Robust ∞ convex optimisation for monocular visual odometry trajectory estimation

Simple item page
dc.contributor.authorRichardson, Mark
dc.contributor.authorAouf, Nabil
dc.contributor.authorBoulekchour, Mohammed
dc.date.accessioned2023-09-20T10:55:13Z
dc.date.available2023-09-20T10:55:13Z
dc.date.issued2014-07-09
dc.description.abstractThe most important applications of many computer vision systems are based on robust features extraction, matching and tracking. Due to their extraction techniques, image features locations accuracy is heavily dependent on the variation in intensity within their neighbourhoods, from which their uncertainties are estimated. In the present work, a robust L∞optimisation solution for monocular motion estimation systems has been presented. The uncertainty estimation techniques based on SIFT derivative approach and its propagation through the eight-point algorithm, singular value decomposition SVD and the triangulation algorithm have proved an improvement to the global motion estimation. Using monocular systems makes the motion estimation challenging due to the absolute scale ambiguity caused by projective effects. For this, we propose robust tools to estimate both the trajectory of a moving object and the unknown absolute scale ratio between consecutive image pairs. Experimental evaluations showed that robust convex optimisation with the L∞norm under uncertain data and the Robust Least Squares clearly outperform classical methods based on Least Squares and Levenberg-Marquardt algorithms.en_UK
dc.identifier.citationBoulekchour M, Aouf N, Richardson M. (2016) Robust ∞ convex optimisation for monocular visual odometry trajectory estimation, Robotica, Volume 34, Issue 3, March 2016, pp. 703-722en_UK
dc.identifier.eissn1469-8668
dc.identifier.issn0263-5747
dc.identifier.urihttps://doi.org/10.1017/S0263574714001829
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/20258
dc.language.isoenen_UK
dc.publisherCambridge University Press (CUP)en_UK
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectConvex optimisationen_UK
dc.subjectL∞ Normen_UK
dc.subjectMonocular visual odometryen_UK
dc.subjectRobust optimisationen_UK
dc.subjectSOCPen_UK
dc.subjectUncertainty propagationen_UK
dc.titleRobust ∞ convex optimisation for monocular visual odometry trajectory estimationen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Odometry_trajectory_estimation-2016.pdf
Size:
4.49 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (CDS)