Growing Neural Gas Video Background Model (GNG-BM)

摘要

This paper presents a novel growing neural gas based background model (GNG-BM) for foreground detection in videos. We proposed a pixel-level background model, where the GNG algorithm is modified for clustering the input pixel data and a new algorithm for initial training is introduced. Also, a new method is introduced for foreground-background classification and online model update. The proposed model is rigorously validated and compared with previous models.