Abstract
The topic of human action recognition from image sequences gained increasing interest throughout the last years. Interestingly, the majority of approaches are restricted to dynamic motion features and therefore not universally applicable. In this paper, we propose to recognize human actions by evaluating a distribution over a set of predefined static poses which we refer to as pose primitives. We aim at a generally applicable approach that also works in still images, or for images taken from a moving camera. Experimental validation takes varying video sequence lengths into account and emphasizes the possibility for action recognition from single images, which we believe is an often overlooked but nevertheless important aspect of action recognition.
The proposed approach uses a set of training video sequences to estimate pose and action class representations. To incorporate the local temporal context of poses, atomic subsequences of poses using n-gram expressions are explored. Action classes can be represented by histograms of poses primitive n-grams which allows for action recognition by means of histogram comparison. Although the suggested action recognition method is independent of the underlying low-level representation of poses, representations remain important for targeting practical problems. Thus, to deal with common problems in video based action recognition, e.g. articulated poses and cluttered background, a recently introduced Histogram of Oriented Gradient based descriptor is extended using a non-negative matrix factorization reconstruction.
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.
Similar content being viewed by others
References
Agarwal, A., Triggs, B.: A Local Basis Representation for Estimating Human Pose from Cluttered Images. In: Narayanan, P.J., Nayar, S.K., Shum, H.-Y. (eds.) ACCV 2006. LNCS, vol. 3851, pp. 50–59. Springer, Heidelberg (2006)
Ali, S., Basharat, A., Shah, M.: Chaotic Invariants for Human Action Recognition. In: ICCV 2007 (2007)
Bissacco, A., Yang, M.H., Soatto, S.: Detecting Humans via Their Pose. In: NIPS 2006 (2006)
Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as Space-Time Shapes. In: ICCV 2005 (2005)
Carlsson, S., Sullivan, J.: Action recognition by shape matching to key frames. In: Workshop on Models versus Exemplars in Computer Vision (2001)
Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: CVPR 2005 (2005)
Ferrari, V., Marin, M., Zisserman, A.: Progressive Search Space Reduction for Human Pose Estimation. In: CVPR 2008 (2008)
Flash, T., Hochner, B.: Motor primitives in vertebrates and invertebrates. Current Opinion in Neurobiology 15(6), 660–666 (2005)
Fod, A., Matarić, M., Jenkins, O.: Automated Derivation of Primitives for Movement Classification. Autonomous Robots 12(1), 39–54 (2002)
Ghahramani, Z.: Building blocks of movement. Nature 407, 682–683 (2000)
Goldenberg, R., Kimmel, R., Rivlin, E., Rudzsky, M.: Behavior classification by eigendecomposition of periodic motions. Pattern Recognition 38, 1033–1043 (2005)
Guerra-Filho, G., Aloimonos, Y.: A Sensory-Motor Language for Human Activity Understanding. In: 6th IEEE-RAS International Conference on Humanoid Robots (HUMANOIDS 2006), pp. 69–75 (2006)
Hamid, R., Johnson, A., Batta, S., Bobick, A., Isbell, C., Coleman, G.: Detection and Explanation of Anomalous Activities: Representing Activities as Bags of Event n-Grams. In: CVPR 2005 (2005)
Hoyer, P.O.: Non-negative Matrix Factorization with sparseness constraints. Journal of Machine Learning Research 5, 1457–1469 (2004)
Ikizler, N., Duygulu, P.: Human Action Recognition Using Distribution of Oriented Rectangular Patches. In: Human Motion ICCV 2007 (2007)
Jhuang, H., Serre, T., Wolf, L., Poggio, T.: A Biologically Inspired System for Action Recognition. In: ICCV 2007 (2007)
Laptev, I., Perez, P.: Retrieving actions in movies. In: ICCV 2007 (2007)
Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401(6755), 788–799 (1999)
Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorizationi. In: NIPS 2001 (2001)
Lu, W.L., Little, J.J.: Simultaneous Tracking and Action Recognition using the PCA-HOG Descriptor. In: CRV 2006 (2006)
Moeslund, T., Fihl, P., Holte, M.: Action Recognition using Motion Primitives. In: Danish Conference on Pattern Recognition and Image Analysis (2006)
Moeslund, T., Reng, L., Granum, E.: Finding Motion Primitives in Human Body Gestures. In: Wolfmann, J., Cohen, G. (eds.) Coding Theory 1988. LNCS (LNAI), vol. 388, pp. 133–144. Springer, Heidelberg (1989)
Niebles, J.C., Fei-Fei, L.: A Hierarchical Model of Shape and Appearance for Human Action Classification. In: CVPR 2007 (2007)
Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words. In: BMVC 2006 (2006)
Ogale, A.S., Karapurkar, A., Aloimonos, Y.: View-invariant modeling and recognition of human actions using grammars. In: ICCV Workshop on Dynamical Vision (2005)
Schack, T., Mechsner, F.: Representation of motor skills in human long-term memory. Neuroscience Letters 391, 77–81 (2006)
Schindler, K., van Gool, L.: Action Snippets: How many frames does human action recognition require? In: CVPR 2008 (2008)
Schroff, F., Criminisi, A., Zisserman, A.: Single-Histogram Class Models for Image Segmentation. In: Kalra, P.K., Peleg, S. (eds.) ICVGIP 2006. LNCS, vol. 4338, pp. 82–93. Springer, Heidelberg (2006)
Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering object categories in image collections. In: Proceedings of the International Conference on Computer Vision (2005)
Thoroughman, K., Shadmehr, R.: Learning of action through adaptive combination of motor primitives. Nature 407, 742–747 (2000)
Thurau, C.: Behavior Histograms for Action Recognition and Human Detection. In: Human Motion ICCV 2007 (2007)
Thurau, C., Bauckhage, C., Sagerer, G.: Synthesizing Movements for Computer Game Characters. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 179–186. Springer, Heidelberg (2004)
Thurau, C., Hlaváč, V.: n-grams of action primitives for recognizing human behavior. In: Kropatsch, W.G., Kampel, M., Hanbury, A. (eds.) CAIP 2007. LNCS, vol. 4673, Springer, Heidelberg (2007)
Thurau, C., Hlaváč, V.: Pose primitive based human action recognition in videos or still images. In: International Conference on Computer Vision and Pattern Recognition (CVPR 2008), IEEE, Los Alamitos (2008)
Vangeneugden, J., Pollick, F., Vogels, R.: Functional differentiation of macaque visual temporal cortical neurons using a parameterized action space. J. Vis. 8(6), 232–232 (2008), http://journalofvision.org/8/6/232/
Weiland, D., Boyer, E.: Action Recognition using Exemplar-based Embedding. In: CVPR 2008 (2008)
Wolpert, D.M., Ghahramani, Z., Flanagan, J.R.: Perspectives and problems in motor learning. TRENDS in Cognitive Sciences 5(11), 487–494 (2001)
Zhang, L., Wu, B., Nevatia, R.: Detection and Tracking of Multiple Humans with Extensive Pose Articulation. In: ICCV 2007 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Thurau, C., Hlaváč, V. (2009). Recognizing Human Actions by Their Pose. In: Cremers, D., Rosenhahn, B., Yuille, A.L., Schmidt, F.R. (eds) Statistical and Geometrical Approaches to Visual Motion Analysis. Lecture Notes in Computer Science, vol 5604. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03061-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-03061-1_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03060-4
Online ISBN: 978-3-642-03061-1
eBook Packages: Computer ScienceComputer Science (R0)