摘要
在条纹投射测量系统的标定过程中对摄像机畸变图像进行修正,能有效地提高系统的标定精度。采用改进的Harris算子检测标定板上特征点的亚像素坐标,通过预标定获得特征点空间坐标,并应用BP神经网络技术校正畸变图像。仿真实验表明该方法能简单有效地提高了标定系统的精度。
Correcting the distorted image of camera in calibration process of fringe projection measurement system that can effectively improve the calibration accuracy of system. In this paper,an improved Harris detector is applied to obtain subpixel coordinates of earmark on the calibration gauge,can obtain the feature space coordinates through pre-calibration, and use BP neural network technology for correcting distorted image. The experimental results show that this simple and effective method can improve the calibration accuracy of system.
出处
《光学仪器》
2008年第4期50-54,共5页
Optical Instruments
基金
国家自然科学基金资助项目(60678036)
