An Efficient SIFT-Based Mode-Seeking Algorithm for Sub-Pixel Registration of Remotely Sensed Images

Several image registration methods, based on the scaled-invariant feature transform (SIFT) technique, have appeared recently in the remote sensing literature. All of these methods attempt to overcome problems encountered by SIFT in multimodal remotely sensed imagery, in terms of the quality of its feature correspondences. The deterministic method presented in this letter exploits the fact that each SIFT feature is associated with a scale, orientation, and position to perform mode seeking (in transformation space) to eliminate outlying corresponding key points (i.e, features) and improve the overall match obtained. We also present an exhaustive empirical study on a variety of test cases, which demonstrates that our method is highly accurate and rather fast. The algorithm is capable of automatically detecting whether it succeeded or failed.

[1]  David M. Mount,et al.  New approaches to robust, point-based image registration , 2011, Image Registration for Remote Sensing.

[2]  Mark R. Pickering,et al.  Modified SIFT for multi-modal remote sensing image registration , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[3]  Mark R. Pickering,et al.  Multi-spectral remote sensing image registration via spatial relationship analysis on sift keypoints , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[4]  Nathan S. Netanyahu,et al.  Georegistration of Landsat data via robust matching of multiresolution features , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Amin Sedaghat,et al.  Uniform Robust Scale-Invariant Feature Matching for Optical Remote Sensing Images , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Tianfu Wang,et al.  Multispectral Image Matching Using Rotation-Invariant Distance , 2011, IEEE Geoscience and Remote Sensing Letters.

[7]  Yasemin Yardımcı,et al.  High-resolution multispectral satellite image matching using scale invariant feature transform and speeded up robust features , 2011 .

[8]  Guoyou Wang,et al.  Robust Scale-Invariant Feature Matching for Remote Sensing Image Registration , 2009, IEEE Geoscience and Remote Sensing Letters.

[9]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[10]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .