Triple-stream Deep Metric Learning of Great Ape Behavioural Actions

01/06/2023
by   Otto Brookes, et al.
15

We propose the first metric learning system for the recognition of great ape behavioural actions. Our proposed triple stream embedding architecture works on camera trap videos taken directly in the wild and demonstrates that the utilisation of an explicit DensePose-C chimpanzee body part segmentation stream effectively complements traditional RGB appearance and optical flow streams. We evaluate system variants with different feature fusion techniques and long-tail recognition approaches. Results and ablations show performance improvements of  12 containing 180,000 manually annotated frames across nine behavioural actions. Furthermore, we provide a qualitative analysis of our findings and augment the metric learning system with long-tail recognition techniques showing that average per class accuracy – critical in the domain – can be improved by  23 compared to the literature on that dataset. Finally, since our embedding spaces are constructed as metric, we provide first data-driven visualisations of the great ape behavioural action spaces revealing emerging geometry and topology. We hope that the work sparks further interest in this vital application area of computer vision for the benefit of endangered great apes.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset