Crowd counting via region based multi-channel convolution neural network

Xiaoguang Cao; Siqi Gao; Xiangzhi Bai

doi:10.1117/12.2295365

15 November 2017 Crowd counting via region based multi-channel convolution neural network

Xiaoguang Cao, Siqi Gao, Xiangzhi Bai

Proceedings Volume 10605, LIDAR Imaging Detection and Target Recognition 2017; 1060537 (2017) https://doi.org/10.1117/12.2295365
Event: LIDAR Imaging Detection and Target Recognition 2017, 2017, Changchun, China

Abstract

This paper proposed a novel region based multi-channel convolution neural network architecture for crowd counting. In order to effectively solve the perspective distortion in crowd datasets with a great diversity of scales, this work combines the main channel and three branch channels. These channels extract both the global and region features. And the results are used to estimate density map. Moreover, kernels with ladder-shaped sizes are designed across all the branch channels, which generate adaptive region features. Also, branch channels use relatively deep and shallow network to achieve more accurate detector. By using these strategies, the proposed architecture achieves state-of-the-art performance on ShanghaiTech datasets and competitive performance on UCF_CC_50 datasets.

Citation Download Citation

Xiaoguang Cao, Siqi Gao, and Xiangzhi Bai "Crowd counting via region based multi-channel convolution neural network", Proc. SPIE 10605, LIDAR Imaging Detection and Target Recognition 2017, 1060537 (15 November 2017); https://doi.org/10.1117/12.2295365

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available