Video-based Smoke Detection Algorithms: A Chronological Survey

Over the past decade, several vision-based algorithms proposed in literature have resulted into development of a large number of techniques for detection of smoke and fire from video images. Video-based smoke detection approaches are becoming practical alternatives to the conventional fire detection methods due to their numerous advantages such as early fire detection, fast response, non-contact, absence of spatial limits, ability to provide live video that conveys fire progress information, and capability to provide forensic evidence for fire investigations. This paper provides a chronological survey of different video-based smoke detection methods that are available in literatures from 1998 to 2014.Though the paper is not aimed at performing comparative analysis of the surveyed methods, perceived strengths and weakness of the different methods are identified as this will be useful for future research in video-based smoke or fire detection. Keywords: Early fire detection, video-based smoke detection, algorithms, computer vision, image processing