Cargando…
Design and Analysis of a Lightweight Context Fusion CNN Scheme for Crowd Counting
Crowd counting, which is widely used in disaster management, traffic monitoring, and other fields of urban security, is a challenging task that is attracting increasing interest from researchers. For better accuracy, most methods have attempted to handle the scale variation explicitly. which results...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6539683/ https://www.ncbi.nlm.nih.gov/pubmed/31035697 http://dx.doi.org/10.3390/s19092013 |
_version_ | 1783422448499163136 |
---|---|
author | Yu, Yang Huang, Jifeng Du, Wen Xiong, Naixue |
author_facet | Yu, Yang Huang, Jifeng Du, Wen Xiong, Naixue |
author_sort | Yu, Yang |
collection | PubMed |
description | Crowd counting, which is widely used in disaster management, traffic monitoring, and other fields of urban security, is a challenging task that is attracting increasing interest from researchers. For better accuracy, most methods have attempted to handle the scale variation explicitly. which results in huge scale changes of the object size. However, earlier methods based on convolutional neural networks (CNN) have focused primarily on improving accuracy while ignoring the complexity of the model. This paper proposes a novel method based on a lightweight CNN-based network for estimating crowd counting and generating density maps under resource constraints. The network is composed of three components: a basic feature extractor (BFE), a stacked à trous convolution module (SACM), and a context fusion module (CFM). The BFE encodes basic feature information with reduced spatial resolution for further refining. Various pieces of contextual information are generated through a short pipeline in SACM. To generate a context fusion density map, CFM distills feature maps from the above components. The whole network is trained in an end-to-end fashion and uses a compression factor to restrict its size. Experiments on three highly-challenging datasets demonstrate that the proposed method delivers attractive performance. |
format | Online Article Text |
id | pubmed-6539683 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-65396832019-06-04 Design and Analysis of a Lightweight Context Fusion CNN Scheme for Crowd Counting Yu, Yang Huang, Jifeng Du, Wen Xiong, Naixue Sensors (Basel) Article Crowd counting, which is widely used in disaster management, traffic monitoring, and other fields of urban security, is a challenging task that is attracting increasing interest from researchers. For better accuracy, most methods have attempted to handle the scale variation explicitly. which results in huge scale changes of the object size. However, earlier methods based on convolutional neural networks (CNN) have focused primarily on improving accuracy while ignoring the complexity of the model. This paper proposes a novel method based on a lightweight CNN-based network for estimating crowd counting and generating density maps under resource constraints. The network is composed of three components: a basic feature extractor (BFE), a stacked à trous convolution module (SACM), and a context fusion module (CFM). The BFE encodes basic feature information with reduced spatial resolution for further refining. Various pieces of contextual information are generated through a short pipeline in SACM. To generate a context fusion density map, CFM distills feature maps from the above components. The whole network is trained in an end-to-end fashion and uses a compression factor to restrict its size. Experiments on three highly-challenging datasets demonstrate that the proposed method delivers attractive performance. MDPI 2019-04-29 /pmc/articles/PMC6539683/ /pubmed/31035697 http://dx.doi.org/10.3390/s19092013 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Yu, Yang Huang, Jifeng Du, Wen Xiong, Naixue Design and Analysis of a Lightweight Context Fusion CNN Scheme for Crowd Counting |
title | Design and Analysis of a Lightweight Context Fusion CNN Scheme for Crowd Counting |
title_full | Design and Analysis of a Lightweight Context Fusion CNN Scheme for Crowd Counting |
title_fullStr | Design and Analysis of a Lightweight Context Fusion CNN Scheme for Crowd Counting |
title_full_unstemmed | Design and Analysis of a Lightweight Context Fusion CNN Scheme for Crowd Counting |
title_short | Design and Analysis of a Lightweight Context Fusion CNN Scheme for Crowd Counting |
title_sort | design and analysis of a lightweight context fusion cnn scheme for crowd counting |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6539683/ https://www.ncbi.nlm.nih.gov/pubmed/31035697 http://dx.doi.org/10.3390/s19092013 |
work_keys_str_mv | AT yuyang designandanalysisofalightweightcontextfusioncnnschemeforcrowdcounting AT huangjifeng designandanalysisofalightweightcontextfusioncnnschemeforcrowdcounting AT duwen designandanalysisofalightweightcontextfusioncnnschemeforcrowdcounting AT xiongnaixue designandanalysisofalightweightcontextfusioncnnschemeforcrowdcounting |