{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T16:56:51Z","timestamp":1782752211455,"version":"3.54.5"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T00:00:00Z","timestamp":1616371200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T00:00:00Z","timestamp":1616371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>A wide range of applications in marine ecology extensively uses underwater cameras. Still, to efficiently process the vast amount of data generated, we need to develop tools that can automatically detect and recognize species captured on film. Classifying fish species from videos and images in natural environments can be challenging because of noise and variation in illumination and the surrounding habitat. In this paper, we propose a two-step deep learning approach for the detection and classification of temperate fishes without pre-filtering. The first step is to detect each single fish in an image, independent of species and sex. For this purpose, we employ the You Only Look Once (YOLO) object detection technique. In the second step, we adopt a Convolutional Neural Network (CNN) with the Squeeze-and-Excitation (SE) architecture for classifying each fish in the image without pre-filtering. We apply transfer learning to overcome the limited training samples of temperate fishes and to improve the accuracy of the classification. This is done by training the object detection model with ImageNet and the fish classifier via a public dataset (Fish4Knowledge), whereupon both the object detection and classifier are updated with temperate fishes of interest. The weights obtained from pre-training are applied to post-training as a priori. Our solution achieves the state-of-the-art accuracy of 99.27% using the pre-training model. The accuracies using the post-training model are also high; 83.68% and 87.74% with and without image augmentation, respectively. This strongly indicates that the solution is viable with a more extensive dataset.<\/jats:p>","DOI":"10.1007\/s10489-020-02154-9","type":"journal-article","created":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T09:07:57Z","timestamp":1616404077000},"page":"6988-7001","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":157,"title":["Temperate fish detection and classification: a deep learning based approach"],"prefix":"10.1007","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4088-1642","authenticated-orcid":false,"given":"Kristian Muri","family":"Knausg\u00e5rd","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arne","family":"Wiklund","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tonje Knutsen","family":"S\u00f8rdalen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kim Tallaksen","family":"Halvorsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alf Ring","family":"Kleiven","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Morten","family":"Goodwin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,3,22]]},"reference":[{"key":"2154_CR1","first-page":"440","volume":"4","author":"D Perry","year":"2018","unstructured":"Perry D, Staveley TAB, Gullstr\u00f6m M (2018) . Habitat connectivity of fish in temperate shallow-water seascapes 4:440","journal-title":"Habitat connectivity of fish in temperate shallow-water seascapes"},{"issue":"3","key":"2154_CR2","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1111\/1365-2656.12780","volume":"87","author":"BG Weinstein","year":"2017","unstructured":"Weinstein BG (2017) A computer vision for animal ecology. J Animal Ecol 87(3):533\u2013545","journal-title":"J Animal Ecol"},{"issue":"1","key":"2154_CR3","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.fishres.2010.10.011","volume":"107","author":"D Pelletier","year":"2011","unstructured":"Pelletier D, Leleu K, Mou-Tham G, Guillemot N, Chabanet P (2011) Comparison of visual census and high definition video transects for monitoring coral reef fish assemblages. Fish Res 107(1):84\u201393","journal-title":"Fish Res"},{"key":"2154_CR4","doi-asserted-by":"publisher","first-page":"726, 01","DOI":"10.3390\/s20030726","volume":"20","author":"V Lopez-Vazquez","year":"2020","unstructured":"Lopez-Vazquez V, Lopez-Guede J, Marini S, Fanelli E, Johnsen E, Aguzzi J (2020) Video image enhancement and machine learning pipeline for underwater animal detection and classification at cabled observatories. Sensors 20:726, 01","journal-title":"Sensors"},{"key":"2154_CR5","first-page":"155","volume":"23","author":"P Francour","year":"1999","unstructured":"Francour P, Liret C, Harvey E (1999) Comparison of fish abundance estimates made by remote underwater video and visual census. Naturalista Siciliano 23:155\u2013168, 01","journal-title":"Naturalista Siciliano"},{"key":"2154_CR6","unstructured":"Li X, Shang M, Qin H, Chen L (2015) Fast accurate fish detection and recognition of underwater images with fast r-cnn. In: OCEANS\u201915 MTS\/IEEE. IEEE, Washington, pp 1\u20135"},{"key":"2154_CR7","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.neucom.2015.10.122","volume":"187","author":"H Qin","year":"2016","unstructured":"Qin H, Li X, Liang J, Peng Y, Zhang C (2016) Deepfish: accurate underwater live fish recognition with a deep architecture. Neurocomputing 187:49\u201358","journal-title":"Neurocomputing"},{"key":"2154_CR8","doi-asserted-by":"crossref","unstructured":"Jin L, Liang H (2017) Deep learning for underwater image recognition in small sample size situations. In: OCEANS 2017-Aberdeen. IEEE, pp 1\u20134","DOI":"10.1109\/OCEANSE.2017.8084645"},{"issue":"2-3","key":"2154_CR9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.fishres.2006.04.009","volume":"80","author":"D White","year":"2006","unstructured":"White D, Svellingen C, Strachan N (2006) Automated measurement of species and length of fish by computer vision. Fish Res 80(2-3):203\u2013210","journal-title":"Fish Res"},{"key":"2154_CR10","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber J (2015) Deep learning in neural networks: an overview. Neur Netw 61:85\u2013117","journal-title":"Neur