AI RESEARCH
Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detection
arXiv CS.CV
•
ArXi:2508.16739v2 Announce Type: replace Unmanned Aerial Vehicles (UAVs) have become increasingly important in disaster emergency response by facilitating aerial video analysis. Due to the limited computational resources available on UAVs, large models cannot be run efficiently for on-board analysis. To overcome this challenge, we propose a lightweight and efficient two-stage framework for wildfire monitoring and fire source detection on UAV platforms. Specifically, in