, an encoder, a bottleneck layer, a decoder and a boundary refinement module BRM; a boundary perception Mama attention module (EMAM) is added in the decoder; training the model by adopting the preprocessed training set; in the training process, optimizing the model by adopting a combined loss function to obtain a trained model; and inputting a to-be-detected image in the test set into the trained model to obtain a muscle segmentation result. The segmentation accuracy of the adhesion boundary between muscle groups can be improved.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) +1

An image segmentation method and system

The application relates to the field of computer vision, and particularly discloses an image segmentation method and system, wherein a boundary distribution map is predicted by a multi-scale boundary distribution generation module as prior knowledge, a space-frequency domain joint supervision strategy is adopted, the boundary distribution map simultaneously approximates a real boundary in a spatial position and a spectral structure, false edge responses caused by local high-frequency interference are effectively inhibited, and the continuity and stability of the boundary are improved; an effective receptive field is expanded by a state space semantic enhancement module, and global semantic consistency is enhanced; a boundary-guided cross-scale decoder is combined with a boundary feature enhancement module, boundary-related responses are strengthened in multi-resolution fusion, and collaborative optimization of region positioning and boundary refinement is realized, so that accurate and complete polyp segmentation results are obtained under complex imaging conditions such as low contrast, various morphologies, and interference such as reflection and wrinkles, and reasonable calculation overhead is maintained.
Owner:CHONGQING UNIV

Renal tumor image segmentation method and system based on multi-scale feature extraction

InactiveCN121304699AImage enhancementImage analysisBoundary refinementKidney Neoplasm
The invention relates to a kidney tumor image segmentation method and system based on multi-scale feature extraction, and the method comprises the steps: extracting the multi-scale features of a kidney tumor image to be processed, dividing feature similarity groups, carrying out the optimization through combining the texture and shape, and obtaining similar feature groups; generating a complementary information flow, adaptively enhancing an interaction weight between groups by using an attention mechanism, and obtaining an enhanced complementary feature representation; evaluating and denoising noise, establishing association mapping among groups based on features after denoising, and performing multi-scale feature fusion and boundary refining by adopting a U-Net network to obtain tumor boundary representation; and the boundary fuzzy degree is evaluated, iterative optimization is carried out by adopting a graph convolutional network, optimized collaborative hierarchical representation is obtained, and finally a high-precision kidney tumor segmentation result and a pixel-level contour are output. According to the method, through multi-scale feature cooperation, attention interaction and boundary optimization, the problems of boundary blur and noise sensitivity in kidney tumor segmentation are effectively solved, and the accuracy and robustness of segmentation are remarkably improved.
Owner:TAIYUAN NORMAL UNIV

Method and system for segmenting non-significant colon polyp in medical image

The invention relates to a segmentation method and system for a non-significant colon polyp in a medical image, and the method comprises the steps: carrying out the collection of an endoscopic image, and obtaining a colon polyp image; performing multi-level feature extraction on the colon polyp image through a multi-branch feature fusion network, and outputting multi-scale features; adding local features in the multi-scale features by adopting a feature fusion strategy, and splicing the local features with the global features to obtain fused features; boundary refining processing is carried out on the fusion features to obtain refined features; and decoding the refined features and outputting a segmentation result graph. Complementation of local features and global features is realized through a multi-branch feature fusion network, and the feature expression ability of the non-significant colon polyp is enhanced; the expressive power and the fusion effect of the multi-scale features are improved through a feature fusion strategy; the RCF module effectively alleviates the segmentation deficiency of the traditional method under the condition of fuzzy boundary, and improves the fine-grained performance of the segmentation result.
Owner:HUNAN INST OF INFORMATION TECH

Polyp segmentation method based on local perception cue generation and morphological boundary refinement

