Static and Dynamic Video Summarization

  • Abdul Amir Abdullah Karim Department of Computers, University of Technology, Baghdad, Iraq
  • Rafal Ali Sameer Department of Computers, College of Science, University of Baghdad, Baghdad, Iraq

Abstract

Video represented by a large number of frames synchronized with audio making video saving requires more storage, it's delivery slower, and computation cost expensive. Video summarization provides entire video information in minimum amount of time. This paper proposes static and dynamic video summarization
methods. The proposed static video summarization method includes several steps which are extracting frames from video, keyframes selection, feature extraction and description, and matching feature descriptor with bag of visual words, and finally save frames when features matched. The proposed dynamic video summarization
method includes in general extracting audio from video, calculating audio features using the average of samples in windows and find the highest average which reflects portion of video with loudest sound. The experimental results for the proposed static video summarization show that there is no redundancy between selected representative keyframes and the subjective evaluation results ensure the importance of the selected keyframes. While the experimental results for the proposed static video summarization show that all the segments of goals have been extracted to provide video summary. Static and dynamic video summarization methods done to football or soccer video type.

Published
Jul 19, 2019
How to Cite
KARIM, Abdul Amir Abdullah; SAMEER, Rafal Ali. Static and Dynamic Video Summarization. Iraqi Journal of Science, [S.l.], p. 1627-1638, july 2019. ISSN 2312-1637. Available at: <http://scbaghdad.edu.iq/eijs/index.php/eijs/article/view/930>. Date accessed: 08 dec. 2019.
Section
Computer Science