Multi-sensor image registration by combination of Relaxation Optimization matching and Partitioning RANSAC

DOI

10.2991/icsem.2013.191How to use a DOI?

Keywords

multi-sensor, image registration, relaxation optimization, RANSAC

Abstract

This paper presents a multi-sensor image registration method by combination of relaxation optimization matching and Partitioning RANSAC. Firstly, the global coarse registration is performed to establish the approximate relationship of reference and slave image. Secondly, in each pyramid level, the normalized MI and relaxation optimization technique are adopted to get the matching points, and partitioning RANSAC is used to delete the existing false matches. The coarse-to-fine strategy is integrated to refine the results, and finally the rubber sheeting method is used to realize the image registration. Two datasets have been experimented, and it can be found that satisfactory registration method can be obtained.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yingdan Wu
AU  - Yang Ming
PY  - 2013/04
DA  - 2013/04
TI  - Multi-sensor image registration by combination of Relaxation Optimization matching and Partitioning RANSAC
BT  - Proceedings of the 2nd International Conference On Systems Engineering and Modeling (ICSEM 2013)
PB  - Atlantis Press
SP  - 917
EP  - 920
SN  - 1951-6851
UR  - https://doi.org/10.2991/icsem.2013.191
DO  - 10.2991/icsem.2013.191
ID  - Wu2013/04
ER  -