Automatic text recognition for video indexing
MULTIMEDIA '96 Proceedings of the fourth ACM international conference on Multimedia
Visual information retrieval: minerva video benchmark
SPPRA'06 Proceedings of the 24th IASTED international conference on Signal processing, pattern recognition, and applications
Creating map-based storyboards for browsing tour videos
Proceedings of the 21st annual ACM symposium on User interface software and technology
VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method
Pattern Recognition Letters
Hi-index | 0.00 |
Large video on demand databases consisting of thousands of digital movies are not easy to handle: the user must have an attractive means to retrieve his movie of choice. For analog video, movie trailers are produced to allow a quick preview and perhaps stimulate possible buyers. This paper presents techniques to automatically produce such movie abstracts of digtial videos. We define a video abstract to be a sequence of still or moving images presenting the content of a video in such a way that the resprective target groupis rapidly provided with concise information about the content while the essential message of the original is preserved. We therefore mainly distinguish video abstracts consisting of a collection of salient still images and video abstracts consisting of a collection of scenes (sequences of images) which are therefore a video themselves. Still-images abstracting systems have been reported often in the literature. We propose a moving-images abstracting system, called VAbstract, and explain its concept, algorithmic realization and advantages. The paper also describes a series of abstracting experiments in which we compared our automatically produced abstracts to manually produced trailers of TV series.