Optimal control for real-time visualization and 3D rendering using neural networks
You-Wei Yuan
Han-Hui Zhan
La-Mei Yan
Zhuzhou Inst. of Technol., Hunan, China;
Abstract
This article describes a novel approach to the real-time visualization and 3D rendering using neural networks. The present scheme is within the general framework of approximate dynamic programming where optimal/suboptimal control is achieved through learning to use pulse-coupled neural networks. The neural network model is proposed in this paper for optimal control with control constraints. The resulting 3D models can then be viewed from any angle and subsequently processed to integrately match them against 3D model data stored in a synthetic database. Our work is unique in that it supports both an online and off-tine visualization and rendering of a distributed system.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
