Advanced search
1 file | 2.28 MB

Silhouette-based multi-sensor smoke detection: coverage analysis of moving object silhouettes in thermal and visual registered images

Steven Verstockt (UGent) , Chris Poppe (UGent) , Sofie Van Hoecke (UGent) , Charles Hollemeersch (UGent) , Bart Merci (UGent) , Bart Sette, Peter Lambert (UGent) and Rik Van de Walle (UGent)
(2012) MACHINE VISION AND APPLICATIONS. 23(6). p.1243-1262
Author
Organization
Abstract
Fire is one of the leading hazards affecting everyday life around the world. The sooner the fire is detected, the better the chances are for survival. Today's fire alarm systems, such as video-based smoke detectors, however, still pose many problems. In order to accomplish more accurate video-based smoke detection and to reduce false alarms, this paper proposes a multi-sensor smoke detector which takes advantage of the different kinds of information represented by visual and thermal imaging sensors. The detector analyzes the silhouette coverage of moving objects in visual and long-wave infrared registered ( aligned) images. The registration is performed using a contour mapping algorithm which detects the rotation, scale and translation between moving objects in the multi-spectral images. The geometric parameters found at this stage are then further used to coarsely map the silhouette images and coverage between them is calculated. Since smoke is invisible in long-wave infrared its silhouette will, contrarily to ordinary moving objects, only be detected in visual images. As such, the coverage of thermal and visual silhouettes will start to decrease in case of smoke. Due to the dynamic character of the smoke, the visual silhouette will also show a high degree of disorder. By focusing on both silhouette behaviors, the system is able to accurately detect the smoke. Experiments on smoke and non-smoke multi-sensor sequences indicate that the automated smoke detection algorithm is able to coarsely map the multi-sensor images. Furthermore, using the low-cost silhouette analysis, a fast warning, with a low number of false alarms, can be given.
Keywords
Image registration, Coverage analysis, Multi-sensor, Multi-modal, Smoke detection, FEATURES, RECOGNITION, VIDEO, MUTUAL INFORMATION, FIRE DETECTION, SYSTEM, REGISTRATION

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.28 MB

Citation

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

Chicago
Verstockt, Steven, Chris Poppe, Sofie Van Hoecke, Charles Hollemeersch, Bart Merci, Bart Sette, Peter Lambert, and Rik Van de Walle. 2012. “Silhouette-based Multi-sensor Smoke Detection: Coverage Analysis of Moving Object Silhouettes in Thermal and Visual Registered Images.” Machine Vision and Applications 23 (6): 1243–1262.
APA
Verstockt, S., Poppe, C., Van Hoecke, S., Hollemeersch, C., Merci, B., Sette, B., Lambert, P., et al. (2012). Silhouette-based multi-sensor smoke detection: coverage analysis of moving object silhouettes in thermal and visual registered images. MACHINE VISION AND APPLICATIONS, 23(6), 1243–1262.
Vancouver
1.
Verstockt S, Poppe C, Van Hoecke S, Hollemeersch C, Merci B, Sette B, et al. Silhouette-based multi-sensor smoke detection: coverage analysis of moving object silhouettes in thermal and visual registered images. MACHINE VISION AND APPLICATIONS. 2012;23(6):1243–62.
MLA
Verstockt, Steven, Chris Poppe, Sofie Van Hoecke, et al. “Silhouette-based Multi-sensor Smoke Detection: Coverage Analysis of Moving Object Silhouettes in Thermal and Visual Registered Images.” MACHINE VISION AND APPLICATIONS 23.6 (2012): 1243–1262. Print.
@article{1970409,
  abstract     = {Fire is one of the leading hazards affecting everyday life around the world. The sooner the fire is detected, the better the chances are for survival. Today's fire alarm systems, such as video-based smoke detectors, however, still pose many problems. In order to accomplish more accurate video-based smoke detection and to reduce false alarms, this paper proposes a multi-sensor smoke detector which takes advantage of the different kinds of information represented by visual and thermal imaging sensors. The detector analyzes the silhouette coverage of moving objects in visual and long-wave infrared registered ( aligned) images. The registration is performed using a contour mapping algorithm which detects the rotation, scale and translation between moving objects in the multi-spectral images. The geometric parameters found at this stage are then further used to coarsely map the silhouette images and coverage between them is calculated. Since smoke is invisible in long-wave infrared its silhouette will, contrarily to ordinary moving objects, only be detected in visual images. As such, the coverage of thermal and visual silhouettes will start to decrease in case of smoke. Due to the dynamic character of the smoke, the visual silhouette will also show a high degree of disorder. By focusing on both silhouette behaviors, the system is able to accurately detect the smoke. Experiments on smoke and non-smoke multi-sensor sequences indicate that the automated smoke detection algorithm is able to coarsely map the multi-sensor images. Furthermore, using the low-cost silhouette analysis, a fast warning, with a low number of false alarms, can be given.},
  author       = {Verstockt, Steven and Poppe, Chris and Van Hoecke, Sofie and Hollemeersch, Charles and Merci, Bart and Sette, Bart and Lambert, Peter and Van de Walle, Rik},
  issn         = {0932-8092},
  journal      = {MACHINE VISION AND APPLICATIONS},
  keyword      = {Image registration,Coverage analysis,Multi-sensor,Multi-modal,Smoke detection,FEATURES,RECOGNITION,VIDEO,MUTUAL INFORMATION,FIRE DETECTION,SYSTEM,REGISTRATION},
  language     = {eng},
  number       = {6},
  pages        = {1243--1262},
  title        = {Silhouette-based multi-sensor smoke detection: coverage analysis of moving object silhouettes in thermal and visual registered images},
  url          = {http://dx.doi.org/10.1007/s00138-011-0359-3},
  volume       = {23},
  year         = {2012},
}

Altmetric
View in Altmetric
Web of Science
Times cited: