CASIA OpenIR  > 精密感知与控制研究中心  > 精密感知与控制
Crowd Counting with Spatial Normalization Network
Xiapeng cheng; dapeng zhang
2020-08-20
Conference Name2020 16th IEEE International Conference on Automation Science and Engineering (CASE)
Conference Date2020-8-20
Conference Place香港
Abstract

Crowd counting, which requires to estimate crowd
density from an image, is still a challenging task in computer
vision. Most of the current methods are focused on large
scale variation of people and ignore the huge distribution
difference of crowd. To tackle these two problems together,
we propose a novel framework named Spatial Normalization
Network (SNNet). We normalize multi-scale features from
parallel subnetworks to a particular scale and then fuse them to
acquire rich spatial information for final accurate density map
predictions. Furthermore, we propose a novel normalization
layer called Spatial Group Normalization (SGN), which firstly
split feature maps along the spatial dimension and then perform
group-wise normalization. It’s useful to solve statistic shift
problems caused by the great difference of distribution in crowd
counting. Moreover, SGN can be naturally plugged into existing
solutions and brings significant improvement in crowd counting.
Our proposed SNNet achieves state-of-the-art performance on
four challenging crowd counting datasets (ShanghaiTech, UCFQNRF,
GCC and TRANCOS datasets), which demonstrates
the effectiveness and robust feature learning capability of our
methods.

Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/40629
Collection精密感知与控制研究中心_精密感知与控制
Corresponding AuthorXiapeng cheng
AffiliationInstitute of Automation, Chinese Academy of Science
Recommended Citation
GB/T 7714
Xiapeng cheng,dapeng zhang. Crowd Counting with Spatial Normalization Network[C],2020.
Files in This Item: Download All
File Name/Size DocType Version Access License
Crowd Counting with (2591KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xiapeng cheng]'s Articles
[dapeng zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiapeng cheng]'s Articles
[dapeng zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiapeng cheng]'s Articles
[dapeng zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Crowd Counting with Spatial Normalization Network.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.