Static and Multiresolution Feature Extraction for Video Summarization

The objective of this paper is to develop a video summarization system to extract significant frames of interest from a given video. To meet the objective, it is proposed to consider both the static features and the wavelet features. Visual attention integrated from the static and wavelet feature set are combined using a prioritized fusion method. Experimental results shows that the static features dominate in certain videos and wavelet features dominate in certain videos. Hence, the proposed fusion approach is suitable for slow motion videos and fast moving videos. Further, the performance of proposed work outperforms the state-of-art methods for video summarization.