{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T18:51:20Z","timestamp":1781808680475,"version":"3.54.5"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014410","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000}}],"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the 1+3 Seed Source Key Technology Research and Development Project of the Sichuan Academy of Agricultural Sciences","award":["2025 (1+3) ZYGG-03"],"award-info":[{"award-number":["2025 (1+3) ZYGG-03"]}]},{"name":"the National Modern Agricultural Industrial Technology System Special Project","award":["CARS-18"],"award-info":[{"award-number":["CARS-18"]}]},{"name":"the Sichuan Provincial Science and Technology Plan Project","award":["21ZDYF2183"],"award-info":[{"award-number":["21ZDYF2183"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Variety breeding has long been a cornerstone of high-quality agriculture, and recent advances in artificial intelligence have opened new avenues for accelerating biological breeding. In this study, we applied multiple object tracking (MOT) technology to silkworm breeding to achieve efficient, non-invasive, and dynamic individual monitoring. Unlike pedestrian or vehicle tracking, silkworms pose unique challenges for MOT due to their small size, dense distribution, and high inter-individual similarity, which complicate accurate tracking and behavioral analysis. To address these issues, we propose WormSORT, an enhanced tracking method based on a tracking-by-detection framework with an optimized data association strategy. A pre-trained detection model identifies silkworms in each frame, and deep feature vectors are extracted using a re-identification network. Identity association is first performed using Intersection over Union (IoU) matching, followed by deep feature similarity for unmatched cases, improving both tracking accuracy and reliability. To further enhance tracking stability, we introduce a candidate input padding mechanism, including IoU padding and feature padding, ensuring that high-confidence unmatched trajectories and detections remain involved in the matching process. To validate the proposed tracking strategy, we constructed two multiple silkworm tracking (MST) datasets: MST-50, containing approximately 50 individuals over 1000 frames, and MST-100, containing approximately 100 individuals over 1200 frames. Experimental results demonstrate that WormSORT outperforms existing methods, including DeepSORT, StrongSORT, OCSORT, ByteTrack, and BotSORT, achieving superior tracking performance. This study provides a valuable reference for silkworm tracking and behavioral analysis, contributing to the advancement of high-quality silkworm rearing and management.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014410","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T17:37:15Z","timestamp":1781545035000},"page":"e1014410","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["WormSORT: A detection-based multiple object tracking model for individual silkworms in breeding environments"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1198-1847","authenticated-orcid":true,"given":"Hongkang","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linbo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiping","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibo","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"issue":"8","key":"pcbi.1014410.ref001","doi-asserted-by":"crossref","first-page":"101221","DOI":"10.1016\/j.animal.2024.101221","article-title":"Microbiological safety assessment of silkworm farms: a case study","volume":"18","author":"L Tassoni","year":"2024","journal-title":"Animal"},{"issue":"1","key":"pcbi.1014410.ref002","doi-asserted-by":"crossref","first-page":"5619","DOI":"10.1038\/s41467-022-33366-x","article-title":"High-resolution silkworm pan-genome provides genetic insights into artificial selection and ecological adaptation","volume":"13","author":"X Tong","year":"2022","journal-title":"Nat Commun"},{"issue":"8016","key":"pcbi.1014410.ref003","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"J Abramson","year":"2024","journal-title":"Nature"},{"key":"pcbi.1014410.ref004","article-title":"Artificial allosteric protein switches with machine-learning-designed receptors","author":"Z Guo","year":"2026","journal-title":"Nat Biotechnol"},{"issue":"3","key":"pcbi.1014410.ref005","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1038\/s41592-026-03007-y","article-title":"DECODE: deep learning-based common deconvolution framework for various omics data","volume":"23","author":"T Zhao","year":"2026","journal-title":"Nat Methods"},{"key":"pcbi.1014410.ref006","doi-asserted-by":"crossref","first-page":"107108","DOI":"10.1016\/j.compag.2022.107108","article-title":"Automatic exposure correction algorithm for online silkworm pupae (Bombyx mori) sex classification","volume":"198","author":"F Guo","year":"2022","journal-title":"Comp Electron Agricul"},{"key":"pcbi.1014410.ref007","doi-asserted-by":"crossref","first-page":"113017","DOI":"10.1016\/j.patcog.2025.113017","article-title":"YOLOv8-DSRI: an improved YOLOV8 instance segmentation algorithm for identifying silkworms in dense environments","volume":"174","author":"C Wen","year":"2026","journal-title":"Pattern