{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T19:36:20Z","timestamp":1790451380707,"version":"4.1.0"},"reference-count":50,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:00:00Z","timestamp":1767139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Multi-fish tracking and behavior analysis in deep-sea cages face two critical challenges: first, the homogeneity of fish appearance and low image quality render appearance-based association unreliable; second, standard linear motion models fail to capture the complex, nonlinear swimming patterns (e.g., turning) of fish, leading to frequent identity switches and fragmented trajectories. To address these challenges, we propose SOD-SORT, which integrates a Constant Turn-Rate and Velocity (CTRV) motion model within an Extended Kalman Filter (EKF) framework into DeepOCSORT, a recent observation-centric tracker. Through systematic Bayesian optimization of the EKF process noise (Q), observation noise (R), and ReID weighting parameters, we achieve harmonious integration of advanced motion modeling with appearance features. Evaluations on the DeepBlueI validation set show that SOD-SORT attains IDF1 = 0.829 and reduces identity switches by 13% (93 vs. 107) compared to the DeepOCSORT baseline, while maintaining comparable MOTA (0.737). Controlled ablation studies reveal that naive integration of CTRV-EKF with default parameters degrades performance substantially (IDs: 172 vs. 107 baseline), but careful parameter optimization resolves this motion-appearance conflict. Furthermore, we introduce a statistical quantization method that converts variable-length trajectories into fixed-length feature vectors, enabling effective unsupervised classification of normal and abnormal swimming behaviors in both the Fish4Knowledge coral reef dataset and real-world Deep Blue I cage videos. The proposed approach demonstrates that principled integration of advanced motion models with appearance cues, combined with high-quality continuous trajectories, can support reliable behavior modeling for aquaculture monitoring applications.<\/jats:p>","DOI":"10.3390\/s26010256","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T14:33:25Z","timestamp":1767191605000},"page":"256","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Multi-Fish Tracking and Behavior Modeling Framework for High-Density Cage Aquaculture"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8247-401X","authenticated-orcid":false,"given":"Xinyao","family":"Xiao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Ocean Sensing & Ocean College, Zhejiang University, Zhoushan 316021, China"},{"name":"Hainan Institute, Zhejiang University, Sanya 572025, China"},{"name":"Hainan Observation and Research Station of Ecological Environment and Fishery Resource in Yazhou Bay, Sanya 572025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4726-0104","authenticated-orcid":false,"given":"Tao","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ocean Sensing & Ocean College, Zhejiang University, Zhoushan 316021, China"},{"name":"State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 311215, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangyan","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ocean Sensing & Ocean College, Zhejiang University, Zhoushan 316021, China"},{"name":"Hainan Institute, Zhejiang University, Sanya 572025, China"},{"name":"Hainan Observation and Research Station of Ecological Environment and Fishery Resource in Yazhou Bay, Sanya 572025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiliang","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ocean Sensing & Ocean College, Zhejiang University, Zhoushan 316021, China"},{"name":"Hainan Institute, Zhejiang University, Sanya 572025, China"},{"name":"Hainan Observation and Research Station of Ecological Environment and Fishery Resource in Yazhou Bay, Sanya 572025, China"},{"name":"State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 311215, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4616-867X","authenticated-orcid":false,"given":"Yanzhen","family":"Gu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ocean Sensing & Ocean College, Zhejiang University, Zhoushan 316021, China"},{"name":"Hainan Institute, Zhejiang University, Sanya 572025, China"},{"name":"Hainan Observation and Research Station of Ecological Environment and Fishery Resource in Yazhou Bay, Sanya 572025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pixue","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Marine Monitoring and Forecasting Center, Shanghai 200062, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Dong","sequence":"additional","affiliation":[{"name":"Northern Navigation Service Center of Maritime Safety Administration, Tianjin 300220, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"ref_1","unstructured":"FAO (2024). The State of World Fisheries and Aquaculture 2024, FAO."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Tian, Z., Qu, P., Li, J., Sun, Y., Li, G., Liang, Z., and Zhang, W. (2023). A survey of deep learning-based low-light image enhancement. Sensors, 23.","DOI":"10.3390\/s23187763"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Li, G., Yao, Z., Hu, Y., Lian, A., Yuan, T., Pang, G., and Huang, X. (2024). Deep Learning-Based Fish Detection Using Above-Water Infrared Camera for Deep-Sea Aquaculture: A Comparison Study. Sensors, 24.","DOI":"10.3390\/s24082430"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, Z., Yan, G., Zhang, J., and Hu, B. (2024). Underwater Image Enhancement Based on Luminance Reconstruction by Multi-Resolution Fusion of RGB Channels. Sensors, 24.","DOI":"10.3390\/s24175776"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., and Paulus, D. (2017, January 17\u201320). Simple online and realtime tracking with a deep association metric. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China.","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref_6","unstructured":"Aharon, N., Orfaig, R., and Bobrovsky, B.-Z. (2022). BoT-SORT: Robust associations multi-pedestrian tracking. arXiv."},{"key":"ref_7","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 24\u201328). Bytetrack: Multi-object tracking by associating every detection box. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bar-Shalom, Y., Li, X.R., and Kirubarajan, T. (2001). Estimation with Applications to Tracking and Navigation: Theory Algorithms and Software, John Wiley & Sons.","DOI":"10.1002\/0471221279"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/s10462-025-11212-y","article-title":"Multi-object tracking review: Retrospective and emerging trend","volume":"58","author":"Guan","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"15249","DOI":"10.1007\/s11042-024-19417-z","article-title":"An optimized deep network-based fish tracking and classification from underwater images","volume":"84","author":"Peddina","year":"2025","journal-title":"Multimed. Tools Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zouin, B., Zahir, J., Baletaud, F., Vigliola, L., and Villon, S. (2024). Improving CNN fish detection and classification with tracking. Appl. Sci., 14.","DOI":"10.3390\/app142210122"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"110408","DOI":"10.1016\/j.compag.2025.110408","article-title":"Adaptive spatial aggregation and viewpoint alignment for three-dimensional online multiple fish tracking","volume":"236","author":"Liu","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Pedersen, M., Lehotsk\u00fd, D., Nikolov, I., and Moeslund, T.B. (2023, January 18\u201321). Brackishmot: The brackish multi-object tracking dataset. Proceedings of the Scandinavian Conference on Image Analysis, Sirkka, Finland.","DOI":"10.1007\/978-3-031-31435-3_2"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"246309","DOI":"10.1155\/2008\/246309","article-title":"Evaluating multiple object tracking performance: The clear mot metrics","volume":"2008","author":"Bernardin","year":"2008","journal-title":"EURASIP J. Image Video Process."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., and Tomasi, C. (2016, January 8\u201316). Performance measures and a data set for multi-target, multi-camera tracking. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref_16","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":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_17","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_18","doi-asserted-by":"crossref","first-page":"2872","DOI":"10.1109\/TPAMI.2021.3054775","article-title":"Deep learning for person re-identification: A survey and outlook","volume":"44","author":"Ye","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_20","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Advances in Neural Information Processing Systems, Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, L., Liu, Y., Li, Y., and Wang, S. (2020, January 23\u201328). Towards real-time multi-object tracking. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"108542","DOI":"10.1016\/j.compag.2023.108542","article-title":"SiamFCA: A new fish single object tracking method based on siamese network with coordinate attention in aquaculture","volume":"216","author":"Mei","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"ref_23","unstructured":"Spampinato, C., Chen-Burger, Y.-H., Nadarajan, G., and Fisher, R.B. (2008, January 22\u201325). Detecting, tracking and counting fish in low quality unconstrained underwater videos. Proceedings of the International Conference on Computer Vision Theory and Applications, Funchal, Portugal."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Beyan, C., and Fisher, R.B. (2013, January 15\u201318). Detecting abnormal fish trajectories using clustered and labeled data. Proceedings of the 2013 IEEE International Conference on Image Processing, Melbourne, Australia.","DOI":"10.1109\/ICIP.2013.6738303"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"33","DOI":"10.5296\/ast.v5i1.10649","article-title":"A principal component analysis of vertical temperature profiles for tracking movements of large pelagic fishes","volume":"5","author":"Carmody","year":"2017","journal-title":"Aquat. Sci. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"29400","DOI":"10.1109\/ACCESS.2023.3247143","article-title":"Fish tracking and continual behavioral pattern clustering using novel Sillago Sihama Vid (SSVid)","volume":"11","author":"Shreesha","year":"2023","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Abinaya, N., and Susan, D. (2020, January 27\u201328). Tracking of Fish School in Aquaculture with Weighted Clustering Technique Using Kalman Filter. Proceedings of the International Conference on Automation, Signal Processing, Instrumentation and Control, Singapore.","DOI":"10.1007\/978-981-15-8221-9_222"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kandimalla, V., Richard, M., Smith, F., Quirion, J., Torgo, L., and Whidden, C. (2022). 