A Crowd Counting Framework Combining with Crowd Location

In the past ten years, crowd detection and counting have been applied in many fields such as station crowd statistics, urban safety prevention, and people flow statistics. However, obtaining accurate positions and improving the performance of crowd counting in dense scenes still face challenges, and...

Full description

Saved in:
Bibliographic Details
Main Authors: Jin Zhang, Sheng Chen, Sen Tian, Wenan Gong, Guoshan Cai, Ying Wang
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/2021/6664281
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850166837984100352
author Jin Zhang
Sheng Chen
Sen Tian
Wenan Gong
Guoshan Cai
Ying Wang
author_facet Jin Zhang
Sheng Chen
Sen Tian
Wenan Gong
Guoshan Cai
Ying Wang
author_sort Jin Zhang
collection DOAJ
description In the past ten years, crowd detection and counting have been applied in many fields such as station crowd statistics, urban safety prevention, and people flow statistics. However, obtaining accurate positions and improving the performance of crowd counting in dense scenes still face challenges, and it is worthwhile devoting much effort to this. In this paper, a new framework is proposed to resolve the problem. The proposed framework includes two parts. The first part is a fully convolutional neural network (CNN) consisting of backend and upsampling. In the first part, backend uses the residual network (ResNet) to encode the features of the input picture, and upsampling uses the deconvolution layer to decode the feature information. The first part processes the input image, and the processed image is input to the second part. The second part is a peak confidence map (PCM), which is proposed based on an improvement over the density map (DM). Compared with DM, PCM can not only solve the problem of crowd counting but also accurately predict the location of the person. The experimental results on several datasets (Beijing-BRT, Mall, Shanghai Tech, and UCF_CC_50 datasets) show that the proposed framework can achieve higher crowd counting performance in dense scenarios and can accurately predict the location of crowds.
format Article
id doaj-art-de157aa6e19c4f1fa46d7a7e97e364df
institution OA Journals
issn 0197-6729
2042-3195
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Journal of Advanced Transportation
spelling doaj-art-de157aa6e19c4f1fa46d7a7e97e364df2025-08-20T02:21:20ZengWileyJournal of Advanced Transportation0197-67292042-31952021-01-01202110.1155/2021/66642816664281A Crowd Counting Framework Combining with Crowd LocationJin Zhang0Sheng Chen1Sen Tian2Wenan Gong3Guoshan Cai4Ying Wang5College of Informatica Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Informatica Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Mathematics and Statistics, Hunan Normal University, Changsha 410081, ChinaChangsha Transportation Information Center, Changsha 410016, ChinaChangsha Tianxia Yida Information Technology Co., Ltd., Changsha 410221, ChinaSchool of Humanities and Management, Hunan University of Chinese Medicine, Changsha 410208, ChinaIn the past ten years, crowd detection and counting have been applied in many fields such as station crowd statistics, urban safety prevention, and people flow statistics. However, obtaining accurate positions and improving the performance of crowd counting in dense scenes still face challenges, and it is worthwhile devoting much effort to this. In this paper, a new framework is proposed to resolve the problem. The proposed framework includes two parts. The first part is a fully convolutional neural network (CNN) consisting of backend and upsampling. In the first part, backend uses the residual network (ResNet) to encode the features of the input picture, and upsampling uses the deconvolution layer to decode the feature information. The first part processes the input image, and the processed image is input to the second part. The second part is a peak confidence map (PCM), which is proposed based on an improvement over the density map (DM). Compared with DM, PCM can not only solve the problem of crowd counting but also accurately predict the location of the person. The experimental results on several datasets (Beijing-BRT, Mall, Shanghai Tech, and UCF_CC_50 datasets) show that the proposed framework can achieve higher crowd counting performance in dense scenarios and can accurately predict the location of crowds.http://dx.doi.org/10.1155/2021/6664281
spellingShingle Jin Zhang
Sheng Chen
Sen Tian
Wenan Gong
Guoshan Cai
Ying Wang
A Crowd Counting Framework Combining with Crowd Location
Journal of Advanced Transportation
title A Crowd Counting Framework Combining with Crowd Location
title_full A Crowd Counting Framework Combining with Crowd Location
title_fullStr A Crowd Counting Framework Combining with Crowd Location
title_full_unstemmed A Crowd Counting Framework Combining with Crowd Location
title_short A Crowd Counting Framework Combining with Crowd Location
title_sort crowd counting framework combining with crowd location
url http://dx.doi.org/10.1155/2021/6664281
work_keys_str_mv AT jinzhang acrowdcountingframeworkcombiningwithcrowdlocation
AT shengchen acrowdcountingframeworkcombiningwithcrowdlocation
AT sentian acrowdcountingframeworkcombiningwithcrowdlocation
AT wenangong acrowdcountingframeworkcombiningwithcrowdlocation
AT guoshancai acrowdcountingframeworkcombiningwithcrowdlocation
AT yingwang acrowdcountingframeworkcombiningwithcrowdlocation
AT jinzhang crowdcountingframeworkcombiningwithcrowdlocation
AT shengchen crowdcountingframeworkcombiningwithcrowdlocation
AT sentian crowdcountingframeworkcombiningwithcrowdlocation
AT wenangong crowdcountingframeworkcombiningwithcrowdlocation
AT guoshancai crowdcountingframeworkcombiningwithcrowdlocation
AT yingwang crowdcountingframeworkcombiningwithcrowdlocation