Intelligent frame selection for anatomic reconstruction from endoscopic video

Using endoscopic video, it is possible to perform 3D reconstruction of the anatomy using the well known epipolar constraint between matched feature points. Through this constraint, it is possible to recover the translation and rotation between camera positions and thus reconstruct the 3D anatomy by triangulation. However, these motion estimates are not stable for small camera motions. In this work, we propose a covariance estimation scheme to select pairs of frames which give rise to stable motion estimates, i.e. minimal variance with respect to pixel match error. We parameterize the essential matrix using a minimal 5 parameter representation and estimate motion covariance based upon the estimated feature match variance. The proposed algorithm is applied to endoscopic video sequences recorded in porcine sinus passages in order to extract stable motion estimates.

[1]  Jay B. West,et al.  Implementation, calibration and accuracy testing of an image-enhanced endoscopy system , 2002, IEEE Transactions on Medical Imaging.

[2]  S. Shankar Sastry,et al.  An Invitation to 3-D Vision , 2004 .

[3]  Fabrice Chassat,et al.  Experimental Protocol for Accuracy Evaluation of 6-d Localizers for Computer-Integrated Surgery: Application to Four Optical Localizers , 1998, MICCAI.

[4]  A Linney,et al.  Image‐enhanced surgical navigation for endoscopic sinus surgery: evaluating calibration, registration and tracking , 2008, The international journal of medical robotics + computer assisted surgery : MRCAS.

[5]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[6]  Fredric B. Meyer,et al.  Endoscopic Transnasal Pituitary Surgery: Report on 180 Cases , 2001, American journal of rhinology.

[7]  Hans-Hellmut Nagel,et al.  Analytical Results on Error Sensitivity of Motion Estimation from Two Views , 1990, ECCV.

[8]  William E. Higgins,et al.  Combined endoscopic video tracking and virtual 3D CT registration for surgical guidance , 2002, Proceedings. International Conference on Image Processing.

[9]  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).

[10]  Francesca Odone,et al.  SVD-matching using SIFT features , 2006, Graph. Model..

[11]  Geoffrey McLennan,et al.  Three-dimensional path planning for virtual bronchoscopy , 2004, IEEE Transactions on Medical Imaging.

[12]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[13]  Darius Burschka,et al.  Scale-Invariant Registration of Monocular Endoscopic Images to CT-Scans for Sinus Surgery , 2004, MICCAI.

[14]  Daniel Mirota,et al.  Robust motion estimation and structure recovery from endoscopic image sequences with an Adaptive Scale Kernel Consensus estimator , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Hans-Hellmut Nagel,et al.  Analytical results on error sensitivity of motion estimation from two views , 1990, Image Vis. Comput..

[16]  T. Banchoff,et al.  Differential Geometry of Curves and Surfaces , 2010 .

[17]  Sugaya Yasuyuki,et al.  High Accuracy Fundamental Matrix Computation and Its Performance Evaluation , 2006 .

[18]  Frank Chongwoo Park,et al.  Robot sensor calibration: solving AX=XB on the Euclidean group , 1994, IEEE Trans. Robotics Autom..

[19]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .