Target-Tracking Based Early Fire Smoke Detection in Video

Author

Wei, Zheng ; Wang, Xingang ; An, Wenchuan ; Che, Jianfeng

Author_Institution

Inst. of Autom., Chinese Acad. of Sci., Beijing, China

fYear

2009

fDate

20-23 Sept. 2009

Firstpage

172

Lastpage

176

Abstract

The paper proposed a target-tracking based fire smoke detection method for early fire-alarming system at large or open space. The method utilizes an improved Gaussian mixture model positioning algorithm, an efficient target tracking algorithm as well as three effective static and dynamic smoke visual features: brightness consistency, motion accumulation and spread. Finally, an algorithm combined temporal and spatial information to assess the fire alarm algorithm is implemented by considering the performance requirements of the fire-alarming system. Experimental results show that the method has low time complexity and is able to rule out the major interference sources.

Keywords

Gaussian processes; computational complexity; smoke detectors; target tracking; video signal processing; Gaussian mixture model; brightness consistency; fire smoke detection; fire-alarming system; low time complexity method; motion accumulation; target-tracking; video technology; Brightness; Cameras; Data mining; Fires; Graphics; Image segmentation; Interference elimination; Layout; Smoke detectors; Space technology;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Graphics, 2009. ICIG '09. Fifth International Conference on

Conference_Location

Xi´an, Shanxi

Print_ISBN

978-1-4244-5237-8

Type

conf

DOI

10.1109/ICIG.2009.173

Filename

5437806