RPEE-Heads Benchmark: A Dataset and Empirical Comparison of Deep Learning Algorithms for Pedestrian Head Detection in Crowds

The automatic detection of pedestrian heads in crowded environments is essential for crowd analysis and management tasks, particularly in high-risk settings such as high dense railway platforms and event entrances. These environments, characterized by dense crowds and dynamic movements, are underrep...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE access Vol. 13; pp. 73451 - 73467
Main Authors:	Abubaker, Mohamad, Alsadder, Zubayda, Abdelhaq, Hamed, Boltes, Maik, Alia, Ahmed
Format:	Journal Article
Language:	English
Published:	IEEE 2025
Subjects:	Accuracy Annotations Computer vision Deep learning Head machine learning Magnetic heads object detection algorithms pedestrian head detection Pedestrians public dataset Rail transportation railway platforms and event entrances real-time detection transformer Training Transformers YOLO you only look once
ISSN:	2169-3536, 2169-3536
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	The automatic detection of pedestrian heads in crowded environments is essential for crowd analysis and management tasks, particularly in high-risk settings such as high dense railway platforms and event entrances. These environments, characterized by dense crowds and dynamic movements, are underrepresented in public datasets, posing challenges for existing deep learning models. To address this gap, we introduce the Railway Platforms and Event Entrances-Heads (RPEE-Heads) dataset, a novel, diverse, high-resolution, and accurately annotated resource. It includes 109,913 annotated pedestrian heads across 1,886 images from 66 video recordings, with an average of 56.2 heads per image. Annotations include bounding boxes for visible head regions. In addition to introducing the RPEE-Heads dataset, this paper evaluates eight state-of-the-art object detection algorithms using the dataset and analyzes the impact of head size on detection accuracy. The experimental results show that You Only Look Once v9 and Real-Time Detection Transformer outperform the other algorithms, achieving mean average precisions of 90.7% and 90.8%, with inference times of 11 and 14 milliseconds, respectively. Moreover, the findings underscore the need for specialized datasets like RPEE-Heads for training and evaluating accurate models for head detection in railway platforms and event entrances. The dataset and pretrained models are available at https://doi.org/10.34735/ped.2024.2 .
AbstractList	The automatic detection of pedestrian heads in crowded environments is essential for crowd analysis and management tasks, particularly in high-risk settings such as high dense railway platforms and event entrances. These environments, characterized by dense crowds and dynamic movements, are underrepresented in public datasets, posing challenges for existing deep learning models. To address this gap, we introduce the Railway Platforms and Event Entrances-Heads (RPEE-Heads) dataset, a novel, diverse, high-resolution, and accurately annotated resource. It includes 109,913 annotated pedestrian heads across 1,886 images from 66 video recordings, with an average of 56.2 heads per image. Annotations include bounding boxes for visible head regions. In addition to introducing the RPEE-Heads dataset, this paper evaluates eight state-of-the-art object detection algorithms using the dataset and analyzes the impact of head size on detection accuracy. The experimental results show that You Only Look Once v9 and Real-Time Detection Transformer outperform the other algorithms, achieving mean average precisions of 90.7% and 90.8%, with inference times of 11 and 14 milliseconds, respectively. Moreover, the findings underscore the need for specialized datasets like RPEE-Heads for training and evaluating accurate models for head detection in railway platforms and event entrances. The dataset and pretrained models are available at https://doi.org/10.34735/ped.2024.2.
