|
doi:10.3850/978-981-08-7724-8_08-02
Video Fire Detection Using Non-visible Light
S. Verstockt1,a, R. Dekeerschieter2, A. Vanoosthuyse2, B. Merci3, B. Sette4, P. Lambert1 and R. Van de Walle1
1Department of Electronics and Information Systems, Multimedia Lab, Ghent University – IBBT, Gaston Crommenlaan 8, bus 201, B-9050 Ledeberg-Ghent, Belgium.
asteven.verstockt@elis.ugent.be
2University College West Flanders, Ghent University Association, Graaf Karel de Goedelaan 5, 8500 Kortrijk, Belgium
3Department of Flow, Heat and Combustion Mechanics, Ghent University, Sint-Pietersnieuwstraat 41, B-9000 Gent, Belgium
4Warringtonfiregent (WFRGent NV), Ottergemsesteenweg 711, B-9000 Ghent, Belgium
ABSTRACT
Based on related work in visible and non-visible light, a set of features to detect flames in long wave infrared (LWIR) thermal images is proposed. The set of features is based on the distinctive geometric, temporal and spatial disorder characteristics of bright flame regions, which are easily detectable in LWIR thermal images. By combining the probabilities of these fast retrievable local flame features we are able to detect the fire at an early stage. Experiments with different LWIR sequences of fire and non-fire real case scenarios show good results. Finally, some related LWIR applications such as looking through smoke and detection of hot spots are discussed.
Keywords: Thermal imaging, Long wave infrared, Video fire detection, Flame features, Extrema detection, Histogram analysis.
Back to TOC
FULL TEXT(PDF)
|