基于TMS320C6416T平台的特征角点图像配准算法

A New Corner Points Image Registration Algorithm Based on TMS320C6416T

提出了一种新的图像配准算法,可以较好地解决图像配准中的平移、旋转和缩放问题。算法首先使用SUSAN算子提取两幅图像的特征角点,然后使用对数极坐标变换和投影相关匹配算法实现特征点匹配。针对算法的特点,设计了以高性能数字信号处理器TMS320C6416T为核心的硬件处理平台。实验结果表明:系统工作稳定,算法配准精度较高。

A new algorithm about image registration is presented, which can solve translations, rotations and scale transformations problems in image registration process. The proposed algorithm is as follows： SUSAN algorithm used to obtain the feature corner points （interesting points） of the two images; log-polar transformation and projection correlation matching algorithm used to acquire the registration parameter of the two images. In connection with the algorithmic characteristic, the hardware platform was designed by using high-performance digital signal processor TMS320C6416T as the core. The experiment results show that the system is stable and the algorithm is effective.