Advanced search
1 file | 10.47 MB

Fire detection in color images using Markov random fields

David Van Hamme (UGent) , Peter Veelaert (UGent) , Wilfried Philips (UGent) and Kristof Teelen (UGent)
Author
Organization
Abstract
Automatic video-based fire detection can greatly reduce fire alert delay in large industrial and commercial sites, at a minimal cost, by using the existing CCTV camera network. Most traditional computer vision methods for fire detection model the temporal dynamics of the flames, in conjunction with simple color filtering. An important drawback of these methods is that their performance degrades at lower framerates, and they cannot be applied to still images, limiting their applicability. Also, real-time operation often requires significant computational resources, which may be unfeasible for large camera networks. This paper presents a novel method for fire detection in static images, based on a Markov Random Field but with a novel potential function. The method detects 99.6% of fires in a large collection of test images, while generating less false positives then a state-of-the-art reference method. Additionally, parameters are easily trained on a 12-image training set with minimal user input.
Keywords
fire detection markov random field texture surveillance

Downloads

  • paper113.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 10.47 MB

Citation

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

Chicago
Van Hamme, David, Peter Veelaert, Wilfried Philips, and Kristof Teelen. 2010. “Fire Detection in Color Images Using Markov Random Fields.” In Lecture Notes in Computer Science, ed. Jacques Blanc-Talon, Don Bone, Wilfried Philips, Dan Popescu, and Paul Scheunders, 6475:88–97. Berlin, Germany: Springer Verlag Berlin.
APA
Van Hamme, D., Veelaert, P., Philips, W., & Teelen, K. (2010). Fire detection in color images using Markov random fields. In Jacques Blanc-Talon, D. Bone, W. Philips, D. Popescu, & P. Scheunders (Eds.), LECTURE NOTES IN COMPUTER SCIENCE (Vol. 6475, pp. 88–97). Presented at the 12th International conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2010), Berlin, Germany: Springer Verlag Berlin.
Vancouver
1.
Van Hamme D, Veelaert P, Philips W, Teelen K. Fire detection in color images using Markov random fields. In: Blanc-Talon J, Bone D, Philips W, Popescu D, Scheunders P, editors. LECTURE NOTES IN COMPUTER SCIENCE. Berlin, Germany: Springer Verlag Berlin; 2010. p. 88–97.
MLA
Van Hamme, David, Peter Veelaert, Wilfried Philips, et al. “Fire Detection in Color Images Using Markov Random Fields.” Lecture Notes in Computer Science. Ed. Jacques Blanc-Talon et al. Vol. 6475. Berlin, Germany: Springer Verlag Berlin, 2010. 88–97. Print.
@inproceedings{1112633,
  abstract     = {Automatic video-based fire detection can greatly reduce fire alert delay in large industrial and commercial sites, at a minimal cost, by using the existing CCTV camera network. Most traditional computer vision methods for fire detection model the temporal dynamics of the flames, in conjunction with simple color filtering. An important drawback of these methods is that their performance degrades at lower framerates, and they cannot be applied to still images, limiting their applicability. Also, real-time operation often requires significant computational resources, which may be unfeasible for large camera networks. This paper presents a novel method for fire detection in static images, based on a Markov Random Field but with a novel potential function. The method detects 99.6\% of fires in a large collection of test images, while generating less false positives then a state-of-the-art reference method. Additionally, parameters are easily trained on a 12-image training set with minimal user input.},
  author       = {Van Hamme, David and Veelaert, Peter and Philips, Wilfried and Teelen, Kristof},
  booktitle    = {LECTURE NOTES IN COMPUTER SCIENCE},
  editor       = {Blanc-Talon, Jacques and Bone, Don and Philips, Wilfried and Popescu, Dan and Scheunders, Paul},
  isbn         = {9783642176906},
  issn         = {0302-9743},
  keyword      = {fire detection markov random field texture surveillance},
  language     = {eng},
  location     = {Sydney, Australia},
  pages        = {88--97},
  publisher    = {Springer Verlag Berlin},
  title        = {Fire detection in color images using Markov random fields},
  url          = {http://dx.doi.org/10.1007/978-3-642-17691-3\_9},
  volume       = {6475},
  year         = {2010},
}

Altmetric
View in Altmetric
Web of Science
Times cited: