Reliable camera motion estimation from compressed MPEG videos using machine learning approach

Zheng Wang, Jinchang Ren, Yubin Wang, Meijun Sun, Jianmin Jiang

Research output: Contribution to journalArticle

70 Downloads (Pure)

Abstract

As an important feature in characterizing video content, camera motion has been widely applied in various multimedia and computer vision applications. A novel method for fast and reliable estimation of camera motion from MPEG videos is proposed, using support vector machine for estimation in a regression model trained on a synthesized sequence. Experiments conducted on real sequences show that the proposed method yields much improved results in estimating camera motions while the difficulty in selecting valid macroblocks and motion vectors is skipped. 

Original languageEnglish
Article number057401
JournalOptical Engineering
Volume52
Issue number5
DOIs
Publication statusPublished - 25 Jul 2013

Keywords

  • motion estimation
  • MPEG videos
  • support vector machines
  • video signal processing

Fingerprint Dive into the research topics of 'Reliable camera motion estimation from compressed MPEG videos using machine learning approach'. Together they form a unique fingerprint.

  • Cite this