The application provides a polyp segmentation method based on local perception prompt generation and morphological boundary refinement, which comprises the following steps: pre-processing a polyp image and extracting global semantic features and local texture features; then, based on the local texture features, a local perception guide image is focused on a significant area, and multi-scale features are adaptively fused to generate task-perception sparse prompts and dense prompts; then, the generated features are input into a mask decoder to generate preliminary segmentation mask features; boundary details and image segmentation operations are performed on the preliminary segmentation mask features to obtain a prediction probability map; the probability distribution of the prediction probability map is dynamically adjusted, a loss function is constructed based on the adjustment result for training, and finally, the segmentation result and the reliability score are jointly output. The application significantly improves the boundary accuracy of segmentation, the model robustness and the cross-domain generalization ability, and provides reliable technical support for early screening of colon polyps.
Owner:EAST CHINA JIAOTONG UNIVERSITY

Shadow removal method based on two-dimensional signed distance field

The invention discloses a shadow removal method based on a two-dimensional signed distance field. The soft weight mask and SDF image of the shadow image are calculated by the 2D signed distance field, and the shadow area and non-shadow area in the original shadow image are extracted by the soft weight mask; the local spatial feature global frequency feature is extracted by the fast Fourier transform module; the attention weight map of the local spatial feature global frequency feature is fused by the information interaction module IIM to obtain the fusion feature; the feature map after boundary refinement is output by the boundary refinement module BRM; the feature of the non-shadow area is extracted by the convolution operation, and the global feature vector, the feature of the non-shadow area and the SDF feature are modulated by the global feature modulation module GFM, and finally a shadow-free image is output. The invention has significant advantages in brightness restoration, boundary transition and smoothness of the shadow area, so that the removed image is close to the real shadow-free effect.
Owner:ANHUI UNIV

Wafer object segmentation method based on boundary-aware SegFormer

The present invention discloses a wafer target segmentation method based on boundary-aware SegFormer, and belongs to the field of digital image processing technology. The present invention proposes an adaptive seed search strategy, uses the correlation between seed position and target positioning accuracy to construct a seed distribution heat map, and adaptively searches for ideal seed targets under the guidance of the heat map to achieve high-precision global segmentation of array targets; the boundary-aware SegFormer network uses recursive gated convolution to emphasize the long-distance and high-order spatial interaction of features, and the improved gated residual boundary refinement module can learn richer edge information. At the same time, a hybrid loss function is introduced to strengthen the supervision of pixels inside and at the edge of the region, guiding the network to better learn the target edge features and improve the boundary segmentation accuracy. The segmentation method of the present invention can completely and accurately segment targets in high-resolution array target images with uneven background, defect pollution, and low edge contrast, and has high real-time performance.
Owner:WUXI JIUXIAO TECH CO LTD

A machine vision-based method, device and medium for detecting defects on a plastic surface

The application discloses a kind of based on machine vision's plastic surface defect detection method, equipment and medium, it is related to visual detection technical field, including, acquisition multiple image data and registration denoising and standardization processing, obtain detection reference parameter, integrate detection reference parameter, generate standardization surface image;Standardization surface image is carried out image segmentation and edge detection, determine candidate defect area, and carry out connected domain screening and boundary thinning processing to candidate defect area, obtain defect contour data;From defect contour data, extract the geometric morphology and image feature of defect area, and integrate output feature parameter, carry out quantization calculation and standardization processing to feature parameter, generate defect feature analysis data.The application realizes the combination batch state identification, detection record generation and report output, so that detection result has good structure, traceability and applicability, to improve the stability and practical value of plastic surface defect detection.
Owner:NANJING SPECIAL PLASTIC TECH CO LTD

Image semantic segmentation method, electronic device, and computer-readable storage medium

The application discloses an image semantic segmentation method, an electronic device and a computer readable storage medium, comprising: obtaining a target image and an image gradient map thereof; inputting the target image into a semantic segmentation network to obtain shallow feature maps and deep feature maps through an encoder; the semantic segmentation network comprises a cascaded encoder, a semantic-boundary double-branch decoder and an output layer; the feature fusion of multiple feature maps is performed through the semantic fusion branch of the decoder to obtain a semantic segmentation prediction result; the boundary information is obtained based on the image gradient map and the multiple feature maps through the boundary refinement branch of the decoder, and the feature fusion of the multiple feature maps is performed based on the boundary information to obtain a boundary prediction result; and the semantic segmentation prediction result and the boundary prediction result are fused through the output layer to obtain a semantic segmentation image of the target image. The application can further depict the object boundary in the semantic segmentation prediction result, thereby improving the accuracy and segmentation effect of semantic segmentation.
Owner:ZHEJIANG DAHUA TECH CO LTD

