Improved Pedestrian Detection Algorithm Based on YOLOv5s

In this study, we propose YOLOv5s-PGD algorithm for dense pedestrian detection, which can improve the recall and reduce the number of parameters compared with YOLOv5s. First, a minimum scale detection layer has been added to deepen the pyramid’s depth and enhance detection accuracy. Second, ghost co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of advanced computational intelligence and intelligent informatics Jg. 28; H. 4; S. 768 - 775
Hauptverfasser: Li, Zhihua, Zhang, Yuanbiao, Wang, Chao, Tan, Guopeng, Yan, Yahui
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Tokyo Fuji Technology Press Co. Ltd 20.07.2024
Schlagworte:
Accuracy
Algorithms
Convolution
Informatics
Object recognition
Parameters
Pedestrians
Real time
ISSN:1343-0130, 1883-8014
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In this study, we propose YOLOv5s-PGD algorithm for dense pedestrian detection, which can improve the recall and reduce the number of parameters compared with YOLOv5s. First, a minimum scale detection layer has been added to deepen the pyramid’s depth and enhance detection accuracy. Second, ghost convolution has been employed to replace standard convolution to increase real-time performance of the algorithm. Finally, depth separable convolution has been used to address issues of high parameters and large computational complexity that lower the efficiency of the algorithm. Experiment results demonstrate that the detection accuracy of the YOLOv5s-PGD algorithm on the CrowdHuman public dataset is up to 85.1%, which is 2.2% higher than that of YOLOv5s. Furthermore, the number of parameters has decreased by 19.7%, and the calculation burden has decreased by 2.5%. Consequently, the proposed YOLOv5s-PGD algorithm better satisfies the requirements of real-time detection, model optimization, and terminal deployment in dense pedestrian scenarios.
AbstractList In this study, we propose YOLOv5s-PGD algorithm for dense pedestrian detection, which can improve the recall and reduce the number of parameters compared with YOLOv5s. First, a minimum scale detection layer has been added to deepen the pyramid’s depth and enhance detection accuracy. Second, ghost convolution has been employed to replace standard convolution to increase real-time performance of the algorithm. Finally, depth separable convolution has been used to address issues of high parameters and large computational complexity that lower the efficiency of the algorithm. Experiment results demonstrate that the detection accuracy of the YOLOv5s-PGD algorithm on the CrowdHuman public dataset is up to 85.1%, which is 2.2% higher than that of YOLOv5s. Furthermore, the number of parameters has decreased by 19.7%, and the calculation burden has decreased by 2.5%. Consequently, the proposed YOLOv5s-PGD algorithm better satisfies the requirements of real-time detection, model optimization, and terminal deployment in dense pedestrian scenarios.
Author Tan, Guopeng
Yan, Yahui
Li, Zhihua
Zhang, Yuanbiao
Wang, Chao
Author_xml – sequence: 1
  givenname: Zhihua
  surname: Li
  fullname: Li, Zhihua
  organization: School of Electronic and Information Engineering, Hebei University of Engineering, No.19 Taiji Road, Economic and Technological Development Zone, Handan, Hebei 056038, China, Hebei Key Laboratory of Security & Protection Information Sensing and Processing, No.19 Taiji Road, Handan Economic and Technological Development Zone, Handan, Hebei 056038, China
– sequence: 2
  givenname: Yuanbiao
  surname: Zhang
  fullname: Zhang, Yuanbiao
  organization: School of Electronic and Information Engineering, Hebei University of Engineering, No.19 Taiji Road, Economic and Technological Development Zone, Handan, Hebei 056038, China, Hebei Key Laboratory of Security & Protection Information Sensing and Processing, No.19 Taiji Road, Handan Economic and Technological Development Zone, Handan, Hebei 056038, China
– sequence: 3
  givenname: Chao
  surname: Wang
  fullname: Wang, Chao
  organization: School of Electronic and Information Engineering, Hebei University of Engineering, No.19 Taiji Road, Economic and Technological Development Zone, Handan, Hebei 056038, China, Hebei Key Laboratory of Security & Protection Information Sensing and Processing, No.19 Taiji Road, Handan Economic and Technological Development Zone, Handan, Hebei 056038, China
– sequence: 4
  givenname: Guopeng
  surname: Tan
  fullname: Tan, Guopeng
  organization: School of Electronic and Information Engineering, Hebei University of Engineering, No.19 Taiji Road, Economic and Technological Development Zone, Handan, Hebei 056038, China, Hebei Key Laboratory of Security & Protection Information Sensing and Processing, No.19 Taiji Road, Handan Economic and Technological Development Zone, Handan, Hebei 056038, China
– sequence: 5
  givenname: Yahui
  surname: Yan
  fullname: Yan, Yahui
  organization: Xinxing Hebei Engineering and Research Inc., Ltd., No.309 Xunzi North Street, Economic Development Zone, Handan, Hebei 056008, China
BookMark eNotkM1OwzAQhC1UJErpC3CKxDnFv4l9LIVCpUjhAAdOlpOswVGTFDutxNtjGk47uzvaHX3XaNYPPSB0S_CKYpWJ-9bUzrnYUL464DyTF2hOpGSpxITPomacpZgwfIWWIbQYR00zzMkcyV138MMJmuQVGgijd6ZPHmGEenRDn6z3n4N341eXPJgQTXH0URblSYQbdGnNPsDyvy7Q-_bpbfOSFuXzbrMu0ppRNqYcBNQMy4rlEnBObKYIbyS3XFlBraSGNSQ3Fai4q7iAJrM0k0JKUTFLBVugu-lujPl9jAl1Oxx9H1_qeJYKxZVS0UUnV-2HEDxYffCuM_5HE6zPkPQESf9B0mdI7BdAzVvY
Cites_doi 10.1109/ICCUBEA.2018.8697857
10.1109/ICCV.2019.00972
10.1109/CVPR.2016.255
10.20965/jaciii.2018.p0683
10.1109/CVPR42600.2020.00165
10.20965/jaciii.2017.p0834
10.1109/TPAMI.2016.2577031
10.1109/CVPR.2017.195
10.1109/CVPR.2016.91
10.20965/jaciii.2017.p0632
10.1088/1742-6596/1952/2/022055
10.3724/SP.J.1089.2019.17283
10.1007/978-3-319-46448-0_2
ContentType Journal Article
Copyright Copyright © 2024 Fuji Technology Press Ltd.
Copyright_xml – notice: Copyright © 2024 Fuji Technology Press Ltd.
DBID AAYXX
CITATION
7SC
7SP
8FD
8FE
8FG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
GNUQQ
HCIFZ
JQ2
K7-
L7M
L~C
L~D
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
DOI 10.20965/jaciii.2024.p0768
DatabaseName CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials - QC
ProQuest Central
ProQuest Technology Collection
ProQuest One
ProQuest Central Korea
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DatabaseTitle CrossRef
Computer Science Database
ProQuest Central Student
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
Advanced Technologies & Aerospace Collection
ProQuest One Academic Eastern Edition
Electronics & Communications Abstracts
ProQuest Technology Collection
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList CrossRef
Computer Science Database
Database_xml – sequence: 1
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1883-8014
EndPage 775
ExternalDocumentID 10_20965_jaciii_2024_p0768
GroupedDBID AAYXX
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
