On the use of convolutional neural networks for graphical model-based human pose estimation

Vu, H; Cheng, E; Wilkinson, R; Lech, M

On the use of convolutional neural networks for graphical model-based human pose estimation

Vu, H Cheng, E

Wilkinson, R Lech, M

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings - 2017 International Conference on Recent Advances in Signal Processing, Telecommunications and Computing, SigTelCom 2016, 2017, pp. 88 - 93
Issue Date:: 2017-02-09

Closed Access

	Filename	Description	Size
	07849801.pdf	Published version	198.91 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Vu, H	en_US
dc.contributor.author	Cheng, E https://orcid.org/0000-0003-1632-8062	en_US
dc.contributor.author	Wilkinson, R	en_US
dc.contributor.author	Lech, M	en_US
dc.date.issued	2017-02-09	en_US
dc.identifier.citation	Proceedings - 2017 International Conference on Recent Advances in Signal Processing, Telecommunications and Computing, SigTelCom 2016, 2017, pp. 88 - 93	en_US
dc.identifier.isbn	9781509022915	en_US
dc.identifier.uri	http://hdl.handle.net/10453/127551
dc.description.abstract	© 2017 IEEE. The recent application of Convolutional Neural Networks (CNNs) to Human Pose Estimation (HPE) from static images have improved estimation accuracy compared to traditional HPE approaches. In particular, a recent novel HPE approach combines a traditional graphical model with CNNs to result in state-of-the-art HPE accuracy, improving the estimation accuracy compared to using either approach alone. However, the accuracy of the CNN used in the hybrid model has not yet been explored, and this paper evaluates the use of CNNs in the hybrid model through investigating different network configurations and fine-tuning the network using pre-trained weights obtained from a large labeled dataset. The proposed CNN configurations not only improve the accuracy of the existing network by up to 2% but also uses fewer parameters, resulting in a higher HPE accuracy and simpler network structure.	en_US
dc.relation.ispartof	Proceedings - 2017 International Conference on Recent Advances in Signal Processing, Telecommunications and Computing, SigTelCom 2016	en_US
dc.relation.isbasedon	10.1109/SIGTELCOM.2017.7849801	en_US
dc.title	On the use of convolutional neural networks for graphical model-based human pose estimation	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Professional Practice and Leadership
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2017 IEEE. The recent application of Convolutional Neural Networks (CNNs) to Human Pose Estimation (HPE) from static images have improved estimation accuracy compared to traditional HPE approaches. In particular, a recent novel HPE approach combines a traditional graphical model with CNNs to result in state-of-the-art HPE accuracy, improving the estimation accuracy compared to using either approach alone. However, the accuracy of the CNN used in the hybrid model has not yet been explored, and this paper evaluates the use of CNNs in the hybrid model through investigating different network configurations and fine-tuning the network using pre-trained weights obtained from a large labeled dataset. The proposed CNN configurations not only improve the accuracy of the existing network by up to 2% but also uses fewer parameters, resulting in a higher HPE accuracy and simpler network structure.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/127551