Bossou chimpanzee video dataset spans three decades of wildlife recordings
BossouChimpanzee: Long-term Chimpanzee Video Dataset
Computer Vision and Pattern Recognition
Summary
Capturing chimpanzees in their natural environment for many years can help us learn about their behavior and thinking. The authors present a large collection of video recordings from wild chimpanzees at Bossou, Guinea, gathered over 30 years. They also release a smaller set focused on identifying different chimpanzees and recognizing their actions. This collection can help both animal behavior researchers and machine learning developers who want to study real-world animal videos.
What this means in practice
- •For animal behavior researchers: Use the long-term video data to study individual chimpanzees and their actions in natural settings.
- •For machine learning engineers: Train and evaluate models for recognizing individual animals and actions using extensive real-world chimpanzee videos.
Authors
Daniel Schofield, Susana Carvalho, Vladimir Iashin, Andrew Zisserman, Max Bain, Arsha Nagrani, David Ng, Claudia Sousa, Boniface Zogbila, Jules Doré, Dora Biro, Misato Hayashi, Tetsuro Matsuzawa
Abstract
We describe the BossouChimpanzee video dataset, a unique long-term visual record of wild chimpanzees at an outdoor laboratory for field experiments in Bossou, Guinea, spanning three decades (1988-2018) and comprising over 1,200 hours of continuous video recordings collected through collaborative fieldwork and research. In this paper, we outline the history and scientific contributions of the experimental paradigm and video archive, provide key statistics and details on the structure of the main video dataset, and release an initial ~74h snapshot, BossouChimpanzee70h, covering 23 identified individuals focused on chimpanzee individual and action recognition, ahead of the full video resource. This dataset represents a valuable resource for cognitive and behavioural research in ethology and a rich benchmark for training and evaluating machine learning models on audiovisual data from the wild.