Dense motion estimation using regularization constraints on local parametric models

This paper presents a method for dense optical flow estimation in which the motion field within patches that result from an initial intensity segmentation is parametrized with models of different order. We propose a novel formulation which introduces regularization constraints between the model para...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 13(2004), 11 vom: 01. Nov., Seite 1432-43
1. Verfasser: Patras, Ioannis (VerfasserIn)
Weitere Verfasser: Worring, Marcel, van den Boomgaard, Rein
Format: Aufsatz
Sprache:English
Veröffentlicht: 2004
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Comparative Study Journal Article
LEADER 01000naa a22002652 4500
001 NLM152085068
003 DE-627
005 20231223061309.0
007 tu
008 231223s2004 xx ||||| 00| ||eng c
028 5 2 |a pubmed24n0507.xml 
035 |a (DE-627)NLM152085068 
035 |a (NLM)15540453 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Patras, Ioannis  |e verfasserin  |4 aut 
245 1 0 |a Dense motion estimation using regularization constraints on local parametric models 
264 1 |c 2004 
336 |a Text  |b txt  |2 rdacontent 
337 |a ohne Hilfsmittel zu benutzen  |b n  |2 rdamedia 
338 |a Band  |b nc  |2 rdacarrier 
500 |a Date Completed 08.12.2004 
500 |a Date Revised 26.10.2019 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a This paper presents a method for dense optical flow estimation in which the motion field within patches that result from an initial intensity segmentation is parametrized with models of different order. We propose a novel formulation which introduces regularization constraints between the model parameters of neighboring patches. In this way, we provide the additional constraints for very small patches and for patches whose intensity variation cannot sufficiently constrain the estimation of their motion parameters. In order to preserve motion discontinuities, we use robust functions as a regularization mean. We adopt a three-frame approach and control the balance between the backward and forward constraints by a real-valued direction field on which regularization constraints are applied. An iterative deterministic relaxation method is employed in order to solve the corresponding optimization problem. Experimental results show that the proposed method deals successfully with motions large in magnitude, motion discontinuities, and produces accurate piecewise-smooth motion fields 
650 4 |a Comparative Study 
650 4 |a Journal Article 
700 1 |a Worring, Marcel  |e verfasserin  |4 aut 
700 1 |a van den Boomgaard, Rein  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 13(2004), 11 vom: 01. Nov., Seite 1432-43  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:13  |g year:2004  |g number:11  |g day:01  |g month:11  |g pages:1432-43 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 13  |j 2004  |e 11  |b 01  |c 11  |h 1432-43