ARCSS
BENPR
BGLVJ
CCPQU
CITATION
GROUPED_DOAJ
HCIFZ
ISHAI
JSI
JSP
K7-
P2P
PHGZM
PHGZT
PQGLB
RJT
RZJ
TUS
7SC
7SP
8FD
8FE
8FG
AZQEC
DWQXO
GNUQQ
JQ2
L7M
L~C
L~D
P62
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c323t-4e5ec308b378e071f6914d84f49f52f82a3d17abe971fb45ed6f2685885b3f253
IEDL.DBID P5Z
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001346228100003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1343-0130
IngestDate Sat Jul 26 02:48:35 EDT 2025
Sat Nov 29 06:43:35 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c323t-4e5ec308b378e071f6914d84f49f52f82a3d17abe971fb45ed6f2685885b3f253
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://doi.org/10.20965/jaciii.2024.p0768
PQID 3082594999
PQPubID 4911628
PageCount 8
ParticipantIDs proquest_journals_3082594999
crossref_primary_10_20965_jaciii_2024_p0768
PublicationCentury 2000
PublicationDate 2024-07-20
PublicationDateYYYYMMDD 2024-07-20
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-07-20
  day: 20
PublicationDecade 2020
PublicationPlace Tokyo
PublicationPlace_xml – name: Tokyo
PublicationTitle Journal of advanced computational intelligence and intelligent informatics
PublicationYear 2024
Publisher Fuji Technology Press Co. Ltd
Publisher_xml – name: Fuji Technology Press Co. Ltd
References key-10.20965/jaciii.2024.p0768-3
key-10.20965/jaciii.2024.p0768-4
key-10.20965/jaciii.2024.p0768-5
key-10.20965/jaciii.2024.p0768-6
key-10.20965/jaciii.2024.p0768-1
key-10.20965/jaciii.2024.p0768-2
key-10.20965/jaciii.2024.p0768-20
key-10.20965/jaciii.2024.p0768-10
key-10.20965/jaciii.2024.p0768-11
key-10.20965/jaciii.2024.p0768-12
key-10.20965/jaciii.2024.p0768-13
key-10.20965/jaciii.2024.p0768-14
key-10.20965/jaciii.2024.p0768-15
key-10.20965/jaciii.2024.p0768-7
key-10.20965/jaciii.2024.p0768-16
key-10.20965/jaciii.2024.p0768-8
key-10.20965/jaciii.2024.p0768-17
key-10.20965/jaciii.2024.p0768-9
key-10.20965/jaciii.2024.p0768-18
key-10.20965/jaciii.2024.p0768-19
References_xml – ident: key-10.20965/jaciii.2024.p0768-3
  doi: 10.1109/ICCUBEA.2018.8697857
– ident: key-10.20965/jaciii.2024.p0768-9
  doi: 10.1109/ICCV.2019.00972
– ident: key-10.20965/jaciii.2024.p0768-2
  doi: 10.1109/CVPR.2016.255
– ident: key-10.20965/jaciii.2024.p0768-4
  doi: 10.20965/jaciii.2018.p0683
– ident: key-10.20965/jaciii.2024.p0768-19
  doi: 10.1109/CVPR42600.2020.00165
– ident: key-10.20965/jaciii.2024.p0768-1
– ident: key-10.20965/jaciii.2024.p0768-13
  doi: 10.20965/jaciii.2017.p0834
– ident: key-10.20965/jaciii.2024.p0768-6
  doi: 10.1109/TPAMI.2016.2577031
– ident: key-10.20965/jaciii.2024.p0768-16
– ident: key-10.20965/jaciii.2024.p0768-17
– ident: key-10.20965/jaciii.2024.p0768-20
  doi: 10.1109/CVPR.2017.195
– ident: key-10.20965/jaciii.2024.p0768-7
  doi: 10.1109/CVPR.2016.91
– ident: key-10.20965/jaciii.2024.p0768-14
– ident: key-10.20965/jaciii.2024.p0768-15
– ident: key-10.20965/jaciii.2024.p0768-11
  doi: 10.20965/jaciii.2017.p0632
– ident: key-10.20965/jaciii.2024.p0768-5
  doi: 10.1088/1742-6596/1952/2/022055
– ident: key-10.20965/jaciii.2024.p0768-10
– ident: key-10.20965/jaciii.2024.p0768-12
– ident: key-10.20965/jaciii.2024.p0768-18
  doi: 10.3724/SP.J.1089.2019.17283
– ident: key-10.20965/jaciii.2024.p0768-8
  doi: 10.1007/978-3-319-46448-0_2
SSID ssj0001326041
ssib051641541
Score 2.2953322
Snippet In this study, we propose YOLOv5s-PGD algorithm for dense pedestrian detection, which can improve the recall and reduce the number of parameters compared with...
