Multilevel video representation with application to keyframe extraction

Abstract

Content-based video analysis calls for efficient video representation. In this paper, a novel multi-level representation of video is proposed based on the principle components derived from low-level visual features. It can characterize the video content from the coarse level to the fine level according to its intrinsic structure. This representation form provides a flexible scheme for video content analysis such as summarization, classification, and retrieval. A newly proposed subspace method, kernel based PCA, is explored to achieve this conveniently. The application in keyframe extraction is investigated to demonstrate the benefits of this representation.