Author	Alsadder, Zubayda Abubaker, Mohamad Boltes, Maik Alia, Ahmed Abdelhaq, Hamed
Author_xml	– sequence: 1 givenname: Mohamad orcidid: 0009-0006-9119-4139 surname: Abubaker fullname: Abubaker, Mohamad organization: Institute for Advanced Simulation, Forschungszentrum Jülich, Jülich, Germany – sequence: 2 givenname: Zubayda orcidid: 0009-0008-2715-3345 surname: Alsadder fullname: Alsadder, Zubayda organization: Institute for Advanced Simulation, Forschungszentrum Jülich, Jülich, Germany – sequence: 3 givenname: Hamed orcidid: 0000-0003-4803-6689 surname: Abdelhaq fullname: Abdelhaq, Hamed email: hamed@najah.edu organization: Faculty of Information Technology and Artificial Intelligence, An-Najah National University, Nablus, Palestine – sequence: 4 givenname: Maik orcidid: 0000-0001-7240-896X surname: Boltes fullname: Boltes, Maik organization: Institute for Advanced Simulation, Forschungszentrum Jülich, Jülich, Germany – sequence: 5 givenname: Ahmed orcidid: 0000-0002-3049-4924 surname: Alia fullname: Alia, Ahmed email: a.alia@fz-juelich.de organization: Institute for Advanced Simulation, Forschungszentrum Jülich, Jülich, Germany
BookMark	eNpNkcFq3DAQhkVJoGmaJ2gPegFvJI8lr3vbOm4SWGhI2rMYSeON0l1pkQwhkIevtxtK5jLDMN8Hw_-JncQUibEvUiykFN3lqu-Hh4dFLWq1AKUBpPzAzmqpuwoU6JN380d2UcqTmGs5r1R7xl7v74ahuiH0hX-n6B53mP984yt-hRMWmjhGz4fdPuTgcMv7tNtjDiVFnkZ-RbTna8IcQ9zw1XaTcpged4WPKfM78lSmHDDyg34-nshNYSZD5H1Oz758ZqcjbgtdvPVz9vvH8Ku_qdY_r2_71bpyADBVaFGMVitZAypooCPbim7Z6CVqJXwjbOcJBNV14xSRqKVva-cBrbbeKgvn7Pbo9QmfzD6H-ckXkzCYf4uUNwbzFNyWjMauJYda6NE1ViEStEJ6ULJVrlFydsHR5XIqJdP43yeFOeRhjnmYQx7mLY-Z-nqkAhG9I7oWhBLwF3BWiL8
CODEN	IAECCG
Cites_doi	10.1016/j.patcog.2024.110896 10.1098/rsif.2019.0871 10.1109/ICCV.2017.324 10.1371/journal.pone.0177328 10.1016/j.neucom.2012.01.036 10.1038/s41598-023-38633-5 10.1007/s11263-009-0275-4 10.1109/ICIP.2019.8803409 10.1007/s40747-024-01422-2 10.1016/j.neucom.2018.01.092 10.1016/j.neucom.2020.03.037 10.1109/ACCESS.2023.3273770 10.3906/elk-1807-212 10.1109/FG.2018.00089 10.1109/TPAMI.2020.3035969 10.1109/IV55152.2023.10186674 10.1007/978-3-030-55973-1_1 10.1109/tnnls.2024.3412947 10.1109/CVPR.2016.141 10.1007/978-3-031-72751-1_1 10.1007/s11831-021-09551-4 10.1109/TMM.2020.3020691 10.1109/DICTA.2017.8227421 10.1007/978-3-031-06381-7_11 10.1109/CVPR.2019.00192 10.1109/ACCESS.2024.3490610 10.1109/ICCV.2015.331 10.1109/CVPR46437.2021.00386 10.1109/ICIP.2016.7532426 10.1109/TCYB.2020.3034316 10.1007/s00371-020-01974-7 10.5244/C.26.21 10.1109/WACV.2018.00127 10.1109/CVPR.2014.81 10.1007/s11042-022-13644-y 10.1109/TPAMI.2021.3124956 10.1109/ROBIO.2017.8324433 10.1109/AICCSA56895.2022.10017883 10.1016/j.ssci.2020.104743 10.1109/CVPR52729.2023.00721 10.1109/TPAMI.2020.3013269 10.5555/1953048.2078195 10.1016/j.neucom.2017.03.074 10.1016/j.aap.2025.107986 10.1109/ICPR.2018.8545068 10.1109/CVPR.2018.00644 10.3390/s22114040 10.1177/1466138113491171 10.1109/ACCESS.2021.3107901 10.5555/3454287.3455008 10.1088/1367-2630/aaf4ca 10.1080/0144929X.2021.1896781 10.1109/ACCESS.2024.3496823 10.1109/ICME.2019.00145 10.1109/ICCV.2015.169 10.2352/EI.2023.35.9.IPAS-293 10.1007/s13748-019-00203-0
ContentType	Journal Article
DBID	97E ESBDL RIA RIE AAYXX CITATION DOA
DOI	10.1109/ACCESS.2025.3563311
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef
DatabaseTitleList
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	73467
ExternalDocumentID	oai_doaj_org_article_6a97eca606fc4b5aae3701d35175c451 10_1109_ACCESS_2025_3563311 10973050
