wu_thesis - 3D Reconstruction of Anatomical Structures from...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 3D Reconstruction of Anatomical Structures from Endoscopic Images Chenyu Wu CMU-RI-TR-10-04 Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Robotics The Robotics Institute Carnegie Mellon University Pittsburgh, Pennsylvania 15213 01/2010 Thesis Committee Branislav Jaramaz (Co-chair) Srinivasa Narasimhan (Co-chair) Yanxi Liu Ko Nishino (Drexel University) Copyright c 2010 by Chenyu Wu. All rights reserved. This thesis is dedicated to my father who taught me to use what I have learned to help people, It is also dedicated to my mother who taught me that if I make a wish and work hard, it will come true. Finally this thesis is dedicated to my grandmothers who taught me to be brave and patient and to my beloved grandfather who moved to heaven last month. iv Abstract Endoscopy is attracting increasing attention for its role in minimally inva- sive, computer-assisted and tele-surgery. Analyzing images from endoscopes to obtain meaningful information about anatomical structures such as their 3D shapes, deformations and appearances, is crucial to such surgical applications. However, 3D reconstruction of bones from endoscopic images is challenging due to the small field of view of the endoscope, large image distortion, fea- tureless surfaces and occlusion by blood and particles. In this thesis, a novel methodology is developed for accurate 3D bone reconstruction from endo- scopic images, by exploiting and enhancing computer vision techniques such as shape from shading, tracking and statistical modeling. We first designed a complete calibration scheme to estimate both geomet- ric and photometric parameters including the rotation angle, light intensity and light sources’ spatial distribution. This is crucial to our further analysis of endoscopic images. A solution is presented to reconstruct the Lambertian sur- face of bones using a sequence of overlapped endoscopic images, where only partial boundaries are visible in each image. We extend the classical shape- from-shading approach to deal with perspective projection and near point light sources that are not co-located with the camera center. Then, by tracking the endoscope, the complete occluding boundary of the bone is obtained by align- ing the partial boundaries from different images. A complete and consistent shape is obtained by simultaneously growing the surface normals and depths in all views. Finally, in order to deal with over-smoothness and occlusions, we employ a statistical atlas to constrain and refine the multi-view shape from shading. A two-level framework is also developed for efficient atlas construc- tion. vi Acknowledgments First and foremost I am heartily thankful to my advisor, Branislav Jaramaz, whose encour- agement, guidance and support from the initial to the final level enabled me to develop an understanding of the subject. This thesis would not have been possible without his insight into this field and continuous advice on problem formulations. He has made available hisinto this field and continuous advice on problem formulations....
View Full Document

This note was uploaded on 05/15/2011 for the course ECON 1100 taught by Professor Dun during the Spring '11 term at Al Fateh University.

Page1 / 131

wu_thesis - 3D Reconstruction of Anatomical Structures from...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online