Advertisement
Published in:
2013 | OriginalPaper | Chapter
55. Combining Steerable Pyramid and Gaussian Mixture Models for Multi-Modal Remote Sensing Image Registration
Authors : Peng Ye, Fang Liu
Published in: Emerging Technologies for Information Systems, Computing, and Management
Publisher: Springer New York
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Multi-modal remote sensing image registration is to align images acquired by different sensors and modalities. It is the fundamental step for following image analysis. Previous multi-resolution methods use spatial pyramids to achieve hierarchical registration with little consideration of the characteristics of pyramid transforms or robust point set registration methods after feature detection. Targeting at both problems, this paper proposes a novel image registration method by combining steerable pyramid and Gaussian mixture models. Steerable pyramid has been proved to be shift-invariant and outperforms traditional pyramid transform. Point set registration methods using Gaussian mixture model has been lately proposed and proved to be more robust and accurate than traditional point set registration methods. Experiments on real multi-modal remote sensing image pair demonstrate the feasibility of proposed method.