Video Time-Space Body Filtering Based on Dual-Directional Markov Chain Monte Carlo Particle Filter

Abstract:

Nowadays with the blooming development of new media and cultural creative industries, the video animation has drawn so many researchers’ attention due to animation production efficiency and animation expression. This paper aims at the difficulty that lack of observation model, proposes a method of video time-space body filtering based on dual-directional Markov chain Monte Carlo particle filter for video motion redirection. At first, after extracting the key frame of a given video, by affine transformation and linear superposition, the subject initializes the video’s time-space parameters and forms the observation model; Secondly, in each time-space body, based on the bi-directional Markov property of each frame, this paper proposed a dual-directional Markov chain Monte Carlo sampling particle filter structure and takes full advantage of the relationship of the front and back frame of the parameters to estimate motion redirection parameters. The research of this paper will produce an efficient and prominent animation expressive video motion redirection method and play an important role on video animation of the development.

• Periodical: Applied Mechanics and Materials (Volume 596)
• Pages: 379-383
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.596.379
• Online since: July 2014
• Authors: Jin Bao Song*, Long Ye, Qin Zhang
• Keywords: Bayesian Filter, Markov Chain Monte Carlo Particle Filter, Monte Carlo Sampling, Particle Filter, Video Tracking

References

[1] Song Jinbao, Wan Jinliang, Ye Long, Zhang Qin. Key Frame Matching and Dual Direction Monte Carlo Particle Filter based Video Tooning[J]. The 2013 International Conference on Control Engineering and Information Technology (ICCEIT 2013), August, 2013, 627-630.

DOI: 10.1201/b17732-55

[2] Yu Jinhui， Patterson John，Liao Jing，Modeling the interaction between objects and cartoon water，Computer Animation and Virtual Worlds, Volume 19, Numbers 3-4, July 2008 , 375-385.

DOI: 10.1002/cav.239

[3] Andrew Selle，Alex Mohr，Stephen Chenney，Cartoon Rendering of Smoke Animations, Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering , Annecy, France ，2004， 57-60.

DOI: 10.1145/987657.987666

[4] Zhang S, Chen T, Zhang Y, Hu S, Martin R, Video-based Running Water Animation in Chinese Painting Style. In Science in China Series F: Information Sciences 52, February 2009, 162-71.

DOI: 10.1007/s11432-009-0035-7

[5] Jinhui Yu, Xinan Jiang, Haiying Chen, Cheng Yao, Real-time Cartoon Water Animation, The Journal of Computer Animation and Social Agent, vol. 18, 2007, pp.405-414.

DOI: 10.1002/cav.207

[6] Haiyan Li, Qingjie Sun, Xiaodan Liu, Qin Zhang, Example-based Stylized Trajectory Synthesis of Falling Leaf, 2010 International Conference on Computer Engineering and Technology, Chengdu, China.

DOI: 10.1109/iccet.2010.5485603

[7] Song Jinbao, Li Junyu, Zhang Qin. The Model Based Behavior Driven Arithmetic Research[J]. Advanced Engineering Forum Vols. 6-7, September, 2012, 1066-1071.

DOI: 10.4028/www.scientific.net/aef.6-7.1066

[8] Jinliang Wan, Jinbao Song. A Parallel Framework for Texture Substitution Coding. 2010 International Conference on Educational and Information Technology (ICEIT2010), September, 2010，72-76.

DOI: 10.1109/iceit.2010.5607785