DocumentCode
2103482
Title
Uncertainty ellipsoids calculations for complex 3D reconstructions
Author
Lhuillier, Maxime ; Perriollat, Mathieu
Author_Institution
CNRS, Universite Blaise Pascal, Aubiere
fYear
2006
fDate
15-19 May 2006
Firstpage
3062
Lastpage
3069
Abstract
Many methods exist for the automatic and optimal 3D reconstruction of camera motion and scene structure from image sequence (´structure from motion´ or SfM). The solution to this problem is not unique: we obtain an other solution by changing the coordinate system where points and cameras are defined. On the other hand, existing methods provide some measure of confidence or uncertainty for the estimation when the ground truth is not available, using a gauge constraint which settle the reconstruction coordinate system. Here we justify and describe a method which estimate the uncertainty ellipsoids, when previous methods are not straightforward to use due to a huge number of parameters to fit. Many examples are given and discussed for big reconstructions
Keywords
image reconstruction; image sensors; image sequences; camera motion; complex 3D reconstructions; gauge constraint; image sequence; reconstruction coordinate system; scene structure; uncertainty ellipsoids calculations; Cameras; Covariance matrix; Ellipsoids; Image reconstruction; Image sequences; Layout; Parameter estimation; Robot vision systems; Robustness; Uncertainty;
fLanguage
English
Publisher
ieee
Conference_Titel
Robotics and Automation, 2006. ICRA 2006. Proceedings 2006 IEEE International Conference on
Conference_Location
Orlando, FL
ISSN
1050-4729
Print_ISBN
0-7803-9505-0
Type
conf
DOI
10.1109/ROBOT.2006.1642167
Filename
1642167
Link To Document