Abstract
Optical marker-based motion capture is a vital tool in applications such as motion and behavioural analysis, animation, and biomechanics. Labelling, that is, assigning optical markers to the pre-defined positions on the body, is a time consuming and labour intensive post-processing part of current motion capture pipelines. The problem can be considered as a ranking process in which markers shuffled by an unknown permutation matrix are sorted to recover the correct order. In this paper, we present a framework for automatic marker labelling which first estimates a permutation matrix for each individual frame using a differentiable permutation learning model and then utilizes temporal consistency to identify and correct remaining labelling errors. Experiments conducted on the test data show the effectiveness of our framework.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adams, R.P., Zemel, R.S.: Ranking via Sinkhorn propagation. ArXiv, pp. 1106–1925 (2011)
Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13, 281–305 (2012)
Birkhoff, G.: Three observations on linear algebra. Univ. Nac. Tacuman, Rev. Ser. A 5, 147–151 (1946)
Etemad, S.A., Arya, A.: Expert-driven perceptual features for modeling style and affect in human motion. IEEE Trans. Hum.-Mach. Syst. 46(4), 534–545 (2016)
Han, S., Liu, B., Wang, R., Ye, Y., Twigg, C.D., Kin, K.: Online optical marker-based hand tracking with deep labels. ACM Trans. Graph. 37(4), 166 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)
Herda, L., Fua, P., Plänkers, R., Boulic, R., Thalmann, D.: Using skeleton-based tracking to increase the reliability of optical motion capture. Hum. Mov. Sci. 20(3), 313–341 (2001). https://doi.org/10.1016/S0167-9457(01)00050-1
Holden, D.: Robust solving of optical motion capture data by denoising. ACM Trans. Graph. 38(1), 1–12 (2018). https://doi.org/10.11499/sicejl1962.40.735
Holzreiter, S.: Autolabeling 3D tracks using neural networks. Clin. Biomech. 20(1), 1–8 (2005)
Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325–1339 (2014)
Loper, M., Mahmood, N., Black, M.J.: MoSh: motion and shape capture from sparse markers. ACM Trans. Graph. 33(6), 220 (2014)
Maycock, J., Röhlig, T., Schröder, M., Botsch, M., Ritter, H.: Fully automatic optical motion tracking using an inverse kinematics approach. In: IEEE/RAS International Conference on Humanoid Robots, pp. 2–7 (2015). https://doi.org/10.1109/HUMANOIDS.2015.7363590
Meyer, J., Kuderer, M., Muller, J., Burgard, W.: Online marker labeling for fully automatic skeleton tracking in optical motion capture. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 5652–5657 (2014). https://doi.org/10.1109/ICRA.2014.6907690
Pons-Moll, G., Romero, J., Mahmood, N., Black, M.J.: Dyna: a model of dynamic human shape in motion. ACM Trans. Graph. (TOG) 34(4), 120 (2015)
Rezatofighi, S.H., et al.: Deep perm-set net: learn to predict sets with unknown permutation and cardinality using deep neural networks. arXiv preprint arXiv:1805.00613 (2018)
Santa Cruz, R., Fernando, B., Cherian, A., Gould, S.: DeepPermNet: visual permutation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3949–3957 (2017)
Schubert, T., Gkogkidis, A., Ball, T., Burgard, W.: Automatic initialization for skeleton tracking in optical motion capture. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 734–739. IEEE (2015)
Sigal, L., Balan, A.O., Black, M.J.: HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int. J. Comput. Vis. 87(1–2), 4 (2010)
Sinkhorn, R.: A relationship between arbitrary positive matrices and doubly stochastic matrices. Ann. Math. Stat. 35(2), 876–879 (1964)
Troje, N.F.: Retrieving information from human movement patterns. In: Shipley, T.F., Zacks, J.M. (eds.) Understanding Events: How Humans See, Represent, and Act on Events. Oxford University, New York, vol. 1, pp. 308–334 (2008)
Yu, Q., Li, Q., Deng, Z.: Online motion capture marker labeling for multiple interacting articulated targets. Comput. Graph. Forum 26(3), 477–483 (2007). https://doi.org/10.1111/j.1467-8659.2007.01070.x
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ghorbani, S., Etemad, A., Troje, N.F. (2019). Auto-labelling of Markers in Optical Motion Capture by Permutation Learning. In: Gavrilova, M., Chang, J., Thalmann, N., Hitzer, E., Ishikawa, H. (eds) Advances in Computer Graphics. CGI 2019. Lecture Notes in Computer Science(), vol 11542. Springer, Cham. https://doi.org/10.1007/978-3-030-22514-8_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-22514-8_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22513-1
Online ISBN: 978-3-030-22514-8
eBook Packages: Computer ScienceComputer Science (R0)