Share Email Print

Proceedings Paper

Second-order convolutional network for crowd counting
Author(s): Luyang Wang; Qiang Zhai; Baoqun Yin; Hazrat Bilal
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Single image crowd counting remains challenging primarily due to various issues, such as large scale variations, perspective and non-uniform crowd distribution. In this paper, we propose a novel architecture referred to Second-Order Convolutional Network (SOCN) to deal with this task from the perspective of improving the feature transformation capability of the network. The proposed SOCN applies a convolutional neural network as the backbone. We introduce three cascaded second-order blocks located behind the backbone to augment the family of transformation operations and increase the nonlinearity of the network, which can extract multi-scale and discriminative features. Furthermore, we design a context attention module (CAM) including dilated convolutions to assign weights to the score map of each second-order block for the purpose that the features which contribute to counting can be highlighted. We conduct various experiments on ShanghaiTeach1 and UCF_CC_502 datasets, and the results demonstrate the effectiveness of our method.

Paper Details

Date Published: 31 July 2019
PDF: 6 pages
Proc. SPIE 11198, Fourth International Workshop on Pattern Recognition, 111980T (31 July 2019); doi: 10.1117/12.2540362
Show Author Affiliations
Luyang Wang, Univ. of Science and Technology of China (China)
Qiang Zhai, Univ. of Science and Technology of China (China)
Baoqun Yin, Univ. of Science and Technology of China (China)
Hazrat Bilal, Univ. of Science and Technology of China (China)

Published in SPIE Proceedings Vol. 11198:
Fourth International Workshop on Pattern Recognition
Xudong Jiang; Zhenxiang Chen; Guojian Chen, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?