Fuzzy foreground detection for infrared videos

We present a foreground detection algorithm based on a fuzzy integral that is particularly suitable for infrared videos. The proposed detection of moving objects is based on fusing intensity and textures using fuzzy integral. The detection results are then used to update the background in a fuzzy way. This method allows to robustly detect moving object in presence of cloudy and rainy conditions. Our theoretical and experimental results show that the proposed method gives similar results than the KaewTraKulPong and Bowden approach based on Mixture Of Gaussians (MOG) with less memory requirement and time consuming. The results using the OTCBVS benchmark/test dataset videos show the robustness of the proposed method.