Type-2 Fuzzy Mixture of Gaussians Model: Application to Background Modeling

摘要: Background modeling is a key step of background subtraction methods used in the context static camera. The goal to obtain clean and then detect moving objects by comparing it with current frame. Mixture Gaussians Model [1] most popular technique presents some limitations when dynamic changes occur scene like camera jitter, illumination movement background. Furthermore, MGM initialized using training sequence which may be noisy and/or insufficient model correctly All these critical situations generate false classification foreground detection mask due related uncertainty. To take into account this uncertainty, we propose use Type-2 Fuzzy Model. Results show relevance proposed approach presence waving trees water rippling.