{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:40:53Z","timestamp":1792024853677,"version":"4.4.0"},"reference-count":39,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Special Fund for Marine Economic Development (six marine industries) of Guangdong Province, China","award":["GDNRC[2024]18"],"award-info":[{"award-number":["GDNRC[2024]18"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Animals"],"abstract":"<jats:p>Accurate monitoring of fish movement is essential for understanding behavioral patterns and group dynamics in aquaculture systems. Underwater scenes\u2014characterized by dense populations, frequent occlusions, non-rigid body motion, and visually similar appearances\u2014present substantial challenges for conventional multi-object tracking methods. We propose an improved CenterTrack-based framework tailored for multi-fish tracking in such environments. The framework integrates three complementary components: a multi-branch feature extractor that enhances discrimination among visually similar individuals, occlusion-aware output heads that estimate visibility states, and a three-stage cascade association module that improves trajectory continuity under abrupt motion and occlusions. To support systematic evaluation, we introduce a self-built dataset named Multi-Fish 25 (MF25), continuous video sequences of 75 individually annotated fish recorded in aquaculture tanks. The experimental results on MF25 show that the proposed method achieves an IDF1 of 82.5%, MOTA of 85.8%, and IDP of 84.7%. Although this study focuses on tracking performance rather than biological analysis, the produced high-quality trajectories form a solid basis for subsequent behavioral studies. The framework\u2019s modular design and computational efficiency make it suitable for practical, online tracking in aquaculture scenarios.<\/jats:p>","DOI":"10.3390\/ani16020156","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T09:40:29Z","timestamp":1767692429000},"page":"156","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhanced CenterTrack for Robust Underwater Multi-Fish Tracking"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1246-4617","authenticated-orcid":false,"given":"Jinfeng","family":"Wang","sequence":"first","affiliation":[{"name":"College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8730-7925","authenticated-orcid":false,"given":"Mingrun","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5344-0071","authenticated-orcid":false,"given":"Zhipeng","family":"Cheng","sequence":"additional","affiliation":[{"name":"College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0388-9426","authenticated-orcid":false,"given":"Renyou","family":"Yang","sequence":"additional","affiliation":[{"name":"Southern Marine Science and Engineering Guangdong Laboratory, Zhanjiang 524000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1385-6564","authenticated-orcid":false,"given":"Qiong","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"122194","DOI":"10.1016\/j.eswa.2023.122194","article-title":"FishTrack: Multi-object tracking method for fish using spatiotemporal information fusion","volume":"238","author":"Liu","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107871","DOI":"10.1016\/j.compag.2023.107871","article-title":"Dynamic fry counting based on multi-object tracking and one-stage detection","volume":"209","author":"Zhang","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.biosystemseng.2024.02.011","article-title":"A fish appetite assessment method based on improved ByteTrack and spatiotemporal graph convolutional network","volume":"240","author":"Zhao","year":"2024","journal-title":"Biosyst. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"107335","DOI":"10.1016\/j.compag.2022.107335","article-title":"Recent advances of target tracking applications in aquaculture with emphasis on fish","volume":"201","author":"Mei","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102534","DOI":"10.1016\/j.aquaeng.2025.102534","article-title":"Group activity amount estimation for fish using multi-object tracking","volume":"110","author":"Liu","year":"2025","journal-title":"Aquac. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4870","DOI":"10.1109\/TCSVT.2024.3524670","article-title":"SparseTrack: Multi-object tracking by performing scene decomposition based on pseudo-depth","volume":"35","author":"Liu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"13001","DOI":"10.1111\/raq.13001","article-title":"Fish tracking, counting, and behaviour analysis in digital aquaculture: A comprehensive survey","volume":"17","author":"Cui","year":"2025","journal-title":"Rev. Aquac."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"742887","DOI":"10.1016\/j.aquaculture.2025.742887","article-title":"Enhanced deep OC-SORT with YOLOv8-seg for robust fry tracking and behavior analysis in aquaculture","volume":"610","author":"Xi","year":"2025","journal-title":"Aquaculture"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"110127","DOI":"10.1016\/j.compag.2025.110127","article-title":"Hypoxia monitoring of fish in intensive aquaculture based on underwater multi-target tracking","volume":"232","author":"Li","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"ref_10","first-page":"5294151","article-title":"Sonar image target detection based on deep learning","volume":"2022","author":"Yu","year":"2022","journal-title":"Math. Probl. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/j.isatra.2024.05.042","article-title":"Zebrafishtracker3D: A 3D skeleton tracking algorithm for multiple zebrafish based on particle matching","volume":"151","author":"Fu","year":"2024","journal-title":"ISA Trans."