Tien-Ren Tsao, Haw-Jye Shyu, John M. Libert and Victor C. Chen,
A Lie Group Approach to a Neural System for
Three-Dimensional Interpretation of Visual Motion,
IEEE Transactions on Neural Networks,
2, 1, pp. 149-155, January 1991.
Tien-Ren Tsao, Haw-Jye Shyu, John M. Libert and Victor C. Chen,
A Lie Group Approach to a Neural System for
Three-Dimensional Interpretation of Visual Motion,
IEEE Transactions on Neural Networks,
2, 1, pp. 149-155, January 1991.This paper presents a novel approach to neural network computation of three-dimensional rigid motion from noisy two-dimensional image flow. We show that the process of 3-D interpretation of image flow can be viewed as a linear signal transformation. The elementary signals of this linear transform are the 2-D vector fields of the six infinitesimal generators of the 3-D Euclidean group. This transform can be performed by a neural network. This paper reports the results of neural network simulations for the 3-D interpretation of image flow and a comparison of the performance of this approach with that using conventional methods. Computer simulation results verify the Lie-group-based neural network approach to three-dimensional motion perception.