Using Resources Competition and Memory Cell Development to Select the Best GMM for Background Subtraction

Abstract

Background subtraction is an essential step in the process of monitoring videos. Several works have proposed models to differentiate the background pixels from the foreground pixels. Mixtures of Gaussian (GMM) are among the most popular models for a such problem. However, the use of a fixed number of Gaussians influence on their results quality. This article proposes an improvement of the GMM based on the use of the artificial immune recognition system (AIRS) to generate and introduce new Gaussians instead of using a fixed number of Gaussians. The proposed approach exploits the robustness of the mutation function in the generation phase of the new ARBs to create new Gaussians. These Gaussians are then filtered into the resource competition phase in order to keep only ones that best represent the background. The system tested on Wallflower and UCSD datasets has proven its effectiveness against other state-of-art methods.