Translator Disclaimer
Paper
14 February 1992 Parallel approach to simultaneously solving the correspondence problem and the pose estimation problem
Author Affiliations +
Proceedings Volume 1613, Mobile Robots VI; (1992) https://doi.org/10.1117/12.135176
Event: Robotics '91, 1991, Boston, MA, United States
Abstract
We describe a parallel-distributed approach to simultaneously solving the correspondence problem and the pose estimation problem. When the correspondence is known our method reduces to a generalized Hopfield network with a node for each image point that has an activation that converges to the ray-length through the image point to the object point. Inexact knowledge of the correspondence between object points and image points is represented as an assignment array that encodes the degree of confidence in each of the possible correspondences, similar to the traditional `assignment problem' of optimization theory. Two neural networks, one for pose estimation and one for solving the assignment problem, interact via the introduction of `pseudo image points,' created from the inexact correspondences. These `pseudo image points' reduce to the actual image points when the correspondence is known.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
William J. Wolfe "Parallel approach to simultaneously solving the correspondence problem and the pose estimation problem", Proc. SPIE 1613, Mobile Robots VI, (14 February 1992); https://doi.org/10.1117/12.135176
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Fuzzy Hopfield-Tank TSP model
Proceedings of SPIE (March 22 1999)
Optimal robustness in noniterative learning
Proceedings of SPIE (April 06 1995)
ReverbaProp: simultaneous learning of credit and weight
Proceedings of SPIE (April 06 1995)

Back to Top