Registration of remote sensing images based on the relevance vector machine

Authors:
Xiaofei Wang;Junping Zhang;Ye Zhang
Affiliations:
Department of Information Engineering, Harbin Institute of Technology, Harbin and College of Electronic Engineering, Heilongjiang University, Harbin;Department of Information Engineering, Harbin Institute of Technology, Harbin;Department of Information Engineering, Harbin Institute of Technology, Harbin
Venue:
ICNC'09 Proceedings of the 5th international conference on Natural computation
Year:
2009

Citing 4
Cited 0

Registration of 3-D images by genetic optimization

Pattern Recognition Letters - Special issue on genetic algorithms
Alignment Using Distributions of Local Geometric Properties

IEEE Transactions on Pattern Analysis and Machine Intelligence
ICP Registration Using Invariant Features

IEEE Transactions on Pattern Analysis and Machine Intelligence
Sparse bayesian learning and the relevance vector machine

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

Remote sensing has become a technique of indispensable importance for us to acquire the information on the ground. In the process of imaging, geometric distortion occurs due to several factors, which causes many difficulties when using those remote images for change detection, information fusion, resolution enhancement and so on. So the image registration is necessary. Aiming at the distortion type for the selection of geometric transformation model in the registration process, a relevance vector machine (RVM) based geometric transformation model is given, which will solve the problem of nonlinear geometric distortion efficiently as well as avoiding the shortcomings in the traditional model. Experiments have been realized this method.