Abstract
Currently, most human action recognition systems are trained with feature sets that have no missing data. Unfortunately, the use of human pose estimation models to provide more descriptive features also entails an increased sensitivity to occlusions, meaning that incomplete feature information will be unavoidable for realistic scenarios. To address this, our approach is to shift the responsibility for dealing with occluded pose data away from the pose estimator and onto the action classifier. This allows the use of a simple, real-time pose estimation (stick-figure) that does not estimate the positions of limbs it cannot find quickly. The system tracks people via background subtraction and extracts the (possibly incomplete) pose skeleton from their silhouette. Hidden Markov Models modified to handle missing data are then used to successfully classify several human actions using the incomplete pose features.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chowdhury, A.K.R., Chellappa, R.: A factorization approach for activity recognition. In: IEEE Computer Vision and Pattern Recognition (2003)
Peursum, P., Venkatesh, S., West, G., Bui, H.H.: Object labelling from human action recognition. In: IEEE Intl Conf. on Pervasive Computing and Communications, pp. 399–406 (2003)
Moore, D.J., Essa, I.A., Hayes, M.H.: Exploiting human actions and object context for recognition tasks. In: IEEE Intl Conf. on Computer Vision, vol. 1, pp. 80–86 (1999)
Fujiyoshi, H., Lipton, A.: Real-time human motion analysis by image skeletonization. In: Workshop on Application of Computer Vision (1999)
Peursum, P., Bui, H.H., Venkatesh, S., West, G.: Technical report 2004/01: Human action recognition with an incomplete real-time pose skeleton. Technical report, Curtin University of Technology, WA Australia (2004), http://impca.cs.curtin.edu.au/publications/techreports.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Peursum, P., Bui, H.H., Venkatesh, S., West, G.A.W. (2004). Classifying Human Actions Using an Incomplete Real-Time Pose Skeleton. In: Zhang, C., W. Guesgen, H., Yeap, WK. (eds) PRICAI 2004: Trends in Artificial Intelligence. PRICAI 2004. Lecture Notes in Computer Science(), vol 3157. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28633-2_119
Download citation
DOI: https://doi.org/10.1007/978-3-540-28633-2_119
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22817-2
Online ISBN: 978-3-540-28633-2
eBook Packages: Springer Book Archive