2005 | OriginalPaper | Buchkapitel
Video Scene Segmentation Using Sequential Change Detection
verfasst von : Zhenyan Li, Hong Lu, Yap-Peng Tan
Erschienen in: Advances in Multimedia Information Processing - PCM 2004
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In content-based video analysis, commonly the first step is to segment a video into independent shots. However, it is rather inefficient to represent video using shot information, as one hour video may contain more than a hundred shots. To address this limitation, most recent work has focused on segmenting a video into scenes, each aggregated by consecutive shots that share similar visual properties or cover a same dramatic event. With the use of sequential change detection and the help of nonparametric density estimation, we propose a novel approach for video scene segmentation in this paper. Experimental results obtained from various test videos suggest that the proposed approach is promising.