Show simple item record

dc.contributor.authorDitria, Ellen M
dc.contributor.authorLopez-Marcano, Sebastian
dc.contributor.authorSievers, Michael
dc.contributor.authorJinks, Eric L
dc.contributor.authorBrown, Christopher J
dc.contributor.authorConnolly, Rod M
dc.date.accessioned2020-10-07T03:16:18Z
dc.date.available2020-10-07T03:16:18Z
dc.date.issued2020
dc.identifier.issn2296-7745
dc.identifier.doi10.3389/fmars.2020.00429
dc.identifier.urihttp://hdl.handle.net/10072/398156
dc.description.abstractAquatic ecologists routinely count animals to provide critical information for conservation and management. Increased accessibility to underwater recording equipment such as action cameras and unmanned underwater devices has allowed footage to be captured efficiently and safely, without the logistical difficulties manual data collection often presents. It has, however, led to immense volumes of data being collected that require manual processing and thus significant time, labor, and money. The use of deep learning to automate image processing has substantial benefits but has rarely been adopted within the field of aquatic ecology. To test its efficacy and utility, we compared the accuracy and speed of deep learning techniques against human counterparts for quantifying fish abundance in underwater images and video footage. We collected footage of fish assemblages in seagrass meadows in Queensland, Australia. We produced three models using an object detection framework to detect the target species, an ecologically important fish, luderick (Girella tricuspidata). Our models were trained on three randomized 80:20 ratios of training:validation datasets from a total of 6,080 annotations. The computer accurately determined abundance from videos with high performance using unseen footage from the same estuary as the training data (F1 = 92.4%, mAP50 = 92.5%) and from novel footage collected from a different estuary (F1 = 92.3%, mAP50 = 93.4%). The computer’s performance in determining abundance was 7.1% better than human marine experts and 13.4% better than citizen scientists in single image test datasets, and 1.5 and 7.8% higher in video datasets, respectively. We show that deep learning can be a more accurate tool than humans at determining abundance and that results are consistent and transferable across survey locations. Deep learning methods provide a faster, cheaper, and more accurate alternative to manual data analysis methods currently used to monitor and assess animal abundance and have much to offer the field of aquatic ecology.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherFrontiers Media SA
dc.relation.ispartofpagefrom429
dc.relation.ispartofjournalFrontiers in Marine Science
dc.relation.ispartofvolume7
dc.subject.fieldofresearchEnvironmental Sciences
dc.subject.fieldofresearchOceanography
dc.subject.fieldofresearchEcology
dc.subject.fieldofresearchcode05
dc.subject.fieldofresearchcode0405
dc.subject.fieldofresearchcode0602
dc.subject.keywordsScience & Technology
dc.subject.keywordsLife Sciences & Biomedicine
dc.subject.keywordsEnvironmental Sciences
dc.subject.keywordsMarine & Freshwater Biology
dc.titleAutomating the Analysis of Fish Abundance Using Object Detection: Optimizing Animal Ecology With Deep Learning
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationDitria, EM; Lopez-Marcano, S; Sievers, M; Jinks, EL; Brown, CJ; Connolly, RM, Automating the Analysis of Fish Abundance Using Object Detection: Optimizing Animal Ecology With Deep Learning, Frontiers in Marine Science, 2020, 7, pp. 429
dcterms.licensehttp://creativecommons.org/licenses/by/4.0/
dc.date.updated2020-10-07T03:11:20Z
dc.description.versionVersion of Record (VoR)
gro.rights.copyright© 2020 Ditria, Lopez-Marcano, Sievers, Jinks, Brown and Connolly. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
gro.hasfulltextFull Text
gro.griffith.authorSievers, Michael K.
gro.griffith.authorBrown, Chris J.
gro.griffith.authorLopez-Marcano, Sebastian E.
gro.griffith.authorConnolly, Rod M.
gro.griffith.authorDitria, Ellen M.
gro.griffith.authorJinks, Eric


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record