A registration and fusion method for multisensor image with different resolution

In this article a registration method based on feature area is proposed. With the method, the problem of image fusion for multisensor with different resolution can be solved. First, the source images are interpolated to the same resolution. The feature area is obtained, the contours of feature area and normal area can be obtained. An image registration approach based on edge-correlation is used to get the registered images. Then, atrous algorithm is used to obtain the fusion image. The method proposed is automated and available. Experiments using actual image are presented

[1]  Siamak Khorram,et al.  A feature-based image registration algorithm using improved chain-code representation combined with invariant moments , 1999, IEEE Trans. Geosci. Remote. Sens..

[2]  M. Hadhoud,et al.  Adaptive image interpolation based on local activity levels , 2003, Proceedings of the Twentieth National Radio Science Conference (NRSC'2003) (IEEE Cat. No.03EX665).

[3]  Xavier Otazu,et al.  Multiresolution-based image fusion with additive wavelet decomposition , 1999, IEEE Trans. Geosci. Remote. Sens..

[4]  Giovanni Ramponi,et al.  Warped distance for space-variant linear image interpolation , 1999, IEEE Trans. Image Process..

[5]  Hui.  A Contour-Based Approach to Multisensor Image Registration , 1995 .

[6]  A. Trous,et al.  The Discrete Wavelet Transform: Wedding the . , 1992 .