Recognition"},{"key":"pcbi.1014410.ref008","doi-asserted-by":"crossref","first-page":"110887","DOI":"10.1016\/j.compag.2025.110887","article-title":"A novel calculation method for co-rearing silkworms molting-awakening rate based on the detection and multi-object tracking co-networks","volume":"238","author":"Z Li","year":"2025","journal-title":"Comp Electron Agricul"},{"key":"pcbi.1014410.ref009","article-title":"Simple online and realtime tracking","year":"2016","journal-title":"2016 IEEE International Conference on Image Processing (ICIP)"},{"key":"pcbi.1014410.ref010","doi-asserted-by":"crossref","first-page":"3645","DOI":"10.1109\/ICIP.2017.8296962","article-title":"Simple online and realtime tracking with a deep association metric","author":"N Wojke","year":"2017","journal-title":"2017 IEEE International Conference on Image Processing (ICIP)"},{"issue":"8","key":"pcbi.1014410.ref011","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-025-11212-y","article-title":"Multi-object tracking review: retrospective and emerging trend","volume":"58","author":"Z Guan","year":"2025","journal-title":"Artif Intell Rev"},{"issue":"6793","key":"pcbi.1014410.ref012","doi-asserted-by":"crossref","DOI":"10.1126\/science.adv7924","article-title":"DefensePredictor: a machine learning model to discover prokaryotic immune systems","volume":"392","author":"PC DeWeirdt","year":"2026","journal-title":"Science"},{"issue":"10","key":"pcbi.1014410.ref013","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1013606","article-title":"Similarity-based transfer learning with deep learning networks for accurate CRISPR-Cas9 off-target prediction","volume":"21","author":"J Charlier","year":"2025","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"pcbi.1014410.ref014","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pbio.3003597","article-title":"A deep learning-based computational pipeline predicts developmental outcome in retinal organoids","volume":"24","author":"C Afting","year":"2026","journal-title":"PLoS Biol"},{"issue":"1","key":"pcbi.1014410.ref015","doi-asserted-by":"crossref","first-page":"4708","DOI":"10.1038\/s41467-026-70070-6","article-title":"An end-to-end generalizable deep learning framework to comprehensively analyze transcriptional regulation","volume":"17","author":"Z Zhang","year":"2026","journal-title":"Nat Commun"},{"issue":"95","key":"pcbi.1014410.ref016","doi-asserted-by":"crossref","DOI":"10.1126\/scirobotics.adn6848","article-title":"Autonomous tracking of honey bee behaviors over long-term periods with cooperating robots","volume":"9","author":"J Ulrich","year":"2024","journal-title":"Sci Robot"},{"issue":"8009","key":"pcbi.1014410.ref017","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1038\/s41586-024-07293-4","article-title":"Machine learning reveals the control mechanics of an insect wing hinge","volume":"628","author":"JM Melis","year":"2024","journal-title":"Nature"},{"issue":"1","key":"pcbi.1014410.ref018","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s42256-023-00776-5","article-title":"Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning framework","volume":"6","author":"Y Han","year":"2024","journal-title":"Nat Mach Intell"},{"key":"pcbi.1014410.ref019","doi-asserted-by":"crossref","first-page":"109555","DOI":"10.1016\/j.compag.2024.109555","article-title":"PupaNet: a versatile and efficient silkworm pupae (Bombyx mori) identification tool for sericulture breeding based on near-infrared spectroscopy and deep transfer learning","volume":"227","author":"H He","year":"2024","journal-title":"Comp Electron Agricul"},{"key":"pcbi.1014410.ref020","doi-asserted-by":"crossref","first-page":"109966","DOI":"10.1016\/j.compag.2025.109966","article-title":"FeYOLO: Improved YOLOv7-tiny model using feature enhancement modules for the detection of individual silkworms in high-density and compact conditions","volume":"231","author":"H Shi","year":"2025","journal-title":"Comp Electron Agricul"},{"key":"pcbi.1014410.ref021","doi-asserted-by":"crossref","first-page":"108670","DOI":"10.1016\/j.compag.2024.108670","article-title":"Real-time detection and counting of wheat ears based on improved YOLOv7","volume":"218","author":"Z Li","year":"2024","journal-title":"Comp Electron Agricul"},{"key":"pcbi.1014410.ref022","doi-asserted-by":"crossref","first-page":"108583","DOI":"10.1016\/j.compag.2023.108583","article-title":"DeepSORT with siamese convolution autoencoder embedded for honey peach young fruit multiple object tracking","volume":"217","author":"T Zhang","year":"2024","journal-title":"Comp Electron Agricul"},{"key":"pcbi.1014410.ref023","doi-asserted-by":"crossref","first-page":"107696","DOI":"10.1016\/j.compag.2023.107696","article-title":"A sheep dynamic counting scheme based on the fusion between an improved-sparrow-search YOLOv5x-ECA model and few-shot deepsort algorithm","volume":"206","author":"Y Cao","year":"2023","journal-title":"Comp Electron Agricul"},{"key":"pcbi.1014410.ref024","doi-asserted-by":"crossref","first-page":"108900","DOI":"10.1016\/j.compag.2024.108900","article-title":"Real-time statistical algorithm for cherry tomatoes with different ripeness based on depth information mapping","volume":"220","author":"Z Meng","year":"2024","journal-title":"Compd Electron