Tracking and reconstruction in a combined optimization approach

We present a novel approach to the structure-from-motion problem which combines the search for correspondences and geometric reconstruction, rather than treating these as separate steps. Through the combination of the two steps, we achieve an implicit feedback of 3D information to aid the correspond...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 34(2012), 2 vom: 23. Feb., Seite 387-401
1. Verfasser: Kähler, Olaf (VerfasserIn)
Weitere Verfasser: Denzler, Joachim
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2012
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM21004473X
003 DE-627
005 20231224010911.0
007 cr uuu---uuuuu
008 231224s2012 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2011.141  |2 doi 
028 5 2 |a pubmed24n0700.xml 
035 |a (DE-627)NLM21004473X 
035 |a (NLM)21768650 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Kähler, Olaf  |e verfasserin  |4 aut 
245 1 0 |a Tracking and reconstruction in a combined optimization approach 
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 21.05.2012 
500 |a Date Revised 01.03.2012 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a We present a novel approach to the structure-from-motion problem which combines the search for correspondences and geometric reconstruction, rather than treating these as separate steps. Through the combination of the two steps, we achieve an implicit feedback of 3D information to aid the correspondence search, and at the same time we avoid an explicit model for tracking errors. The reconstruction results are therefore optimal in case of, for example, Gaussian noise on image intensities. We also present an efficient online framework for structure-from-motion with our combined approach, thoroughly evaluate the method in experiments and compare the results to state-of-the-art methods 
650 4 |a Journal Article 
700 1 |a Denzler, Joachim  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 34(2012), 2 vom: 23. Feb., Seite 387-401  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:34  |g year:2012  |g number:2  |g day:23  |g month:02  |g pages:387-401 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2011.141  |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 34  |j 2012  |e 2  |b 23  |c 02  |h 387-401