By Topic

Remotely Sensed Images Registration Based on Wavelet Transform Using Affine Invariant Moment

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Aiye Shi ; Coll. of Comput. & Inf. Eng., HoHai Univ., Nangjing ; Min Tang ; Fengchen Huang ; Lizhong Xu
more authors

This paper presents an accurate and automatic feature-based method for registration of remotely sensed images.The proposed method uses the redundant wavelet transform to obtain feature points. Firstly, modulus maximum of wavelet coefficients of reference and sensed images are detected based on multi-scale multiplication, respectively. Then, affine invariant moments are calculated using a circular neighborhood area centered on the detected modulus maximum point. After that, corresponding feature points are detected by minimum distance rule with the threshold in the Euclidean space of the invariants. Finally, the transformation parameters are obtained by least square method. Also,the center spline function is used as interpolation function when wrapping the sensed image to reference image. Experiment applying our proposed method on Landsat TM remotely sensed images prove our proposed method effective.

Published in:

Intelligent Information Technology Application, 2008. IITA '08. Second International Symposium on  (Volume:1 )

Date of Conference:

20-22 Dec. 2008