Automatic detection, identification and counting of deep-water snappers on underwater baited video using deep learning
Deep-sea demersal fisheries in the Pacific have strong commercial, cultural, and recreational value, especially snappers (Lutjanidae) which make the bulk of catches. Yet, managing these fisheries is challenging due to the scarcity of data. Stereo-Baited Remote Underwater Video Stations (BRUVS) can p...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2025.1476616/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832086587258699776 |
|---|---|
| author | Florian Baletaud Florian Baletaud Florian Baletaud Sébastien Villon Antoine Gilbert Jean-Marie Côme Sylvie Fiat Corina Iovan Laurent Vigliola |
| author_facet | Florian Baletaud Florian Baletaud Florian Baletaud Sébastien Villon Antoine Gilbert Jean-Marie Côme Sylvie Fiat Corina Iovan Laurent Vigliola |
| author_sort | Florian Baletaud |
| collection | DOAJ |
| description | Deep-sea demersal fisheries in the Pacific have strong commercial, cultural, and recreational value, especially snappers (Lutjanidae) which make the bulk of catches. Yet, managing these fisheries is challenging due to the scarcity of data. Stereo-Baited Remote Underwater Video Stations (BRUVS) can provide valuable quantitative information on fish stocks, but manually processing large amounts of videos is time-consuming and sometimes unrealistic. To address this issue, we used a Region-based Convolutional Neural Network (Faster R-CNN), a deep learning architecture to automatically detect, identify and count deep-water snappers in BRUVS. Videos were collected in New Caledonia (South Pacific) at depths ranging from 47 to 552 m. Using a dataset of 12,100 annotations from 11 deep-water snapper species observed in 6,364 images, we obtained good model performance for the 6 species with sufficient annotations (F-measures >0.7, up to 0.87). The correlation between automatic and manual estimates of fish MaxN abundance in videos was high (0.72 – 0.9), but the Faster R-CNN showed an underestimation bias at higher abundances. A semi-automatic protocol where our model supported manual observers in processing BRUVS footage improved performance with a correlation of 0.96 with manual counts and a perfect match (R=1) for some key species. This model can already assist manual observers to semi-automatically process BRUVS footage and will certainly improve when more training data will be available to decrease the rate of false negatives. This study further shows that the use of artificial intelligence in marine science is progressive but warranted for the future. |
| format | Article |
| id | doaj-art-a16caf33672c49baab55349a2989bf74 |
| institution | Kabale University |
| issn | 2296-7745 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj-art-a16caf33672c49baab55349a2989bf742025-02-06T11:44:43ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452025-02-011210.3389/fmars.2025.14766161476616Automatic detection, identification and counting of deep-water snappers on underwater baited video using deep learningFlorian Baletaud0Florian Baletaud1Florian Baletaud2Sébastien Villon3Antoine Gilbert4Jean-Marie Côme5Sylvie Fiat6Corina Iovan7Laurent Vigliola8ENTROPIE, Institut de Recherche pour le Développement (IRD), UR, UNC, IFREMER, CNRS, Centre IRD de Nouméa, Noumea, New CaledoniaSoproner, Groupe GINGER, Noumea, New CaledoniaBurgeap, Groupe GINGER, Lyon, FranceENTROPIE, Institut de Recherche pour le Développement (IRD), UR, UNC, IFREMER, CNRS, Centre IRD de Nouméa, Noumea, New CaledoniaSoproner, Groupe GINGER, Noumea, New CaledoniaBurgeap, Groupe GINGER, Lyon, FranceENTROPIE, Institut de Recherche pour le Développement (IRD), UR, UNC, IFREMER, CNRS, Centre IRD de Nouméa, Noumea, New CaledoniaENTROPIE, Institut de Recherche pour le Développement (IRD), UR, UNC, IFREMER, CNRS, Centre IRD de Nouméa, Noumea, New CaledoniaENTROPIE, Institut de Recherche pour le Développement (IRD), UR, UNC, IFREMER, CNRS, Centre IRD de Nouméa, Noumea, New CaledoniaDeep-sea demersal fisheries in the Pacific have strong commercial, cultural, and recreational value, especially snappers (Lutjanidae) which make