Fast Stereo Matching Using Adaptive Window
Zhou Xiu · Chinese Journal of Computers · 2006
It is crucial to choose an appropriate window size for area-based stereo matching.A method that only use gray information to decide the window size is presented in this paper,which improves the approach using local gray and disparity variation to select window size.On the premise of a sure find of an optimal window size,this method can easily make use of integral image to speed up matching computation,so the calculation is independent of the window size.The proposed method is tested with the international standard image data and compared with some other methods.The experimental results show that its performance is the best among local matching methods,although worse than some excellent global-optimal approaches,its complexity is much lower than them.