Object-based segmentation of moving sequences using multiple features

In this paper a novel two-stage architecture for object-based segmentation of moving sequences is proposed using multiple features such as motion, intensity and texture. The first stage locates perceptually meaningful objects using a hierarchy of single-feature segmentation processes. The second stage refines the boundaries of located objects using a suitable combination of features and a set of appropriate rules. Experimental results show that the proposed approach yields intuitively correct as well as accurate segmentations of moving sequences.