Advancing Early Wildfire Detection: Integration of Vision Language Models with UAV Remote Sensing for Enhanced Situational Awareness

Early wildfire detection is critical for effective suppression efforts, necessitating rapid alerts and precise localization. While computer vision techniques offer reliable fire detection, they often lack contextual understanding. This paper addresses this limitation by utilising Vision Language Models (VLMs) to generate structured scene descriptions from Unmanned Aerial Vehicle (UAV) imagery. UAV-based remote sensing provides diverse perspectives of potential wildfires, and state-of-the-art VLMs enable rapid and detailed scene characterization. We evaluate both cloud-based (OpenAI, Google DeepMind) and open-weight, locally deployed VLMs on a novel evaluation dataset specifically curated for forest fire scene understanding. Our results demonstrate that relatively compact, fine-tuned VLMs can provide rich contextual information, including forest type, fire state, and fire type. Specifically, our best-performing model, ForestFireVLM-7B (fine-tuned from Qwen2-5-VL-7B), achieves a 76.6% average accuracy across all categories, surpassing the strongest closed-weight baseline (Gemini 2.0 Pro at 65.5%). Furthermore, zero-shot evaluation on the publicly available FIgLib dataset demonstrates state-of-the-art smoke detection accuracy using VLMs. Our findings highlight the potential of fine-tuned, open-weight VLMs for enhanced wildfire situational awareness via detailed scene interpretation.