Abstract

Unmanned aerial vehicles (UAVs) are increasingly being used for early wildfire monitoring in remote areas, but UAV endurance is fundamentally constrained by the battery capacity. This work presents an energy-aware edge-vision framework for UAV fire detection that jointly models neural inference and wireless communication and optimizes the operating point of the complete onboard pipeline. Five you only look once (YOLO)v5 scales were fine-tuned on a YOLO-formatted version of the FLAME aerial fire dataset, which was extended with multi-frame fire tracking to enable event-level evaluations. We jointly optimized the model scale, detection confidence threshold, and inference stride using theoretical and empirical estimators that balance energy consumption against the probability of detecting fire events. The results showed that compact YOLOv5 models provide the best trade-off between energy and accuracy for this UAV application: larger variants increase the inference cost without consistent recall gains on the evaluated dataset. In addition, temporal subsampling reduces the total energy approximately in proportion to the stride while preserving near-perfect event-level detection for fires of a moderate duration. The optimized configuration lowers energy consumption by up to 4.4 times with only a 0.03% reduction in recall, supporting longer-endurance UAV missions for wildfire monitoring.

IPC Classification

Keywords