Locally oriented optical flow computation

This paper proposes the use of an adaptive locally oriented coordinate frame when calculating an optical flow field. The coordinate frame is aligned with the least curvature direction in a local window about each pixel. This has advantages to both fitting the flow field to the image data and in impo...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 21(2012), 4 vom: 13. Apr., Seite 1573-86
Auteur principal: Niu, Yan (Auteur)
Autres auteurs: Dick, Anthony, Brooks, Michael
Format: Article en ligne
Langue:English
Publié: 2012
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000caa a22002652c 4500
001 NLM21372765X
003 DE-627
005 20250213113140.0
007 cr uuu---uuuuu
008 231224s2012 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2011.2177847  |2 doi 
028 5 2 |a pubmed25n0712.xml 
035 |a (DE-627)NLM21372765X 
035 |a (NLM)22155955 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Niu, Yan  |e verfasserin  |4 aut 
245 1 0 |a Locally oriented optical flow computation 
264 1 |c 2012 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 18.07.2012 
500 |a Date Revised 22.03.2012 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a This paper proposes the use of an adaptive locally oriented coordinate frame when calculating an optical flow field. The coordinate frame is aligned with the least curvature direction in a local window about each pixel. This has advantages to both fitting the flow field to the image data and in imposing smoothness constraints between neighboring pixels. In terms of fitting, robustness is obtained to a wider variety of image motions due to the extra invariance provided by the coordinate frame. Smoothness constraints are naturally propagated along image boundaries which often correspond to motion boundaries. In addition, moving objects can be efficiently segmented in the least curvature direction. We show experimentally the benefits of the method and demonstrate robustness to fast rotational motion, such as what often occurs in human motion 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Dick, Anthony  |e verfasserin  |4 aut 
700 1 |a Brooks, Michael  |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 21(2012), 4 vom: 13. Apr., Seite 1573-86  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnas 
773 1 8 |g volume:21  |g year:2012  |g number:4  |g day:13  |g month:04  |g pages:1573-86 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2011.2177847  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 21  |j 2012  |e 4  |b 13  |c 04  |h 1573-86