Novel 3D Back Reconstruction using Stereo Digital Cameras

• Author / Creator

  Kumar, Anish

• This thesis presents the research and development of a novel procedure for creating a 3D image of the back using stereo digital 2D images. The procedure requires minimal user input and is intuitive. The procedure is comprised of 3 stages – image data acquisition, image registration and image reconstruction. Back Image data was acquired using automated template matching of a pegboard in a unique stereo camera configuration that improves speed over existing processes. To improve the registration process, a new approach combining image segmentation and differential geometry with belief propagation was developed. Stray data points were removed in the 3D Back image reconstruction process and missing data points were interpolated using a unique method of Moving Least Squares – Bezier Curve. The procedure was tested on human subjects. The results demonstrate that the procedure can be used clinically to obtain 3D back images for the evaluation of scoliosis.

• Subjects / Keywords

  • Stereo Registration
  • Moving Least Squares
  • Differential Geometry
  • Stereo Imaging
  • Belief Propagation
  • Computer Vision
  • Scoliosis
  • 3D Reconstruction
  • Back
  • Bezier Curves
  • Stereo Camera setup

• Graduation date

  Fall 2011

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/R3MX3W

• License

  This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.