A multiscale region-based approach to automatic SAR image registration using CLPSO

In this paper, a novel approach to automatic SAR image registration is proposed. First, the bi-temporal images are decomposed by wavelet transform. Then, the sensed image and its wavelet approximation component are divided to some saliency region based on spectrum residua approach. And the saliency regions are fitted into ellipses. Finally, the region matching is performed by searching the corresponding regions in the reference image at every layer by the comprehensive learning particle swarm optimization (CLPSO) twice. Thus, the registration in every layer is a coarse-to-fine process, which effectively improves the efficiency, accuracy and stability. The proposed technique is validated by testing on real SAR images and compared with existing state-of-the-art techniques.

[1]  V. Mani,et al.  Multiobjective Discrete Particle Swarm Optimization for Multisensor Image Alignment , 2013, IEEE Geoscience and Remote Sensing Letters.

[2]  Su Yang,et al.  Image matching based on orientation-magnitude histograms and global consistency , 2012, Pattern Recognit..

[3]  Peihua Qiu,et al.  Intensity-Based Image Registration by Nonparametric Local Smoothing , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[5]  Liqing Zhang,et al.  Saliency Detection: A Spectral Residual Approach , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  A. Ardeshir Goshtasby,et al.  2-D and 3-D Image Registration: for Medical, Remote Sensing, and Industrial Applications , 2005 .

[7]  Geeta Varadan,et al.  A generalized search scheme for automatic registration of remote-sensing data , 2012 .

[8]  Mahua Bhattacharya,et al.  Affine-based registration of CT and MR modality images of human brain using multiresolution approaches: comparative study on genetic algorithm and particle swarm optimization , 2010, Neural Computing and Applications.

[9]  Jing J. Liang,et al.  Comprehensive learning particle swarm optimizer for global optimization of multimodal functions , 2006, IEEE Transactions on Evolutionary Computation.

[10]  Luís Corte-Real,et al.  HAIRIS: A Method for Automatic Image Registration Through Histogram-Based Image Segmentation , 2011, IEEE Transactions on Image Processing.