Flame recognition in video

Citation
W. Phillips et al., Flame recognition in video, PATT REC L, 23(1-3), 2002, pp. 319-327
Citations number
6
Language
INGLESE
art.tipo
Article
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
PATTERN RECOGNITION LETTERS
ISSN journal
0167-8655 → ACNP
Volume
23
Issue
1-3
Year of publication
2002
Pages
319 - 327
Database
ISI
SICI code
0167-8655(200201)23:1-3<319:FRIV>2.0.ZU;2-1
Abstract
This paper presents an automatic system for fire detection in video sequenc es. There are several previous methods to detect fire, however, all except two use spectroscopy or particle sensors. The two that use visual informati on suffer from the inability to cope with a moving camera or a moving scene . One of these is not able to work on general data, such as movie sequences . The other is too simplistic and unrestrictive in determining what is cons idered fire; so that it can be used reliably only in aircraft dry bays. We propose a system that uses color and motion information computed from video sequences to locate fire. This is done by first using an approach that is based upon creating a Gaussian-smoothed color histogram to detect the fire- colored pixels, and then using a temporal variation of pixels to determine which of these pixels are actually fire pixels. Next, some spurious fire pi xels are automatically removed using an erode operation, and some missing f ire pixels are found using region growing method. Unlike the two previous v ision-based methods for fire detection, our method is applicable to more ar eas because of its insensitivity to camera motion. Two specific application s not possible with previous algorithms are the recognition of fire in the presence of global camera motion or scene motion and the recognition of fir e in movies for possible use in an automatic rating system. We show that ou r method works in a variety of conditions, and that it can automatically de termine when it has insufficient information. (C) 2002 Published by Elsevie r Science B.V.