Agricul"},{"key":"pcbi.1014410.ref025","doi-asserted-by":"crossref","first-page":"109727","DOI":"10.1016\/j.compag.2024.109727","article-title":"Estimation of passion fruit yield based on YOLOv8n + OC-SORT + CRCM algorithm","volume":"229","author":"S Tu","year":"2025","journal-title":"Comp Electron Agriculture"},{"key":"pcbi.1014410.ref026","doi-asserted-by":"crossref","first-page":"106527","DOI":"10.1016\/j.engappai.2023.106527","article-title":"Multi-object tracking via deep feature fusion and association analysis","volume":"124","author":"H Li","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"pcbi.1014410.ref027","doi-asserted-by":"crossref","first-page":"110249","DOI":"10.1016\/j.patcog.2023.110249","article-title":"SCGTracker: spatio-temporal correlation and graph neural networks for multiple object tracking","volume":"149","author":"Y Zhang","year":"2024","journal-title":"Pattern Recognition"},{"issue":"4","key":"pcbi.1014410.ref028","doi-asserted-by":"crossref","DOI":"10.1007\/s00138-023-01398-y","article-title":"VGT-MOT: visibility-guided tracking for online multiple-object tracking","volume":"34","author":"S Wang","year":"2023","journal-title":"Machine Vision and Appl"},{"issue":"4","key":"pcbi.1014410.ref029","doi-asserted-by":"crossref","first-page":"2761","DOI":"10.1007\/s00371-023-02983-y","article-title":"MotionTrack: rethinking the motion cue for multiple object tracking in USV videos","volume":"40","author":"Z Liang","year":"2023","journal-title":"Vis Comput"},{"issue":"4","key":"pcbi.1014410.ref030","doi-asserted-by":"crossref","first-page":"7452","DOI":"10.1109\/TASE.2023.3342791","article-title":"NTrack: a multiple-object tracker and dataset for infield cotton boll counting","volume":"21","author":"MAA Muzaddid","year":"2024","journal-title":"IEEE Trans Automat Sci Eng"},{"issue":"4","key":"pcbi.1014410.ref031","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1007\/s11263-020-01393-0","article-title":"MOTChallenge: a benchmark for single-camera multiple target tracking","volume":"129","author":"P Dendorfer","year":"2020","journal-title":"Int J Comput Vis"},{"key":"pcbi.1014410.ref032","article-title":"YOLOv10: Real-Time End-to-End Object Detection","author":"A Wang","year":"2024","journal-title":"ArXiv"},{"key":"pcbi.1014410.ref033","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2019.00190","article-title":"Bag of tricks and a strong baseline for deep person re-identification","author":"H Luo","year":"2019","journal-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"key":"pcbi.1014410.ref034","doi-asserted-by":"crossref","first-page":"8725","DOI":"10.1109\/TMM.2023.3240881","article-title":"StrongSORT: make DeepSORT great again","volume":"25","author":"Y Du","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"pcbi.1014410.ref035","article-title":"ByteTrack: multi-object tracking by associating every detection box","author":"Y Zhang","year":"2022","journal-title":"17th European Conference on Computer Vision (ECCV 2022); 2022 2022\/\/; Tel Aviv, Israel: Tel Aviv, Israel: Springer Nature Switzerland"},{"key":"pcbi.1014410.ref036","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.00934","article-title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","author":"J Cao","year":"2023","journal-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada: IEEE"},{"key":"pcbi.1014410.ref037","author":"N Aharon","year":"2022","journal-title":"BoT-SORT: robust associations multi-pedestrian tracking"},{"key":"pcbi.1014410.ref038","first-page":"107234","article-title":"Lightweight silkworm recognition based on Multi-scale feature fusion","volume":"200","author":"C Wen","year":"2022","journal-title":"Comp ElectronAgricul"},{"key":"pcbi.1014410.ref039","author":"PS Shilpashree","year":"2023","journal-title":"Classification of healthy and diseased silkworms using ensemble learning and CNN"},{"issue":"14","key":"pcbi.1014410.ref040","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.3390\/ani15142011","article-title":"WormNet: a multi-view network for silkworm re-identification","volume":"15","author":"H Shi","year":"2025","journal-title":"Animals (Basel)"},{"key":"pcbi.1014410.ref041","volume-title":"AM-SORT: adaptable motion predictor with historical trajectory embedding for multi-object tracking","author":"V Kim","year":"2025"},{"issue":"3","key":"pcbi.1014410.ref042","doi-asserted-by":"crossref","DOI":"10.1007\/s00138-024-01531-5","article-title":"BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking","volume":"35","author":"VD Stanojevic","year":"2024","journal-title":"Machine Vision and Appl"},{"key":"pcbi.1014410.ref043","volume-title":"Gr-IoU: ground-intersection over union for robust multi-object tracking with 3D geometric constraints","author":"K Toida","year":"2025"},{"key":"pcbi.1014410.ref044","volume-title":"Enhanced Kalman with adaptive appearance motion SORT for grounded generic multiple object tracking","author":"DLD Anh","year":"2025"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014410","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T17:52:43Z","timestamp":1781805163000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014410"}},"subtitle":[],"editor":[{"given":"Jinshan","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":44,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014410","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]}}}