cs.CVNov 7, 2026

Vision Language Models for Primary Structure Threat Identification in Wildland Urban Interface Fires

Authors: Zhangding Liu, Neda Mohammadi, John E. Taylor

Organizations: School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA · School of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta, GA, USA · The University of Sydney, Sydney, NSW, Australia

Abstract

Wildland urban interface (WUI) fires increasingly threaten communities and infrastructure, motivating the need for rapid visual assessment. Recent research has focused primarily on detecting fire and assessing post-event damage. However, structure-level fire threat identification during active WUI fire events remains underexplored. This study evaluates Qwen3-VL-8B-Instruct for this active-fire decision using two separately scored tracks: 1,824 synthetic images from 491 designed WUI scenarios and 45 frames from a controlled-burn experiment conducted in collaboration with Columbus Fire & EMS Department. Under zero-shot prompting, the model returned valid target fields for 1,808 synthetic images and 39 controlled-burn frames. Accuracy among valid outputs was 94.0% for the synthetic track and 69.2% for the controlled-burn track, compared with a 16.0% random-selection baseline for the latter. On the synthetic track, the model generally identified the intended target across varied designed WUI scenarios when the relevant fire-spread cues were visually distinct. Controlled-burn performance was well above random selection, but errors showed difficulty interpreting spatial relations in complex scenes. The dual-track protocol provides scalable stress testing in designed scenarios and a controlled-burn reference for assessing model behavior under physical fire conditions. Future work can use the synthetic data for VLM post-training and then evaluate the adapted models on larger and more diverse real WUI fire datasets.

Explore similar work

CardsList
  1. FlameVQA: A Physically-Grounded UAV Wildfire VQA Benchmark with Radiometric Thermal Supervision

    Jun 25, 2026Mobin Habibpour, John Spodnik, Niloufar Alipour Talemi +1VLM EvaluationVisual Question Answering

  2. WildFireVQA: A Large-Scale Radiometric Thermal VQA Benchmark for Aerial Wildfire Monitoring

    Apr 22, 2026Mobin Habibpour, Niloufar Alipour Talemi, John Spodnik +2Thermal ImagingVisual Question Answering

  3. A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and Reporting

    Oct 1, 2026Duowen Chen, Yuchen Sun, Zhiqi Li +4Vision-Language ModelsMemory-Augmented VLMs