Multi-sensor Fire Detection by Fusing Visual and Non-visual Flame Features
This paper proposes a feature-based multi-sensor fire detector operating on ordinary video and long wave infrared (LWIR) thermal images. The detector automatically extracts hot objects from the thermal images by dynamic background subtraction and histogram-based segmentation. Analogously, moving objects are extracted from the ordinary video by intensity-based dynamic background subtraction. These hot and moving objects are then further analyzed using a set of flame features which focus on the distinctive geometric, temporal and spatial disorder characteristics of flame regions. By combining the probabilities of these fast retrievable visual and thermal features, we are able to detect the fire at an early stage. Experiments with video and LWIR sequences of fire and non-fire real case scenarios show good results and indicate that multi-sensor fire analysis is very promising.
KeywordsFalse Alarm Moving Object Fire Detection Spatial Disorder Real Case Scenario
- 1.Verstockt, S., Merci, B., Sette, B., Lambert, P., Van de Walle, R.: State of the art in vision-based fire and smoke detection. In: Proc. 14th International Conference on Automatic Fire Detection, pp. 285–292 (2009)Google Scholar
- 3.Toreyin, B.U., Cinbis, R.G., Dedeoglu, Y., Cetin, A.E.: Fire Detection in Infrared Video Using Wavelet Analysis. SPIE Optical Engineering 46, 1–9 (2007) 067204Google Scholar
- 6.Chen, T.-H., Wu, P.-H., Chiou, Y.-C.: An early fire-detection method based on image processing. In: Proc. International Conference on Image Processing, pp. 1707–1710 (2004)Google Scholar
- 7.Xenics Infrared Solutions: Situational Firefighting, http://www.xenics.com/