Abstract
Recent work in human activity recognition has focused on bottom-up approaches that rely on spatiotemporal features, both dense and sparse. In contrast, articulated motion, which naturally incorporates explicit human action information, has not been heavily studied; a fact likely due to the inherent challenge in modeling and inferring articulated human motion from video. However, recent developments in data-driven human pose estimation have made it plausible. In this paper, we extend these developments with a new middle-level representation called dynamic pose that couples the local motion information directly and independently with human skeletal pose, and present an appropriate distance function on the dynamic poses. We demonstrate the representative power of dynamic pose over raw skeletal pose in an activity recognition setting, using simple codebook matching and support vector machines as the classifier. Our results conclusively demonstrate that dynamic pose is a more powerful representation of human action than skeletal pose.
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
Preview
Unable to display preview. Download preview PDF.
References
Laptev, I.: On space-time interest points. In: IJCV (2005)
Klaser, A., Marszalek, M., Schmid, C.: A spatio-temporal descriptor based on 3d-gradients. In: BMVC (2008)
Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: CVPR, pp. 3169–3176 (2011)
Rodriguez, M.D., Ahmed, J., Shah, M.: Action mach: A spatio-temporal maximum average correlation height filter for action recognition. In: CVPR (2008)
Niebles, J.C., Chen, C.-W., Fei-Fei, L.: Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 392–405. Springer, Heidelberg (2010)
Gaidon, A., Harchaoui, Z., Schmid, C.: A time series kernel for action recognition. In: BMVC (2011)
Ali, S., Basharat, A., Shah, M.: Chaotic invariants for human action recognition. In: ICCV (2007)
Ramanan, D., Forsyth, D.A.: Automatic annotation of everyday movements. In: NIPS (2003)
Shakhnarovich, G., Viola, P., Darrell, T.: Fast Pose Estimation with Parameter-Sensitive Hashing. In: ICCV (2003)
Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: CVPR (2011)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. TPAMI 32, 1627–1645 (2010)
Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3d human pose annotations. In: ICCV (2009)
Yao, A., Gall, J., Fanelli, G., Gool, L.V.: Does human action recognition benefit from pose estimation? In: BMVC (2011)
Schüldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: ICPR (2004)
Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. TPAMI 29(12), 2247–2253 (2007)
Essa, I., Pentland, A.: Coding, analysis, interpretation and recognition of facial expressions. TPAMI 19(7), 757–763 (1997)
Derpanis, K.G., Sizintsev, M., Cannons, K., Wildes, R.P.: Efficient action spotting based on a spacetime oriented structure representation. In: CVPR (2010)
Tran, K.N., Kakadiaris, I.A., Shah, S.K.: Modeling motion of body parts for action recognition. In: BMVC (2011)
Brendel, W., Todorovic, S.: Activities as Time Series of Human Postures. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 721–734. Springer, Heidelberg (2010)
Lin, Z., Jiang, Z., Davis, L.S.: Recognizing actions by shape-motion prototype trees. In: ICCV (2009)
Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: CVPR (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xu, R., Agarwal, P., Kumar, S., Krovi, V.N., Corso, J.J. (2012). Combining Skeletal Pose with Local Motion for Human Activity Recognition. In: Perales, F.J., Fisher, R.B., Moeslund, T.B. (eds) Articulated Motion and Deformable Objects. AMDO 2012. Lecture Notes in Computer Science, vol 7378. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31567-1_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-31567-1_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31566-4
Online ISBN: 978-3-642-31567-1
eBook Packages: Computer ScienceComputer Science (R0)