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_29","doi-asserted-by":"crossref","unstructured":"J\u00e4ger, J., Wolff, V., Fricke-Neuderth, K., Mothes, O., and Denzler, J. (2017, January 19\u201322). Visual fish tracking: Combining a two-stage graph approach with CNN-features. Proceedings of the OCEANS 2017-Aberdeen, Aberdeen, UK.","DOI":"10.1109\/OCEANSE.2017.8084691"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"23679","DOI":"10.1007\/s11042-016-4045-3","article-title":"Robust tracking of fish schools using CNN for head identification","volume":"76","author":"Wang","year":"2017","journal-title":"Multimed. Tools Appl."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Palconit, M.G.B., Almero, V.J.D., Rosales, M.A., Sybingco, E., Bandala, A.A., Vicerra, R.R.P., and Dadios, E.P. (2020, January 16\u201319). Towards tracking: Investigation of genetic algorithm and LSTM as fish trajectory predictors in turbid water. Proceedings of the 2020 IEEE Region 10 Conference (TENCON), Osaka, Japan.","DOI":"10.1109\/TENCON50793.2020.9293730"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wang, S.H., Zhao, J., Liu, X., Qian, Z.-M., Liu, Y., and Chen, Y.Q. (2017, January 5\u20139). 3D tracking swimming fish school with learned kinematic model using LSTM network. Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA.","DOI":"10.1109\/ICASSP.2017.7952320"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"108600","DOI":"10.1016\/j.compag.2023.108600","article-title":"TFMFT: Transformer-based multiple fish tracking","volume":"217","author":"Li","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"102246","DOI":"10.1016\/j.aquaeng.2022.102246","article-title":"Recognizing fish behavior in aquaculture with graph convolutional network","volume":"98","author":"Huang","year":"2022","journal-title":"Aquac. Eng."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Gong, L., Hu, Z., and Zhou, X. (2022, January 26\u201328). A few samples underwater fish tracking method based on semi-supervised and attention mechanism. Proceedings of the 2022 6th International Conference on Robotics, Control and Automation (ICRCA), Xiamen, China.","DOI":"10.1109\/ICRCA55033.2022.9828911"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.compag.2015.12.014","article-title":"Automated multiple fish tracking in three-dimension using a structured light sensor","volume":"121","author":"Saberioon","year":"2016","journal-title":"Comput. Electron. Agric."},{"key":"ref_37","first-page":"72","article-title":"Offshore cage aquaculture of China: Current situation, problems and countermeasures","volume":"35","author":"Zhu","year":"2017","journal-title":"Chin. Fish. Econ"},{"key":"ref_38","first-page":"90","article-title":"Study on strategies for developing offshore as the new spaces for mariculture in China","volume":"18","author":"Mai","year":"2016","journal-title":"Strateg. Study Chin. Acad. Eng."},{"key":"ref_39","first-page":"198","article-title":"General technology research of 100 thousand ton deep sea aquaculture platform","volume":"39","author":"Cai","year":"2017","journal-title":"Ship Eng."},{"key":"ref_40","unstructured":"(2025, August 21). Fish4Knowledge Homepage. Available online: https:\/\/homepages.inf.ed.ac.uk\/rbf\/Fish4Knowledge\/."},{"key":"ref_41","unstructured":"(2025, October 01). Fish4Knowledge Video Sample Download Page. Available online: https:\/\/groups.inf.ed.ac.uk\/vision\/DATASETS\/FISH4KNOWLEDGE\/WEBSITE\/F4KDATASAMPLES\/INTERFACE\/DATASAMPLES\/search.php."},{"key":"ref_42","unstructured":"(2025, October 01). Fish4Knowledge Overview. Available online: https:\/\/groups.inf.ed.ac.uk\/vision\/DATASETS\/FISH4KNOWLEDGE\/WEBSITE\/overview.htm."},{"key":"ref_43","unstructured":"(2025, October 01). Fish Recognition Ground-Truth Data. Available online: https:\/\/homepages.inf.ed.ac.uk\/rbf\/Fish4Knowledge\/GROUNDTRUTH\/RECOG\/."},{"key":"ref_44","unstructured":"(2025, October 01). Fish Trajectory Ground Truth Dataset. Available online: https:\/\/homepages.inf.ed.ac.uk\/rbf\/Fish4Knowledge\/GROUNDTRUTH\/BEHAVIOR\/."},{"key":"ref_45","unstructured":"Jocher, G., Jing, Q., and Ayush, C. (2023). Ultralytics YOLOv8, Ultralytics. version 8.0.0."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Maggiolino, G., Ahmad, A., Cao, J., and Kitani, K. (2023, January 8\u201311). Deep oc-sort: Multi-pedestrian tracking by adaptive re-identification. Proceedings of the 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICIP49359.2023.10222576"},{"key":"ref_47","unstructured":"Heindl, C. (2022). Py-motmetrics: Metrics for Multiple Object Tracker (MOT) Benchmarking, Zenodo."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Qin, Z., Wang, L., Zhou, S., Fu, P., Hua, G., and Tang, W. (2024, January 16\u201320). Towards generalizable multi-object tracking. Proceedings of the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01797"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A New Approach to Linear Filtering and Prediction Problems","volume":"82","author":"Kalman","year":"1960","journal-title":"J. Basic Eng."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Li, Q., Zheng, Y., Xie, X., Chen, Y., Liu, W., and Ma, W.-Y. (2008, January 5\u20137). Mining user similarity based on location history. Proceedings of the 16th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Irvine, CA, USA.","DOI":"10.1145\/1463434.1463477"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/256\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:13:49Z","timestamp":1767676429000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/256"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,31]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010256"],"URL":"https:\/\/doi.org\/10.3390\/s26010256","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,31]]}}}