基于线性不变矩的特征图象配准算法研究(英文)

Feature-based Image Registration Algorithm Using Invariant Line Moments

针对图象差异较大的光学图象与合成孔径雷达图象 (SAR)的特点 ,设计了一种基于特征的图象配准的算法 ,包括特征提取、匹配、控制点选取、变换系数计算和误差计算等步骤 在特征提取中 ,对于雷达图象需要进行预处理并采用LOG提取图象轮廓 在匹配算法中 ,以线性不变矩作为特征量 ,对现有基于图象轮廓特征的匹配算法进行了改进 采用上海浦东地区的Radarsat 1S2模式图象与LandsatTM 5波段图象作为待配准图象 实验结果表明 ,该方法可以较好地完成光学图象与SAR图象的配准 。

A practical feature based approach for multi sensor image registration is presented. The characteristic of this approach is that it uses an invariant line moment (ILM) shape descriptor to establish correspondences between the potentially matched contours detected from the two images. The steps of the approach include feature extraction, contours matching, control points extraction and transformation parameters estimation. In feature extraction, the performance of the Laplacian of Gaussian operators is improved. After the detected edge points are refined and sorted, contour correspondences are performed by an image matching algorithm developed in this research. Experimental results on Radarsat -1 and Landsat TM 5 images indicate that this approach is quite robust in matching the multi sensor satellite images.