Identifying individual jaguars from camera-trap images using the HotSpotter program-Reference-Cited by-同舟云学术

Identifying individual jaguars from camera-trap images using the HotSpotter program

Published:2023-10-16 Issue:6 Volume:87 Page:602-605
ISSN:0025-1461
Container-title:Mammalia
language:en
Short-container-title:

Author:

Wiig Øystein¹^ORCID,da Silva Teixeira Karollyna²,Sena Leonardo³,Santos de Oliveira Halícia Celeste²,Mendes-Oliveira Ana Cristina²

Affiliation:

1. Natural History Museum, University of Oslo , POB 1172 Blindern, NO-0318 Oslo , Norway

2. Laboratory of Ecology and Zoology of Vertebrates (LABEV), Institute of Biological Science, Federal University of Pará , Belém , Para , Brazil

3. Center for Advanced Biodiversity Studies (Ceabio), Biological Sciences Institute, Federal University of Pará , Belém , Para , Brazil

Abstract

Abstract We identified individual jaguars from a database of camera-trap images collected in the Eastern Amazonian rainforest using the artificial intelligence software HotSpotter. We identified individuals from 131 of 217 images. Twenty-five different individuals were identified based on images of the left side. We compared our results with the results from an undergraduate study that manually identified 18 jaguar individuals from 53 images also used in the present study. One of the 18 individuals was found to be misclassified based on HotSpotter. We found HotSpotter to be useful in identifying individual jaguars in our study area.

Publisher

Walter de Gruyter GmbH

Subject

Animal Science and Zoology,Ecology, Evolution, Behavior and Systematics

Link

https://www.degruyter.com/document/doi/10.1515/mammalia-2023-0071/pdf

Reference13 articles.

1. Bodesheim, P., Blunk, J., Körschens, M., Brust, C.-A., Käding, C., and Denzler, J. (2022). Pre-trained models are not enough: active and lifelong learning is important for long-term visual monitoring of mammals in biodiversity research—individual identification and attribute prediction with image features from deep neural networks and decoupled decision models applied to elephants and great apes. Mamm. Biol. 102: 853–875, https://doi.org/10.1007/s42991-022-00224-8.

2. Bohnett, E., Poya Faryabi, S., Lewison, R., An, L., Bian, X., Rajabi, A.M., Jahed, N., Rooyesh, H., Mills, E., Ramos, S., et al.. (2023). Human expertise combined with artificial intelligence improves performance of snow leopard camera trap studies. Glob. Ecol. Conserv. 41: e02350, https://doi.org/10.1016/j.gecco.2022.e02350.

3. Burton, A.C., Neilson, E., Moreira, D., Ladle, A., Steenweg, R., Fisher, J.T., Bayne, E., and Butin, S. (2015). Wildlife camera trapping: a review and recommendations for linking surveys to ecological processes. J. Appl. Ecol. 52: 675–685, https://doi.org/10.1111/1365-2664.12432.

4. Crall, J.P., Stewart, C.V., Berger‐Wolf, T.Y., Rubenstein, D., and Sundaresan, S.R. (2013). HotSpotter—patterned species instance recognition. In: 2013 IEEE Workshop on Applications of Computer Vision (WACV). Institute of Electrical and Electronics Engineers, 15–17 January 2013, Tampa, Florida, USA, pp. 230–237.

5. Dunbar, S.G., Anger, E.C., Parham, J.R., Kingen, C., Wright, M.K., Hayes, C.T., Safi, S., Holmberg, J., Salinas, L., and Baumbach, D.S. (2021). HotSpotter: using a computer-driven photo-id application to identify sea turtles. J. Exp. Mar. Biol. Ecol. 535: 151590, https://doi.org/10.1016/j.jembe.2020.151490.