Title :
Monocular Lie algebra approach for 3D motion estimation
Author :
Ortegon-Aguilar, Jaime ; Bayro-Corrochano, Eduardo
Author_Institution :
Dept. of Comput. Sci., CINVESTAV Unidad Guadalajara, Jalisco, Mexico
Abstract :
This work presents a monocular method to estimate 3D motion of an object in the visual space. Our method is based on the theory of system identification, it identifies the optimal estimated value of the parameters that defines a 3D motion. The Lie algebra approach assures the estimation of the parameters of the shortest orbit (geodesic) of the involved group action. Experiments validate the effectiveness of the method.
Keywords :
Lie algebras; Lie groups; computer vision; motion estimation; parameter estimation; 3D motion estimation; monocular Lie algebra; parameter estimation; system identification theory; visual space; Algebra; Computer science; Jacobian matrices; Laboratories; Least squares approximation; Matrix decomposition; Motion estimation; Neural networks; Parameter estimation; System identification;
Conference_Titel :
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
Print_ISBN :
0-7695-2128-2
DOI :
10.1109/ICPR.2004.1334095
