| description |
We present a new approach to the problem of matching 3D curves . The
approach has an algorithmic complexity sublinear with the number of
models, and can operate in the presence of noise and partial occlusions .
Our method buids upon the seminal work of [27, 28], where curves are
first smoothed using B-splines, with matching based on hashing using
curvature and torsion measures . However, we introduce two enhancements
* Ce travail a été en partie financé par Digital Equipment Corporation .We present a new approach to the problem of matching 3D curves . The
approach has an algorithmic complexity sublinear with the number of
models, and can operate in the presence of noise and partial occlusions .
Our method buids upon the seminal work of [27, 28], where curves are
first smoothed using B-splines, with matching based on hashing using
curvature and torsion measures . However, we introduce two enhancements
* Ce travail a été en partie financé par Digital Equipment Corporation . We present a new approach to the problem of matching 3D curves . The
approach has an algorithmic complexity sublinear with the number of
models, and can operate in the presence of noise and partial occlusions .
Our method buids upon the seminal work of [27, 28], where curves are
first smoothed using B-splines, with matching based on hashing using
curvature and torsion measures . However, we introduce two enhancements
* Ce travail a été en partie financé par Digital Equipment Corporation . we make use of non-uniform B-spline approximations, which permits us
to better retain information at high curvature locations . The spline
approximations are controlled (i.e ., regularized) by making use of normal
vectors to the surface in 3-D on which the curves lie, and by an explicit
minimization of a bending energy . These measures allow a more accurate
estimation of position, curvatue, torsion and Frénet frames along the
curve ; • the computational complexity of the recognition process is considerably
decreased with explicit use of the Frénet frame for hypotheses generation .
As opposed to previous approaches, the method better copes with partial
occlusion . Moreover, following a statistical study of the curvature and
torsion covariances, we optimize the hash table discretization and
discover improved invariants for recognition, différent than the torsion
measure. Finally, knowledge of invariant uncertainties is used to compute
an optimal global transformation using an extended Kalman filter . We present experimental results using synthetic data and also using
characteristic curves extracted front 3D medical images .
|