Triple-stream Deep Metric Learning of Great Ape Behavioural Actions

Otto Brookes, Majid Mirmehdi, Hjalmar Kühl, Tilo Burghardt

2023

Abstract

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-Chimp 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% in top-1 accuracy over previous results achieved on the PanAf-500 dataset 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. We provide all key source code and network weights alongside this publication.

Paper Citation

in Harvard Style

Brookes O., Mirmehdi M., Kühl H. and Burghardt T. (2023). Triple-stream Deep Metric Learning of Great Ape Behavioural Actions. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 294-302. DOI: 10.5220/0011798400003417

in Bibtex Style

@conference{visapp23,
author={Otto Brookes and Majid Mirmehdi and Hjalmar Kühl and Tilo Burghardt},
title={Triple-stream Deep Metric Learning of Great Ape Behavioural Actions},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={294-302},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011798400003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Triple-stream Deep Metric Learning of Great Ape Behavioural Actions
SN - 978-989-758-634-7
AU - Brookes O.
AU - Mirmehdi M.
AU - Kühl H.
AU - Burghardt T.
PY - 2023
SP - 294
EP - 302
DO - 10.5220/0011798400003417
PB - SciTePress