Abstract
We propose a novel biologically inspired framework for the recognition of human full-body actions. First, we extract body pose and motion features from depth map sequences. We then cluster pose-motion cues with a two-stream hierarchical architecture based on growing neural gas (GNG). Multi-cue trajectories are finally combined to provide prototypical action dynamics in the joint feature space. We extend the unsupervised GNG with two labelling functions for classifying clustered trajectories. Noisy samples are automatically detected and removed from the training and the testing set. Experiments on a set of 10 human actions show that the use of multi-cue learning leads to substantially increased recognition accuracy over the single-cue approach and the learning of joint pose-motion vectors.
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
Roy, P.C., Bouzouane, A., Giroux, S., Bouchard, B.: Possibilistic Activity Recognition in Smart Homes for Cognitively Impaired People. Applied Artificial Intelligence: An International Journal 25, 883–926 (2011)
Suarez, J., Murphy, R.: Hand Gesture Recognition with Depth Images: A review. In: IEEE Int. Symposium on Robot and Human Interactive Communication, France, pp. 411–417 (2012)
Xu, R., Agarwal, P., Kumar, S., Krovi, V.N., Corso, J.J.: Combining Skeletal Pose with Local Motion for Human Activity Recognition. In: Perales, F.J., Fisher, R.B., Moeslund, T.B. (eds.) AMDO 2012. LNCS, vol. 7378, pp. 114–123. Springer, Heidelberg (2012)
Papadopoulos, G.T., Axenopoulos, A., Daras, P.: Real-Time Skeleton-Tracking-Based Human Action Recognition Using Kinect Data. In: Gurrin, C., Hopfgartner, F., Hurst, W., Johansen, H., Lee, H., O’Connor, N. (eds.) MMM 2014, Part I. LNCS, vol. 8325, pp. 473–483. Springer, Heidelberg (2014)
Giese, M.A., Poggio, T.: Neural Mechanisms for the Recognition of Biological Movements. Nature Reviews Neuroscience 4, 179–192 (2003)
Escobar, M.-J., Kornprobst, P.: Action Recognition with a Bioinspired Feedforward Motion Processing Model: The Richness of Center-Surround Interactions. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 186–199. Springer, Heidelberg (2008)
Kohonen, T.: Self-organizing Maps. Series in Information Sciences, vol. 30. Springer, Heidelberg (1995)
Fritzke, B.: A Growing Neural Gas Network Learns Topologies. In: Advances in Neural Information Processing Systems, vol. 7, pp. 625–632. MIT Press (1995)
Martinetz, T., Schluten, K.: A ”neural-gas” network learns topologies. In: Artificial Neural Networks, pp. 397–402. Elsevier (1991)
Jiang, Z., Lin, Z., Davis, L.S.: Recognizing Human Actions by Learning and Matching Shape-Motion Prototype Trees. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(3), 533–547 (2012)
Parisi, G.I., Wermter, S.: Hierarchical SOM-based Detection of Novel Behavior for 3D Human Tracking. In: IEEE Int. Joint Conf. on Neural Networks (IJCNN), USA, pp. 1380–1387 (2013)
Parisi, G.I., Barros, P., Wermter, S.: FINGeR: Framework for Interactive Neural-based Gesture Recognition. In: European Symposium of Artificial Neural Networks (ESANN), Belgium, pp. 443–447 (2014)
Miikkulainen, R., Bednar, J.A., Choe, Y., Sirosh, J.: Computational Maps in the Visual Cortex. Springer, New York (2005)
Beyer, O., Cimiano, P.: Online Labelling Strategies for Growing Neural Gas. In: Yin, H., Wang, W., Rayward-Smith, V. (eds.) IDEAL 2011. LNCS, vol. 6936, pp. 76–83. Springer, Heidelberg (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Parisi, G.I., Weber, C., Wermter, S. (2014). Human Action Recognition with Hierarchical Growing Neural Gas Learning. In: Wermter, S., et al. Artificial Neural Networks and Machine Learning – ICANN 2014. ICANN 2014. Lecture Notes in Computer Science, vol 8681. Springer, Cham. https://doi.org/10.1007/978-3-319-11179-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-11179-7_12
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11178-0
Online ISBN: 978-3-319-11179-7
eBook Packages: Computer ScienceComputer Science (R0)