Evaluation of a feature-based global-motion estimation system

D.S. Farin, P.H.N. With, de

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

24 Citations (Scopus)

Abstract

Global-motion estimators are an important part of current video-coding systems like MPEG-4, content analysis and description systems like MPEG-7, and many video-object segmentation algorithms. Feature-based motion estimators use the motion vectors obtained for a set of selected points to calculate the parameters of the globalmotion model. This involves the detection of feature points, the computation of correspondences between two sets of features, and the motion parameter estimation. In this paper, we will present a feature-based global-motion estimation system and discuss each of its parts in detail. The idea is to provide an overview of a general purpose feature-based motion estimator and to point out the important design aspects. We evaluate the performance of different feature detection algorithms, propose an efficient feature-correspondence algorithm, and we compare the difference between a non-linear parameter estimation and a linear approximation. Finally, the RANSAC based robust parameter estimation is examined, we show why it does not reach its theoretical performance, and propose a modification to increase its accuracy. Our global-motion estimator has an average accuracy of ˜ 0.15 pixels with real-time execution. Keywords: Global-motion estimation, feature-point detection, robust estimation, feature correspondences.
Original languageEnglish
Title of host publicationVisual Communications and Image Processing (VCIP)
EditorsShipeng Li
Place of PublicationBellingham
PublisherSPIE
Pages1331-1342
DOIs
Publication statusPublished - 2005
EventVisual Communications and Image Processing 2005 (VCIP 2005), July 12-15, 2005, Beijing, China - Beijing, China
Duration: 12 Jul 200515 Jul 2005

Publication series

NameProceedings of SPIE
Volume5960

Conference

ConferenceVisual Communications and Image Processing 2005 (VCIP 2005), July 12-15, 2005, Beijing, China
Abbreviated titleVCIP 2005
Country/TerritoryChina
CityBeijing
Period12/07/0515/07/05

Fingerprint

Dive into the research topics of 'Evaluation of a feature-based global-motion estimation system'. Together they form a unique fingerprint.

Cite this