A fuzzy approach for background subtraction

Background Subtraction is a widely used approach to detect moving objects from static cameras. Many different methods have been proposed over the recent years and can be classified following different mathematical model: determinist model, statistical model or filter model. The presence of critical situations i.e. noise, illumination changes and structural background changes introduce two main problems: The first one is the uncertainty in the classification of the pixel in foreground and background. The second one is the imprecision in the localization of the moving object. In this context, we propose a fuzzy approach for background subtraction. For this, we use the Choquet integral in the foreground detection and propose fuzzy adaptive background maintenance. Results show the pertinence of our approach.