Robust optical flow estimation in MPEG sequences

Rapantzikos, K; Zervakis, M

dc.contributor.author	Rapantzikos, K	en
dc.contributor.author	Zervakis, M	en
dc.date.accessioned	2014-03-01T02:43:30Z
dc.date.available	2014-03-01T02:43:30Z
dc.date.issued	2005	en
dc.identifier.issn	15206149	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31445
dc.subject	Hypothesis Test	en
dc.subject	Objective Function	en
dc.subject	Optical Flow Estimation	en
dc.subject	Velocity Field	en
dc.subject	Video Analysis	en
dc.subject	Video Indexing	en
dc.subject	Optical Flow	en
dc.subject	Real Time	en
dc.subject.other	Decompression	en
dc.subject.other	Motion discontinuities	en
dc.subject.other	Real time video indexing	en
dc.subject.other	Robust optical flow estimation	en
dc.subject.other	Computer vision	en
dc.subject.other	Functions	en
dc.subject.other	Image analysis	en
dc.subject.other	Motion compensation	en
dc.subject.other	Optical flows	en
dc.subject.other	Robustness (control systems)	en
dc.subject.other	Image compression	en
dc.title	Robust optical flow estimation in MPEG sequences	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICASSP.2005.1415549	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICASSP.2005.1415549	en
heal.identifier.secondary	1415549	en
heal.publicationDate	2005	en
heal.abstract	Motion information is essential in many computer vision and video analysis tasks. Since MPEG is still one of the most prevalent formats for representing, transferring and storing video data, the analysis of its motion field is important for real time video indexing and segmentation, event analysis and surveillance applications. Our work considers the problem of improving the optical flow field in MPEG sequences. We address the issues of robust, incremental, dense optical flow estimation by combining information from two different velocity fields: the available MPEG motion field and the one inferred by a multiresolution robust regularization technique applied on the DC coefficients. Thus, the regularization technique is based only on information that is directly available in the compressed stream avoiding therefore the time and memory consuming decompression. We extend standard techniques by adding a temporal continuity and an MPEG consistency constraint, both as mathematical constraints in the objective function and as hypothesis tests for the presence of motion discontinuities. Our approach is shown to perform well over a range of different motion scenarios and can serve as a basis for efficient video analysis tasks. © 2005 IEEE.	en
heal.journalName	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings	en
dc.identifier.doi	10.1109/ICASSP.2005.1415549	en
dc.identifier.volume	II	en
dc.identifier.spage	II893	en
dc.identifier.epage	II896	en