Difference between revisions of "Projects:PointSetRigidRegistration"
| Line 8: | Line 8: | ||
Typically, registration algorithms compute the transformations paramaters by maximizing a metric given an estimate of the correspondence between points across the two sets of interest. This can be viewed as a posterior estimation problem problem, in which the corresponding distribution can naturally be estimated using a particle filter. In this work, we treat motion as a local variation in the pose parameters obatined from running a few iterations of the standard Iterative Closest Point (ICP) algorithm. Employing this idea, we introduce stochastic motion dynamics to widen the narrow band of convergence as well as provide a dynamical model of uncertainity. This is described in the following figure. | Typically, registration algorithms compute the transformations paramaters by maximizing a metric given an estimate of the correspondence between points across the two sets of interest. This can be viewed as a posterior estimation problem problem, in which the corresponding distribution can naturally be estimated using a particle filter. In this work, we treat motion as a local variation in the pose parameters obatined from running a few iterations of the standard Iterative Closest Point (ICP) algorithm. Employing this idea, we introduce stochastic motion dynamics to widen the narrow band of convergence as well as provide a dynamical model of uncertainity. This is described in the following figure. | ||
| − | + | [[StochasticDynamics_Translation.png]] | |
In contrast with other techniques, our approach requires no annealing schedule, which results in a reduction in computational complexity as well as maintains the temoral coherency of the state (no loss of information). Also, unlike most alternative approaches for point set registration, we make no geometric assumptions on the two data sets. | In contrast with other techniques, our approach requires no annealing schedule, which results in a reduction in computational complexity as well as maintains the temoral coherency of the state (no loss of information). Also, unlike most alternative approaches for point set registration, we make no geometric assumptions on the two data sets. | ||
Revision as of 23:09, 27 April 2008
Home < Projects:PointSetRigidRegistrationBack to NA-MIC Collaborations, Georgia Tech Algorithms
Particle Filtering with Stochastic Dynamics for Point Set Registration
We propose a particle filtering scheme for the registration of 2D and 3D point set undergoing a rigid body transformation. Moreover, we incorporate stochastic dynamics to model the uncertainity of the registration process.
Description
Typically, registration algorithms compute the transformations paramaters by maximizing a metric given an estimate of the correspondence between points across the two sets of interest. This can be viewed as a posterior estimation problem problem, in which the corresponding distribution can naturally be estimated using a particle filter. In this work, we treat motion as a local variation in the pose parameters obatined from running a few iterations of the standard Iterative Closest Point (ICP) algorithm. Employing this idea, we introduce stochastic motion dynamics to widen the narrow band of convergence as well as provide a dynamical model of uncertainity. This is described in the following figure.
StochasticDynamics_Translation.png
In contrast with other techniques, our approach requires no annealing schedule, which results in a reduction in computational complexity as well as maintains the temoral coherency of the state (no loss of information). Also, unlike most alternative approaches for point set registration, we make no geometric assumptions on the two data sets.
Project Status
Key Investigators
- Georgia Tech: Romeil Sandhu, Samuel Dambreville, Allen Tannenbaum
Publications
In press
- R. Sandhu, S. Dambreville, A. Tannenbaum. Particle Filtering for Registration of 2D and 3D Point Sets with Stochastic Dynamics. In CVPR, 2008.
