A Spatial-Feature-Enhanced MMI Algorithm for Multimodal Airborne Image Registration

被引：34

作者：

Fan, Xiaofeng ^{[1
]}

Rhody, Harvey ^{[1
]}

Saber, Eli ^{[2
]}

机构：

[1] Rochester Inst Technol, Dept Image Sci, Rochester, NY 14623 USA

[2] Rochester Inst Technol, Dept Elect Engn, Rochester, NY 14623 USA

来源：

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2010年 / 48卷 / 06期

基金：

美国国家航空航天局;

关键词：

Harris corner detector; maximization of mutual information (MMI); multimodal image registration; MUTUAL-INFORMATION;

D O I：

10.1109/TGRS.2010.2040390

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

Maximization of mutual information (MI) (MMI) has a wide application in multimodal image registration. The conventional MMI algorithm is based on the statistics derived from image sampling and does not use spatial features. In this paper, we proposed an improved MMI registration algorithm that combines the spatial information through a feature-based selection mechanism. A Harris corner filter is chosen to classify the pixels. The classification results are used to focus sample selection, joint entropy estimation, and weighted MI information calculation. Although features play an important role, conventional feature matching is not used, which removes an important challenge to the use of feature-based information. The advantages of the proposed algorithm are improved robustness by incorporation of spatial features and significant reduction in computing time for registration. Experiments with challenging synthetic images and multimodal airborne infrared images are provided to demonstrate the improvement.

引用

页码：2580 / 2589

页数：10

共 37 条

[11]

Ehlers M., 1992, INTRO WAVELETS

[12]

FAN X, 2006, P W NEW YORK IM PROC

[13]

FAN X, 2005, P IEEE AIPR ANN WORK, P86

[14]

Gan R, 2005, LECT NOTES COMPUT SC, V3565, P210

[15] A REGION-BASED APPROACH TO DIGITAL IMAGE REGISTRATION WITH SUBPIXEL ACCURACY [J].

GOSHTASBY, A ;

STOCKMAN, GC ;

PAGE, CV .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1986, 24 (03) :390-400

[16] Band, selection for hyperspectral image classification using mutual information [J].

Guo, Baofeng ;

Gunn, Steve R. ;

Damper, R. I. ;

Nelson, J. D. B. .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2006, 3 (04) :522-526

[17]

Harris C, 1988, ALVEY VISION C, V15, P10, DOI DOI 10.5244/C.2.23

[18]

Holden M, 2004, LECT NOTES COMPUT SC, V3216, P797

[19]

Holm M., 1991, P INT GEOSCIENCE REM, P2439

[20] Robust multispectral image registration using mutual-information models [J].

Kern, Jeffrey P. ;

Pattichis, Marios S. .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (05) :1494-1505

← 1 2 3 4 →