Keyframe Extraction Using Linear Rotation Invariant Coordinates

Year 2022, Volume: 26 Issue: 5, 1040 - 1051, 20.10.2022

Hasan Mutlu Ufuk Çelikcan

https://doi.org/10.16984/saufenbilder.1148511

Abstract

Keyframe extraction is a widely applied remedy for issues faced with 3D motion capture -based computer animation. In this paper, we propose a novel keyframe extraction method, where the motion is represented in linear rotation invariant coordinates and the dimensions covering 95% of the data are automatically selected using principal component analysis. Then, by K-means classification, the summarized data is clustered and a keyframe is extracted from each cluster based on cosine similarity. To validate the method, an online user study was conducted. The results of the user study show that 45% of the participants preferred the keyframes extracted using the proposed method, outperforming the alternative by 6%.

Keywords

Keyframe extraction , linear rotation invariant coordinates , motion data summarization

References

• [1] Y. Lipman, O. Sorkine, D. Levin, D. Cohen-Or, “Linear rotation-invariant coordinates for meshes” ACM Transactions on Graphics, vol. 24, no. 3, p. 479–487, jul 2005.
• [2] A. Mackiewicz, W. Ratajczak, “Principal components analysis (pca)” Computers & Geosciences, vol. 19, no. 3, pp. 303–342, 1993.
• [3] S. Lloyd, “Least squares quantization in pcm,” IEEE Transactions on Information Theory, vol. 28, no. 2, pp. 129–137, 1982.
• [4] M. Kapadia, I.-k. Chiang, T. Thomas, N. I. Badler, J. T. Kider, “Efficient motion retrieval in large motion databases,” in Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, ser. I3D ’13. New York, NY, USA: Association for Computing Machinery, 2013, p. 19–28.
• [5] C. Jin, T. Fevens, S. Mudur, “Optimized keyframe extraction for 3d character animations,” Computer Animation and Virtual Worlds, vol. 23, no. 6, pp. 559–568, 2012.
• [6] A. Voulodimos, I. Rallis, N. Doulamis, “Physics-based keyframe selection for human motion summarization,” Multimedia Tools and Applications, vol. 79, no. 5, pp. 3243–3259, 2020.
• [7] T. Sapinski, D. Kaminska, A. Pelikant, G. Anbarjafari, “Emotion recognition from skeletal movements,” Entropy, vol. 21, no. 7, 2019.
• [8] G. Xia, H. Sun, X. Niu, G. Zhang, L. Feng, “Keyframe extraction for human motion capture data based on joint kernel sparse representation,” IEEE Transactions on Industrial Electronics, vol. 64, no. 2, pp. 1589–1599, 2017.
• [9] W. Choensawat, M. Nakamura, K. Hachimura, “Genlaban: A tool for generating labanotation from motion capture data,” Multimedia Tools and Applications, vol. 74, no. 23, pp. 10823-10846, 2015.
• [10] T. Miura, T. Kaiga, N. Matsumoto, H. Katsura, K. Tajima, H. Tamamoto, “Application of the bayesian information criterion to keyframe extraction from motion capture data,” in SIGGRAPH Asia 2011 Posters, ser. SA ’11. New York, NY, USA: Association for Computing Machinery, 2011.
• [11] E. Bulut, T. Capin, “Key frame extraction from motion capture data by curve saliency,” CASA, 2007.
• [12] H. Togawa, M. Okuda, “Position-based keyframe selection for human motion animation,” in 11th International Conference on Parallel and Distributed Systems (ICPADS’05), vol. 2, 2005, pp. 182–185
• [13] Y. Yang, L. Zeng, H. Leung, “Keyframe extraction from motion capture data for visualization,” in 2016 International Conference on Virtual Reality and Visualization (ICVRV), 2016, pp. 154–157.
• [14] Q. Zhang, X. Xue, D. Zhou, X. Wei, “Motion key-frames extraction based on amplitude of distance characteristic curve,” International Journal of Computational Intelligence Systems, vol. 7, no. 3, pp. 506–514, 2014.
• [15] C. Halit, T. Capin, “Multiscale motion saliency for keyframe extraction from motion capture sequences,” Computer Animation and Virtual Worlds, vol. 22, no. 1, pp. 3–14, 2011.
• [16] R. Roberts, J. P. Lewis, K. Anjyo, J. Seo, Y. Seol, “Optimal and interactive keyframe selection for motion capture,” in SIGGRAPH Asia 2018 Technical Briefs, ser. SA ’18. New York, NY, USA: Association for Computing Machinery, 2018.
• [17] B. Sun, D. Kong, S. Wang, J. Li, “Keyframe extraction for human motion capture data based on affinity propagation,” in 2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), 2018, pp. 107–112.
• [18] Q. Zhang, S.-P. Yu, D.-S. Zhou, X.-P. Wei, “An efficient method of key-frame extraction based on a cluster algorithm,” Journal of Human Kinetics, vol. 39, no. 1, pp. 5–14, 2013.
• [19] K.-S. Huang, C.-F. Chang, Y.-Y. Hsu, S.-N. Yang, “Key probe: A technique for animation keyframe extraction,” The Visual Computer, vol. 21, pp. 532–541, 2005.
• [20] Q. Zhang, S. Zhang, D. Zhou, “Keyframe extraction from human motion capture data based on a multiple population genetic algorithm,” Symmetry, vol. 6, pp. 926–937, 2014.
• [21] X.-m. Liu, A.-m. Hao, D. Zhao, “Optimization-based key frame extraction for motion capture animation,” The Visual Computer, vol. 29, 2012.
• [22] M. Müller, T. Röder, M. Clausen, B. Eberhardt, B. Krüger, A. Weber, “Documentation mocap database hdm05,” Universität Bonn, Tech. Rep. CG-2007-2, 2007.