TY - GEN
T1 - Motion estimation in high resolution image reconstruction from compressed video sequences
AU - Alvarez, L. D.
AU - Molina, Rafael
AU - Katsaggelos, Aggelos K.
PY - 2004
Y1 - 2004
N2 - In order to obtain a high resolution image from a compressed video sequence it is essential to correctly estimate the motion vectors in the sequence. Most of the approaches reported in the literature address this problem using standard motion estimation techniques. In this paper we tackle the correct estimation of the motion vectors by consistently estimating the optical flow across multiple images. Consistency is achieved by adding a regularization term to the classical Lucas-Kanade approach to motion estimation. The proposed algorithm is tested on real video sequences.
AB - In order to obtain a high resolution image from a compressed video sequence it is essential to correctly estimate the motion vectors in the sequence. Most of the approaches reported in the literature address this problem using standard motion estimation techniques. In this paper we tackle the correct estimation of the motion vectors by consistently estimating the optical flow across multiple images. Consistency is achieved by adding a regularization term to the classical Lucas-Kanade approach to motion estimation. The proposed algorithm is tested on real video sequences.
UR - http://www.scopus.com/inward/record.url?scp=20444470275&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=20444470275&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2004.1421423
DO - 10.1109/ICIP.2004.1421423
M3 - Conference contribution
AN - SCOPUS:20444470275
SN - 0780385543
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1795
EP - 1798
BT - 2004 International Conference on Image Processing, ICIP 2004
T2 - 2004 International Conference on Image Processing, ICIP 2004
Y2 - 18 October 2004 through 21 October 2004
ER -