Crowd Counting via Weighted VLAD on a Dense Attribute Feature Map
- 8 December 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 28 (8) , 1788-1797
Abstract
Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power of image representation is still an open problem. Conventional holistic features used in crowd counting often fail to capture semantic attributes and spatial cues of the image. In this paper, we propose integrating semantic information into learning locality-aware feature (LAF) sets for accurate crowd counting. First, with the help of a convolutional neural network, the original pixel space is mapped onto a dense attribute feature map, where each dimension of the pixelwise feature indicates the probabilistic strength of a certain semantic class. Then, LAF built on the idea of spatial pyramids on neighboring patches is proposed to explore more spatial context and local information. Finally, the traditional vector of locally aggregated descriptor (VLAD) encoding method is extended to a more generalized form weighted-VLAD (W-VLAD) in which diverse coefficient weights are taken into consideration. Experimental results validate the effectiveness of our presented method.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61473086, 61375001)
- open fund of the Key Laboratory of Measurement
- Ministry of Education (MCCSE2013B01)
- Natural Science Foundation of Jiangsu Province (BK20140566, BK20150470)
- China Postdoctoral Science Foundation (2014M561586)
This publication has 29 references indexed in Scilit:
- Cross-scene crowd counting via deep convolutional neural networks2015
- Deeply learned attributes for crowded scene understanding2015
- Crowd Counting and Profiling: Methodology and Evaluation2013
- Multi-source Multi-scale Counting in Extremely Dense Crowd Images2013
- Cumulative Attribute Space for Age and Crowd Density Estimation2013
- Feature Mining for Localised Crowd Counting2012
- A Discriminative Latent Model of Object Classes and Attributes2010
- Statistical physics of social dynamicsReviews of Modern Physics, 2009
- Counting Crowded Moving Objects2006
- Crowd monitoring using image processingElectronics & Communication Engineering Journal, 1995