Abstract
Human action recognition is a key process for robots when targeting natural and effective interactions with humans. Such systems need solving the challenging task of designing robust algorithms handling intra and inter-personal variability: for a given action, people do never reproduce the same movements, preventing from having stable and reliable models for recognition. In our work, we use the latent force model (LFM [2]) to introduce mechanistic criteria in explaining the time series describing human actions in terms actual forces. According to LFM’s, the human body can be seen as a dynamic system driven by latent forces. In addition, the hidden structure of these forces can be captured through Gaussian processes (GP) modeling. Accordingly, regression processes are able to give suitable models for both classification and prediction. We applied this formalism to daily life actions recognition and tested it successfully on a collection of real activities. The obtained results show the effectiveness of the approach. We discuss also our future developments in addressing intention recognition, which can be seen as the early detection facet of human activities recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognitionin parts from single depth images. In: CVPR (2011)
Alvarez, M.A., Luengo, D., Lawrence, N.D.: Latent force models. In: van Dyk, D., Welling, M. (eds.) Proceedings of 12th International Conference Artificial Intelligence and Statistics, pp. 9–16, April 2009
Wang, J., Liu, Z., Wu, Y., et al.: Mining actionlet ensemble for action recognition with depth cameras. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1290–1297. IEEE (2012)
Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3D skeletons as points in a lie group. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 588–595 (2014)
Koppula, H.S., Gupta, R., Saxena, A.: Learning human activities and object affordances from RGB-D videos. Int. J. Robot. Res. 32(8), 951–970 (2013)
Piyathilaka, L., Kodagoda, S.: Gaussian mixture based HMM for human daily activity recognition using 3D skeleton features. In: 2013 8th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp. 567–572. IEEE (2013)
Sung, J., Ponce, C., Selman, B., et al.: Unstructured human activity detection from RGBD images. In: 2012 IEEE International Conference on Robotics and Automation (ICRA), pp. 842–849. IEEE (2012)
Zhang, H., Parker, L.E.: 4-dimensional local spatio-temporal features for human activity recognition. In: 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2044–2049. IEEE (2011)
Cheng, G., Wan, Y., Saudagar, A.N., Namuduri, K., Buckles, B.P.: Advances in Human Action Recognition: A Survey. CoRR abs/1501.05964 (2015). http://arxiv.org/abs/1501.05964
Chaudhry, R., Ofli, F., Kurillo, G., Bajcsy, R., Vidal, R.: Bio-inspired dynamic 3D discriminative skeletal features for human action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (2013)
Slama, R., Wannous, H., Daoudi, M., Srivastava, A.: Accurate 3D action recognition using learning on the Grassmann manifold. Pattern Recogn. 48(2), 556–567 (2015). Elsevier
Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, pp. 1110–1118 (2015). doi:10.1109/CVPR.2015.7298714
Bernier, E., Chellali, R., Thouvenin, I.M.: Human gesture segmentation based on change point model for efficient gesture interface. In: 2013 IEEE RO-MAN, South Corea, pp. 258–263 (2013)
Huang, D., Yao, S., Wang, Y., De La Torre, F.: Sequential max-margin event detectors. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part III. LNCS, vol. 8691, pp. 410–424. Springer, Heidelberg (2014)
Chellali, R., Renna, I.: Emblematic gestures recognition. In: 2012 Proceedings of the ASME 11th Biennial Conference on Engineering Systems Design and Analysis (ESDA 2012). ASME ESDA 2012, vol. 2, pp. 755–753 (2012)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Li, Z.C., Chellali, R., Yang, Y. (2016). Latent Force Models for Human Action Recognition. In: Kubota, N., Kiguchi, K., Liu, H., Obo, T. (eds) Intelligent Robotics and Applications. ICIRA 2016. Lecture Notes in Computer Science(), vol 9834. Springer, Cham. https://doi.org/10.1007/978-3-319-43506-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-43506-0_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-43505-3
Online ISBN: 978-3-319-43506-0
eBook Packages: Computer ScienceComputer Science (R0)