Generating optimal video summaries
- 7 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1559-1562
- https://doi.org/10.1109/icme.2000.871066
Abstract
Proposes a novel technique for video summarization based on singular value decomposition (SVD). For the input video sequence, we create a feature frame matrix A, and perform the SVD on it. From this SVD, we are able to derive not only the refined feature space to better cluster visually similar frames, but also a metric to measure the amount of visual content contained in each frame cluster using its degree of visual change. Then, in this refined feature space, we find the most static frame cluster, define it as the content unit, and use the content value computed from this cluster as well as the distance between frames as the thresholds to cluster the rest of the frames. Based on this clustering result, the optimal set of keyframes is generated as the content summary of the original video. Our approach ensures that the summarized video representation contains little redundancy, and gives equal attention to the same amount of visual contents. Besides the optimal keyframe set, our system can also generate summarized motion video for an input video sequence with a user-specified time length. Examples of the summarized motion videos can be viewed at .Keywords
This publication has 5 references indexed in Scilit:
- Time-constrained keyframe selection techniquePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Video summarization by curve simplificationPublished by Association for Computing Machinery (ACM) ,1998
- VideoMAP and VideoSpaceIconPublished by Association for Computing Machinery (ACM) ,1993
- IMPACTPublished by Association for Computing Machinery (ACM) ,1991
- Indexing by latent semantic analysisJournal of the American Society for Information Science, 1990