Share Email Print

Optical Engineering

Reliable camera motion estimation from compressed MPEG videos using machine learning approach
Author(s): Zheng Wang; Jinchang Ren; Yubin Wang; Meijun Sun; Jianmin Jiang
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper 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.

Paper Details

Date Published: 7 May 2013
PDF: 8 pages
Opt. Eng. 52(5) 057401 doi: 10.1117/1.OE.52.5.057401
Published in: Optical Engineering Volume 52, Issue 5
Show Author Affiliations
Zheng Wang, Tianjin Univ. (China)
Jinchang Ren, Univ. of Strathclyde (United Kingdom)
Yubin Wang, Tianjin Univ. (China)
Meijun Sun, Tianjin Univ. (China)
Jianmin Jiang, Tianjin Univ. (China)

© SPIE. Terms of Use
Back to Top