CzechLynx: A Dataset for Individual Identification and Pose Estimation of the Eurasian Lynx
This dataset addresses the need for standardized evaluation in wildlife monitoring, particularly for individual animal re-identification, though it is incremental as it focuses on a specific domain.
The authors tackled the problem of individual identification and pose estimation for the Eurasian lynx by introducing CzechLynx, a large-scale dataset with over 30k camera trap images and 100k synthetic images, resulting in a resource for benchmarking models across spatial and temporal domains.
We introduce CzechLynx, the first large-scale, open-access dataset for individual identification, 2D pose estimation, and instance segmentation of the Eurasian lynx (Lynx lynx). CzechLynx includes more than 30k camera trap images annotated with segmentation masks, identity labels, and 20-point skeletons and covers 219 unique individuals across 15 years of systematic monitoring in two geographically distinct regions: Southwest Bohemia and the Western Carpathians. To increase the data variability, we create a complementary synthetic set with more than 100k photorealistic images generated via a Unity-based pipeline and diffusion-driven text-to-texture modeling, covering diverse environments, poses, and coat-pattern variations. To allow testing generalization across spatial and temporal domains, we define three tailored evaluation protocols/splits: (i) geo-aware, (ii) time-aware open-set, and (iii) time-aware closed-set. This dataset is targeted to be instrumental in benchmarking state-of-the-art models and the development of novel methods for not just individual animal re-identification.