Share Email Print

Optical Engineering

Efficient video-equipped fire detection approach for automatic fire alarm systems
Author(s): Myeongsu Kang; Truong Xuan Tung; Jong-Myon Kim
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

This paper proposes an efficient four-stage approach that automatically detects fire using video capabilities. In the first stage, an approximate median method is used to detect video frame regions involving motion. In the second stage, a fuzzy c-means-based clustering algorithm is employed to extract candidate regions of fire from all of the movement-containing regions. In the third stage, a gray level co-occurrence matrix is used to extract texture parameters by tracking red-colored objects in the candidate regions. These texture features are, subsequently, used as inputs of a back-propagation neural network to distinguish between fire and nonfire. Experimental results indicate that the proposed four-stage approach outperforms other fire detection algorithms in terms of consistently increasing the accuracy of fire detection in both indoor and outdoor test videos.

Paper Details

Date Published: 4 January 2013
PDF: 10 pages
Opt. Eng. 52(1) 017002 doi: 10.1117/1.OE.52.1.017002
Published in: Optical Engineering Volume 52, Issue 1
Show Author Affiliations
Myeongsu Kang, Univ. of Ulsan (Korea, Republic of)
Truong Xuan Tung, Univ. of Ulsan (Korea, Republic of)
Jong-Myon Kim, Univ. of Ulsan (Korea, Republic of)

© SPIE. Terms of Use
Back to Top