Two efficient solutions for visual odometry using directional correspondence

This paper presents two new, efficient solutions to the two-view, relative pose problem from three image point correspondences and one common reference direction. This three-plus-one problem can be used either as a substitute for the classic five-point algorithm, using a vanishing point for the refe...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 34(2012), 4 vom: 01. Apr., Seite 818-24
1. Verfasser: Naroditsky, Oleg (VerfasserIn)
Weitere Verfasser: Zhou, Xun S, Gallier, Jean, Roumeliotis, Stergios I, Daniilidis, Kostas
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2012
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, U.S. Gov't, Non-P.H.S.
LEADER 01000naa a22002652 4500
001 NLM213620243
003 DE-627
005 20231224021945.0
007 cr uuu---uuuuu
008 231224s2012 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2011.226  |2 doi 
028 5 2 |a pubmed24n0712.xml 
035 |a (DE-627)NLM213620243 
035 |a (NLM)22144517 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Naroditsky, Oleg  |e verfasserin  |4 aut 
245 1 0 |a Two efficient solutions for visual odometry using directional correspondence 
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 10.09.2012 
500 |a Date Revised 31.05.2012 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a This paper presents two new, efficient solutions to the two-view, relative pose problem from three image point correspondences and one common reference direction. This three-plus-one problem can be used either as a substitute for the classic five-point algorithm, using a vanishing point for the reference direction, or to make use of an inertial measurement unit commonly available on robots and mobile devices where the gravity vector becomes the reference direction. We provide a simple, closed-form solution and a solution based on algebraic geometry which offers numerical advantages. In addition, we introduce a new method for computing visual odometry with RANSAC and four point correspondences per hypothesis. In a set of real experiments, we demonstrate the power of our approach by comparing it to the five-point method in a hypothesize-and-test visual odometry setting 
650 4 |a Journal Article 
650 4 |a Research Support, U.S. Gov't, Non-P.H.S. 
700 1 |a Zhou, Xun S  |e verfasserin  |4 aut 
700 1 |a Gallier, Jean  |e verfasserin  |4 aut 
700 1 |a Roumeliotis, Stergios I  |e verfasserin  |4 aut 
700 1 |a Daniilidis, Kostas  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 34(2012), 4 vom: 01. Apr., Seite 818-24  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:34  |g year:2012  |g number:4  |g day:01  |g month:04  |g pages:818-24 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2011.226  |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 4  |b 01  |c 04  |h 818-24