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"737215","DOI":"10.1016\/j.aquaculture.2021.737215","article-title":"Behavioral spatial-temporal characteristics-based appetite assessment for fish school in recirculating aquaculture systems","volume":"545","author":"Wei","year":"2021","journal-title":"Aquaculture"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"110742","DOI":"10.1016\/j.compag.2025.110742","article-title":"FMRFT: Fusion Mamba and DETR for query time sequence intersection fish tracking","volume":"237","author":"Yao","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Folkman, L., Vo, Q.L., Johnston, C., Stanti\u0107, B., and Pitt, K.A. (2025). A computer vision method to estimate ventilation rate of Atlantic salmon in sea fish farms. arXiv.","DOI":"10.1016\/j.aquaeng.2025.102645"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"741535","DOI":"10.1016\/j.aquaculture.2024.741535","article-title":"Automated computer vision-based individual salmon (Salmo salar) breathing rate estimation (SaBRE) for improved state observability","volume":"595","author":"Schellewald","year":"2025","journal-title":"Aquaculture"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Khiem, N.M., Van Thanh, T., Dung, N.H., and Takahashi, Y. (2025). A novel approach combining YOLO and DeepSORT for detecting and counting live fish in natural environments through video. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0323547"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Abangan, A.S., Kopp, D., and Faillettaz, R. (2023). Artificial intelligence for fish behavior recognition: Advances and applications. Front. Mar. Sci., 10.","DOI":"10.3389\/fmars.2023.1010761"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., and Kr\u00e4henb\u00fchl, P. (2020, January 23\u201328). Tracking objects as points. Proceedings of the Computer Vision\u2014ECCV 2020, Glasgow, UK.","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"96522","DOI":"10.1109\/ACCESS.2023.3294710","article-title":"Activity segmentation and fish tracking from sonar videos by combining artifacts filtering and a Kalman approach","volume":"11","author":"Winkler","year":"2023","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kandimalla, V., Richard, M., Smith, F., Quirion, J., Torgo, L., and Whidden, C. (2023). Automated Detection, Classification and Counting of Fish in Fish Passages with Deep Learning. Front. Mar. Sci., 8.","DOI":"10.3389\/fmars.2021.823173"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Shelhamer, E., and Darrell, T. (2017). Deep layer aggregation. arXiv.","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_23","unstructured":"Jurafsky, D., Chai, J., Schluter, N., and Tetreault, J. (2020). Dice loss for data-imbalanced NLP tasks. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics."},{"key":"ref_24","unstructured":"Luiten, J. (2026, January 01). TrackEval. Available online: https:\/\/github.com\/JonathonLuiten\/TrackEval."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","article-title":"HOTA: A higher order metric for evaluating multi-object tracking","volume":"129","author":"Luiten","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., and Upcroft, B. (2016, January 25\u201328). Simple online and realtime tracking. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wojke, N., and Bewley, A. (2018, January 12\u201315). Deep cosine metric learning for person re-identification. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA.","DOI":"10.1109\/WACV.2018.00087"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., and Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. arXiv.","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., and Wang, X. (2022, January 23\u201327). ByteTrack: Multi-object tracking by associating every detection box. Proceedings of the Computer Vision\u2014ECCV 2022, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Cao, J., Pang, J., Weng, X., Khirodkar, R., and Kitani, K. (2023, January 17\u201324). Observation-centric SORT: Rethinking SORT for robust multi-object tracking. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., and Wei, Y. (2022, January 23\u201327). MOTR: End-to-end multiple-object tracking with transformer. Proceedings of the Computer Vision\u2014ECCV 2022, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","article-title":"FairMOT: On the fairness of detection and re-identification in multiple object tracking","volume":"129","author":"Zhang","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_33","unstructured":"Xu, Y., Ban, Y., Delorme, G., Gan, C., Rus, D., and Alameda-Pineda, X. (2021). TransCenter: Transformers with dense representations for multiple-object tracking. arXiv."},{"key":"ref_34","unstructured":"Sun, P., Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., Wang, C., and Luo, P. (2020). TransTrack: Multiple-object tracking with transformer. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"109078","DOI":"10.1016\/j.compeleceng.2024.109078","article-title":"TPTrack: Strengthening tracking-by-detection methods from tracklet processing perspectives","volume":"114","author":"Li","year":"2024","journal-title":"Comput. Electr. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"125653","DOI":"10.1016\/j.eswa.2024.125653","article-title":"Uniformity and deformation: A benchmark for multi-fish real-time tracking in the farming","volume":"264","author":"Huang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yin, T., Koltun, V., and Kr\u00e4henb\u00fchl, P. (2022, January 18\u201324). Global Tracking Transformers. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00857"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2019). MobileNetV2: Inverted residuals and linear bottlenecks. arXiv.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Animals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/2\/156\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T09:48:53Z","timestamp":1767692933000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/2\/156"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["ani16020156"],"URL":"https:\/\/doi.org\/10.3390\/ani16020156","relation":{},"ISSN":["2076-2615"],"issn-type":[{"value":"2076-2615","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]}}}