A Dataset and Application for Facial Recognition of Individual Gorillas in Zoo Environments
This work provides a new dataset and a high-performing facial recognition system for individual gorillas, which could aid researchers and conservationists in zoo environments.
This paper introduces a video dataset containing over 5,000 facial bounding box annotations for seven western lowland gorillas at Bristol Zoo Gardens. Using this dataset, a standard deep learning pipeline achieved 92% mAP for individual gorilla recognition from single frames, which improved to 97% mAP with tracking-by-detection and identity voting.
We put forward a video dataset with 5k+ facial bounding box annotations across a troop of 7 western lowland gorillas at Bristol Zoo Gardens. Training on this dataset, we implement and evaluate a standard deep learning pipeline on the task of facially recognising individual gorillas in a zoo environment. We show that a basic YOLOv3-powered application is able to perform identifications at 92% mAP when utilising single frames only. Tracking-by-detection-association and identity voting across short tracklets yields an improved robust performance of 97% mAP. To facilitate easy utilisation for enriching the research capabilities of zoo environments, we publish the code, video dataset, weights, and ground-truth annotations at data.bris.ac.uk.