Publication Details

Detecting fire in video stream using statistical analysis

KOPLÍK Karel, JANKŮ Peter and DULÍK Tomáš. Detecting fire in video stream using statistical analysis. In: Proceeding of the 21st International Conference on Circuits, Systems, Communications and Computers, CSCC 2017. Crete: EDP Sciences, 2017, pp. 1-5. ISSN 2261-236X. Available from: https://www.matec-conferences.org/articles/matecconf/abs/2017/39/matecconf_cscc2017_02055/matecconf_cscc2017_02055.html
Czech title
Detekce ohně ve streamovaném videu s využitím statistické analýzy.
Type
conference paper
Language
english
Authors
Koplík Karel, Ing. (DCGM FIT BUT)
Janků Peter, Ing., Ph.D. (TBU)
Dulík Tomáš, Ing., Ph.D. (TBU)
URL
Keywords

cameras, computer circuits, computer harware descritpion languages, fire detectors, signal detection, statstical methods, video streaming

Abstract

The real time fire detection in video stream is one of the most interesting problems in computer vision. In fact, in most cases it would be nice to have fire detection algorithm implemented in usual industrial cameras and/or to have possibility to replace standard industrial cameras with one implementing the fire detection algorithm. In this paper, we present new algorithm for detecting fire in video. The algorithm is based on tracking suspicious regions in time with statistical analysis of their trajectory. False alarms are minimized by combining multiple detection criteria: pixel brightness, trajectories of suspicious regions for evaluating characteristic fire flickering and persistence of alarm state in sequence of frames. The resulting implementation is fast and therefore can run on wide range of affordable hardware.

Published
2017
Pages
1-5
Journal
MATEC Web of Conferences, vol. 125, no. 1, ISSN 2261-236X
Proceedings
Proceeding of the 21st International Conference on Circuits, Systems, Communications and Computers, CSCC 2017
Conference
21st International Conference on Circuits, Systems, Communications and Computers (CSCC 2017), Agia Pelagia Beach, Crete Island, GR
Publisher
EDP Sciences
Place
Crete, GR
DOI
10.1051/matecconf/201712502055
EID Scopus
2-s2.0-85032867765
BibTeX 
@INPROCEEDINGS{FITPUB12262,
   author = "Karel Kopl\'{i}k and Peter Jank\r{u} and Tom\'{a}\v{s} Dul\'{i}k",
   title = "Detecting fire in video stream using statistical analysis",
   pages = "1--5",
   booktitle = "Proceeding of the 21st International Conference on Circuits, Systems, Communications and Computers, CSCC 2017",
   journal = "MATEC Web of Conferences",
   volume = 125,
   number = 1,
   year = 2017,
   location = "Crete, GR",
   publisher = "EDP Sciences",
   ISSN = "2261-236X",
   doi = "10.1051/matecconf/201712502055",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12262"
}
Back to top