{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T12:32:02Z","timestamp":1782822722022,"version":"3.54.5"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T00:00:00Z","timestamp":1734566400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372397"],"award-info":[{"award-number":["62372397"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Humanities and Social Sciences Research Project of the Ministry of Education","award":["21YJAZH002"],"award-info":[{"award-number":["21YJAZH002"]}]},{"name":"the Shanxi Province Natural Fund Project","award":["202203021221222"],"award-info":[{"award-number":["202203021221222"]}]},{"name":"the Shanxi Provincial Cultural Relics Bureau 2024 Cultural Relics Research Project","award":["2024KT23"],"award-info":[{"award-number":["2024KT23"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>In semantic image segmentation tasks, most methods fail to fully use the characteristics of different scales and levels but rather directly perform upsampling. This may cause some effective information to be mistaken for redundant information and discarded, which in turn causes object segmentation confusion. As a convolutional layer deepens, the loss of spatial detail information makes the segmentation effect achieved at the object boundary insufficiently accurate. To address the above problems, we propose an edge optimization and category-aware multibranch semantic segmentation network (ECMNet). First, an attention-guided multibranch fusion backbone network is used to connect features with different resolutions in parallel and perform multiscale information interaction to reduce the loss of spatial detail information. Second, a category perception module is used to learn category feature representations and guide the pixel classification process through an attention mechanism to optimize the resulting segmentation accuracy. Finally, an edge optimization module is used to integrate the edge features into the middle and the deep supervision layers of the network through an adaptive algorithm to enhance its ability to express edge features and optimize the edge segmentation effect. The experimental results show that the MIoU value reaches 79.2% on the Cityspaces dataset and 79.6% on the CamVid dataset, that the number of parameters is significantly lower than those of other models, and that the proposed method can effectively achieve improved semantic image segmentation performance and solve the partial category segmentation confusion problem, giving it certain application prospects.<\/jats:p>","DOI":"10.1371\/journal.pone.0315621","type":"journal-article","created":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T18:43:11Z","timestamp":1734633791000},"page":"e0315621","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multibranch semantic image segmentation model based on edge optimization and category perception"],"prefix":"10.1371","volume":"19","author":[{"given":"Zhuolin","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3687-3738","authenticated-orcid":true,"given":"Jianfang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cunhe","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,12,19]]},"reference":[{"key":"pone.0315621.ref001","first-page":"86","article-title":"Image threshold segmentation algorithms and comparative research.","author":"ZY Zhang","year":"2017","journal-title":"Information and Communication."},{"issue":"6","key":"pone.0315621.ref002","first-page":"939","article-title":"Research and implementation of instance segmentation and edge optimization algorithms","volume":"41","author":"ZX Liang","year":"2020","journal-title":"Journal of Graphics"},{"issue":"3","key":"pone.0315621.ref003","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1145\/1015706.1015720","article-title":"\u201cGrabcut\u201d interactive foreground extraction using iterated grap cuts.","volume":"23","author":"C Rother","year":"2004","journal-title":"ACM Transactions on Graphics(TOG)."},{"issue":"9","key":"pone.0315621.ref004","doi-asserted-by":"crossref","first-page":"2352","DOI":"10.1162\/neco_a_00990","article-title":"Deep convolutional neural networks for image classification: A comprehensive review.","volume":"29","author":"W Rawat","year":"2017","journal-title":"Neural computation."},{"key":"pone.0315621.ref005","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"J Long","year":"2015","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"pone.0315621.ref006","first-page":"9685","article-title":"Boosting monocular depth estimation models to high-resolution via content-adaptive multi-resolution merging","author":"SMH Miangoleh","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0315621.ref007","first-page":"1402","article-title":"Edter: Edge detection with transformer","author":"M Pu","year":"2022","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"issue":"4","key":"pone.0315621.ref008","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1080\/0952813X.2021.1908432","article-title":"SPMNet: A light-weighted network with separable pyramid module for real-time semantic segmentation","volume":"34","author":"S Gao","year":"2022","journal-title":"Journal of Experimental & Theoretical Artificial Intelligence."