VSUMM: An Approach for Automatic Video Summarization and Quantitative Evaluation

Abstract

In this paper, we propose an approach for video summarization (VSUMM). The video summaries are generated based on visual features. A factorial experiment is designed to analyze the relative impact of the attributes. We demonstrate the validity of the VSUMM approach by testing it on a collection of videos from Open Video Project. We provide a comparison among results of the proposed summarization technique with Open Video storyboard. A subjective evaluation showed that the summaries are produced with good quality.