{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/underwater-fish-detection-using-deep-learning","title":"Underwater Fish Detection using Deep Learning for Water Power Applications","arxiv_id":"1811.01494","date":"2018-11-05","proceeding":null,"authors":["Wenwei Xu","Shari Matzner"],"abstract":"Clean energy from oceans and rivers is becoming a reality with the\ndevelopment of new technologies like tidal and instream turbines that generate\nelectricity from naturally flowing water. These new technologies are being\nmonitored for effects on fish and other wildlife using underwater video.\nMethods for automated analysis of underwater video are needed to lower the\ncosts of analysis and improve accuracy. A deep learning model, YOLO, was\ntrained to recognize fish in underwater video using three very different\ndatasets recorded at real-world water power sites. Training and testing with\nexamples from all three datasets resulted in a mean average precision (mAP)\nscore of 0.5392. To test how well a model could generalize to new datasets, the\nmodel was trained using examples from only two of the datasets and then tested\non examples from all three datasets. The resulting model could not recognize\nfish in the dataset that was not part of the training set. The mAP scores on\nthe other two datasets that were included in the training set were higher than\nthe scores achieved by the model trained on all three datasets. These results\nindicate that different methods are needed in order to produce a trained model\nthat can generalize to new data sets such as those encountered in real world\napplications.","url_abs":"http://arxiv.org/abs/1811.01494v1","url_pdf":"http://arxiv.org/pdf/1811.01494v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"underwater-fish-detection-using-deep-learning","repo_url":"https://github.com/wenweixu/keras-yolo3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"fish-detection","task_name":"Fish Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}