An empirical study of automatic wildlife detection using drone thermal imaging and object detection

TL;DR

This paper presents an empirical study on using drone-mounted thermal imaging and object detection algorithms for wildlife monitoring, providing a new dataset and benchmarking results to advance automated animal detection methods.

Contribution

It introduces a realistic drone-derived wildlife thermal dataset and benchmarks state-of-the-art object detection algorithms, highlighting challenges and future directions in drone-based wildlife monitoring.

Findings

Thermal imaging enables effective wildlife detection from drones.

Benchmarking reveals strengths and limitations of current object detection models.

The dataset supports future research in automated wildlife monitoring.

Abstract

Artificial intelligence has the potential to make valuable contributions to wildlife management through cost-effective methods for the collection and interpretation of wildlife data. Recent advances in remotely piloted aircraft systems (RPAS or ``drones'') and thermal imaging technology have created new approaches to collect wildlife data. These emerging technologies could provide promising alternatives to standard labourious field techniques as well as cover much larger areas. In this study, we conduct a comprehensive review and empirical study of drone-based wildlife detection. Specifically, we collect a realistic dataset of drone-derived wildlife thermal detections. Wildlife detections, including arboreal (for instance, koalas, phascolarctos cinereus) and ground dwelling species in our collected data are annotated via bounding boxes by experts. We then benchmark state-of-the-art object detection algorithms on our collected dataset. We use these experimental results to identify issues and discuss future directions in automatic animal monitoring using drones.