An Improved Motion Image Optical Flow Algorithm

Abstract

We proposed an improved motion image optical flow method which can artificially adjust and select the threshold value according to the reality condition and different position of the image .Using traditional method,such as Horn-Schunck’s optical flow estimation algorithm,will possibly lead to the problem of losing edge information or obtaining unsmooth optical flow field, when weight coefficient is too big or too small at the same time. The experimental results show that the motion image and its edge are more clear and the value of PSNR and RMSE have been all improved by using the improved algorithm, moreover the improved algorithm will not increase more computation complexity.