Title :
A Novel Computational Approach for Fire Detection
Author :
Duong, Ha Dai ; Tinh, Dao Thanh
Author_Institution :
Fac. of Inf. Technol., Le Qui Don Tech. Univ., Hanoi, Vietnam
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.
Keywords :
Gaussian processes; correlation methods; fires; image colour analysis; image motion analysis; object detection; video databases; Gaussian mixture model method; RGB space; correlation coefficient; fire colored pixel clustering; fire detection; object movement determination; turbulent analysis; video data; Algorithm design and analysis; Computational modeling; Conferences; Correlation; Fires; Image color analysis; Pixel; Correlation Coefficient; Fire Detection; Gaussian Mixture Model;
Conference_Titel :
Knowledge and Systems Engineering (KSE), 2010 Second International Conference on
Conference_Location :
Hanoi
Print_ISBN :
978-1-4244-8334-1
DOI :
10.1109/KSE.2010.12
