SURF based video summarization and its optimization
Dipti Jadhav, Udhav Bhosle · 2017
Video Summarization (VS) is a technique of extracting keyframes from the video based on the video content. It provides the user with a concise representation of the video content from which the video is semantically understood. This paper proposes a video summarization technique based on Speeded Up Robust Features (SURF). Authors further propose a Graph Theory based approach to optimize the number of keyframes based on the objective function that the graph generated by the optimized video summary is a simple graph with a simple walk. The proposed algorithm is tested on two different videos from OpenVideo database. The video summarization results and its optimization obtained shows non-redundancy and improvement in the semantic understanding of the video summary.