Genre	orig-research
GrantInformation_xml	– fundername: German Federal Ministry of Education and Research (BMBF) within Palestinian–German Science Bridge Project Framework grantid: 01DH16027 – fundername: Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) grantid: 491111487 funderid: 10.13039/501100001659
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION
ID	FETCH-LOGICAL-c333t-aba0fb65123a53439eb7098468a650d40b9de30e224c5ee021d72cd3ab6bdb5b3
IEDL.DBID	DOA
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001480472500048&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:23:19 EDT 2025 Sat Nov 29 07:57:29 EST 2025 Wed Aug 27 01:53:39 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c333t-aba0fb65123a53439eb7098468a650d40b9de30e224c5ee021d72cd3ab6bdb5b3
ORCID	0000-0001-7240-896X 0000-0003-4803-6689 0009-0008-2715-3345 0000-0002-3049-4924 0009-0006-9119-4139
OpenAccessLink	https://doaj.org/article/6a97eca606fc4b5aae3701d35175c451
PageCount	17
ParticipantIDs	doaj_primary_oai_doaj_org_article_6a97eca606fc4b5aae3701d35175c451 crossref_primary_10_1109_ACCESS_2025_3563311 ieee_primary_10973050
PublicationCentury	2000
PublicationDate	20250000 2025-00-00 2025-01-01
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– year: 2025 text: 20250000
PublicationDecade	2020
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2025
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref57 ref12 ref56 ref15 ref14 (ref49) 2018 ref53 ref52 ref11 ref55 ref10 ref54 ref17 ref16 ref19 ref18 Ren (ref25); 28 Jocher (ref21) 2023 ref50 ref46 Shao (ref39) 2018 ref45 ref48 ref47 ref42 ref44 ref43 Boltes (ref68) 2025 ref8 ref7 ref9 ref4 ref3 ref6 Wu (ref59) 2019 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref38 Bradski (ref62) 2000; 25 (ref51) 2018 ref24 Jocher (ref58) 2023 ref23 ref67 ref26 ref20 ref64 ref63 ref22 ref66 ref65 ref28 ref27 ref29 ref60 ref61 Zhao (ref41) 2023
References_xml	– volume: 25 start-page: 120 year: 2000 ident: ref62 article-title: The OpenCV library publication-title: Dr. Dobb’s J. Softw. Tools – ident: ref5 doi: 10.1016/j.patcog.2024.110896 – ident: ref53 doi: 10.1098/rsif.2019.0871 – ident: ref37 doi: 10.1109/ICCV.2017.324 – ident: ref52 doi: 10.1371/journal.pone.0177328 – year: 2023 ident: ref58 article-title: Ultralytics YOLO – ident: ref67 doi: 10.1016/j.neucom.2012.01.036 – ident: ref63 doi: 10.1038/s41598-023-38633-5 – ident: ref64 doi: 10.1007/s11263-009-0275-4 – ident: ref45 doi: 10.1109/ICIP.2019.8803409 – ident: ref9 doi: 10.1007/s40747-024-01422-2 – ident: ref7 doi: 10.1016/j.neucom.2018.01.092 – ident: ref15 doi: 10.1016/j.neucom.2020.03.037 – ident: ref11 doi: 10.1109/ACCESS.2023.3273770 – ident: ref57 doi: 10.3906/elk-1807-212 – ident: ref43 doi: 10.1109/FG.2018.00089 – volume-title: YOLOv8 year: 2023 ident: ref21 – ident: ref30 doi: 10.1109/TPAMI.2020.3035969 – ident: ref65 doi: 10.1109/IV55152.2023.10186674 – ident: ref54 doi: 10.1007/978-3-030-55973-1_1 – ident: ref14 doi: 10.1109/tnnls.2024.3412947 – ident: ref48 doi: 10.1109/CVPR.2016.141 – ident: ref22 doi: 10.1007/978-3-031-72751-1_1 – ident: ref19 doi: 10.1007/s11831-021-09551-4 – ident: ref13 doi: 10.1109/TMM.2020.3020691 – ident: ref34 doi: 10.1109/DICTA.2017.8227421 – ident: ref47 doi: 10.1007/978-3-031-06381-7_11 – ident: ref35 doi: 10.1109/CVPR.2019.00192 – ident: ref31 doi: 10.1109/ACCESS.2024.3490610 – volume: 28 start-page: 91 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref25 article-title: Faster