Share Email Print
cover

Proceedings Paper

Automatic remote sensing imagery registration based on improved SIFT
Author(s): Huawei Li; Chongguang Zhu; Fengping Di
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

With the rapid development of remote sensing technology and the current diversity of new sensors, we can get more and more multi-source remote sensing data in the same area. It is the key to match those remote sensing data in wide application. And most current methods of registering remote sensing imagery require human involvement, so, there is a need for automated techniques in the remote sensing area. Especially the multi-source and multi-temporal remote sensing data call for new demands for automated techniques. In this paper, the authors proposed a feature matching approach based on improved SIFT (Scale Invariant Feature Transform) for remote sensing imagery registration. In this method, the feature mainly is the specific characteristic of the remote sensing imagery. The experiment results using this automatic remote sensing registration method indicate that the improved descriptors are more distinctive and robust, which results in a higher matching performance and a better matching efficiency.

Paper Details

Date Published: 14 November 2007
PDF: 6 pages
Proc. SPIE 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications, 679037 (14 November 2007); doi: 10.1117/12.774762
Show Author Affiliations
Huawei Li, Institute of Remote Sensing Applications (China)
Chongguang Zhu, Institute of Remote Sensing Applications (China)
Fengping Di, Institute of Remote Sensing Applications (China)


Published in SPIE Proceedings Vol. 6790:
MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications

© SPIE. Terms of Use
Back to Top