Seahorse photo sequences improve automated animal identification
Open-set multi-view seahorse re-identification from underwater photograph sequences
Computer Vision and Pattern Recognition
Summary
It can be hard to recognize individual seahorses from underwater photos because the pictures often vary in quality. The authors created methods that look at multiple photos together to better identify each seahorse, figure out its species group, and determine its sex. They tested their methods on nearly 36,000 real underwater photos of 474 wild seahorses. Their approach showed better accuracy than previous methods that look at single pictures.
What this means in practice
- •For wildlife monitoring teams: Automate tracking of individual seahorses in the wild using photos taken over time for population studies.
- •For marine conservation organizations: Efficiently identify and monitor seahorse populations to support conservation efforts with less human intervention.
Authors
Tristan Fauvel, Sylvie Louisy, Patrick Louisy, Thomas Fauvel
Abstract
Automated animal re-identification from photograph sequences can facilitate minimally invasive Capture-Mark-Recapture studies at scale. Yet, photographs taken during an observation session can vary greatly in quality, not always providing the necessary information for accurate re-identification. In this paper, we present new methods for taxonomic classification, sex determination, and open-set re-identification from image sequences. We train and evaluate our models on a dataset of 35,914 photographs of 474 individual seahorses observed in the wild. We demonstrate that our approach, by combining information from multiple photographs, yields state-of-the-art performance.