Abstract
We use charting, a non-linear dimensionality reduction algorithm, for articulated human motion classification in multi-view sequences or 3D data. Charting estimates automatically the intrinsic dimensionality of the latent subspace and preserves local neighbourhood and global structure of high-dimensional data. We classify human actions sub-sequences of varying lengths of skeletal poses, adopting a multi-layered subspace classification scheme with layered pruning and search. The sub-sequences of varying lengths of skeletal poses can be extracted using either markerless articulated tracking algorithms or markerless motion capture systems. We present a qualitative and quantitative comparison of single-subspace and multiple-subspace classification algorithms. We also identify the minimum length of action skeletal poses, required for accurate classification, using competing classification systems as the baseline. We test our motion classification framework on HumanEva, CMU, HDM05 and ACCAD mocap datasets and achieve similar or better classification accuracy than various comparable systems.
Similar content being viewed by others
References
Barr, V., Markov, Z.: The optimality of naive bayes. In: Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference. Miami Beach, Florida, USA (2004)
Blackburn, J., Ribeiro, E.: Human motion recognition using isomap and dynamic time warping. In: Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation. Rio De Janeiro (2007)
Bobick, A.: Movement, activity, and action: The role of knowledge in the perception of motion. In: Royal Society Workshop on Knowledge-based Vision in Man and Machine, vol. 352. London (1997)
Brand, M.: Charting a manifold. In: Advances in Neural Information Processing Systems (NIPS). Vancouver (2002)
Chen, J., Kim, M., Wang, Y., Ji, Q.: Switching gaussian process dynamic models for simultaneous composite motion tracking and recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009). Miami (2009)
Boyer, E., Weinland, D., Ronfard, R.: Action recognition from arbitrary views using 3d exemplars. In: International Conference on Computer Vision (ICCV). Rio de Janeiro (2007)
ACCAD Motion Capture dataset. http://accad.osu.edu
CMU Motion Capture dataset. http://www.mocap.cs.cmu.edu
Dee, H., Hogg, D.: Detecting inexplicable behaviour. In: Proceedings of the British Machine Vision Conference (BMVC). London (2004)
Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: International Conference on Computer Vision (ICCV). Beijing (2005)
Gur, E., Weizman, Y., Perdu, P., Zalevsky, Z.: Radon-transform-based image enhancement for microelectronic chip inspection. IEEE Trans. Device Mater. Reliab. 10(3) (2010)
Husz, Z., Wallace, A., Green, P.: Human activity recognition with action primitives. In: IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS). London (2007)
Jaeggli, T., Koller-Meier, E., Van Gool, L.: Multi-activity tracking in lle body pose space. In: ICCV 2nd Workshop on HUMAN MOTION Understanding, Modeling, Capture and Animation. Rio De Janeiro (2007)
John, V., Trucco, E.: Multiple view human articulated tracking using charting and particle swarm optimisation. In: Proceedings of the 1st international workshop on 3D video processing. 3DVP ’10, Florence (2010)
John, V., Trucco, E., Ivekovic, S.: Markerless human articulated tracking using hierarchical particle swarm optimisation. Image Vision Comput. 28, 1530–1547 (2010)
John, V., Trucco, E., McKenna, S.: Markerless human motion capture using charting and manifold constrained particle swarm optimisation. In: Proceedings of the BMVC 2010 UK postgraduate, workshop. London (2010)
Liang, W., Hou, G., Han, L., Wu, X., Jia, Y.: Discriminative human action recognition in the learned hierarchical manifold space. In: Image Vision Comput. 28, pp. 836–849, (2010)
Rivlin, E., Raskin, L., Rudzsky, M.: Tracking and classifying of human motions with gaussian process annealed particle filter. In Asian Conference on Computer Vision, Tokyo (2007)
