桥梁配准方法的研究与实现

Research and Implementation of Bridge Registration

以全色、多光谱图像中的桥梁目标为研究对象,采用具有尺度不变特征的SIFT算法,对图像进行特征点的提取与匹配,利用Delaunay三角网格对两幅图像特征点进行修正,通过投影变换将两幅图像变换到同一坐标系下进行配准,并利用均方根误差和相关系数进行配准评价;实验结果表明该方法可以减少图像的配准时间,配准精度达到亚像素级。

Bridges in panchromatic and multi--spectral images are studied. Firstly a scale--invariant feature extracting algorithm SIFT is used for feature extraction and matching. Secondly amend feature points of two images by Delaunay triangulation, project two images to the same coordinate, then register. The registration results are evaluated by the root mean square error and correlation coefficient. Experimental results show that the improved image matching algorithm can reduce registration time, and registration accuracy can reach sub--pixel.