|
Digital Library of the
European Council for Modelling and Simulation |
Title: |
A Comparison Of Posture Recognition Using Supervised And Unsupervised
Learning Algorithms |
Authors: |
Maleeha Kiran, Chee Seng Chan, Weng Kin Lai, Kyaw Kyaw Hitke Ali, Othman Khalifa |
Published in: |
(2010).ECMS
2010 Proceedings edited by A Bargiela S A Ali D Crowley E J H Kerckhoffs.
European Council for Modeling and Simulation. doi:10.7148/2010 ISBN:
978-0-9564944-1-2 24th
European Conference on Modelling and Simulation, Simulation Meets Global Challenges Kuala
Lumpur, June 1-4 2010 |
Citation
format: |
Kiran, M., Chan, C. S., Lai, W.
K., Ali, K. K. H., & Khalifa, O. (2010). A Comparison Of Posture
Recognition Using Supervised And Unsupervised Learning Algorithms. ECMS 2010
Proceedings edited by A Bargiela S A Ali D Crowley E J H Kerckhoffs (pp.
226-232). European Council for Modeling and Simulation. doi:10.7148/2010-0226-0232 |
DOI: |
http://dx.doi.org/10.7148/2010-0226-0232 |
Abstract: |
Recognition of
human posture is one step in the pro- cess of analyzing human behaviour.
However, it is an ill-defined problem due to the high degree of freedom
exhibited by the human body. In this paper, we study both supervised and
unsupervised learning algorithms to recognise human posture in image
sequences. In particular, we are interested in a specific set of postures,
which are representative of typical applications found in video analytics.
The algorithms chosen for this paper are K-means, artificial neural network,
self-organizing maps and particle swarm optimization. Experimental results
have shown that the supervised learning algorithms out- perform the
unsupervised learning algorithms in terms of the number of correctly
classified postures. Our future work will focus on detecting abnormal behaviour
based on these recognised static postures. |
Full
text: |