We propose a new approach to temporal video segmentation in which shot boundaries are detected by object-level matching of video frames. I-frames are initially segmented using features extracted from the HSV color space. Two consecutive I-frames are compared in terms of the color, size and position of their objects. A shot boundary is detected if there is a strong mismatch between frame objects. We have developed a web-based video retrieval system for demonstrating our work and for performing user queries.
Object Level Frame Comparison for Video Shot Detection
01.01.2005
309949 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Comparison of video shot boundary detection techniques
British Library Online Contents | 1996
|Automatic video data structuring through shot partitioning and key-frame computing
British Library Online Contents | 1997
|British Library Online Contents | 2004
|