Abstract

A technique to construct an affine invariant descriptor for remote-sensing image registration based on the scale invariant features transform (SIFT) in a kernel space is proposed. Affine invariant SIFT descriptor is first developed in an elliptical region determined by the Hessian matrix of the feature points. Thereafter, the descriptor is mapped to a feature space induced by a kernel, and a new descriptor is constructed by whitening the mapped descriptor in the feature space, with the transform called KW-SIFT. In a final step, the new descriptor is used to register remote-sensing images. Experimental results for remote-sensing image registration indicate that the proposed method improves the registration performance as compared with other related methods.

© 2011 Chinese Optics Letters

Remote sensing image registration approach based on a retrofitted SIFT algorithm and Lissajous-curve trajectories

Zhi-li Song, Sheng Li, and Thomas F. George
Opt. Express 18(2) 513-522 (2010)

Nonrigid registration of remote sensing images via sparse and dense feature matching

Jun Chen, Linbo Luo, Chengyin Liu, Jin-Gang Yu, and Jiayi Ma
J. Opt. Soc. Am. A 33(7) 1313-1322 (2016)

Image registration method for multimodal images

Wang Bingjian, Lu Quan, Li Yapeng, Li Fan, Bai Liping, Lu Gang, and Lai Rui
Appl. Opt. 50(13) 1861-1867 (2011)

Dynamic descriptors for contextual classification of remotely sensed hyperspectral image data analysis

Wun C. Chiou
Appl. Opt. 23(21) 3889-3892 (1984)

Multi-sensor image registration based on algebraic projective invariants

Bin Li, Wei Wang, and Hao Ye
Opt. Express 21(8) 9824-9838 (2013)