the bulk of catches. Yet, managing these fisheries is challenging due to the scarcity of data. Stereo-Baited Remote Underwater Video Stations (BRUVS) can provide valuable quantitative information on fish stocks, but manually processing large amounts of videos is time-consuming and sometimes unrealistic. To address this issue, we used a Region-based Convolutional Neural Network (Faster R-CNN), a deep learning architecture to automatically detect, identify and count deep-water snappers in BRUVS. Videos were collected in New Caledonia (South Pacific) at depths ranging from 47 to 552 m. Using a dataset of 12,100 annotations from 11 deep-water snapper species observed in 6,364 images, we obtained good model performance for the 6 species with sufficient annotations (F-measures >0.7, up to 0.87). The correlation between automatic and manual estimates of fish MaxN abundance in videos was high (0.72 – 0.9), but the Faster R-CNN showed an underestimation bias at higher abundances. A semi-automatic protocol where our model supported manual observers in processing BRUVS footage improved performance with a correlation of 0.96 with manual counts and a perfect match (R=1) for some key species. This model can already assist manual observers to semi-automatically process BRUVS footage and will certainly improve when more training data will be available to decrease the rate of false negatives. This study further shows that the use of artificial intelligence in marine science is progressive but warranted for the future.https://www.frontiersin.org/articles/10.3389/fmars.2025.1476616/fulldeep-water snapper fisheriesartificial intelligencesemi-automaticBRUVSfaster R-CNN |
| spellingShingle | Florian Baletaud Florian Baletaud Florian Baletaud Sébastien Villon Antoine Gilbert Jean-Marie Côme Sylvie Fiat Corina Iovan Laurent Vigliola Automatic detection, identification and counting of deep-water snappers on underwater baited video using deep learning Frontiers in Marine Science deep-water snapper fisheries artificial intelligence semi-automatic BRUVS faster R-CNN |
| title | Automatic detection, identification and counting of deep-water snappers on underwater baited video using deep learning |
| title_full | Automatic detection, identification and counting of deep-water snappers on underwater baited video using deep learning |
| title_fullStr | Automatic detection, identification and counting of deep-water snappers on underwater baited video using deep learning |
| title_full_unstemmed | Automatic detection, identification and counting of deep-water snappers on underwater baited video using deep learning |
| title_short | Automatic detection, identification and counting of deep-water snappers on underwater baited video using deep learning |
| title_sort | automatic detection identification and counting of deep water snappers on underwater baited video using deep learning |
| topic | deep-water snapper fisheries artificial intelligence semi-automatic BRUVS faster R-CNN |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2025.1476616/full |
| work_keys_str_mv | AT florianbaletaud automaticdetectionidentificationandcountingofdeepwatersnappersonunderwaterbaitedvideousingdeeplearning AT florianbaletaud automaticdetectionidentificationandcountingofdeepwatersnappersonunderwaterbaitedvideousingdeeplearning AT florianbaletaud automaticdetectionidentificationandcountingofdeepwatersnappersonunderwaterbaitedvideousingdeeplearning AT sebastienvillon automaticdetectionidentificationandcountingofdeepwatersnappersonunderwaterbaitedvideousingdeeplearning AT antoinegilbert automaticdetectionidentificationandcountingofdeepwatersnappersonunderwaterbaitedvideousingdeeplearning AT jeanmariecome automaticdetectionidentificationandcountingofdeepwatersnappersonunderwaterbaitedvideousingdeeplearning AT sylviefiat automaticdetectionidentificationandcountingofdeepwatersnappersonunderwaterbaitedvideousingdeeplearning AT corinaiovan automaticdetectionidentificationandcountingofdeepwatersnappersonunderwaterbaitedvideousingdeeplearning AT laurentvigliola automaticdetectionidentificationandcountingofdeepwatersnappersonunderwaterbaitedvideousingdeeplearning |