| 增强现实系统中基于神经网络的磁力跟踪器校正 |
| |
| 引用本文： | 丰艳,陈一民.增强现实系统中基于神经网络的磁力跟踪器校正[J].上海大学学报(英文版),2006,10(5):431-435. |
| |
| 作者姓名： | 丰艳 陈一民 |
| |
| 作者单位： | School of Computer Engineering and Science, Shanghai University, Shanghai 200072, P.R. China |
| |
| 基金项目： | Project supported by Science Foundation of Shanghai Municipal Commission of Science and Technology （Grant No. 025115008） |
| |
| 摘 要： | Nonlinear errors always exist in data obtained from tracker in augmented reality （AR）, which badly influence the effect of AR. This paper proposes to rectify the errors using BP neural network. As BP neural network is prone to getting into local extrema and convergence is slow, genetic algorithm is employed to optimize the initial weights and threshold of neural network. This paper discusses how to set the crucial parameters in the algorithm. Experimental results show that the method ensures that the neural network achieves global convergence quickly and correctly. Tracking precision of AR system is improved after the tracker is rectified, and the third dimension of AR system is enhanced.
|
| 关 键 词： | BP网络 神经网络 遗传算法 增强现实 磁力跟踪 |
| 文章编号： | 1007-6417（2006）05-0431-05 |
| 收稿时间： | 2005-03-09 |
| 修稿时间： | 2005-09-09 |
Rectification of magnetic force tracker using neural network in augmented reality system |
| |
| Yan Feng Ph. D. Candidate,Yi-min Chen.Rectification of magnetic force tracker using neural network in augmented reality system[J].Journal of Shanghai University(English Edition),2006,10(5):431-435. |
| |
| Authors: | Yan Feng Ph D Candidate Yi-min Chen |
| |
| Abstract: | Nonlinear errors always exist in data obtained from tracker in augmented reality (AR), which badly influence the effect of AR. This paper proposes to rectify the errors using BP neural network. As BP neural network is prone to getting into local extrema and convergence is slow, genetic algorithm is employed to optimize the initial weights and threshold of neural network. This paper discusses how to set the crucial parameters in the algorithm. Experimental results show that the method ensures that the neural network achieves global convergence quickly and correctly. Tracking precision of AR system is improved after the tracker is rectified, and the third dimension of AR system is enhanced. |
| |
| Keywords: | BP neural network genetic algorithm augmented reality(AR) magnetic force tracker rectification |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
