pq-Space Based 2D/3D Registration for Endoscope Tracking

This paper presents a new pq-space based 2D/3D registration method for camera pose estimation for endoscope tracking. The proposed technique involves the extraction of surface normals for each pixel of the video images by using a linear local shape-from-shading algorithm derived from the unique camera/lighting constrains of the endoscopes. We illustrate how to use the derived pq-space distribution to match to that of the 3D tomographic model, and demonstrate the accuracy of the proposed method by using an electro-magnetic tracker and a specially constructed airway phantom. Comparison to existing intensity-based techniques has also been made, which highlights the major strength of the proposed method in its robustness against illumination and tissue deformation.

[1]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[2]  N. Ayache,et al.  Landmark-based registration using features identified through differential geometry , 2000 .

[3]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Y. J. Tejwani,et al.  Robot vision , 1989, IEEE International Symposium on Circuits and Systems,.

[5]  Philip David,et al.  SoftPOSIT: Simultaneous Pose and Correspondence Determination , 2002, ECCV.

[6]  Daniel Rueckert,et al.  Using Photo-Consistency to Register 2D Optical Images of the Human Face to a 3D Surface Model , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Isaac N. Bankman,et al.  Handbook of Medical Imaging. Processing and Analysis , 2002 .

[8]  William E. Higgins,et al.  Technique for registering 3D virtual CT images to endoscopic video , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[9]  Mads Nielsen,et al.  Computer Vision — ECCV 2002 , 2002, Lecture Notes in Computer Science.

[10]  Larry S. Davis,et al.  Model-based object pose in 25 lines of code , 1992, International Journal of Computer Vision.

[11]  Eric Mjolsness,et al.  New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence , 1998, NIPS.

[12]  Takayuki Okatani,et al.  3D Shape Reconstruction from an Endoscope Image Based on Shading , 1997 .

[13]  Bostjan Likar,et al.  A hierarchical approach to elastic registration based on mutual information , 2001, Image Vis. Comput..

[14]  Berthold K. P. Horn,et al.  Shape from shading , 1989 .

[15]  Peter Burger,et al.  Differential algorithm for the determination of shape from shading using a point light source , 1992, Image Vis. Comput..

[16]  Berthold K. P. Horn.  Understanding Image Intensities , 1977, Artif. Intell..

[17]  Shoji Tominaga,et al.  Estimating Reflection Parameters from a Single Color Image , 2000, IEEE Computer Graphics and Applications.

[18]  Anand Rangarajan,et al.  A new point matching algorithm for non-rigid registration , 2003, Comput. Vis. Image Underst..

[19]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[20]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[21]  Kensaku Mori,et al.  Method for tracking camera motion of real endoscope by using virtual endoscopy system , 2000, Medical Imaging.