{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T17:44:55Z","timestamp":1780335895968,"version":"3.54.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Key Research and Development Project of Hainan Province","award":["ZDYF2023XDNY176"],"award-info":[{"award-number":["ZDYF2023XDNY176"]}]},{"name":"the Key Research and Development Project of Hainan Province","award":["ZDYF2023XDNY176"],"award-info":[{"award-number":["ZDYF2023XDNY176"]}]},{"name":"the Key Research and Development Project of Hainan Province","award":["ZDYF2023XDNY176"],"award-info":[{"award-number":["ZDYF2023XDNY176"]}]},{"name":"Project of Hainan Seed Industry Laboratory Foundation","award":["B23H10004"],"award-info":[{"award-number":["B23H10004"]}]},{"name":"Project of Hainan Seed Industry Laboratory Foundation","award":["B23H10004"],"award-info":[{"award-number":["B23H10004"]}]},{"name":"Project of Hainan Seed Industry Laboratory Foundation","award":["B23H10004"],"award-info":[{"award-number":["B23H10004"]}]},{"name":"Project of Sanya Yazhouwan Science and Technology City Management Foundation","award":["SKJC-2023-01-004"],"award-info":[{"award-number":["SKJC-2023-01-004"]}]},{"name":"Project of Sanya Yazhouwan Science and Technology City Management Foundation","award":["SKJC-2023-01-004"],"award-info":[{"award-number":["SKJC-2023-01-004"]}]},{"name":"Project of Sanya Yazhouwan Science and Technology City Management Foundation","award":["SKJC-2023-01-004"],"award-info":[{"award-number":["SKJC-2023-01-004"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Accurate and non-invasive measurement of fish phenotypic characteristics in underwater environments is crucial for advancing aquaculture. Traditional manual methods require significant labor to anesthetize and capture fish, which not only raises ethical concerns but also risks causing injury to the animals. Alternative hardware-based approaches, such as acoustic technology and active structured light techniques, are often costly and may suffer from limited measurement accuracy. In contrast, image-based methods utilizing low-cost binocular cameras present a more affordable solution, although they face challenges such as light refraction between water and the waterproof enclosure, which can cause discrepancies between image coordinates and actual positions. To address these challenges, we have developed a fish keypoint detection dataset and trained both a fish object detection model and a keypoint detection model using the RTMDet and RTMPose architectures to identify keypoints on Plectropomus leopardus. Since the binocular camera must be housed in a waterproof enclosure, we correct for birefringence caused by the water and the enclosure by applying refraction corrections to the detected keypoint coordinates. This ensures that the keypoint coordinates obtained underwater are consistent with those in air, thereby improving the accuracy of subsequent stereo matching. Once the corrected keypoint coordinates are obtained, we apply the least squares method, in conjunction with binocular stereo imaging principles, to perform stereo matching and derive the actual 3D coordinates of the keypoints. We calculate the fish body length by measuring the 3D coordinates of the snout and tail. Our model achieved <jats:bold>98.6%<\/jats:bold> accuracy in keypoints detection (AP@0.5:0.95). Underwater tests showed an average measurement error of approximately <jats:bold>3.2 mm<\/jats:bold> (MRPE=3.50%) for fish in a tank, with real-time processing at <jats:bold>28 FPS<\/jats:bold> on an NVIDIA GTX 1060 GPU. These results confirm that our method effectively detects keypoints on fish bodies and measures their length without physical contact or removal from the tank. By eliminating invasive procedures, our approach not only improves measurement efficiency but also aligns with ethical standards in aquaculture. Compared to existing techniques, our method offers enhanced accuracy (reducing MRPE by 53.8% compared to baseline methods) and practicality, making it a valuable tool for the aquaculture industry.<\/jats:p>","DOI":"10.1038\/s41598-025-08863-w","type":"journal-article","created":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T07:40:59Z","timestamp":1751960459000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Automated underwater plectropomus leopardus phenotype measurement through cylinder"],"prefix":"10.1038","volume":"15","author":[{"given":"Mengran","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaocheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guojun","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cun","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjie","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenmin","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,8]]},"reference":[{"key":"8863_CR1","unstructured":"Food and Agriculture Organization of the United Nations. The state of world fisheries and aquaculture 2022 (2022)."