Lawrence, N.: Gaussian process latent variable models for visualisation of high dimensional data. In: Neural Information Processing (NIPS). pp. 2004, Whistler (2003)
Lawrence, Neil D.: Probabilistic non-linear principal component analysis with gaussian process latent variable models. 6, 1783–1816 (2005)
Lv, F., Nevatia, R.: Recognition and segmentation of 3d human action using hmm and multi-class adaboost. In: European Conference of Computer Vision (ECCV). Graz (2006)
Moeslund, T., Granum, E.: A survey of computer vision-based human motion capture. 81(3), 90–126 (2001)
Moeslund, T., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. In: Computer Vision and Image Understanding (CVIU), vol. 104, (2006)
Müller, M., Röder, T., Clausen, M., Eberhardt, B., Krüger, B., Weber, A.: Documentation mocap database hdm05. Technical Report CG-2007-2, Universität Bonn (2007)
Niebles, J., Wang, H., Fei-fei, L.: Unsupervised learning of human action categories using spatial-temporal words. In: Proceedings of British Machine Vision Conference (BMVC). Edinburgh (2006)
Ning, H., Xu, W., Gong, Y., Huang, T.: Latent pose estimator for continuous action recognition. In: Proceedings on European Conference on Computer Vision (ECCV). Marseille (2008)
Poppe, R.: Vision-based human motion analysis: An overview. Comput. Vis. Image Understand. (CVIU) 108(1–2), 4–18 (2007)
Raskin, L., Rudzsky, M., Rivlin, E.: 3d human body-part tracking and action classification using a hierarchical body model. In: Proceedings of British Machine Vision Conference (BMVC). London (2009)
Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. In. SCIENCE, vol. 290 (2000)
Roweis, S., Saul, L., Hinton, G.: Global coordination of local linear models. In: Neural Information Processing Systems (NIPS). Vancoiver (2001)
Schindler, K., van Gool, L.: Action snippets: How many frames does human action recognition require? In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Anchorage (2008)
Urtasun, R., Jordan, M., Shyr, A.: Sufficient dimension reduction for visual sequence classification. In: Proceedings of Computer Vision and Pattern Recognition (CVPR). SanFrancisco (2010)
Sidenbladh, H., Black, M., Fleet, D.: Stochastic tracking of 3d human figures using 2d image motion. In: Proceedings of the European Conference on Computer Vision (ECCV). Dublin (2000)
Sigal, L., Balan, A., Black, M.: Humaneva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. 87(1–2), pp. 4–27 (2010)
Schindler, K., Suter, D., Chin, T., Wang, L.: Extrapolating learned manifolds for human activity recognition. In: Proceedings of the International Conference on Image Processing (ICIP), San Diego (2007)
Tenenbaum, J., Silvj, V., Langford, V.: A Global Geometric Framework for Nonlinear Dimensionality Reduction. In: Science, vol. 290 (2000)
Urtasun, R., Darrell, T.: Discriminative gaussian process latent variable model for classification. In: Proceedings of the international conference on Machine learning. Oregon (2007)
Urtasun, R., Fleet, D., Fua, P.: Monocular 3-d tracking of the golf swing. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR). San Diego (2005)
Wang, L., Suter, D.: Learning and matching of dynamic shape manifolds for human action recognition (2007)
Weinland, D., Ronfard, R., Boyer, E.: Free viewpoint action recognition using motion history volumes. 104, pp. 249–257 (2006)
Yamato, J., Ohya, J., Ishii, K.: Recognizing human action in time-sequential images using hidden markov model. In: Computer Vision and Pattern Recognition, 1992. Proceedings CVPR ’92, 1992 IEEE Computer Society Conference on (1992)
Author information
Authors and Affiliations
Corresponding author
Additional information
This article is based on the first author’s Ph.D research at School of Computing, University of Dundee.
Rights and permissions
About this article
Cite this article
John, V., Trucco, E. Charting-based subspace learning for video-based human action classification. Machine Vision and Applications 25, 119–132 (2014). https://doi.org/10.1007/s00138-013-0508-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-013-0508-y