基于小波分析的可见光图像自动配准方法研究

Research on Automated Image Registration Technique for Visual Image Based on Wavelet Analysis

研究了一种快速、准确、抗噪的可见光图像自动配准方法。首先用小波分析技术提取两幅图像的特征点， 然后对两幅图像之间的角度差进行补偿， 最后用多层特征点匹配技术完成两幅图像的变换参数的估计。对一定研究领域的可见光图像自动配准的仿真实验表明： 该方法可以比较快速、准确、自动地得到这些图像之间的配准参数， 且对噪声具有一定的适应能力。

To develop a quick,accurate and antinoise automated image registration technique for visual image, the wavelet analysis has been used to extract the feature points in two images followed by the compensation for input image with angle difference between them. A hierarchical feature matching algorithm has been adopted to get the final transforming parameters between the two images. The simulation results for several visual images in some fields show that the method can quickly, accurately and automatically register these images and is antinoise to some extent.