Fusion of Multiple Polarimetric SAR Images Using Nonsubsampled Contourlet Transform
Nonsubsampled Contourlet Transform (NSCT) is a new improved multiresolution geometry analysis technique based on Contourlet Transform. NSCT can represent images more effectively because of its flexible multi-scale, multi direction and shift invariance. In this paper, a method of fusing multi-polarization SAR images based on NSCT was proposed. The images were firstly decomposed by NSCT, and then different fusion rules were chosen according to the particular sets of NSCT coefficients. A weighted averaging method was adopted for low frequency subband fusion. For the fusion of high frequency directional subband images, optimal weighted sum algorithm of region intensities was performed. Finally, the fused image is obtained by applying the inverse NSCT. Experiments show that the proposed algorithm can perform better than Daubechies 4 wavelet transform (DWT) method, and both show better than without fusion, in terms of the visual quality and the improved spatial information.
Nonsubsampled Contourlet transform Image fusion Polarimetric SAR
Xiaoxia Sun Jixian Zhang Qin Yan Jingxiang Gao
China University of Mining and Technology, Xuzhou, China Chinese Acddemy of Saweying and Mapping, Be Chinese Acddemy of Saweying and Mapping, Beijing, China China University of Mining and Technology, Xuzhou, China
国际会议
成都
英文
1810-1813
2010-12-17（万方平台首次上网日期，不代表论文的发表时间）