The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition

TL;DR

This paper introduces the PanAf-FGBG dataset, which pairs wildlife behaviour videos with background videos to evaluate how backgrounds influence behaviour recognition, especially in out-of-distribution scenarios, and proposes a normalization technique to improve model robustness.

Contribution

The paper presents the novel PanAf-FGBG dataset with paired background and foreground videos, enabling direct assessment of background effects on wildlife behaviour recognition models.

Findings

Background information significantly impacts out-of-distribution recognition.

Latent-space normalization improves model performance by over 5% mAP.

Background duration within videos affects recognition accuracy.

Abstract

Computer vision analysis of camera trap video footage is essential for wildlife conservation, as captured behaviours offer some of the earliest indicators of changes in population health. Recently, several high-impact animal behaviour datasets and methods have been introduced to encourage their use; however, the role of behaviour-correlated background information and its significant effect on out-of-distribution generalisation remain unexplored. In response, we present the PanAf-FGBG dataset, featuring 20 hours of wild chimpanzee behaviours, recorded at over 350 individual camera locations. Uniquely, it pairs every video with a chimpanzee (referred to as a foreground video) with a corresponding background video (with no chimpanzee) from the same camera location. We present two views of the dataset: one with overlapping camera locations and one with disjoint locations. This setup enables, for the first time, direct evaluation of in-distribution and out-of-distribution conditions, and for the impact of backgrounds on behaviour recognition models to be quantified. All clips come with rich behavioural annotations and metadata including unique camera IDs and detailed textual scene descriptions. Additionally, we establish several baselines and present a highly effective latent-space normalisation technique that boosts out-of-distribution performance by +5.42% mAP for convolutional and +3.75% mAP for transformer-based models. Finally, we provide an in-depth analysis on the role of backgrounds in out-of-distribution behaviour recognition, including the so far unexplored impact of background durations (i.e., the count of background frames within foreground videos).