Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
535471 | Pattern Recognition Letters | 2008 | 11 Pages |
Abstract
In this paper, we propose a parametric model for the video content analysis. We use the autoregressive (AR) modeling to model the frame feature sequence over time and make the future analysis in the AR parametric space. Based on our parametric framework, applications of detecting shot boundaries in video sequences, extracting key frames and combined spatial–temporal features for shot classification are proposed. Experiments show that our new parametric framework can present the video content better than the traditional color histogram.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Wei Chen, Yu-Jin Zhang,