Advanced search
1 file | 1.47 MB

Multi-sensor fire detection by fusing visual and non-visual flame features

Author
Organization
Abstract
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 lire and non-fire real case scenarios show good results in id indicate that multi-sensor fire analysis is very promising.

Downloads

  • 2010.06 - ICISP2010 - Steven Verstockt et al. - Multi-Sensor Fire Detection by Fusing Visual and Non-Visual Flame Features.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.47 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Verstockt, Steven, Alexander Vanoosthuyse, Sofie Van Hoecke, Peter Lambert, and Rik Van de Walle. 2010. “Multi-sensor Fire Detection by Fusing Visual and Non-visual Flame Features.” In Lecture Notes in Computer Science, ed. A Elmoataz, O Lezoray, F Nouboud, D Mammass, and J Meunier, 6134:333–341. Berlin, Germany: Springer.
APA
Verstockt, S., Vanoosthuyse, A., Van Hoecke, S., Lambert, P., & Van de Walle, R. (2010). Multi-sensor fire detection by fusing visual and non-visual flame features. In A. Elmoataz, O. Lezoray, F. Nouboud, D. Mammass, & J. Meunier (Eds.), LECTURE NOTES IN COMPUTER SCIENCE (Vol. 6134, pp. 333–341). Presented at the 4th International Conference on Image and Signal Processing, Berlin, Germany: Springer.
Vancouver
1.
Verstockt S, Vanoosthuyse A, Van Hoecke S, Lambert P, Van de Walle R. Multi-sensor fire detection by fusing visual and non-visual flame features. In: Elmoataz A, Lezoray O, Nouboud F, Mammass D, Meunier J, editors. LECTURE NOTES IN COMPUTER SCIENCE. Berlin, Germany: Springer; 2010. p. 333–41.
MLA
Verstockt, Steven, Alexander Vanoosthuyse, Sofie Van Hoecke, et al. “Multi-sensor Fire Detection by Fusing Visual and Non-visual Flame Features.” Lecture Notes in Computer Science. Ed. A Elmoataz et al. Vol. 6134. Berlin, Germany: Springer, 2010. 333–341. Print.
@inproceedings{1017884,
  abstract     = {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 lire and non-fire real case scenarios show good results in id indicate that multi-sensor fire analysis is very promising.},
  author       = {Verstockt, Steven and Vanoosthuyse, Alexander and Van Hoecke, Sofie and Lambert, Peter and Van de Walle, Rik},
  booktitle    = {LECTURE NOTES IN COMPUTER SCIENCE},
  editor       = {Elmoataz, A and Lezoray, O and Nouboud, F and Mammass, D and Meunier, J},
  isbn         = {9783642136801},
  issn         = {0302-9743},
  language     = {eng},
  location     = {Trois Rivi{\`e}res, QC, Canada},
  pages        = {333--341},
  publisher    = {Springer},
  title        = {Multi-sensor fire detection by fusing visual and non-visual flame features},
  url          = {http://dx.doi.org/10.1007/978-3-642-13681-8\_39},
  volume       = {6134},
  year         = {2010},
}

Altmetric
View in Altmetric
Web of Science
Times cited: