An Improved Optical Flow Method for Image Registration with Large-scale Movements
一种应用于图像配准中大尺度位移估计的改进光流法

In this paper,an improved optical flow method for image registration is proposed.It is novel in the way that it improves the optical flow method with an initial motion estimator:extended phase correlation technique (EPCT),using merits of the latter to compensate deficiencies of the former.In a more detailed manner,it can be said that the optical flow method can reach the sub-pixel accuracy and calculate complex distortion patterns like chirping and tilting but is weak with large-scale movements.Because EPCT covers measurements of large translations and rotations with pixel level accuracy and is efficient in the calculating load,it can be treated as a good initial motion estimator for optical flow method.Tests have proved that this improved method will significantly enhance the registration performance,especially,for images with large-scale movements and robust against random noises.