Abstract
Motion-compensated frame interpolation is required in many applications, e.g. packet-based video transmission error concealment, frame rate up-conversion, etc. One of the most important challenges of temporal interpolation is the accuracy of motion estimation. Several approaches for improving the motion estimation performance are proposed in this paper. Global motion vectors and motion segmentation allow for motion vectors field refinement. Performance of proposed motion-compensated temporal interpolation method is compared with several modern temporal interpolation methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rajala, S., Abdelqadar, I., Bilbro, G., Snyder, W.: Motion estimation optimization. In: Proceedings of IEEE Internernational Conference on Acoustics, Speech and Signal Processing (ICASSP 1992), San Francisco, 23–26 March 1992, pp. 253–256 (1992). doi:10.1109/ICASSP.1992.226203
Veselov, A., Gilmutdinov, M.: Algorithm of motion field optimization for temporal frame interpolation. Informatsionno-upravliaiushchie sistemy 4(71), 25–28 (2014)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell. 26(9), 1124–1137 (2004). doi:10.1109/TPAMI.2004.60
Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with application to image analysis and automated cartography. Commun. Assoc. Comp. Mach. 24, 381–395 (1981)
Haan, G.: Motion estimation and compensation. Ph.D. thesis, Delft University of Technology, 17 September 1992
Huang, A.-M., Nguyen, T.: Correlation-based motion vector processing with adaptive interpolation scheme for motion-compensated frame interpolation. IEEE Trans. Image Process. 18(4), 740–752 (2009)
Veselov A., Gilmutdinov M.: Iterative hierarchical true motion estimation for temlioral frame interliolation. In: IEEE International Worksholi on Multimedia Signal Processing, MMSP (2014)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. B 39(1), 138 (1977)
Weiss, Y., Adelson, E.H.: Perceptually organized EM: a framework for motion segmentation that combines information about form and motion. In: M.I.T Media Laboratory Perceptual Computing Section Technical Report No. 315. ICCV 1998 (1998)
Wang, Q.: HMRF-EM-image: implementation of the Hidden Markov random field model and its expectation-maximization algorithm, 18 December 2012. arXiv:1207.3510v2 [cs.CV]
Frame rate conversion filter MSU. http://compression.graphicon.ru/video/motion_estimation/
Seong-Gyun, J., Chul, L., Chang-Su, K.: Motion-compensated frame interpolation based on multihypothesis motion estimation and texture optimization. IEEE Trans. Image Process. 22(11), 4497–4509 (2013)
Frame rate conversion filter MVTools Avisynth plugin. http://avisynth.org.ru/mvtools/mvtools2.html
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Nemcev, N., Gilmutdinov, M. (2017). Modified EM-Algorithm for Motion Field Refinement in Motion Compensated Frame Interpoliation. In: Galinina, O., Andreev, S., Balandin, S., Koucheryavy, Y. (eds) Internet of Things, Smart Spaces, and Next Generation Networks and Systems. ruSMART NsCC NEW2AN 2017 2017 2017. Lecture Notes in Computer Science(), vol 10531. Springer, Cham. https://doi.org/10.1007/978-3-319-67380-6_63
Download citation
DOI: https://doi.org/10.1007/978-3-319-67380-6_63
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67379-0
Online ISBN: 978-3-319-67380-6
eBook Packages: Computer ScienceComputer Science (R0)