#23: Automatic spatio-temporal video sequence segmentation


J. Vass, K. Palaniappan, and X. Zhuang

IEEE Int. Conf. Image Processing, pgs. 958--962, 1998

detection, motion, segmentation, image analysis, color, shape, data mining, cbir

PlainText, Bibtex, PDF, URL, DOI, Google Scholar

Abstract

In the paper, an automatic spatio-temporal video sequence segmentation algorithm is proposed. To ad- dress this very daficult computer vision problem, sev- eral novel algorithms have been developed which use both spatial and temporal information. First, a novel temporal segmentation algorithm is developed based on our previous work in motion estimation. Second, an iterative split-and-merge spatial segmentation scheme is proposed with an initial segmentation being pro- vided by recursive conditioned dilation operation merg- ing pixels into homogeneous regions, followed by an it- erative refinement algorithm to obtain the final spatial segmentation. Third, temporal and spatial segmenta- tion are linked to form spatio-temporal segmentation with the shape of each object being simplified by a mor- phological close-opening operation to obtain the final segmentation. Performance evaluation shows that the developed algorithm can successfully segment moving object without any human intervention.