doi: 10.17586/2226-1494-2018-18-4-623-629


APPLICATION OF SPARTIAL INTERPOLATION METHOD IN SYNTHESIS OF VIDEO SEQUENCE INTERMEDIATE FRAMES

N. S. Nemcev, M. R. Gilmutdinov, A. I. Veselov


Read the full article  ';
Article in Russian

For citation: Nemcev N.S., Gilmutdinov M.R., Veselov A.I. Application of spartial interpolation method in synthesis of video sequence intermediate frames. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2018, vol. 18, no. 4, pp. 623–629 (in Russian). doi: 10.17586/2226-1494-2018-18-4-623-629

Abstract

Subject of Research.We have carried out the research of existing synthesis methods of the video sequence intermediate frames based on the procedure of motion estimation and compensation. A method for the video sequence intermediate frames synthesis is proposed based on the techniques of images spatial interpolation and the procedure for true motion estimation and compensation of the video sequence. Method. The paper describes the approach for the synthesis of video sequence intermediate frames based on the true motion estimation principle. The approach is based on the iterative hierarchical refinement procedure for the elements of the vector field and the approach for spatial interpolation of particular regions of the frame based on the image area fill techniques. Main Results. Сomparison results of the proposed approach with existing modern analogs show its higher efficiency in synthesizing frames of video sequences containing objects with complex motion. Practical Relevance. The proposed approach can be used in practice in the task of video sequences encoding and increasing of their frame rate


Keywords: visual data processing, true motion estimation, true motion model, visual data temporal interpolation, spatial interpolation, global motion estimation, EM-algorithm

References
1.        De Haan G., Biezen P., Huijgen H., Ojo O.A. True-motion estimation with 3-D recursive search block matching. IEEE Transactions on Circuits and Systems for Video Technology, 1993, vol. 3, no. 5, pp. 368–379. doi: 10.1109/76.246088
2.        Haan G. Motion Estimation and Compensation. PhD thesis. Delft University of Technology, 1992.
3.        Bogatyrev V.A., Bogatyrev S.V. Redundant data transmission using aggregated channels in real-time network. Journal of Instrument Engineering, 2016, vol. 59, no. 9, pp. 735–740. (in Russian) doi: 10.17586/0021-3454-2016-59-9-735-740
4.        Bogatyrev V.A. Fault tolerance of clusters configurations with direct connection of storage devices. Automatic Control and Computer Sciences, 2011, vol. 45, no. 6, pp. 330–337. doi: 10.3103/S0146411611060046
5.        Bogatyrev V.A., Bogatyrev S.V. Optimality criteria of multilevel failure-safe computer systems. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2009, no. 5, pp. 92–97. (in Russian)
6.        Bogatyrev V.A., Bogatyrev A.V. Functional reliability of real-time systems. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2013, no. 4, pp. 150–151. (inRussian)
7.        Bogatyrev V.A., Bogatyrev S.V., Bogatyrev A.V. Optimization of the tree-structured network with redundant of switching nodes and links. Telekommunikatsii, 2013, no. 2, pp. 42–48. (in Russian)
8.        Rajala S., Abdelqadar I., Bilbro G., Snyder W. Motion estimation optimization. Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP. San Francisco, 1992, pp. 253–256. doi: 10.1109/ICASSP.1992.226203
9.        Veselov A., Gilmutdinov M. Iterative hierarchical true motion estimation for temporal frame interliolation. IEEE 16th Int. Workshop on Multimedia Signal Processing, MMSP, 2014. doi: 10.1109/mmsp.2014.6958822
10.     Boykov Y., Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, vol. 26, no. 9, pp. 1124–1137. doi: 10.1109/TPAMI.2004.60
11.     Lakshman H., Schwarz H., Wiegand T. Adaptive motion model selection using a cubic spline based estimation framework. Proc. 17th IEEE Int. Conf. on Image Processing, ICIP, 2010, pp. 805–808. doi: 10.1109/spcom.2010.5560522
12.     Veselov A., Gilmutdinov M. Algorithm of motion field optimization for temporal frame interpolation. Informatsionno-Upravliaiushchie Sistemy, 2014, no. 4, pp. 25–28. (in Russian)
13.     Huang A.M., Nguyen T. Correlation-based motion vector processing with adaptive interpolation scheme for motion-compensated frame interpolation. IEEE Transactions on Image Processing, 2009, vol. 18, no. 4, pp. 740–752. doi: 10.1109/tip.2008.2010206
14.     Dempster A.P., Laird N.M., Rubin D.B. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 1977, vol. 39, no. 1, pp. 1–38.
15.     Criminisi A., Perez P., Toyama K. Region filling and object removal by exemplar-based image inpainting. IEEE Transactions on Image Processing, 2004, vol. 13, no. 9, pp. 1200–1212. doi: 10.1109/tip.2004.833105
16.     Fischler M.A., Bolles R.C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Readings in Computer Vision, 1987, pp. 726–740. doi: 10.1016/b978-0-08-051581-6.50070-2
17.     Nemcev N.S. Global Motion Estimation in the problem of visual data spatio-temporal. Proc. 12th Int. Conf. on International Innovation Research, 2018, vol. 1, pp. 96–100. (in Russian)
18.     Nemcev N.S., Gilmutdinov M.R. Classification of reliability of vector field elements. Nauchnaya Sessiya GUAP, 2017, pp. 307–314. (in Russian)
19.     Weiss Y., Adelson E.H. Perceptually organized EM: A framework for motion segmentation that combines information about form and motion. Technical Report no. 315. Cambridge, MIT Media Laboratory Perceptual Computing Section, 1995.
20.     Quan Wang. HMRF-EM-image: implementation of the hidden Markov random field model and its expectation-maximization algorithm. arXiv:1207.3510v2 [cs.CV], 2012.
21.     Nemcev N., Gilmutdinov M. Modified EM-algorithm for motion field refinement in motion compensated frame interpoliation. Lecture Notes in Computer Science, 2017, pp. 662–670. doi: 10.1007/978-3-319-67380-6_63
22.     Frame Rate Conversion Filter MSU-FRC. Available at: http://compression.graphicon.ru/video/motion_estimation/ (accessed 26.04.2018).
23.     Frame Rate Conversion Filter MVTools Avisynth Plugin. Available at: http://avisynth.org.ru/mvtools/mvtools2.html (accessed 26.04.2018).
24.     Jeong S.G., Lee C., Kim C.S. Motion-compensated frame interpolation based on multihypothesis motion estimation and texture optimization. IEEE Transactions on Image Processing, 2013, vol. 22, no. 11, pp. 4497–4509. doi: 10.1109/tip.2013.2274731


Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Copyright 2001-2021 ©
Scientific and Technical Journal
of Information Technologies, Mechanics and Optics.
All rights reserved.

Яндекс.Метрика