System for Automatic Registration of Remote Sensing Images

Dmitry Fedorov, Leila M.G. Fonseca
Division of Image Processing
National Institute for Space Research
12.227-010 Sao Jose dos Campos, Brazil
e-mail: fedorov [at] dpi.inpe.br; leila [at] dpi.inpe.br

Charles Kenney, B.S. Manjunath
Department of Electrical and Computer Engineering
University of California, Santa Barbara, CA, USA.
e-mail: kenney [at] ece.ucsb.edu; manj [at] ece.ucsb.edu

Abstract

Image registration is the process of matching two images so that corresponding coordinate points in the two images correspond to the same physical region of the scene being imaged. It's an important operation needed in remote sensing that basically involves the identification of many control points. As the manual identification of control points may be time-consuming and tedious, automated techniques have been developed. This paper describes a system for automatic registration of satellite images under development at the Division of Image Processing (National Institute for Space Research - INPE) and the Vision Lab (Electrical & Computer Engineering department, UCSB). The system provides tools that allow automatic registration and mosaic of remote sensing images. It is designed to accept different types of data (TM, SPOT, JERS, etc.) and information provided by the user that are used to speed up the processing or avoid mismatched control points. A statistical procedure is used to characterize good and bad registrations. Based on this "good fit-bad fit" statistical testing the user can stop or modify the parameters and continue the processing. Extensive algorithm tests have been performed by registering optical, radar, multi-sensor, high-resolution images and video sequences. We have included very difficult image registration examples in order to show the strengths and limits of our approach. We developed a registration system online demo (http://nayana.ece.ucsb.edu/registration) that contains several examples that can be executed using web browser.
[PDF] [BibTex]
D. Fedorov, L. M. G. Fonseca, C. Kenney, B. S, Manjunath,
IEEE International Geoscience and Remote Sensing Symposium (IGARSS02), Toronto, Canada, Jun. 2002.
Node ID: 376 , DB ID: 174 , Lab: VRL , Target: Proceedings
Subject: [Image Registration and Fusion] « Look up more