Comparative analysis in satellite image Registration

This paper proposes a comparative study and analysis in satellite image Registration. Image registration techniques are aimed to improve the geometrical consistency of satellite images. This technique can be employed for the detection of changes in images. We are analyzing Point based, Edge based and Contour based image registration techniques. In the first method control points are selected manually and registration is performed using cross correlation. Edge based image registration emphasized on corner features. Two pairs of optimal matching corners were selected from matched corners as control points and transformation is applied. In contour based approach contour points are extracted from image and based on the contour points image registration is performed. Finally localization error and matching error is calculated and analyzed.

[1]  Victor J. D. Tsai,et al.  Automated image mosaicking , 2005 .

[2]  B. S. Manjunath,et al.  An axiomatic approach to corner detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  Amara Lynn Graps,et al.  An introduction to wavelets , 1995 .

[4]  L. Meddeber,et al.  An automatic registration and mosaicking system based on contour features and wavelet transform for remote sensing images , 2009, 2009 3rd International Conference on Signals, Circuits and Systems (SCS).

[5]  Leila Maria Garcia Fonseca,et al.  Control point assessment for image registration , 1999, XII Brazilian Symposium on Computer Graphics and Image Processing (Cat. No.PR00481).

[6]  Peijun Du,et al.  Image registration based on corner detection and affine transformation , 2010, 2010 3rd International Congress on Image and Signal Processing.

[7]  Qi Zeng,et al.  Image registration method based on improved Harris corner detector , 2010 .

[8]  Karsten Jacobsen,et al.  Handling of Large Block of High Resolution Space Images , 2006 .

[9]  Chien-Liang Liu,et al.  DEM-Aided Block Adjustment for Satellite Images With Weak Convergence Geometry , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[11]  Ferran Marqués,et al.  Automatic satellite image georeferencing using a contour-matching approach , 2003, IEEE Trans. Geosci. Remote. Sens..

[12]  A. Ardeshir Goshtasby,et al.  Volume image registration by template matching , 2001, Image Vis. Comput..

[13]  B. S. Manjunath,et al.  Registration Techniques for Multisensor Remotely Sensed Imagery , 1996 .