New Fuzzy Object Segmentation Algorithm for Video Sequences

A new fuzzy moving object segmentation algorithm for video sequences is presented in this paper. Our proposed efficient object segmentation algorithm consists of three steps, namely the spatial segmentation step, the temporal tracking step, and the step for identifying the moving object from the frame in a fuzzy way. Especially, our proposed algorithm can robustly distinguish the foreground part, which is a near stationary region but surrounded by some regions with moving variation, from the background. Using several different real video sequences, experimental results demonstrate that the object segmentation accuracy of our proposed fuzzy-based algorithm is encouraging when compared to the recently published object segmentation algorithms by Chien et al. and Kim et al.