OpenStripe enables accurate wild tiger identification and spatial pattern analysis
OpenStripe supports open-set identification and spatial stripe profiling in wild Amur tigers
Computer Vision and Pattern Recognition
Summary
Tracking individual wild tigers using camera images is hard because the animals move and backgrounds vary. The authors developed OpenStripe, a system that looks at tiger stripes in photos and breaks them down into specific local patterns to tell tigers apart. They tested it on images from 28 wild Amur tigers and got much better identification results than other methods. OpenStripe also showed that tigers closer together geographically have more similar stripe patterns.
What this means in practice
- •For wildlife conservation teams: Automatically group and identify individual tigers from field images without prior knowledge of how many animals exist.
- •For ecological researchers: Analyze spatial variation in tiger stripe patterns to study animal movement and population structure in the wild.
Authors
Yichun Peng, Yansong Li, Jin Hou, Qi Song, Xi Guo, Ning Zhang, Degang Wei, Huang Yang, Yu Guan, Jianping Ge, Lei Bao, Tianming Wang
Abstract
Non-invasive camera-trap monitoring of endangered wildlife requires open-set individual identification---grouping field images into identities without predefined classes or a known population size---yet pose deformation and cluttered backgrounds complicate image comparison. Here, we present OpenStripe, a multi-agent framework that reconstructs canonical two-dimensional (2D) tiger torso patterns and encodes four interpretable local stripe structures: breakpoints, bifurcations, irregular structures, and round structures. We evaluated OpenStripe on 100 camera-trap records from 28 wild Amur tigers (Panthera tigris altaica), representing nearly one-third of the documented population in the Northeast China Tiger and Leopard National Park. Combining all four complementary structures enabled automatic identity grouping with 0.90 matched accuracy and a 0.85 adjusted Rand index (ARI), outperforming 49 baseline configurations under the same backend (up to 0.43 accuracy and 0.14 ARI). In addition, results from OpenStripe indicate that stripe similarity in Amur tigers declines with geographic distance and suggest that traits such as fractal dimension and inter-stripe spacing are associated with geographic proximity. OpenStripe thus provides an interpretable representation that connects automated individual grouping with spatial phenotypic profiling in wild populations.