This is an old revision of the document!


Iterative Closest Oriented Point Registration (ICOP)

Project Overview

The iterative closest point (ICP) algorithm is a popular method for registering geometric representations of 3D shapes and has been extensively applied to problems of rigid body shape alignment in medical research. ICP-based algorithms seek optimal alignment by iterating two key steps: a correspondence phase that computes closest point pairs and a registration phase that computes the transform to align the point pairs.

To date, ICP variants have relied on point position information for computing shape alignment. We have a developed a new algorithm, namely Iterative Closest Oriented Point (ICOP), which incorporates both position and surface normal information to compute a shape alignment. Position and orientation information for each point are combined in a probabilistic framework and incorporated into both registration and correspondence phases of the algorithm. It is hypothesized that using this richer descriptor set may improve registration accuracy and robustness when orientations are known or may be determined, especially in case of sparsely sampled data.

Project Personnel

  • Seth Billings
  • Emad Boctor
  • Russell Taylor

Funding

  • National Science Foundation, Graduate Research Fellowship Program (NSF GRFP)
  • National Institutes of Health, Individual Graduate Partnership Program (NIH GPP)
  • Gift from Intuitive Surgical
  • Johns Hopkins University Internal Funds

Affiliated labs

Publications

research.imlop.1404689154.txt.gz · Last modified: 2019/08/07 12:05 (external edit)




ERC CISST    LCSR    WSE    JHU