David Johnston
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
David Johnston has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Christin Brangwynne Khan
Northeast Fisheries Science Center, National Marine Fisheries Service, NOAA, Woods Hole, MA 02543, USA
1 shared publication - Claire Charlton
Centre for Marine Science and Technology, Curtin University, Perth, WA 6102, Australia
1 shared publication - Drew Blount
Wild Me, Portland, USA
1 shared publication E. Slooten
Department of Zoology, University of Otago, PO Box 56, Dunedin, New Zealand
1 shared publication- Els Vermeulen
Mammal Research Institute Whale Unit, Department of Zoology and Entomology University of Pretoria Pretoria South Africa
1 shared publication - Fredrik Christiansen
Marine Mammal Research, Department of Ecoscience Aarhus University Roskilde Denmark
1 shared publication
Latest Publications
- 26 August 2022
- Published by Springer Nature in Mammalian Biology
- Vol. 102 (4) , 1525-1536
Morphometrics and body condition of southern right whales on the calving grounds at Port Ross, Auckland Islands
- 26 August 2022
- Published by Springer Nature in Mammalian Biology
- Vol. 102 (4) , 1525-1536
Morphometrics and body condition of southern right whales on the calving grounds at Port Ross, Auckland Islands
- Open Access
- 3 June 2022
- Published by Springer Nature in Mammalian Biology
- Vol. 102 (3) , 1025-1042
Artificial intelligence for right whale photo identification: from data science competition to worldwide collaboration
Photo identification is an important tool in the conservation management of endangered species, and recent developments in artificial intelligence are revolutionizing existing workflows to identify individual animals. In 2015, the National Oceanic and Atmospheric Administration hosted a Kaggle data science competition to automate the identification of endangered North Atlantic right whales (Eubalaena glacialis). The winning algorithms developed by Deepsense.ai were able to identify individuals with 87% accuracy using a series of convolutional neural networks to identify the region of interest, create standardized photographs of uniform size and orientation, and then identify the correct individual. Since that time, we have brought in many more collaborators as we moved from prototype to production. Leveraging the existing infrastructure by Wild Me, the developers of Flukebook, we have created a web-based platform that allows biologists with no machine learning expertise to utilize semi-automated photo identification of right whales. New models were generated on an updated dataset using the winning Deepsense.ai algorithms. Given the morphological similarity between the North Atlantic right whale and closely related southern right whale (Eubalaena australis), we expanded the system to incorporate the largest long-term photo identification catalogs around the world including the United States, Canada, Australia, South Africa, Argentina, Brazil, and New Zealand. The system is now fully operational with multi-feature matching for both North Atlantic right whales and southern right whales from aerial photos of their heads (Deepsense), lateral photos of their heads (Pose Invariant Embeddings), flukes (CurvRank v2), and peduncle scarring (HotSpotter). We hope to encourage researchers to embrace both broad data collaborations and artificial intelligence to increase our understanding of wild populations and aid conservation efforts.
- 3 June 2022
- Published by Springer Nature in Mammalian Biology
- Vol. 102 (3) , 1025-1042
Open AccessArtificial intelligence for right whale photo identification: from data science competition to worldwide collaboration
Photo identification is an important tool in the conservation management of endangered species, and recent developments in artificial intelligence are revolutionizing existing workflows to identify individual animals. In 2015, the National Oceanic and Atmospheric Administration hosted a Kaggle data science competition to automate the identification of endangered North Atlantic right whales (Eubalaena glacialis). The winning algorithms developed by Deepsense.ai were able to identify individuals with 87% accuracy using a series of convolutional neural networks to identify the region of interest, create standardized photographs of uniform size and orientation, and then identify the correct individual. Since that time, we have brought in many more collaborators as we moved from prototype to production. Leveraging the existing infrastructure by Wild Me, the developers of Flukebook, we have created a web-based platform that allows biologists with no machine learning expertise to utilize semi-automated photo identification of right whales. New models were generated on an updated dataset using the winning Deepsense.ai algorithms. Given the morphological similarity between the North Atlantic right whale and closely related southern right whale (Eubalaena australis), we expanded the system to incorporate the largest long-term photo identification catalogs around the world including the United States, Canada, Australia, South Africa, Argentina, Brazil, and New Zealand. The system is now fully operational with multi-feature matching for both North Atlantic right whales and southern right whales from aerial photos of their heads (Deepsense), lateral photos of their heads (Pose Invariant Embeddings), flukes (CurvRank v2), and peduncle scarring (HotSpotter). We hope to encourage researchers to embrace both broad data collaborations and artificial intelligence to increase our understanding of wild populations and aid conservation efforts.
- 24 August 2021
- Published by Oxford University Press (OUP)
- p. 191-247
Identification
"Identification" published on by Oxford University Press.
- 24 August 2021
- Published by Oxford University Press (OUP)
- p. 191-247
Identification
"Identification" published on by Oxford University Press.
- 1 January 2017
- Published by Walter de Gruyter GmbH in Behaviour
- Vol. 154 (9-10) , 1029-1050
A time-based method for defining associations using photo-identification
Photo-identification is an invaluable method for documenting associations. Based on the assumption that individuals photographed close together in time are physically close in space, the metadata associated with digital photography offers an opportunity to base association analyses on time between images. This was tested via analysis of associations within a population of bottlenose dolphins (Tursiops truncatus) in Doubtful Sound, New Zealand. We compared the widely used group-membership method and an alternative time-based method. Overall social structures between methods were similar; high degrees of association among all individuals and little support for sub-groups. Results also indicated an increase in the precision of pairwise indices for the time-based method. This study validated the approach of using time as a basis for analyses of associations. Importantly, this method can be retrospectively applied to any photo-ID data set in which images of uniquely identifiable individuals are time-stamped by the camera.
- 1 January 2017
- Published by Walter de Gruyter GmbH in Behaviour
- Vol. 154 (9-10) , 1029-1050
A time-based method for defining associations using photo-identification
Photo-identification is an invaluable method for documenting associations. Based on the assumption that individuals photographed close together in time are physically close in space, the metadata associated with digital photography offers an opportunity to base association analyses on time between images. This was tested via analysis of associations within a population of bottlenose dolphins (Tursiops truncatus) in Doubtful Sound, New Zealand. We compared the widely used group-membership method and an alternative time-based method. Overall social structures between methods were similar; high degrees of association among all individuals and little support for sub-groups. Results also indicated an increase in the precision of pairwise indices for the time-based method. This study validated the approach of using time as a basis for analyses of associations. Importantly, this method can be retrospectively applied to any photo-ID data set in which images of uniquely identifiable individuals are time-stamped by the camera.