Skip to Main Content
In the methods of video based fire detection, wavelet was usually used to test whether a pixel belongs to fire region, while fast Fourier transform was used to describe the contour of fire area. We try these two methods on images with forest flame, and develop one new approach combined both wavelet and FFT. In our method, contour of fire is found firstly, then is presented by FFT, and then temporal wavelet is employed to analyze the FFT descriptors from all frames of a video clip. Our approach avoids the setting of contour threshold value in FFT method, and also detects more accurate fire frames than wavelet method. The novel approach is tested with some video clips of forest fire, and the experimental results are satisfying.