Efficient Colour Based Fire Pixel Classification Using Image Processing
In this paper an efficient colour based fire pixel segmentation using image processing is proposed. The proposed method adopts rule based colour model due to its less complexity and effectiveness. YCbCr colour space effectively separates luminance from chrominance compared to other colour spaces like RGB and rgb. The proposed method not only separates fire flame pixels but also separates high temperature fire centre pixels by taking in to account of statistical parameter of fire image in YCbCr colour space like standard deviation. The results obtained are compared with other methods in the literature and shows higher fire detection rate and less false detection rate. The proposed method can be used for real time forest fire detection with moving camera.
R. Edwin Raj, M. Marsaline Beno and M. Carolin Mabel
C. E. Prema et al., "Efficient Colour Based Fire Pixel Classification Using Image Processing", Applied Mechanics and Materials, Vol. 626, pp. 52-57, 2014