Multi-Object Tracking Consistently Improves Wildlife Inference

TL;DR

This paper demonstrates that integrating multi-object tracking with wildlife classification models enhances accuracy and consistency in ecological monitoring by leveraging temporal data.

Contribution

The study introduces a method combining MOT models with wildlife classifiers to improve prediction stability and accuracy in real-world camera-trap data.

Findings

MOT integration improves classifier F1-Score by up to 5.1%.

Fused predictions outperform standalone classifiers across datasets.

Temporal tracking reduces misclassification caused by environmental noise.

Abstract

Camera traps have become a common tool for wildlife monitoring efforts in ecological research and biodiversity conservation. Wildlife classification models have benefited from the increase in wildlife visual data. These models reach high levels of accuracy on curated, high-quality datasets. However, their performance remains sensitive to real-world environmental constraints. They often produce inconsistent predictions when performing inference on temporally coherent sequences. The predicted label for a single individual shifts rapidly between frames. This study exploits the temporal nature of camera-trap data to augment inferred predictions from a wildlife classification model. Specifically, we adopt several standard Multi-Object Tracking (MOT) models to link detections across consecutive frames. The curated trajectories are used to fuse the softmax class probabilities. The fused probability score produces a single consensus class label estimate that overrides misclassifications caused by noise. The analysis of the experimental results shows that our proposed strategy improves over a standalone classifier over all datasets and for each metric. Specifically, the best-performing MOT models gain a weighted F1-Score of 5.1%, 3.1% and 2.0% over the classifier across three MOT datasets.