| 基于BP神经网络的姿态测量系统摄像机标定 |
| |
| 引用本文： | 蔡盛,李清安,乔彦峰. 基于BP神经网络的姿态测量系统摄像机标定[J]. 光电子．激光, 2007, 18(7): 832-834 |
| |
| 作者姓名： | 蔡盛 李清安 乔彦峰 |
| |
| 作者单位： | 中国科学院长春光学精密机械与物理研究所,吉林,长春,130023;中国科学院研究生院,北京,100039;北京华北光学仪器有限公司,北京,100050;中国科学院长春光学精密机械与物理研究所,吉林,长春,130023 |
| |
| 摘 要： | 针对摄像机标定过程中复杂的成像和畸变模型,利用误差逆传播(BP)神经网络对复杂非线性映射关系的强大逼近能力,对姿态测量系统中的摄像机进行隐式标定,建立了姿态测量中三维空间目标特征点与它在图像平面上像点间的映射关系,使姿态测量系统无须进行复杂的摄像机标定,直接恢复目标特征点的三维信息,从而计算得到目标姿态信息.结果表明,该方法对于空间点坐标恢复的均方根误差小于0.015 mm,可以获得较高的精度.
|
| 关 键 词： | 姿态测量 摄像机标定 误差逆传播 误差逆传播(BP)神经网络 |
| 文章编号： | 1005-0086（2007）07-0832-03 |
| 修稿时间： | 2006-08-05 |
Camera Calibration of Attitude Measurement System Based on BP Neural Network |
| |
| CAI Sheng,LI Qing-an,QIAO Yan-feng. Camera Calibration of Attitude Measurement System Based on BP Neural Network[J]. Journal of Optoelectronics·laser, 2007, 18(7): 832-834 |
| |
| Authors: | CAI Sheng LI Qing-an QIAO Yan-feng |
| |
| Affiliation: | 1. Changehun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Scienee,Changehun 130033, China; 2. Graduate School of the Chinese Academy of Sciences,Beijing 100039,China; 3. Beijing Huabei Optical Instrument Company,Beijing 100050,China |
| |
| Abstract: | For the complicated models of image formation and lens distortion that exist in the camera calibration,cameras are calibrated implicitly by using BP neural network because it is able to fit the complicated nonlinear mapping relation.And the mapping relationship between objects under 3-D coordinate and pixels under image coordinate system is set up,so the 3-D information can be reconstructed,then the tri-dimensional gesture can be obtained.Experimental results show that the root mean square error(RMSE)of spa... |
| |
| Keywords: | attitude measurement camera calibration error back propagation error back propagation(BP)neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
|
