Automatic Selection of Control Points for Remote Sensing Image Registration Based on MultiScale SIFT

In this paper, we present an automated image registration algorithm, which combines the multi-scale wavelet transform (WT) with Scale Invariant Feature Transform (SIFT). The control points are selected using three levels WT. First, the image is decomposed into multi-scale levels using WT, then low frequency (approximation) images are input to SIFT algorithm for automatically obtaining control points. Experimental results show the efficiency and the accuracy of the proposed technique for selecting enough and correct control points.

[1]  Ardeshir Goshtasby,et al.  A Region-Based Approach to Digital Image Registration with Subpixel Accuracy , 1986, IEEE Transactions on Geoscience and Remote Sensing.

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

[3]  Jie Tian,et al.  Rapid Multi-modality preRegistration based on SIFT descriptor , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Andrew Zisserman,et al.  Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?" , 2002, ECCV.

[5]  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..

[6]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[7]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[8]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[9]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Martial Hebert,et al.  Efficient multiple model recognition in cluttered 3-D scenes , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[11]  Leila Maria Garcia Fonseca,et al.  Automatic registration and mosaicking system for remotely sensed imagery , 2003, SPIE Remote Sensing.