Markov random fields and block matching for multiresolution motion estimation

Remy Leconge; Olivier Laligant; Frederic Truchetet

doi:10.1117/12.378876

Translator Disclaimer

29 February 2000 Markov random fields and block matching for multiresolution motion estimation

Remy Leconge, Olivier Laligant, Frederic Truchetet

Author Affiliations +

Proceedings Volume 3968, High-Speed Imaging and Sequence Analysis II; (2000) https://doi.org/10.1117/12.378876
Event: Electronic Imaging, 2000, San Jose, CA, United States

Abstract

For medical application, we are interested in estimation of optical flow on the face and particularly on area around the eyes. Among the methods of optical flow estimation, gradient estimation and block matching are the main ones. However the gradient based approach can only be applied for small displacement. Generally the process of block matching gives only good result if the searching strategy is judiciously selected. Our approach is based on a Markov random field model combined with an algorithm of block matching in a multiresolution scheme. The multiresolution approach leads to detect a large range of displacement amplitude. The large displacements are detected on the coarse scales and the small ones will be detected successively on finer scales in a coarse scales and the small ones will be detected successively on finer scales. The tracking of motion is achieved by a block matching algorithm. This method gives the otpical flow whatever the amplitude of the motion is, if included in the range defined by the multiresolution approach. The result show clearly the complementary of Markov random fields estimation and block matching across the scales.

Citation Download Citation

Remy Leconge, Olivier Laligant, and Frederic Truchetet "Markov random fields and block matching for multiresolution motion estimation", Proc. SPIE 3968, High-Speed Imaging and Sequence Analysis II, (29 February 2000); https://doi.org/10.1117/12.378876

ACCESS THE FULL ARTICLE