An Improved Algorithm for Video Summarization - A Rank Based Approach

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Video summarization is one of the promising approaches for effective comprehension of video content by selecting informative frames of the video. The aim is to produce a summary of the video which is interesting to the user and representing the whole video. In this paper the proposed approach for video summarization takes various features into account such as representativeness, uniformity, static attention, temporal attention and quality which includes colorfulness, brightness, contrast, hue count, edge distribution for selecting keyframes. Experiments have been conducted on videos from open-video.org and results are compared with the standard ground truth. The results are also compared with the algorithm in literature and is found to produce better results.

Original languageEnglish
Pages (from-to)812-819
Number of pages8
JournalProcedia Computer Science
Volume89
DOIs
Publication statusPublished - 2016

Fingerprint

Luminance
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

@article{99157d841af842b4bc326b1a7304ed7d,
title = "An Improved Algorithm for Video Summarization - A Rank Based Approach",
abstract = "Video summarization is one of the promising approaches for effective comprehension of video content by selecting informative frames of the video. The aim is to produce a summary of the video which is interesting to the user and representing the whole video. In this paper the proposed approach for video summarization takes various features into account such as representativeness, uniformity, static attention, temporal attention and quality which includes colorfulness, brightness, contrast, hue count, edge distribution for selecting keyframes. Experiments have been conducted on videos from open-video.org and results are compared with the standard ground truth. The results are also compared with the algorithm in literature and is found to produce better results.",
author = "Manasa Srinivas and Pai, {M. M.Manohara} and Pai, {Radhika M.}",
year = "2016",
doi = "10.1016/j.procs.2016.06.065",
language = "English",
volume = "89",
pages = "812--819",
journal = "Procedia Computer Science",
issn = "1877-0509",
publisher = "Elsevier BV",

}

An Improved Algorithm for Video Summarization - A Rank Based Approach. / Srinivas, Manasa; Pai, M. M.Manohara; Pai, Radhika M.

In: Procedia Computer Science, Vol. 89, 2016, p. 812-819.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An Improved Algorithm for Video Summarization - A Rank Based Approach

AU - Srinivas, Manasa

AU - Pai, M. M.Manohara

AU - Pai, Radhika M.

PY - 2016

Y1 - 2016

N2 - Video summarization is one of the promising approaches for effective comprehension of video content by selecting informative frames of the video. The aim is to produce a summary of the video which is interesting to the user and representing the whole video. In this paper the proposed approach for video summarization takes various features into account such as representativeness, uniformity, static attention, temporal attention and quality which includes colorfulness, brightness, contrast, hue count, edge distribution for selecting keyframes. Experiments have been conducted on videos from open-video.org and results are compared with the standard ground truth. The results are also compared with the algorithm in literature and is found to produce better results.

AB - Video summarization is one of the promising approaches for effective comprehension of video content by selecting informative frames of the video. The aim is to produce a summary of the video which is interesting to the user and representing the whole video. In this paper the proposed approach for video summarization takes various features into account such as representativeness, uniformity, static attention, temporal attention and quality which includes colorfulness, brightness, contrast, hue count, edge distribution for selecting keyframes. Experiments have been conducted on videos from open-video.org and results are compared with the standard ground truth. The results are also compared with the algorithm in literature and is found to produce better results.

UR - http://www.scopus.com/inward/record.url?scp=84986552448&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986552448&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2016.06.065

DO - 10.1016/j.procs.2016.06.065

M3 - Article

VL - 89

SP - 812

EP - 819

JO - Procedia Computer Science

JF - Procedia Computer Science

SN - 1877-0509

ER -