Registration of Multispectral Satellite Images with Orientation-Restricted SIFT

被引：36

作者：

Vural, Mehmet Firat

Yardimci, Yasemin

Temizel, Alptekin

机构：

来源：

2009 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-5 | 2009年

关键词：

D O I：

10.1109/IGARSS.2009.5417801

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

In this study, a modified version of the popular SIFT algorithm is introduced. The algorithm is robust to nonlinear intensity changes between images which makes it a strong candidate for multispectral image registration. The proposed Orientation Restricted SIFT algorithm combines the SIFT descriptor vector elements in opposite directions In this way, better feature matching performance is achieved with shorter descriptor vectors which translate into shorter matching complexity The effect of scale restriction and contrast stretching is demonstrated on multispectral satellite images and scale restriction is found to be useful in eliminating incorrectly matched features.

引用

页码：1545 / 1548

页数：4

共 14 条

[1]

[Anonymous], 1994, J APPL STAT, DOI DOI 10.1080/757582976

[2]

[Anonymous], 2003, IMAGE VISION COMPUTI

[3]

Anuta P.E., 1970, IEEE Transactions on Geoscience Electronics, V8, P353, DOI [10.1109/tge.1970.271435, 10.1109/TGE.1970.271435, DOI 10.1109/TGE.1970.271435]

[4]

BEIS J, 1997, IEEE COMP SOC C COMP

[5]

BROWN M., 2002, BRIT MACHINE VISION, P656, DOI DOI 10.5244/C.16.23

[6]

CHEN J, 2006, EMBS ANN INT C NEW Y

[7]

FLUSSER J, 1994, IEEE T GEOSCIENCE RE, V32

[8]

HONG G, 2005, IEEE SPRS 3 INT S RE

[9]

LIU J, 2008, OPTICAL ENG, V47, DOI DOI 10.1117/12969121

[10]

Lowe David G., 1999, P 7 IEEE INT C COMP

← 1 2 →