Congested Crowd Counting via Adaptive Multi-Scale Context Learning
In this paper, we propose a novel congested crowd counting network for crowd density estimation, i.e., the Adaptive Multi-scale Context Aggregation Network (MSCANet). MSCANet efficiently leverages the spatial context information to accomplish crowd density estimation in a complicated crowd scene. To...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/11/3777 |
id |
doaj-fa1068247957414a87e65f68335068a2 |
---|---|
record_format |
Article |
spelling |
doaj-fa1068247957414a87e65f68335068a22021-06-01T01:35:39ZengMDPI AGSensors1424-82202021-05-01213777377710.3390/s21113777Congested Crowd Counting via Adaptive Multi-Scale Context LearningYani Zhang0Huailin Zhao1Zuodong Duan2Liangjun Huang3Jiahao Deng4Qing Zhang5School of Computer Science and Information Engineering, Shanghai Institute of Technology, Shanghai 201418, ChinaSchool of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai 201418, ChinaSchool of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science and Information Engineering, Shanghai Institute of Technology, Shanghai 201418, ChinaSchool of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science and Information Engineering, Shanghai Institute of Technology, Shanghai 201418, ChinaIn this paper, we propose a novel congested crowd counting network for crowd density estimation, i.e., the Adaptive Multi-scale Context Aggregation Network (MSCANet). MSCANet efficiently leverages the spatial context information to accomplish crowd density estimation in a complicated crowd scene. To achieve this, a multi-scale context learning block, called the Multi-scale Context Aggregation module (MSCA), is proposed to first extract different scale information and then adaptively aggregate it to capture the full scale of the crowd. Employing multiple MSCAs in a cascaded manner, the MSCANet can deeply utilize the spatial context information and modulate preliminary features into more distinguishing and scale-sensitive features, which are finally applied to a 1 × 1 convolution operation to obtain the crowd density results. Extensive experiments on three challenging crowd counting benchmarks showed that our model yielded compelling performance against the other state-of-the-art methods. To thoroughly prove the generality of MSCANet, we extend our method to two relevant tasks: crowd localization and remote sensing object counting. The extension experiment results also confirmed the effectiveness of MSCANet.https://www.mdpi.com/1424-8220/21/11/3777crowd countingcrowd density estimationmulti-scale context learningcrowd localizationremote sensing object counting |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yani Zhang Huailin Zhao Zuodong Duan Liangjun Huang Jiahao Deng Qing Zhang |
spellingShingle |
Yani Zhang Huailin Zhao Zuodong Duan Liangjun Huang Jiahao Deng Qing Zhang Congested Crowd Counting via Adaptive Multi-Scale Context Learning Sensors crowd counting crowd density estimation multi-scale context learning crowd localization remote sensing object counting |
author_facet |
Yani Zhang Huailin Zhao Zuodong Duan Liangjun Huang Jiahao Deng Qing Zhang |
author_sort |
Yani Zhang |
title |
Congested Crowd Counting via Adaptive Multi-Scale Context Learning |
title_short |
Congested Crowd Counting via Adaptive Multi-Scale Context Learning |
title_full |
Congested Crowd Counting via Adaptive Multi-Scale Context Learning |
title_fullStr |
Congested Crowd Counting via Adaptive Multi-Scale Context Learning |
title_full_unstemmed |
Congested Crowd Counting via Adaptive Multi-Scale Context Learning |
title_sort |
congested crowd counting via adaptive multi-scale context learning |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-05-01 |
description |
In this paper, we propose a novel congested crowd counting network for crowd density estimation, i.e., the Adaptive Multi-scale Context Aggregation Network (MSCANet). MSCANet efficiently leverages the spatial context information to accomplish crowd density estimation in a complicated crowd scene. To achieve this, a multi-scale context learning block, called the Multi-scale Context Aggregation module (MSCA), is proposed to first extract different scale information and then adaptively aggregate it to capture the full scale of the crowd. Employing multiple MSCAs in a cascaded manner, the MSCANet can deeply utilize the spatial context information and modulate preliminary features into more distinguishing and scale-sensitive features, which are finally applied to a 1 × 1 convolution operation to obtain the crowd density results. Extensive experiments on three challenging crowd counting benchmarks showed that our model yielded compelling performance against the other state-of-the-art methods. To thoroughly prove the generality of MSCANet, we extend our method to two relevant tasks: crowd localization and remote sensing object counting. The extension experiment results also confirmed the effectiveness of MSCANet. |
topic |
crowd counting crowd density estimation multi-scale context learning crowd localization remote sensing object counting |
url |
https://www.mdpi.com/1424-8220/21/11/3777 |
work_keys_str_mv |
AT yanizhang congestedcrowdcountingviaadaptivemultiscalecontextlearning AT huailinzhao congestedcrowdcountingviaadaptivemultiscalecontextlearning AT zuodongduan congestedcrowdcountingviaadaptivemultiscalecontextlearning AT liangjunhuang congestedcrowdcountingviaadaptivemultiscalecontextlearning AT jiahaodeng congestedcrowdcountingviaadaptivemultiscalecontextlearning AT qingzhang congestedcrowdcountingviaadaptivemultiscalecontextlearning |
_version_ |
1721412073721692160 |