Title :
A MRF approach to optical flow estimation
Author :
Vlontzos, J.A. ; Geiger, D.
Author_Institution :
Siemens Corporate Res. Inc., Princeton, NJ, USA
Abstract :
A Markov random field (MRF) formulation for the problem of optical flow computation is studied. An adaptive window matching scheme is used to obtain a good measure of the correlation between the two images. A confidence measure for each match is also used. Thus, the input to the system is the adaptive correlation and the corresponding confidence. The MRF model is then used to estimate the velocity field and the velocity discontinuities. The problem of occlusions is addressed, and a relationship between occlusions and motion discontinuities is established
Keywords :
Markov processes; image processing; Markov random field; adaptive window matching; optical flow computation; optical flow estimation; velocity field; Adaptive systems; Eigenvalues and eigenfunctions; Image motion analysis; Lighting; Markov random fields; Motion estimation; Noise reduction; Optical computing; Optical imaging; Pixel;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223240
