An Efficient Foreground Object Detection Method Using a Color Cluster-Based Background Modeling Algorithm

This paper presents a block-based color cluster background modeling and a foreground detection algorithm that possesses efficient processing and low memory requirement in a complex scene. In training phase, the color cluster and pixel distribution line (PDL) are efficiently used to reduce the background information. In detection phase, we can extract the foreground objects precisely and fast in complex scene by comparing the color clusters and PDLs. In order to overcome the block effect, refinement procedure is proposed to identify pixel-based foreground objects. Experimental results indicate that the proposed approach has consumes 32.5% less memory and reduce total error pixels by at least 16.9% compared to other existing methods.