基于全局位姿评估的条纹反向视觉测量  

Fringe Inverse Videogrammetry Based on Global Pose Estimation

作　　者：肖永亮[1] 苏显渝[1] 陈文静[1] 

机构地区：[1]四川大学光电科学技术系,四川成都610064

出　　处：《中国激光》2011年第8期207-213,共7页Chinese Journal of Lasers

基　　金：国家自然科学基金(60838002)资助课题

摘　　要：提出基于全局位姿评估的条纹反向视觉测量。利用带测头的摄像机拍摄二维正弦条纹,根据傅里叶分析提取的平面特征点全局评估摄像机位姿,进而测量测头的球心坐标。摄像机的位姿评估是条纹反向视觉测量的关键技术,在测头标定和坐标测量中均需要进行位姿评估。位姿评估的误差函数包括重投影误差和物空间误差两类,两者在基于平面的位姿评估中均存在两个局部极小值,采用全局位姿评估算法可以避免误差函数陷入局部极小以高精度获取摄像机位姿,完成测头标定和坐标测量。实验结果表明,该方法可以高精度测量物体的三维坐标。Fringe inverse videogrammetry based on global pose estimation is presented. The camera pose is estimated with planar characteristic points extracted from fringes by Fourier analysis. The fringes are captured using camera with probe, and the coordinates of probe can be measured with the help of the camera pose. The camera pose estimation is the key step in fringe inverse videogrammetry. The cost function for iterative pose estimation involves image-space error and object-space error, both having two local minima. The danger that the cost function converges to a local minimum can be avoided by use of global pose estimation. High-precision pose of camera can be obtained to accomplish the probe calibration and coordinate measurement. The experiments demonstrate that the method can measure the three-dimensional coordinates precisely.

关 键 词：机器视觉 反向视觉测量 全局位姿评估 正弦条纹 傅里叶分析 

分 类 号：O436[机械工程—光学工程]