A complete framework for temporal video segmentation

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper we propose a complete high level segmentation algorithm of video flows into scenes. In the first stage of our implementation we detected shot boundaries using an enhanced graph partition method based on non-linear scale space filtering at reduce computational time. In the second phase we develop static summaries for each detected shot based on a leap extraction technique that selects a variable number of keyframes depending on the visual content variation. Finally, we propose an iterative, temporally constrained shot clustering technique that detects video scenes with an average precision and recall rates of 85% and 84%.

Original languageEnglish
Title of host publicationProceedings of the 1st IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2011
Pages156-160
Number of pages5
DOIs
Publication statusPublished - 26 Oct 2011
Externally publishedYes
Event1st IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2011 - Berlin, Germany
Duration: 6 Sept 20118 Sept 2011

Publication series

NameDigest of Technical Papers - IEEE International Conference on Consumer Electronics
ISSN (Print)0747-668X

Conference

Conference1st IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2011
Country/TerritoryGermany
CityBerlin
Period6/09/118/09/11

Keywords

  • scene detection
  • shot merging
  • static summary
  • temporal constraints

Fingerprint

Dive into the research topics of 'A complete framework for temporal video segmentation'. Together they form a unique fingerprint.

Cite this