Scale-Informed Density Estimation for Dense Crowd Counting

Li, Z; Zou, Y; Wang, G; Zhang, J

Scale-Informed Density Estimation for Dense Crowd Counting

Li, Z Zou, Y Wang, G Zhang, J

Permalink

Publication Type:: Conference Proceeding
Citation:: 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019, 2019
Issue Date:: 2019-12-01

Closed Access

	Filename	Description	Size
	08965799.pdf	Published version	438.86 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	Li, Z	en_US
dc.contributor.author	Zou, Y	en_US
dc.contributor.author	Wang, G	en_US
dc.contributor.author	Zhang, J https://orcid.org/0000-0002-7240-3541	en_US
dc.date.issued	2019-12-01	en_US
dc.identifier.citation	2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019, 2019	en_US
dc.identifier.isbn	9781728137230	en_US
dc.identifier.uri	http://hdl.handle.net/10453/139244
dc.description.abstract	© 2019 IEEE. Dense crowd counting (DCC) remains challenging due to the scale variation and occlusion. Several deep learning based DCC methods have achieved the state-of-Arts on public datasets. However, experimental results show that the scale variation is still the main factor to hinder the DCC performance. In this work, we propose a scale-informed dense crowd counting method focusing on handling the negative effect caused by scale variation. More specifically, we propose a method to obtain the scale information of the patch from its GT density maps via estimating the mean value of the Gaussian kernel width and then a scale-classifier is deigned and trained accordingly. Moreover, with the estimated scale information, two sub-nets are dedicatedly deigned to learn the density maps for large-scale head patch and small-scale patch separately. Experimental results validate the performance of our proposed method which achieves the best performance on three dense crowd datasets.	en_US
dc.relation.ispartof	2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019	en_US
dc.relation.isbasedon	10.1109/VCIP47243.2019.8965799	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Scale-Informed Density Estimation for Dense Crowd Counting	en_US
dc.type	Conference Proceeding
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 Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
utslib.copyright.status	closed_access	*
pubs.publication-status	Published	en_US

Abstract:

© 2019 IEEE. Dense crowd counting (DCC) remains challenging due to the scale variation and occlusion. Several deep learning based DCC methods have achieved the state-of-Arts on public datasets. However, experimental results show that the scale variation is still the main factor to hinder the DCC performance. In this work, we propose a scale-informed dense crowd counting method focusing on handling the negative effect caused by scale variation. More specifically, we propose a method to obtain the scale information of the patch from its GT density maps via estimating the mean value of the Gaussian kernel width and then a scale-classifier is deigned and trained accordingly. Moreover, with the estimated scale information, two sub-nets are dedicatedly deigned to learn the density maps for large-scale head patch and small-scale patch separately. Experimental results validate the performance of our proposed method which achieves the best performance on three dense crowd datasets.

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

http://hdl.handle.net/10453/139244