},{"key":"pone.0315621.ref009","doi-asserted-by":"crossref","first-page":"1992","DOI":"10.1109\/ICASSP.2019.8682746","volume-title":"ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).","author":"H Lu","year":"2019"},{"key":"pone.0315621.ref010","first-page":"7151","article-title":"Context encoding for semantic segmentation","author":"H Zhang","year":"2018","journal-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition"},{"key":"pone.0315621.ref011","first-page":"11348","article-title":"SOE-Net: A self-attention and orientation encoding network for point cloud based place recognition","author":"Y Xia","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition"},{"key":"pone.0315621.ref012","doi-asserted-by":"crossref","first-page":"1894","DOI":"10.1109\/ICIP42928.2021.9506485","volume-title":"2021 IEEE International Conference on Image Processing (ICIP).","author":"A Lou","year":"2021"},{"key":"pone.0315621.ref013","first-page":"3684","article-title":"Denseaspp for semantic segmentation in street scenes","author":"M Yang","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"pone.0315621.ref014","doi-asserted-by":"crossref","first-page":"112317","DOI":"10.1016\/j.jcp.2023.112317","article-title":"RelaxNet: A structure-preserving neural network to approximate the Boltzmann collision operator","volume":"490","author":"T Xiao","year":"2023","journal-title":"Journal of Computational Physics"},{"key":"pone.0315621.ref015","first-page":"1","volume-title":"2021 International Conference on Visual Communications and Image Processing (VCIP).","author":"T Zhang","year":"2021"},{"key":"pone.0315621.ref016","doi-asserted-by":"crossref","first-page":"1949","DOI":"10.1109\/TIP.2021.3049959","article-title":"Bilateral attention network for RGB-D salient object detection","volume":"30","author":"Z Zhang","year":"2021","journal-title":"IEEE transactions on image processing"},{"key":"pone.0315621.ref017","first-page":"2881","article-title":"Pyramid scene parsing network","author":"H Zhao","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"pone.0315621.ref018","first-page":"801","article-title":"Encoder-decoder with Atrous Separable Convolution for Semantic Image Segmentation.","author":"LC Chen","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)."},{"key":"pone.0315621.ref019","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2021\/142","volume-title":"Context-aware cross-level fusion network for camouflaged object detection","author":"Y Sun","year":"2021"},{"issue":"3","key":"pone.0315621.ref020","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","article-title":"Attention mechanisms in computer vision: A survey","volume":"8","author":"MH Guo","year":"2022","journal-title":"Computational Visual Media"},{"key":"pone.0315621.ref021","first-page":"3","author":"S Woo","year":"2018","journal-title":"Cbam: Convolutional block attention module \/\/Proceedings of the European conference on computer vision (ECCV)."},{"key":"pone.0315621.ref022","first-page":"5217","article-title":"Canet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning","author":"C Zhang","year":"2019","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"pone.0315621.ref023","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.neucom.2021.12.003","article-title":"RELAXNet: Residual efficient learning and attention expected fusion network for real-time semantic segmentation.","volume":"474","author":"J Liu","year":"2022","journal-title":"Neurocomputing"},{"key":"pone.0315621.ref024","first-page":"4015","article-title":"Segment anything.","author":"A Kirillov","year":"2023","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"pone.0315621.ref025","first-page":"5693","article-title":"Deep high-resolution representation learning for human pose estimation","author":"K Sun","year":"2019","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"pone.0315621.ref026","doi-asserted-by":"crossref","first-page":"3141","DOI":"10.1109\/ICIP46576.2022.9897365","volume-title":"2022 IEEE International Conference on Image Processing (ICIP).","author":"K Sofiiuk","year":"2022"},{"key":"pone.0315621.ref027","first-page":"18063","article-title":"Transflow: Transformer as flow learner","author":"Y Lu","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"issue":"07","key":"pone.0315621.ref028","doi-asserted-by":"crossref","first-page":"13106","DOI":"10.1609\/aaai.v34i07.7013","article-title":"Eemefn: Low-light image enhancement via edge-enhanced multi-exposure fusion network","volume":"34","author":"M Zhu","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"pone.0315621.ref029","first-page":"670","volume-title":"ICPR International Workshops and Challenges: Virtual Event, January 10\u201315, 2021, Proceedings, Part VI.","author":"Q Guo","year":"2021"},{"issue":"6A","key":"pone.0315621.ref030","first-page":"220700137","article-title":"Multi-path semantic segmentation based on edge optimization and global Modeling","volume":"50","author":"Q Chen","year":"2023","journal-title":"Computer Science"},{"key":"pone.0315621.ref031","volume-title":"Boundary Attention: Learning to Find Faint Boundaries at Any Resolution","author":"MG Polansky","year":"2024"},{"key":"pone.0315621.ref032","first-page":"9716","article-title":"Rethinking bisenet for real-time semantic segmentation","author":"M Fan","year":"2021","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"pone.0315621.ref033","first-page":"405","article-title":"Icnet for real-time semantic segmentation on high-resolution images","author":"H Zhao","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)."},{"key":"pone.0315621.ref034","first-page":"325","article-title":"Bisenet: Bilateral segmentation network for real-time semantic segmentation.","author":"C Yu","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)."},{"key":"pone.0315621.ref035","volume-title":"Ocnet: Object context network for scene parsing","author":"Y Yuan","year":"2018"},{"key":"pone.0315621.ref036","first-page":"267","article-title":"Psanet: Point-wise spatial attention network for scene parsing.","author":"H Zhao","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)."},{"key":"pone.0315621.ref037","first-page":"770","article-title":"Deep residual learning for image recognition","author":"K He","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"pone.0315621.ref038","volume-title":"Very deep convolutional networks for large-scale image recognition","author":"K Simonyan","year":"2014"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0315621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T18:43:35Z","timestamp":1734633815000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0315621"}},"subtitle":[],"editor":[{"given":"Yawen","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,19]]},"references-count":38,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12,19]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0315621","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,19]]}}}