rgrl : Rensselaer (Generalized) Registration Library
The library is designed as a set of techniques to allow realization of a variety of correspondence-based registration algorithms.
Components of the framework include initializers, feature sets, correspondence generators, robust transformation estimators, and convergence testers. Multiple feature types may be used either simultaneously or sequentially, and multiresolution is handled naturally.
- the engine that represent the framework
- basic primitives of correspondence-based registration
- pre-computed or constructed dynamically
- a collection of features
- with representations suitable for spatial queries such as finding the nearest neighbors
- method to generate the initial transformation
- generating correspondences from the two image feature sets.
- estimating the spatial relationship that maps the moving image to the fixed image using the matches
- transformation parameters stored in the rgrl_transformation of the same model
class rgrl_scale_estimator and rgrl_weighter
- for robust transformation estimation in the presence of outliers/mis-matches
- testing whether the estimation has converged to a stable solution or is oscillating.