MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting

Abstract Crowd counting aims to count the number of people in crowded scenes, which is important to the security systems, traffic control and so on. The existing methods typically using local features cannot properly handle the perspective distortion and the varying scales in congested scene images,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Haoyu Zhao, Weidong Min, Xin Wei, Qi Wang, Qiyan Fu, Zitai Wei
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Photography TR1-1050 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/a5d7c22753c04e09809600b1301edb75
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a5d7c22753c04e09809600b1301edb75
record_format	dspace
spelling	oai:doaj.org-article:a5d7c22753c04e09809600b1301edb752021-11-29T03:38:16ZMSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting1751-96671751-965910.1049/ipr2.12175https://doaj.org/article/a5d7c22753c04e09809600b1301edb752021-12-01T00:00:00Zhttps://doi.org/10.1049/ipr2.12175https://doaj.org/toc/1751-9659https://doaj.org/toc/1751-9667Abstract Crowd counting aims to count the number of people in crowded scenes, which is important to the security systems, traffic control and so on. The existing methods typically using local features cannot properly handle the perspective distortion and the varying scales in congested scene images, and henceforth perform wrong people counting. To alleviate this issue, this study proposes a multi‐scale residual feature‐aware network (MSR‐FAN) that combines multi‐scale features using multiple receptive field sizes and learns the feature‐aware information on each image. The MSR‐FAN is trained end‐to‐end to generate high‐quality density map and evaluate the crowd number. The method consists of three parts. To handle the perspective changes problem, the first part, the direction‐based feature‐enhanced network, is designed to encode the perspective information in four directions based on the initial image feature. The second part, the proposed multi‐scale residual block module, gets the global information to handle the represent the regional feature better. This module explores features of different scales as well as reinforce the global feature. The third part, the feature‐aware block, is designed to extract the feature hidden in the different channels. Experiment results based on benchmark datasets show that the proposed approach outperforms the existing state‐of‐the‐art methods.Haoyu ZhaoWeidong MinXin WeiQi WangQiyan FuZitai WeiWileyarticlePhotographyTR1-1050Computer softwareQA76.75-76.765ENIET Image Processing, Vol 15, Iss 14, Pp 3512-3521 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Photography TR1-1050 Computer software QA76.75-76.765
spellingShingle	Photography TR1-1050 Computer software QA76.75-76.765 Haoyu Zhao Weidong Min Xin Wei Qi Wang Qiyan Fu Zitai Wei MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting
description	Abstract Crowd counting aims to count the number of people in crowded scenes, which is important to the security systems, traffic control and so on. The existing methods typically using local features cannot properly handle the perspective distortion and the varying scales in congested scene images, and henceforth perform wrong people counting. To alleviate this issue, this study proposes a multi‐scale residual feature‐aware network (MSR‐FAN) that combines multi‐scale features using multiple receptive field sizes and learns the feature‐aware information on each image. The MSR‐FAN is trained end‐to‐end to generate high‐quality density map and evaluate the crowd number. The method consists of three parts. To handle the perspective changes problem, the first part, the direction‐based feature‐enhanced network, is designed to encode the perspective information in four directions based on the initial image feature. The second part, the proposed multi‐scale residual block module, gets the global information to handle the represent the regional feature better. This module explores features of different scales as well as reinforce the global feature. The third part, the feature‐aware block, is designed to extract the feature hidden in the different channels. Experiment results based on benchmark datasets show that the proposed approach outperforms the existing state‐of‐the‐art methods.
format	article
author	Haoyu Zhao Weidong Min Xin Wei Qi Wang Qiyan Fu Zitai Wei
author_facet	Haoyu Zhao Weidong Min Xin Wei Qi Wang Qiyan Fu Zitai Wei
author_sort	Haoyu Zhao
title	MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting
title_short	MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting
title_full	MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting
title_fullStr	MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting
title_full_unstemmed	MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting
title_sort	msr‐fan: multi‐scale residual feature‐aware network for crowd counting
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/a5d7c22753c04e09809600b1301edb75
work_keys_str_mv	AT haoyuzhao msrfanmultiscaleresidualfeatureawarenetworkforcrowdcounting AT weidongmin msrfanmultiscaleresidualfeatureawarenetworkforcrowdcounting AT xinwei msrfanmultiscaleresidualfeatureawarenetworkforcrowdcounting AT qiwang msrfanmultiscaleresidualfeatureawarenetworkforcrowdcounting AT qiyanfu msrfanmultiscaleresidualfeatureawarenetworkforcrowdcounting AT zitaiwei msrfanmultiscaleresidualfeatureawarenetworkforcrowdcounting
_version_	1718407665634246656

MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting

Ejemplares similares