Extraction of Depth Information for Micromanipulation Using Normalized Spectral Principal Component Analysis
ZENG Ming1, MENG Qing-hao1, ZHANG Jian-xun2, WANG Xiang-hui3
1. School of Electrical Engineering and Automation, Tianjin University, Tianjin 300072, China; 2. Institute of Robotics & Automatic Information System, Nankai University, Tianjin 300071, China; 3. Institute of Modern Optics, Nankai University, Tianjin 300071, China
Abstract:This paper proposes a novel spectral analysis method named normalized spectral image,which is invariant to translation and scaling.The influence of large-scale movement of micro-manipulation tools in the testing window(X-Y plane) on the algorithm robustness can be eliminated by using normalized spectral images.Meanwhile,principal component analysis(PCA) technique is used to reduce the dimensions of data and to suppress noise,and the real-time performance and accuracy of the algorithm is improved.Experimental results demonstrate the effectiveness of the proposed method.
[1] 卢桂章,张建勋,赵新.面向生物工程实验的微操作机器人[J].南开大学学报,1999,32(3):42-46.
[2] 毕树生,宗光华.用于生物工程的微操作机器人系统的若干问题[J].仪器仪表学报,2000,21(6):560-564,573.
[3] Sun Y,Nelson B J.Biological cell injection using an autonomous microrobotic system[J].The International Journal of Robotics Reaserch,2002,21(10-11):861 -868.
[4] 孙立宁,陈立国,刘品宽,等.微操作机器人显微视觉系统若干问题[J].光学精密工程,2002,10(2):171-175.
[5] Rayala J,Gupta S,Mullick S K.Estimation of depth from defocus as polynomial system identification[J].IEE Proceeding:Vision,Image and Signal Processing,2001,148(5):356 -362.
[6] Ziou D,Deschenes F.Depth from defocus estimation in spatial domain[J].Computer Vision and Image Understanding,2001,81(2):143-165.
[7] 吕遐东,黄心汉,王敏,等.基于显微图像散焦特征的微操作机器人深度信息提取[J].机器人,2003,25(4):322-326.
[8] 谢少荣,彭商贤,赵新,等.基于虚拟显微镜技术的微操作工具Z方向定位方法研究[J].高技术通讯,2001,11(9):72-75.
[9] 张建勋,薛大庆,卢桂章,等.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.
[10] 曾明,张建勋,陈少杰,等.基于高频能量参数Eh的微操作纵向深度估计[J].机器人,2004,26(4):351-356.
[11] Dunteman G H.Principal Component Analysis[M].London:Sage Publication Ltd,1989.