DocumentCode :
2537484
Title :
Linear estimation of object pose from local fits to segments
Author :
Bilbro, G.L. ; Snyder, W.E.
Author_Institution :
North Carolina State University, Raleigh, NC
Volume :
4
fYear :
1987
fDate :
31837
Firstpage :
1747
Lastpage :
1752
Abstract :
A planar or quadric surface can be fit to a segment of range data in a locally optimal sense by selecting the minimum eigensolution of a scatter matrix for that segment. We obtain a globally optimal fit by perturbing the local eigensystems with constraints reflecting relations among the corresponding primitives of a model. These pairwise relations define a view-invariant description of the model. For segments containing a few hundred pixels, the resulting perturbation is small enough to justify a linear treatment of the coupled system. From this globally optimal fit, we determine the pose of the object algebraically.
Keywords :
Geometry; Image analysis; Image processing; Image segmentation; Maximum likelihood estimation; Motion estimation; Object recognition; Scattering; Solid modeling; Surface fitting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation. Proceedings. 1987 IEEE International Conference on
Type :
conf
DOI :
10.1109/ROBOT.1987.1087745
Filename :
1087745
Link To Document :
بازگشت