| Issue |
MATEC Web Conf.
Volume 125, 2017
21st International Conference on Circuits, Systems, Communications and Computers (CSCC 2017)
|
|
|---|---|---|
| Article Number | 02055 | |
| Number of page(s) | 5 | |
| Section | Systems | |
| DOI | https://doi.org/10.1051/matecconf/201712502055 | |
| Published online | 04 October 2017 | |
Detecting fire in video stream using statistical analysis
1 Brno University of Technology, Faculty of Information Technology, Czech Republic
2 Tomas Bata University in Zlin, Faculty of applied informatics, Nad Stranemi 4511, 760 05 Zlin, Czech Republic
3 UNIS, a.s., Jundrovská 33, 624 00 Brno, Czech Republic, Czech Republic
* Corresponding author: janku@fai.utb.cz
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.
© The Authors, published by EDP Sciences, 2017
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.