TY - GEN
T1 - A MRF approach to optical flow estimation
AU - Vlontzos, J. A.
AU - Geiger, D.
PY - 1992
Y1 - 1992
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84997280601&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84997280601&partnerID=8YFLogxK
U2 - 10.1109/CVPR.1992.223240
DO - 10.1109/CVPR.1992.223240
M3 - Conference contribution
AN - SCOPUS:84997280601
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 853
EP - 856
BT - Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PB - IEEE Computer Society
T2 - 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992
Y2 - 15 June 1992 through 18 June 1992
ER -