Title :
Phase-based image motion estimation and registration
Author :
Hemmendorff, Magnus ; Andersson, M.T. ; Knutsson, Hans
Author_Institution :
Dept. of Electr. Eng., Linkoping Univ., Sweden
Abstract :
Conventional gradient methods (optical flow), for motion estimation assume intensity conservation between frames. This assumption is often violated in real applications. The remedy is a novel method that computes constraints on the local motion. These constraint are given on the same form as in conventional methods. Thus, it can directly substitute the gradient method in most applications. Experiments indicate a superior accuracy, even on synthetic images where the intensity conservation assumption is valid. The conventional gradient methods seem obsolete
Keywords :
filtering theory; gradient methods; image registration; image sequences; motion estimation; accuracy; confidence measure; experiments; gradient methods; intensity conservation; local motion constraints; optical flow; phase-based image motion estimation; phase-based image registration; quadrature filter method; synthetic images; Band pass filters; Gradient methods; Image motion analysis; Interference constraints; Motion estimation; Nonlinear optics; Optical filters; Signal analysis; Spatiotemporal phenomena; Tracking;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on
Conference_Location :
Phoenix, AZ
Print_ISBN :
0-7803-5041-3
DOI :
10.1109/ICASSP.1999.757558