Quality control method for premade perch dish based on machine vision

The invention discloses a method for controlling the quality of a perch premade dish based on machine vision. The method comprises the following steps: obtaining a preprocessed perch premade dish image; inputting the pre-processed perch pre-prepared dish image into a residual dense block context feature extraction network, and outputting a multi-scale feature tensor; generating a boundary binary image, an Euler number heat image and a boundary attention weight tensor by a boundary topology branch; outputting a preliminary segmentation mask through a channel-space rearrangement mechanism; an optimized sub-pixel level segmentation network is obtained; in the inference stage, boundary refinement and topological consistency correction are carried out on the preliminarily segmented mask based on the boundary binary image and the Euler number heat image, and a target mask image is obtained; calculating a morphological integrity index set based on the target mask graph; and the integrity scoring module outputs an integrity judgment result according to a preset scoring threshold. According to the method, sub-pixel-level reconstruction and high-precision positioning of prefabricating vegetable body boundaries, tiny gaps and fractures of the weever are realized.
Owner:JIANGSU MARINE RESOURCES DEV RES INST LIAN YUNGANG

Shadow elimination method based on two-dimensional symbol distance field

The invention discloses a shadow elimination method based on a two-dimensional symbol distance field, and the method comprises the steps: calculating a soft weight mask and an SDF image of a shadow image through the 2D symbol distance field, and extracting a shadow region and a non-shadow region in an original shadow image through the soft weight mask; a fast Fourier transform module extracts local spatial features and global frequency features; fusing the attention weight maps of the local spatial features and the global frequency features through an information interaction module IIM to obtain fused features; a boundary refining module BRM is used to output a boundary refined feature map; and extracting the features of the non-shadow area through convolution operation, modulating the global feature vector, the features of the non-shadow area and the SDF features through a global feature modulation module GFM, and finally outputting a shadow-free image. The method has remarkable advantages in the aspects of brightness recovery, boundary transition and smoothness of the shadow region, so that the removed image is close to a real shadow-free effect.
Owner:ANHUI UNIV

A stacked document segmentation method based on multi-feature fusion boundary refinement and multi-dimensional semantic verification

PendingCN123094498ABoundary refinementRadiology
This invention relates to a stacked document segmentation method based on multi-feature fusion boundary refinement and multi-dimensional semantic verification. Specifically, it includes: segmenting an input image into document instances to identify the boundaries of multiple independent document instances; refining the seam lines by fusing shadow features, text line continuity features, and edge line features to obtain accurate boundaries for independent document instances; performing perspective correction and optical character recognition (OCR) on each refined independent document instance; performing multi-dimensional verification and correction on the segmentation results of each document instance based on text semantic features; and outputting OCR results for independent document instances with accurate boundaries and clear states based on the combined verification results. This invention enables the accurate segmentation of multiple physically stacked documents into independent document instances during digitization in actual clinical prescription review work, facilitating subsequent optical character recognition (OCR) and content utilization.
Owner:SINOPHARM DIGITAL TECHNOLOGY (BEIJING) CO LTD

A Building Extraction Method from Airborne Oblique Remote Sensing Images Based on Boxes and Image-Level Annotations

This invention relates to a method for extracting buildings from airborne oblique remote sensing images based on bounding boxes and image-level annotations, belonging to the field of remote sensing image information extraction technology. To address the issues of relying on large amounts of annotation information for pixel-level instance segmentation and mask overlap caused by insufficient image-level annotation information, this invention employs a strategy combining a weakly supervised instance segmentation network with a pseudo-mask refinement module to generate pseudo-instance masks. A pseudo-instance mask boundary refinement module filters out redundant boundary information in the pseudo-instance masks, and supplements and optimizes the mask boundary information by incorporating information from the remote sensing image. Simultaneously, a peak attention module is used to obtain the peak response map of instances after enhanced peak attention, extracting precise location clues for the instances. This, combined with the boundary-refined pseudo-instance mask, confirms the center point position and offset map of the target building. Finally, a mask classification refinement module obtains more accurate instance information.
Owner:HARBIN ENG UNIV

