Abstract
Activity recognition is an important application of body sensor networks. To this end, accurate segmentation of different episodes in the data stream is a pre-requisite of subsequent pattern classification. Current techniques for this purpose tend to require specific supervised learning, thus limiting their general application to pervasive sensing applications. This paper presents an improved multiple eigenspace segmentation algorithm that addresses the common problem of under-segmentation in episode detection. Results show that the proposed algorithm significantly increases the segmentation accuracy when compared to existing methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Yang, G.Z.: Body Sensor Networks. Springer, London (2006)
Kahol, K., Tripathi, P., Panchanathan, S.: Gesture Segmentation in Complex Motion Sequences. In: Proceedings IEEE International Conference on Image Processing 2003, pp. 105–108 (2003)
Kang, S.B., Ikeuchi, K.: Toward Automatic Robot Instruction from Perception- Temporal Segmentation of task from Human Hand Motion. IEEE Transactions on Robotics and Automation 11(5), 670–681 (1995)
Feng, N., Mohamed, A.: HMM-Based Segmentation and Recognition of Human Activities from Video Sequences. In: Proceedings of IEEE International Conference on Multimedia and Expo, pp. 804–807 (2005)
Hundtofte, C.S., Hager, G.D., Okamura, A.M.: Building a Task Language for Segmentation and Recognition of User Input to Cooperative Manipulation Systems. In: Proceedings of the 10th IEEE Virtual Reality Conference, pp. 225–230 (2002)
Huynh, T., Schiele, B.: Unsupervised Discovery of Structure in Activity Data using Multiple Eigenspaces. LNCS, pp. 151–167 (2006)
Ali, A., King, R.C., Yang, G.Z.: Semi-supervised Segmentation for Activity Recognition with Multiple Eigenspaces. In: Proceedings of 5th IEEE Body Sensor Networks Conference, pp. 314–317 (2008)
Leonardis, A., Bischof, H., Maver, J.: Multiple Eigenspaces. Pattern Recognition 35, 2613–2627 (2002)
Lo, B., Thiemjarus, S., King, R.C., Yang, G.Z.: Body Sensor Network – A Wireless Sensor Platform for Pervasive healthcare Monitoring. In: Proceedings of 3rd International Conference On Pervasive Sensing, pp. 77–80 (2005)
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
Ali, A., Thiemjarus, S., Yang, GZ. (2009). Episode Segmentation Using Recursive Multiple Eigenspaces. In: Barnaghi, P., Moessner, K., Presser, M., Meissner, S. (eds) Smart Sensing and Context. EuroSSC 2009. Lecture Notes in Computer Science, vol 5741. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04471-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-04471-7_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04470-0
Online ISBN: 978-3-642-04471-7
eBook Packages: Computer ScienceComputer Science (R0)