SourceID proquest
crossref
SourceType Aggregation Database
Index Database
StartPage 768
SubjectTerms Accuracy
Algorithms
Convolution
Informatics
Object recognition
Parameters
Pedestrians
Real time
Title Improved Pedestrian Detection Algorithm Based on YOLOv5s
URI https://www.proquest.com/docview/3082594999
Volume 28
WOSCitedRecordID wos001346228100003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: DOA
  dateStart: 20070101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib051641541
  issn: 1343-0130
  databaseCode: M~E
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: P5Z
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: K7-
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: BENPR
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV05T8MwFLagZWChnKJQqgxsKDTxkdgTaqEVElUbIUCFJWp8cAjS0oT-fmwnUdWFhSWDLVnWl-d3-fl7AJwHTFHoY-4iLKAOUALoMoGISxLGvYQryuxbmKdhOBrRyYRFZcItK8sqK51oFbWYcZMj7xhaFWKYVNjV_Ns1XaPM7WrZQmMT1A1LgmndEJGXSp6IDgW0h-Cvci7aV_FwEYNhU0aEvOIdDTQcKJ2PKTeEDlCbrcu5uaFat1Xrqtran0HjvzvfBTul5-l0C1HZAxsy3QeNqquDUx7yA0CLPIMUTiSFtG09UudG5rZmK3W6n6968fzty-lpAygcPfQ8Ho6XJDsEj4P-w_WtW_ZXcDmCKHexJJLr3SUopFK7GipgPhYUK8wUgfofTpHww2kimZ5LMJEiUNDw1VOSIAUJOgK1dJbKY-AkFHEhEoJCwTFDnAoVcEGZ8JjWEmHYBBcVkvG8oNGIdfhhcY8L3GODe2xxb4JWhWRcHqksXsF48vf0Kdg2S5kELPRaoJYvfuQZ2OLL_D1btEG91x9F920bfOvvXei2rdT8Aqe1xDk
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V07T8MwED4hQIKFN-JRwANMKJD6kdgDQoWCQC0tAyCYQmM7PASh0FDEn-I3ck4aoS5sDKyxZNn5zne-8919AJuBSiStcu0xbig6KAH1lGHCE7HSfqwTqfJamKtm2GrJ62t1PgJfZS2MS6ssdWKuqM2LdjHyXddWRbhOKmq_--o51ij3ulpSaBRi0bCfH-iy9fZO64jvFqXHRxeHJ96AVcDTjLLM41ZYjbPFLJQWDWwSqCo3kidcJYLiyjvMVMNObBWOxVxYEyTUdWmXImYJdSwRqPLHOJOhO1eN0CvlV6DrgTeS6k-MB-9GPi98Pu7Slphf1O1Q13Nl97GjXQMJimZyp-texIZt47BpyO3d8fR_-1MzMDW4WZNacRRmYcSmczBdslaQgRKbB1nEUawh59bYnLYkJXWb5TlpKak93eFmsvtncoAG3hD8dNNutvuitwCXf7L-RRhNX1K7BCSWTBsTCxYazRXT0iSBNlIZX6EWDMNl2C6Ri7pFm5AI3asc56jAOXI4RznOy1ApkYsGKqMX_cC28vvwBkycXJw1o-Zpq7EKk25aF2ymfgVGs7d3uwbjup899N7Wc-kkcPvXIH8D-XwcbA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Improved+Pedestrian+Detection+Algorithm+Based+on+YOLOv5s&rft.jtitle=Journal+of+advanced+computational+intelligence+and+intelligent+informatics&rft.au=Li%2C+Zhihua&rft.au=Zhang%2C+Yuanbiao&rft.au=Wang%2C+Chao&rft.au=Tan%2C+Guopeng&rft.date=2024-07-20&rft.issn=1343-0130&rft.eissn=1883-8014&rft.volume=28&rft.issue=4&rft.spage=768&rft.epage=775&rft_id=info:doi/10.20965%2Fjaciii.2024.p0768&rft.externalDBID=n%2Fa&rft.externalDocID=10_20965_jaciii_2024_p0768
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1343-0130&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1343-0130&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1343-0130&client=summon