Image segmentation with object boundary refinement

Embodiments of the present invention set forth techniques for image segmentation with object boundary refinement. In some embodiments, the techniques include receiving an image and an indication of a region within the image, wherein the region includes an object, determining, by a machine learning model, a boundary of the object within the region; receiving a boundary parameter; and determining a portion of the region that includes the object, the determining of the portion of the region being based on the boundary and the boundary parameter. In some embodiments, the machine learning model generates a per-pixel score for each pixel of the region, each per-pixel score indicating a likelihood that the pixel is included in the object, and the boundary parameter includes a score threshold applied to the per-pixel scores to determine the pixels that are included in the portion of the region.
Owner:SCALE AI INC

Method, device and equipment for automatically segmenting overlapped cells and medium

The invention provides an automatic segmentation method for overlapped cells, which can be applied to the technical field of image segmentation. The method comprises the following steps: acquiring a to-be-segmented cell image; extracting a multi-scale feature map of the to-be-segmented cell image by using the backbone network, and performing target category prediction, boundary regression prediction and coarse segmentation mask prediction to obtain a coarse segmentation mask; performing overlapping cell decomposition and recombination on the coarse segmentation mask by using a deformable overlapping removal module to obtain a recombinant segmentation mask; performing bilinear interpolation up-sampling on the recombined segmentation mask by using a point rendering boundary refining module, extracting low-confidence points, and extracting fine-grained features and coarse-grained features of the low-confidence points from different multi-scale feature maps; based on the fine-grained features and the coarse-grained features, the low-confidence points are subjected to reclassification, and categories of the low-confidence points are obtained; and iteratively interpolating the up-sampling and reclassification process until the resolution of the recombined segmentation mask is recovered to the resolution of the original image, and outputting an overlapped cell segmentation result.
Owner:INST OF MICROELECTRONICS CHINESE ACAD OF SCI LTD

In-pipeline sewage monitoring system and method based on deep learning

The invention discloses a system and a method for monitoring sewage in a pipeline based on deep learning. The method comprises the following steps: S1, collecting image data, and preprocessing to generate a standardized sewage image sequence; s2, introducing a radial position code and an axial position code of the pipeline, and generating a structure-enhanced image feature sequence; s3, inputting an improved Mask2Former image segmentation network, and executing semantic query grouping and boundary refinement prediction to output an abnormal segmentation quantity set; s4, applying a radial distribution consistency constraint and an axial continuity constraint to generate a sewage state feature vector; s5, executing state judgment, and generating a sewage abnormal state identifier; s6, matching with a preset sewage state threshold rule, and entering a sewage discharge process judgment mode; and S7, repeatedly executing the steps S1 to S4 and executing recovery judgment to form a monitoring result. According to the invention, stable identification and accurate determination of abnormal sewage in the pipeline are realized, and the monitoring reliability and the sewage discharge control safety are improved.
Owner:XUZHOU HUAHONG SPECIAL STEEL CO LTD

Colon polyp image segmentation system and method based on UNet

The invention discloses a UNet-based colon polyp image segmentation system and method, and the method comprises the steps: constructing and training a colon polyp segmentation model, inputting a to-be-segmented colorectal polyp image into the trained colon polyp segmentation model, and obtaining a polyp segmentation image; the colon polyp segmentation model takes UNet as a main network, and comprises a cascade convolution module, a convolution attention module, a feature fusion module and a boundary refining module; according to the model provided by the invention, the segmentation accuracy of the colon polyp edge can be effectively improved, and meanwhile, the robustness of the network is improved.
Owner:ZHONGBEI UNIV