This project addresses the issue of motion saliency detection in videosequences. Saliency detection has attracted a lot of attention in recentyears. It aims at locating semantic regions in videos for further videounderstanding. This project focuses on the issue of motion saliencydetection for video content analysis.A new method Temporal Spectral Residualto capture the salient objects from video sequences is proposed. Based onthe analysis on temporal slices, it can automatically separate foregroundmotion objects from the background. It also has an effective strategy foradaptive threshold selection and noise removal. Different from conventionalbackground modeling methods with complex mathematical model, this method issimply based on Fourier spectrum analysis, which makes it simple and fast.

Publications

• Xinyi Cui, Qingshan Liu, Dimitris N. Metaxas. "Temporal Spectral Residual: Fast Motion Saliency Detection." Proceedings of the 17th ACM international conference on Multimedia, pp.617-620. 2009.