Marker-based quadri-ocular tracking system for surgery

This study presents a quadri-ocular tracking system, which is based on PC and infrared reflective markers, for a spine surgical robot. The authors mainly focus on four tasks of the system. First of all, a two-step strategy for point correspondence of the multi-ocular system is introduced. The strategy enhances the traditional epipolar constrain for a bi-ocular system, and it decomposes the point correspondence of the multi-ocular system into several bi-ocular systems and corresponding steps to improve the speed of the system. Second, this paper proposes a fast algorithm of three-dimensional point reconstruction based on the perpendicular feet of back-projection lines. A marker constraint is also dug up to solve the combination problem of target recognition. Finally, this study uses a generalised inverse and singular value decomposition-based method to locate the pose of the target. The experiments show that the speed and accuracy of the system are satisfactory.

[1]  Yepeng Guan.  Stereo vision based video real-time 3D pointing gesture recognition , 2007 .

[2]  J. Ross Beveridge,et al.  An algorithm for projective point matching in the presence of spurious points , 2007, Pattern Recognit..

[3]  Jing Zhang,et al.  Motion Segmentation by Multibody Trifocal Tensor Using Line Correspondence , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[4]  Zhouping Yin,et al.  Three-dimensional point-based shape registration algorithm based on adaptive distance function , 2011 .

[5]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[6]  René Vidal,et al.  Three-View Multibody Structure from Motion , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  T. Poggio,et al.  A computational theory of human stereo vision , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[8]  Zhengyou Zhang,et al.  Flexible camera calibration by viewing a plane from unknown orientations , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  Luis M. Bergasa,et al.  Face tracking and pose estimation with automatic three-dimensional model construction , 2009 .

[10]  Zhengyou Zhang,et al.  Determining the Epipolar Geometry and its Uncertainty: A Review , 1998, International Journal of Computer Vision.

[11]  Dmitry B. Goldgof,et al.  Matching and motion estimation of three-dimensional point and line sets using eigenstructure without correspondences , 1992, Pattern Recognit..

[12]  Hong Hua,et al.  A fast connected components labeling algorithm and its application to real-time pupil detection , 2009, Machine Vision and Applications.

[13]  S. Basah,et al.  Conditions for motion-background segmentation using fundamental matrix , 2009, DICTA 2009.

[14]  Klaus Dorfmüller,et al.  Robust tracking for augmented reality using retroreflective markers , 1999, Comput. Graph..

[15]  A. Hasman,et al.  Simultaneous estimation of stereo correspondence and camera geometry from marker tracks , 1995, Computers in Cardiology 1995.

[16]  Robert van Liere,et al.  Optical tracking using projective invariant marker pattern properties , 2003, IEEE Virtual Reality, 2003. Proceedings..

[17]  Tao Daniel Alter.  3-D Pose from 3 Points Using Weak-Perspective , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  H. C. Longuet-Higgins,et al.  A computer algorithm for reconstructing a scene from two projections , 1981, Nature.

[19]  Andrea Sanna,et al.  A Wii remote-based infrared-optical tracking system , 2010, Entertain. Comput..