Novel Salient Point Extraction Method Based on Local Complexity in Video Sequences
Zhuoyi Chen · Computer Engineering and Applications Journal · 2006
Salient point extraction is an important research issue in content-based video analysis.In this paper,an efficient Salient point extraction approach is presented based on nonparametric clustering,which provides the capability of browsing digital video sequences more efficiently.In particular,initial salient point is extracted based on pixel-level local complexity analysis.Then salient point extraction is accomplished by density-estimation-based nonparametric clustering,which can efficiently analyze complex multimodal feature space.Experiments verify the effectiveness of the proposed approach.