Publication detail

Detecting fire in video stream using statistical analysis

KOPLÍK, K. JANKŮ, P. DULÍK, T.

Original Title

Detecting fire in video stream using statistical analysis

Type

conference paper

Language

English

Original 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.

Keywords

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

Authors

KOPLÍK, K.; JANKŮ, P.; DULÍK, T.

Released

4. 10. 2017

Publisher

EDP Sciences

Location

Crete

ISBN

2261-236X

Periodical

MATEC Web of Conferences

Year of study

125

Number

1

State

French Republic

Pages from

1

Pages to

5

Pages count

5

URL

BibTex

@inproceedings{BUT163779,
  author="Karel {Koplík} and Peter {Janků} and Tomáš {Dulík}",
  title="Detecting fire in video stream using statistical analysis",
  booktitle="Proceeding of the 21st International Conference on Circuits, Systems, Communications and Computers, CSCC 2017",
  year="2017",
  journal="MATEC Web of Conferences",
  volume="125",
  number="1",
  pages="1--5",
  publisher="EDP Sciences",
  address="Crete",
  doi="10.1051/matecconf/201712502055",
  issn="2261-236X",
  url="https://www.matec-conferences.org/articles/matecconf/abs/2017/39/matecconf_cscc2017_02055/matecconf_cscc2017_02055.html"
}