The segmentation of video streams into their component shots is a pre-requisite for most applications involving content-based access to video libraries. In this paper, we address the segmentation problem from a probabilistic standpoint which exposes the major limitations of current solutions, and we suggest better alternatives derived from Bayesian principles. These principles lead to a framework which, by allowing the incorporation of prior knowledge about the video structure in its statistical model, leads to higher segmentation accuracy and provides a basis for content characterization which can later be used to categorize the video, retrieve it according to its content, or compare it to other instances stored in a database
A Bayesian video modeling framework for shot segmentation and content characterization
01.01.1997
905471 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
A Bayesian Video Modeling Framework for Shot Segmentation and Content Characterization
British Library Conference Proceedings | 1997
|Fuzzy framework for unsupervised video content characterization and shot classification
British Library Online Contents | 2001
|Statistical Framework for Shot Segmentation and Classification in Sports Video
Springer Verlag | 2007
|British Library Online Contents | 2004
|Using Lateral Ranking for Motion-Based Video Shot Retrieval and Dynamic Content Characterization
BASE | 2005
|