},{"key":"8863_CR2","unstructured":"Group, W.\u00a0B. The sunken billions revisited: Progress and challenges in global fisheries (2021)."},{"key":"8863_CR3","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/j.compag.2018.05.025","volume":"150","author":"M Saberioon","year":"2018","unstructured":"Saberioon, M. & C\u00edsa\u0159, P. Automated within tank fish mass estimation using infrared reflection system. Comput. Electron. Agric. 150, 484\u2013492 (2018).","journal-title":"Comput. Electron. Agric."},{"key":"8863_CR4","volume":"95","author":"J Smith","year":"2021","unstructured":"Smith, J., Tanaka, A. & M\u00fcller, R. Labor cost analysis in modern aquaculture systems. Aquac. Eng. 95, 102214 (2021).","journal-title":"Aquac. Eng."},{"key":"8863_CR5","volume":"528","author":"TL Nguyen","year":"2020","unstructured":"Nguyen, T. L., Wang, Q. & Oppedal, F. Stress-induced mortality in aquaculture: A meta-analysis. Aquaculture 528, 735487 (2020).","journal-title":"Aquaculture"},{"key":"8863_CR6","doi-asserted-by":"crossref","unstructured":"Mroz, S. et al. Comparing the quality of human pose estimation with blazepose or openpose. In 2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART), 1\u20134 (IEEE, 2021).","DOI":"10.1109\/BioSMART54244.2021.9677850"},{"key":"8863_CR7","unstructured":"Liu, X., Zhang, W. & Li, H. Underwater fish length estimation via deep regression networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2208\u20132215 (2022)."},{"key":"8863_CR8","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1038\/s41598-021-81499-8","volume":"11","author":"CJ Thiele","year":"2021","unstructured":"Thiele, C. J., Hudson, M. D., Russell, A. E., Saluveer, M. & Sidaoui-Haddad, G. Microplastics in fish and fishmeal: an emerging environmental challenge?. Sci. Rep. 11, 2045 (2021).","journal-title":"Sci. Rep."},{"key":"8863_CR9","unstructured":"Lee, H., Park, S. & Kim, M. Multi-interface refraction error analysis in underwater stereo vision. In Proceedings of the IEEE OCEANS Conference, 1\u20136 (IEEE, 2022)."},{"key":"8863_CR10","unstructured":"Chen, Y.-R. & Hwang, J.-N. Fish4knowledge dataset. Online Repository (2016)."},{"key":"8863_CR11","unstructured":"Hydroacoustic Technology Inc. Eventmeasure \u00aeunderwater measurement system specifications. Product Brochure (2023)."},{"key":"8863_CR12","doi-asserted-by":"crossref","unstructured":"Suo, F., Huang, K., Ling, G., Li, Y. & Xiang, J. Fish keypoints detection for ecology monitoring based on underwater visual intelligence. In 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV), 542\u2013547 (IEEE, 2020).","DOI":"10.1109\/ICARCV50220.2020.9305424"},{"key":"8863_CR13","doi-asserted-by":"crossref","unstructured":"Voskakis, D., Makris, A. & Papandroulakis, N. Deep learning based fish length estimation. an application for the mediterranean aquaculture. In OCEANS 2021: San Diego\u2013Porto, 1\u20135 (IEEE, 2021).","DOI":"10.23919\/OCEANS44145.2021.9705813"},{"key":"8863_CR14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0251281","volume":"16","author":"J Zhou","year":"2021","unstructured":"Zhou, J., Shi, B., Liu, G. & Ju, S. Accuracy analysis of dam deformation monitoring and correction of refraction with robotic total station. PLoS One 16, e0251281 (2021).","journal-title":"PLoS One"},{"key":"8863_CR15","doi-asserted-by":"crossref","unstructured":"Li, J. et al. Human pose regression with residual log-likelihood estimation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 11025\u201311034 (2021).","DOI":"10.1109\/ICCV48922.2021.01084"},{"key":"8863_CR16","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.aquaeng.2017.01.003","volume":"76","author":"JM Miranda","year":"2017","unstructured":"Miranda, J. M. & Romero, M. A prototype to measure rainbow trout\u2019s length using image processing. Aquac. Eng. 76, 41\u201349 (2017).","journal-title":"Aquac. Eng."},{"key":"8863_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.103788","volume":"129","author":"J Guan","year":"2021","unstructured":"Guan, J. et al. Automated pixel-level pavement distress detection based on stereo vision and deep learning. Autom. Constr. 129, 103788 (2021).","journal-title":"Autom. Constr."},{"key":"8863_CR18","doi-asserted-by":"crossref","unstructured":"McNally, W., Vats, K., Wong, A. & McPhee, J. Rethinking keypoint representations: Modeling keypoints and poses as objects for multi-person human pose estimation. In European Conference on Computer Vision, 37\u201354 (Springer, 2022).","DOI":"10.1007\/978-3-031-20068-7_3"},{"key":"8863_CR19","unstructured":"DeVries, T. & Taylor, G.