Abstract：This paper presents a depth extraction method for micromanipulation robot based on monocular micro vision. With the depth description in micro manipulating space, one kind of image features has been extracted from 2-D image plane to evaluate defocusing. It is demonstrated by experimental results that the method is available and the determined defocus feature is consistent with the robot movement property in Z direction.
[1] 孙立宁, 陈立国, 刘品宽, 荣伟斌. 微操作机器人显微视觉系统若干问题[J]. 光学精密过程, 2002,10(2):171-175. [2] Pentland A P. A new sense for depth of field[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1987,9(7):523-531. [3] Ens J, Lawrence P. An investigation of methods for determing depth from focus[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1993,15(2):97-107. [4] Xiong Y, Shafer S A. Depth from focusing and defocusing[A]. Proc. IEEE Conf. Computer Vision and Pattern Recognition[C], 1993, New York:68-73. [5] 张建勋, 薛大庆, 卢桂章, 李彬. 通过显微图像特征抽取获得微操作目标纵向信息[J]. 机器人, 2001,23(1):73-77. [6] Sang Ku Kim, Sang Rae Park. Simultaneous out of focus blur estimation and restoration for a digital auto-focusing system[J]. IEEE Transactions on Consumer Electronics, 1998,44(3):1071-1075.
