| This describes a method for determining an object's
pose given its 3D model and a 2D view. This 2D-3D registration problem
arises in a number of applications, e.g, image guided spine procedures.
Previous approaches often rely on a good estimate for the initialization
of the pose parameters and an optimization procedure to refine this initial
pose estimation, e.g., the iterative closest point (ICP). However,
such algorithms can falsely indentify local minima, leading to registration
errors if the initial pose is not carefully chosen. The specification
of appropriate initial conditions, however is time consuming. We
propose an approach where sample 2D views are generated from the 3D model
and matched against the given view (2D-2D registration). Additional
views are then generated in the vicinity of the best view and the procedure
is repeated until convergence. Results of estimating the the coordinates
of a vertebrae spine bone from its 3D model, obtained from volumetric (CT
or MR) data, and a 2D view, as might be obtained from flouroscopic data,
demonstrates that the pose can be reliably obtained without requiring extensive
user interface. |
Figure. 1 - Demonstration of 3D-2D projection. |
