| 基于神经网络的运动参数估计 |
| |
| 引用本文： | 孙立,汪亚明,黄文清,吴铮,夏一民.基于神经网络的运动参数估计[J].计算机工程与设计,2008,29(12). |
| |
| 作者姓名： | 孙立 汪亚明 黄文清 吴铮 夏一民 |
| |
| 作者单位： | 浙江理工大学,信息与电子学院,浙江,杭州,310018 |
| |
| 摘 要： | 分别就两种约束使用神经网络对三维刚体运动进行参数估计.一是基于三维点匹配,将预测的运动参数作用于运动前的坐标,与运动后坐标进行比较;二是基于二维运动场,将使用预测的运动参数计算得出的二维运动场与图像序列中计算得出的二维运动场进行比较.两个神经网络均使用Newton-Raphson方法更新权值,以达到目标误差最小化.通过实验验证了该神经网络方法.
|
| 关 键 词： | 计算机视觉 运动参数估计 三维点匹配 二维运动场 神经网络 |
Neural networks for 3D rigid motion estimation |
| |
| SUN Li,WANG Ya-ming,HUANG Wen-qing,WU Zheng,XIA Yi-min.Neural networks for 3D rigid motion estimation[J].Computer Engineering and Design,2008,29(12). |
| |
| Authors: | SUN Li WANG Ya-ming HUANG Wen-qing WU Zheng XIA Yi-min |
| |
| Affiliation: | SUN Li,WANG Ya-ming,HUANG Wen-qing,WU Zheng,XIA Yi-min(College of Informatics , Electronics,Zhejiang Sci-Tech University,Hangzhou 310018,China) |
| |
| Abstract: | Neural networks is used to estimate three-dimensional(3D) rigid motion parameters based two constraints.The one is based on 3D correspondences.The points' coordinates before motion are updated by the presupposed motion parameters and then compared to those after motion.The other is based two-dimensional(2D) motion fields.The motion fields from presupposition are compared to those computed from image sequences.Both network updates its weights by newton-raphson procedure for minimizing the error measures.Expe... |
| |
| Keywords: | computer vision motion estimation 3D points matched 2D motion fields neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
