Dynamic background learning through deep auto-encoder networks

Xu, P; Liu, Q; Ye, M; Yang, Y; Li, X; Ding, J

Dynamic background learning through deep auto-encoder networks

Xu, P Liu, Q Ye, M Yang, Y

Li, X Ding, J

Permalink

Publication Type:: Conference Proceeding
Citation:: MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia, 2014, pp. 107 - 116
Issue Date:: 2014-01-01

Closed Access

	Filename	Description	Size
	dynamic.pdf	Published version	1.33 MB	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	Xu, P	en_US
dc.contributor.author	Liu, Q	en_US
dc.contributor.author	Ye, M	en_US
dc.contributor.author	Yang, Y https://orcid.org/0000-0001-5528-0546	en_US
dc.contributor.author	Li, X	en_US
dc.contributor.author	Ding, J	en_US
dc.date.issued	2014-01-01	en_US
dc.identifier.citation	MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia, 2014, pp. 107 - 116	en_US
dc.identifier.isbn	9781450330633	en_US
dc.identifier.uri	http://hdl.handle.net/10453/120166
dc.description.abstract	Background learning is a pre-processing of motion detection which is a basis step of video analysis. For the static background, many previous works have already achieved good performance. However, the results on learning dynamic background are still much to be improved. To address this challenge, in this paper, a novel and practical method is proposed based on deep auto-encoder networks. Firstly, dynamic background images are extracted through a deep auto-encoder network (called Background Extraction Network) from video frames containing motion objects. Then, a dynamic background model is learned by another deep autoencoder network (called Background Learning Network) using the extracted background images as the input. To be more flexible, our background model can be updated on-line to absorb more training samples. Our main contributions are 1) a cascade of two deep auto-encoder networks which can deal with the separation of dynamic background and foregrounds very efficiently; 2) a method of online learning is adopted to accelerate the training of Background Extraction Network. Compared with previous algorithms, our approach obtains the best performance over six benchmark data sets. Especially, the experiments show that our algorithm can handle large variation background very well.	en_US
dc.relation.ispartof	MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia	en_US
dc.relation.isbasedon	10.1145/2647868.2654914	en_US
dc.title	Dynamic background learning through deep auto-encoder networks	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/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

Background learning is a pre-processing of motion detection which is a basis step of video analysis. For the static background, many previous works have already achieved good performance. However, the results on learning dynamic background are still much to be improved. To address this challenge, in this paper, a novel and practical method is proposed based on deep auto-encoder networks. Firstly, dynamic background images are extracted through a deep auto-encoder network (called Background Extraction Network) from video frames containing motion objects. Then, a dynamic background model is learned by another deep autoencoder network (called Background Learning Network) using the extracted background images as the input. To be more flexible, our background model can be updated on-line to absorb more training samples. Our main contributions are 1) a cascade of two deep auto-encoder networks which can deal with the separation of dynamic background and foregrounds very efficiently; 2) a method of online learning is adopted to accelerate the training of Background Extraction Network. Compared with previous algorithms, our approach obtains the best performance over six benchmark data sets. Especially, the experiments show that our algorithm can handle large variation background very well.

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

http://hdl.handle.net/10453/120166