Skip navigation.

UCSD Computer Vision

Fire Detection in Video

Nick True, Serge Belongie


Smoke detectors and heat detectors currently provide the first line of defense against catastrophic structure fires. However, these technologies are ineffective in large open spaces such as tunnels, lobbies, arenas, and in the outdoors. On the other hand, a video based fire detection system has none of these shortcomings. Furthermore, a single camera can cover a much larger area than a single smoke detector. However, the current video based fire detection technologies rely on good quality video to work properly. Thus, the goal of this project is to derive a robust algorithm for detecting fire and smoke in low quality videos in real time.