Netw"},{"key":"2154_CR11","doi-asserted-by":"crossref","unstructured":"Andersen P. -A., Goodwin M, Granmo O. -C. (2018) The dreaming variational autoencoder for reinforcement learning environments. In: International conference on innovative techniques and applications of artificial intelligence. Springer, pp 143\u2013155","DOI":"10.1007\/978-3-030-04191-5_11"},{"key":"2154_CR12","doi-asserted-by":"crossref","unstructured":"Rathi D, Jain S, Indu S (2017) Underwater fish species classification using convolutional neural network and deep learning. In: 2017 Ninth international conference on advances in pattern recognition (ICAPR). IEEE, pp 1\u20136","DOI":"10.1109\/ICAPR.2017.8593044"},{"key":"2154_CR13","doi-asserted-by":"crossref","unstructured":"Chen G, Sun P, Shang Y (2017) Automatic fish classification system using deep learning. In: 2017 IEEE 29th international conference on tools with artificial intelligence (ICTAI). IEEE, pp 24\u201329","DOI":"10.1109\/ICTAI.2017.00016"},{"key":"2154_CR14","doi-asserted-by":"publisher","first-page":"109930","DOI":"10.1016\/j.jfoodeng.2020.109930","volume":"278","author":"A Taheri-Garavand","year":"2020","unstructured":"Taheri-Garavand A, Nasiri A, Banan A, Zhang Y-D (2020) Smart deep learning-based approach for non-destructive freshness diagnosis of common carp fish. J Food Eng 278:109930","journal-title":"J Food Eng"},{"key":"2154_CR15","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u2013 1105"},{"key":"2154_CR16","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L. -J., Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: IEEE Conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2154_CR17","unstructured":"Huang PX, Boom BB, Fisher RB Fish recognition ground-truth data, 2013 [Online; accessed 30.01.2018]"},{"key":"2154_CR18","doi-asserted-by":"crossref","unstructured":"Liu S, Li X, Gao M, Cai Y, Nian R, Li P, Yan T, Lendasse A (2018) Embedded online fish detection and tracking system via yolov3 and parallel correlation filter. In: OCEANS 2018 MTS\/IEEE Charleston, pp 1\u20136","DOI":"10.1109\/OCEANS.2018.8604658"},{"key":"2154_CR19","doi-asserted-by":"crossref","unstructured":"Xu W, Matzner S (2018) Underwater fish detection using deep learning for water power applications. In: 2018 International conference on computational science and computational intelligence (CSCI), pp 313\u2013318","DOI":"10.1109\/CSCI46756.2018.00067"},{"key":"2154_CR20","unstructured":"Pedersen M, Haurum JB, Gade R, Moeslund TB (2019) Detection of marine animals in a new underwater dataset with varying visibility. In: CVPR Workshops"},{"key":"2154_CR21","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv:abs\/1804.02767"},{"key":"2154_CR22","unstructured":"Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? arXiv:abs\/1411.1792"},{"key":"2154_CR23","doi-asserted-by":"crossref","unstructured":"Olsvik E, Trinh CM, Knausg\u00e5rd KM, Wiklund A, S\u00f8rdalen TK, Kleiven AR, Jiao L, Goodwin M (2019) Biometric fish classification of temperate species using convolutional neural network with squeeze-and-excitation. In: International conference on industrial, engineering and other applications of applied intelligent systems. Springer, pp 89\u2013101","DOI":"10.1007\/978-3-030-22999-3_9"},{"issue":"10","key":"2154_CR24","doi-asserted-by":"publisher","first-page":"2586","DOI":"10.1093\/icesjms\/fsw135","volume":"73","author":"KT Halvorsen","year":"2016","unstructured":"Halvorsen KT, S\u00f8rdalen TK, Durif C, Knutsen H, Olsen EM (2016) Male-biased sexual size dimorphism in the nest building corkwing wrasse (symphodus melops): implications for a size regulated fishery. ICES J Mar Sci 73(10):2586\u20132594","journal-title":"ICES J Mar Sci"},{"issue":"3","key":"2154_CR25","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1093\/icesjms\/fsw221","volume":"74","author":"KT Halvorsen","year":"2017","unstructured":"Halvorsen KT, S\u00f8rdalen TK, V\u00f8llestad LA, Skiftesvik AB, Espeland SH, Olsen EM, Grabowski J (2017) Sex- and size-selective harvesting of corkwing wrasse (symphodus melops)\u2014a cleaner fish used in salmonid aquaculture. ICES J Mar Sci 74(3):660\u2013669","journal-title":"ICES J Mar Sci"},{"key":"2154_CR26","unstructured":"Fordham S, Fowler S, Coelho R, Goldman K, Francis M (2016) Squalus acanthias the iucn red list of threatened species 2016: e.t91209505a2898271."},{"key":"2154_CR27","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala SK, Girshick RB, Farhadi A (2015) You only look once: unified, real-time object detection. arXiv:abs\/1506.02640","DOI":"10.1109\/CVPR.2016.91"},{"key":"2154_CR28","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv:abs\/2004.10934"},{"key":"2154_CR29","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein MS, Berg AC, Li F (2014) Imagenet large scale visual recognition challenge. arXiv:abs\/1409.0575"},{"key":"2154_CR30","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2017) Squeeze-and-excitation networks. arXiv:abs\/1709.01507","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2154_CR31","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:abs\/1412.6980"},{"key":"2154_CR32","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th international conference on neural information processing systems - volume 1 NIPS\u201912, (USA), pp 1097\u20131105"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-02154-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-020-02154-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-02154-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T04:11:34Z","timestamp":1649823094000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-020-02154-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,22]]},"references-count":32,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["2154"],"URL":"https:\/\/doi.org\/10.1007\/s10489-020-02154-9","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,22]]},"assertion":[{"value":"15 December 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}