\u00a0W. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)."},{"key":"8863_CR20","doi-asserted-by":"crossref","unstructured":"Huang, J., Zhu, Z., Guo, F. & Huang, G. The devil is in the details: Delving into unbiased data processing for human pose estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5700\u20135709 (2020).","DOI":"10.1109\/CVPR42600.2020.00574"},{"key":"8863_CR21","doi-asserted-by":"crossref","unstructured":"Maji, D., Nagori, S., Mathew, M. & Poddar, D. Yolo-pose: Enhancing yolo for multi person pose estimation using object keypoint similarity loss. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2637\u20132646 (2022).","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"8863_CR22","doi-asserted-by":"publisher","first-page":"100","DOI":"10.2331\/suisan.20-00041","volume":"87","author":"N Furuta","year":"2021","unstructured":"Furuta, N., Tanaka, T. & Komeyama, K. Method for automating fish-size measurement and camera calibration using a three-dimensional structure and an optical character recognition technique. Nippon Suisan Gakkaishi 87, 100\u2013107 (2021).","journal-title":"Nippon Suisan Gakkaishi"},{"key":"8863_CR23","doi-asserted-by":"crossref","unstructured":"Lu, H., Li, Y. & Serikawa, S. Computer vision for ocean observing. Artif. Intell. Comput. 1\u201316 (2017).","DOI":"10.1007\/978-3-319-46245-5_1"},{"key":"8863_CR24","doi-asserted-by":"publisher","first-page":"13748","DOI":"10.1038\/s41598-018-32089-8","volume":"8","author":"S Marini","year":"2018","unstructured":"Marini, S. et al. Tracking fish abundance by underwater image recognition. Sci. Rep. 8, 13748 (2018).","journal-title":"Sci. Rep."},{"key":"8863_CR25","doi-asserted-by":"publisher","first-page":"1354","DOI":"10.1093\/icesjms\/fsz186","volume":"77","author":"R Garcia","year":"2020","unstructured":"Garcia, R. et al. Automatic segmentation of fish using deep learning with application to fish size measurement. ICES J.Mar. Sci. 77, 1354\u20131366 (2020).","journal-title":"ICES J.Mar. Sci."},{"key":"8863_CR26","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1007\/s11263-021-01482-8","volume":"129","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Chen, Z. & Tao, D. Towards high performance human keypoint detection. Int. J. Comput. Vis. 129, 2639\u20132662 (2021).","journal-title":"Int. J. Comput. Vis."},{"key":"8863_CR27","doi-asserted-by":"publisher","DOI":"10.3788\/gzxb20154402.0211002","volume":"44","author":"W Zhang","year":"2015","unstructured":"Zhang, W., Deng, X., Zhang, Q. & Li, H. Non-parallel system underwater image transformation model. Acta Photonica Sinica 44, 211002 (2015).","journal-title":"Acta Photonica Sinica"},{"key":"8863_CR28","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s44295-023-00002-3","volume":"1","author":"J Dong","year":"2023","unstructured":"Dong, J. et al. A detection-regression based framework for fish keypoints detection. Intell. Mar. Technol. Syst. 1, 9 (2023).","journal-title":"Intell. Mar. Technol. Syst."},{"key":"8863_CR29","unstructured":"Lyu, C. et al. Rtmdet: An empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784 (2022)."},{"key":"8863_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Z. Flexible camera calibration by viewing a plane from unknown orientations. In Proceedings of the Seventh IEEE International Conference on Computer Vision, vol.\u00a01, 666\u2013673 (Ieee, 1999).","DOI":"10.1109\/ICCV.1999.791289"},{"key":"8863_CR31","doi-asserted-by":"crossref","unstructured":"Hornberg, A. & GODDING, R. Camera calibration. Handbook of Machine and Computer Vision 291\u2013316 (2017).","DOI":"10.1002\/9783527413409.ch5"},{"key":"8863_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105419","volume":"173","author":"C Shi","year":"2020","unstructured":"Shi, C., Wang, Q., He, X., Zhang, X. & Li, D. An automatic method of fish length estimation using underwater stereo system based on labview. Comput. Electron. Agric. 173, 105419 (2020).","journal-title":"Comput. Electron. Agric."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-08863-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-08863-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-08863-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T09:35:40Z","timestamp":1752140140000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-08863-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,8]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["8863"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-08863-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,8]]},"assertion":[{"value":"7 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"24461"}}