Duong, H.D. and Tinh, D.T. (2010) A novel computational approach for fire detection. In: 2nd International Conference on Knowledge and Systems Engineering, KSE 2010, 7 October 2010 through 9 October 2010, Hanoi.
A novel computational approach for fire detection.pdf
Download (186kB) | Preview
Abstract
This paper proposes a model for detecting fire captured in video data by combining the methods of correlation coefficient, Gaussian Mixture Model - GMM and turbulent analysis. The method of correlation efficient is used to determine movement objects. We use GMM to cluster fire-colored pixel in the RGB space. The objective of turbulent analysis is to detect the flame of fire. A model built on three above methods will be presented and the experimental results are discussed in Section III. © 2010 IEEE.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Divisions: | Faculties > Faculty of Information Technology |
Identification Number: | 10.1109/KSE.2010.12 |
Uncontrolled Keywords: | Colored pixels; Computational approach; Correlation coefficient; Fire detection; Gaussian Mixture Model; RGB space; Video data; Correlation methods; Systems engineering; Fires |
Additional Information: | Conference code: 83923. Language of original document: English. |
URI: | http://eprints.lqdtu.edu.vn/id/eprint/10162 |