Three-dimensional (3-D) modeling based on an ensemble of multilayer self-organizing (SO) neural networks is described. Our objective for 3-D modeling is to construct a representation of a 3-D object shape from sensed surface points acquired from the object. Current modeling techniques can be classified into two categories: the static and the dynamic approaches, the former grounded in computational geometry, and the latter rooted in the mechanics of elastic materials. In this paper, a neural-based dynamic modeling approach is presented. The method used is proved to converge and experimental results are shown which support its applicability to real problems.
ASJC Scopus subject areas
- Computer Science Applications
- Computer Networks and Communications
- Artificial Intelligence