To read the full version of this content please select one of the options below:

Remote monitoring of an omnidirectional smoke detection system using texture features image processing techniques

Chun-Chi Peng (Mechanical and Systems Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan)
Kuei-Shu Hsu (Department of Applied Geoinformatics, Chia Nan University of Pharmacy and Science, Tainan City, Taiwan)
Ming-Guo Her (Department of Mechanical Engineering, Tatung University, Taipei, Taiwan)
Yen-Chia Peng (Mechanical and Systems Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan)
Jinn-Feng Jiang (Project Coordination and Liaison Section, Planning and Promotion Department, Metal Industries Research and Development Center, Taipei, Taiwan)
Yi-Jie Chen (Project Coordination and Liaison Section, Planning and Promotion Department, Metal Industries Research and Development Center, Taipei, Taiwan)

Engineering Computations

ISSN: 0264-4401

Article publication date: 28 October 2014

Downloads
178

Abstract

Purpose

The purpose of this paper is to develop an early fire-alarm raising system based on video processing, and combine it with the omnidirectional projecting system. It not only gives alarm immediately in early fire so that people can be able to strive for more time to escape from the spot, but also solves problem of discontinued screen which was presented fire scene.

Design/methodology/approach

The smoke detection system is made by image processing. The flowchart of smoke detection is improved, which the method of background updating can filter out the moving objects that only stay for a short time in the image; and avoids these objects being determined to be the background. Moreover, the authors extract the flickering area to separate the non-smoke and smoke from the candidate of smoke regions. Finally, the image processing is applied in omnidirectional projecting system, then presented the 360-degree fire scene.

Findings

The results show that the smoke detection system can accurately detect the smoke and mark its location, then combining it with the omnidirectional projecting system, although the resolution of omnidirectional projecting system is not enough, it can present a continued screen and location of smoke on the 360-degree cylindrical screen.

Originality/value

This paper develops the smoke detection based on a improved method of image processing, and the control center staff can see the 360-degree fire scene via omnidirectional projecting system, so shorten the time to find the source of smoke.

Keywords

Acknowledgements

Financial support of this research by two institutes. First of all is Tatung University, Taipei, Taiwan, under the grant B100-M01-001. Second is Industrial Technology Research Institute, Hsinchu, Taiwan, under the grant B353C41230.

Citation

Peng, C.-C., Hsu, K.-S., Her, M.-G., Peng, Y.-C., Jiang, J.-F. and Chen, Y.-J. (2014), "Remote monitoring of an omnidirectional smoke detection system using texture features image processing techniques", Engineering Computations, Vol. 31 No. 8, pp. 1611-1626. https://doi.org/10.1108/EC-11-2012-0256

Publisher

:

Emerald Group Publishing Limited

Copyright © 2014, Emerald Group Publishing Limited