Abstract
Action recognition from 3d pose data has gained increasing attention since the data is readily available for depth or RGB-D videos. The most successful approaches so far perform an expensive feature selection or mining approach for training. In this work, we introduce an algorithm that is very efficient for training and testing. The main idea is that rich structured data like 3d pose does not require sophisticated feature modeling or learning. Instead, we reduce pose data over time to histograms of relative location, velocity, and their correlations and use partial least squares to learn a compact and discriminative representation from it. Despite of its efficiency, our approach achieves state-of-the-art accuracy on four different benchmarks. We further investigate differences of 2d and 3d pose data for action recognition.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Campbell, L., Bobick, A.: Recognition of human body motion using phase space constraints. In: ICCV (1995)
Bissacco, A., Chiuso, A., Ma, Y., Soatto, S.: Recognition of human gaits. In: CVPR (2001)
Wu, S., Oreifej, O., Shah, M.: Action recognition in videos acquired by a moving camera using motion decomposition of Lagrangian particle trajectories. In: ICCV (2011)
Efros, A., Berg., A., Mori, G., Malik, J.: Recognizing action at a distance. In: CVPR (2003)
Thurau, C., Hlavac, V.: Pose primitive based human action recognition in videos or still images. In: CVPR (2008)
Ikizler-Cinbis, N., Cinbis, R., Sclaroff, S.: Learning actions from the web. In: ICCV (2009)
Eweiwi, A., Cheema, M.S., Bauckhage, C.: Discriminative joint non-negative matrix factorization for human action classification. In: Weickert, J., Hein, M., Schiele, B. (eds.) GCPR 2013. LNCS, vol. 8142, pp. 61–70. Springer, Heidelberg (2013)
Laptev, I.: On space-time interest points. IJCV 64, 107–123 (2005)
Willems, G., Tuytelaars, T., Van Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 650–663. Springer, Heidelberg (2008)
Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)
Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. 103, 60–79 (2013)
Xia, L., Aggarwal, J.: Spatio-temporal depth cuboid similarity feature for activity recognition using depth camera. In: CVPR (2013)
Ye, M., Zhang, Q., Wang, L., Zhu, J., Yang, R., Gall, J.: A survey on human motion analysis from depth data. In: Grzegorzek, M., Theobalt, C., Koch, R., Kolb, A. (eds.) Time-of-Flight and Depth Imaging. LNCS, vol. 8200, pp. 149–187. Springer, Heidelberg (2013)
Yang, Y., Ramanan, D.: Articulated human detection with flexible mixtures of parts. IEEE Trans. Pattern Anal. Mach. Intell. 35, 2878–2890 (2013)
Shotton, J., Girshick, R.B., Fitzgibbon, A.W., Sharp, T., Cook, M., Finocchio, M., Moore, R., Kohli, P., Criminisi, A., Kipman, A., Blake, A.: Efficient human pose estimation from single depth images. IEEE Trans. Pattern Anal. Mach. Intell. 35, 2821–2840 (2013)
Yao, A., Gall, J., van Gool, L.: Coupled action recognition and pose estimation from multiple views. Int. J. Comput. Vis. 100, 16–37 (2012)
Tran, K.N., Kakadiaris, I.A., Shah, S.K.: Modeling motion of body parts for action recognition. In: BMVC (2011)
Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.: Towards understanding action recognition. In: ICCV (2013)
Wang, C., Wang, Y., Yuille, A.: An approach to pose-based action recognition. In: CVPR (2013)
Wang, J., Liu, Z., Liu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: CVPR (2012)
Zanfir, M., Leordeanu, M., Sminchisescu, C.: The moving pose: an efficient 3D kinematics descriptor for low-latency action recognition and detection. In: ICCV (2013)
Wanqing, L., Zhengyou, Z., Zicheng, L.: Action recognition based on a bag of 3D points. In: CVPRW (2010)
Oreifej, O., Liu, Z.: Hon4d: Histogram of oriented 4D normals for activity recognition from depth sequences. In: CVPR (2013)
Barker, M., Rayens, W.: Partial least squares for discrimination. J. Chemometr. 17, 166–173 (2003)
Hajd, M.A., Gonzlez, J., Davis, L.: On partial least squares in head pose estimation: how to simultaneously deal with misalignment. In: CVPR (2012)
Harada, T., Ushiku, Y., Yamashita, Y., Kuniyoshi, Y.: Discriminative spatial pyramid. In: CVPR (2011)
Schwartz, W.R., Kembhavi, A., Harwood, D., Davis, L.S.: Human detection using partial least squares analysis. In: ICCV (2009)
Sharma, A., Jacobs, D.: Bypassing synthesis: PLS for face recognition with pose, low-resolution and sketch. In: CVPR (2011)
Rosipal, R., Be, P.P., Trejo, L.J., Cristianini, N., Shawe-Taylor, J., Williamson, B.: Kernel partial least squares regression in reproducing Kernel Hilbert space. JMLR 2, 97–123 (2001)
Tenorth, M., Bandouch, J., Beetz, M.: The TUM Kitchen data set of everyday manipulation activities for motion tracking and action recognition. In: ICCV Workshops (2009)
Li, M., Yuan, B.: 2D-LDA: a statistical linear discriminant analysis for image matrix. Pattern Recogn. Lett. 26, 527–532 (2005)
Bauckhage, C., Käster, T.: Benefits of separable, multilinear discriminant classification. In: ICPR (2006)
Wang, J., Wu, Y.: Learning maximum margin temporal warping for action recognition. In: ICCV (2013)
Wang, J., Liu, Z., Chorowski, J., Chen, Z., Wu, Y.: Robust 3D action recognition with random occupancy patterns. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 872–885. Springer, Heidelberg (2012)
Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3D skeletons as points in a lie group. In: CVPR (2014)
Acknowledgment
This work was carried out in the project automatic activity recognition in large image databases which is funded by the German Research Foundation (DFG). The authors would also like to acknowledge the financial support provided by the DFG Emmy Noether program (GA 1927/1-1).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Eweiwi, A., Cheema, M.S., Bauckhage, C., Gall, J. (2015). Efficient Pose-Based Action Recognition. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9007. Springer, Cham. https://doi.org/10.1007/978-3-319-16814-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-16814-2_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16813-5
Online ISBN: 978-3-319-16814-2
eBook Packages: Computer ScienceComputer Science (R0)