@inproceedings{092c68e34c974dfa96901e38e68a302f,
title = "Crowd counting via region based multi-channel convolution neural network",
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.",
keywords = "Convolution neural network, Crowd counting, Crowd density",
author = "Xiaoguang Cao and Siqi Gao and Xiangzhi Bai",
note = "Publisher Copyright: {\textcopyright} 2017 SPIE.; LIDAR Imaging Detection and Target Recognition 2017 ; Conference date: 23-07-2017 Through 25-07-2017",
year = "2017",
doi = "10.1117/12.2295365",
language = "英语",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Weimin Bao and Yueguang Lv and Daren Lv",
booktitle = "LIDAR Imaging Detection and Target Recognition 2017",
address = "美国",
}