Early video-based smoke detection in outdoor spaces by spatio-temporal clustering

The early smoke detection in outdoor spaces concerns to people's life and safety tasks. Such technique is necessary in video surveillance systems near building, on bridges, ships, into tunnels, in landscape monitoring systems, etc. We have suggested a novel video-based method of smoke detection by spatio-temporal clustering which involves three developing stages. The first stage connects with motion detection, the second stage is based on a colour and texture analysis of moving regions and the third stage is enhanced by a spatio-temporal clustering of moving regions with a turbulence parameter. A spatio-temporal volume data permits effectively dynamic track of smoke propagation in outdoor spaces using the designed real-time software. Experimental results show that the proposed set of spatial and temporal features always permits to detect the smoke and non-smoke moving objects in outdoor scenes with a complex background; the percent of true detected smoke elements in test video sequences is up to 89%. Copyright © 2013 Inderscience Enterprises Ltd.