Large displacement optical flow : descriptor matching in variational motion estimation

Optical flow estimation is classically marked by the requirement of dense sampling in time. While coarse-to-fine warping schemes have somehow relaxed this constraint, there is an inherent dependency between the scale of structures and the velocity that can be estimated. This particularly renders the...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 33(2011), 3 vom: 02. März, Seite 500-13
1. Verfasser: Brox, Thomas (VerfasserIn)
Weitere Verfasser: Malik, Jitendra
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2011
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't Research Support, U.S. Gov't, Non-P.H.S.
LEADER 01000naa a22002652 4500
001 NLM200348450
003 DE-627
005 20231223220410.0
007 cr uuu---uuuuu
008 231223s2011 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2010.143  |2 doi 
028 5 2 |a pubmed24n0668.xml 
035 |a (DE-627)NLM200348450 
035 |a (NLM)20714020 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Brox, Thomas  |e verfasserin  |4 aut 
245 1 0 |a Large displacement optical flow  |b descriptor matching in variational motion estimation 
264 1 |c 2011 
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 23.06.2011 
500 |a Date Revised 21.04.2011 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a Optical flow estimation is classically marked by the requirement of dense sampling in time. While coarse-to-fine warping schemes have somehow relaxed this constraint, there is an inherent dependency between the scale of structures and the velocity that can be estimated. This particularly renders the estimation of detailed human motion problematic, as small body parts can move very fast. In this paper, we present a way to approach this problem by integrating rich descriptors into the variational optical flow setting. This way we can estimate a dense optical flow field with almost the same high accuracy as known from variational optical flow, while reaching out to new domains of motion analysis where the requirement of dense sampling in time is no longer satisfied 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
650 4 |a Research Support, U.S. Gov't, Non-P.H.S. 
700 1 |a Malik, Jitendra  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 33(2011), 3 vom: 02. März, Seite 500-13  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:33  |g year:2011  |g number:3  |g day:02  |g month:03  |g pages:500-13 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2010.143  |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 33  |j 2011  |e 3  |b 02  |c 03  |h 500-13