Comparison of Two Individual Identification Algorithms for Snow Leopards after Automated Detection
Preprint
Abstract
1. Photo-identification of individual snow leopards ( Panthera uncia ) is the primary technique for density estimation for the species. A high volume of images from multiple projects, combined with pre-existing historical catalogs, has made identifying snow leopard individuals within the images cost- and time-intensive. 2. To speed the classification among a high volume of photographs, we trained and evaluated image classification methods for PIE v2 (a triplet loss network), and we compared PIE’s accuracy to the HotSpotter algorithm (a SIFT based algorithm). Analyzed data were collected from a curated catalog of free-ranging snow leopards photographed across years (2012-2019) in Afghanistan and from samples in captivity provided by zoos from Finland, Sweden, Germany, and the United States. 3. Results show that PIE outperforms HotSpotter. We also found weaknesses in the initial PIE model, like a minor amount of background matching, which was addressed, although likely not fully resolved, by applying background subtraction (BGS) and left-right mirroring (LR) methods. The PIE BGS LR model combined with Hotspotter showed a Rank-1: 85%, Rank-5: 95%, Rank-20: 99%. 4. Overall, our results recommend implementing PIE v2 simultaneously with HotSpotter on Whiskerbook.org .Keywords
All Related Versions
- Published version: Ecological Informatics, 77.
This publication has 15 references indexed in Scilit:
- Identifying individual snow leopards from camera trap images2019
- Machine learning for image based species identificationMethods in Ecology and Evolution, 2018
- An Animal Detection Pipeline for Identification2018
- A computer vision for animal ecologyJournal of Animal Ecology, 2017
- Animal Recognition and Identification with Deep Convolutional Neural Networks for Automated Wildlife Monitoring2017
- YOLO9000: Better, Faster, Stronger2017
- HotSpotter — Patterned species instance recognition2013
- A critique of density estimation from camera‐trap dataThe Journal of Wildlife Management, 2011
- A HIERARCHICAL MODEL FOR SPATIAL CAPTURE–RECAPTURE DATAEcology, 2008
- Estimating Snow Leopard Population Abundance Using Photography and Capture–Recapture TechniquesWildlife Society Bulletin, 2006