R-CNN: Towards real-time object detection with region proposal networks – ident: ref28 doi: 10.1109/ICCV.2015.331 – ident: ref40 doi: 10.1109/CVPR46437.2021.00386 – ident: ref42 doi: 10.1109/ICIP.2016.7532426 – volume-title: LabelImg ident: ref56 – ident: ref6 doi: 10.1109/TCYB.2020.3034316 – ident: ref16 doi: 10.1007/s00371-020-01974-7 – ident: ref32 doi: 10.5244/C.26.21 – ident: ref33 doi: 10.1109/WACV.2018.00127 – ident: ref23 doi: 10.1109/CVPR.2014.81 – ident: ref66 doi: 10.1007/s11042-022-13644-y – ident: ref36 doi: 10.1109/TPAMI.2021.3124956 – volume-title: Data Archive of Experimental Data from Studies About Pedestrian Dynamics year: 2018 ident: ref51 – ident: ref44 doi: 10.1109/ROBIO.2017.8324433 – ident: ref4 doi: 10.1109/AICCSA56895.2022.10017883 – ident: ref50 doi: 10.1016/j.ssci.2020.104743 – ident: ref20 doi: 10.1109/CVPR52729.2023.00721 – volume-title: Crowd Management in Transport Infrastructures (Project Number 13n14530 to 13n14533) year: 2018 ident: ref49 – ident: ref29 doi: 10.1109/TPAMI.2020.3013269 – ident: ref60 doi: 10.5555/1953048.2078195 – ident: ref8 doi: 10.1016/j.neucom.2017.03.074 – ident: ref1 doi: 10.1016/j.aap.2025.107986 – ident: ref27 doi: 10.1109/ICPR.2018.8545068 – ident: ref26 doi: 10.1109/CVPR.2018.00644 – volume-title: Detectron2 year: 2019 ident: ref59 – ident: ref12 doi: 10.3390/s22114040 – ident: ref3 doi: 10.1177/1466138113491171 – year: 2023 ident: ref41 article-title: DETRs beat YOLOs on real-time object detection publication-title: arXiv:2304.08069 – ident: ref18 doi: 10.1109/ACCESS.2021.3107901 – ident: ref61 doi: 10.5555/3454287.3455008 – year: 2018 ident: ref39 article-title: CrowdHuman: A benchmark for detecting human in a crowd publication-title: arXiv:1805.00123 – ident: ref55 doi: 10.1088/1367-2630/aaf4ca – ident: ref2 doi: 10.1080/0144929X.2021.1896781 – ident: ref10 doi: 10.1109/ACCESS.2024.3496823 – year: 2025 ident: ref68 article-title: Petrack – ident: ref38 doi: 10.1109/ICME.2019.00145 – ident: ref24 doi: 10.1109/ICCV.2015.169 – ident: ref46 doi: 10.2352/EI.2023.35.9.IPAS-293 – ident: ref17 doi: 10.1007/s13748-019-00203-0
SSID	ssj0000816957
Score	2.3409455
Snippet	The automatic detection of pedestrian heads in crowded environments is essential for crowd analysis and management tasks, particularly in high-risk settings...
SourceID	doaj crossref ieee
SourceType	Open Website Index Database Publisher
StartPage	73451
SubjectTerms	Accuracy Annotations Computer vision Deep learning Head machine learning Magnetic heads object detection algorithms pedestrian head detection Pedestrians public dataset Rail transportation railway platforms and event entrances real-time detection transformer Training Transformers YOLO you only look once
SummonAdditionalLinks	– databaseName: IEEE Electronic Library (IEL) dbid: RIE link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwELVa1AM99AOoCi3VHDg2kF3H9rq3JSziUKEVKhK3aGxPYEU3u9oNPfHjO3bSFRx64BZZluP4TTRvbM8bIY7I1GTRywxxqLMi1CqzpHUWYp5kVKKsfUoU_mkuL0c3N3baJ6unXBgiSpfP6Dg-prP8sPAPcavsJJ6Wsn1yhP7aGN0la202VGIFCatMryzEXU_GZckfwTHgUB1LpaUcDJ55nyTS_6yqSnIq5-9fOJ0P4l3PHmHcwf1RvKJmR7x9oim4Kx6vppNJdsHQreGUTfBujqv7HzCGM2zZY7WATYDJfDlL2iBQbuoQwqKGM6Il9JKrtzD-fbtYzdq7-RqY2sKUAqUqHw3E4blzm-5xNTBroORwPqz3xPX55Fd5kfUlFjIvpWwzdJjXTrPXl6gkkxNyJrfMSUbI1C0UubOBZE7s6L0iYkIQzNAHiU674JSTn8RWs2joswDnjKYwUkzpQmFHQ8ueLxSITDhVII374vu_pa-WnZJGlSKQ3FYdUlVEquqR2henEZ5N1yiDnRoYgqr_qyqN1pBHDsJqXziFSNLkgyAVkyJfKB5kL8L25H0dYgf_af8ituMcui2Wr2KrXT3QoXjj_7Sz9epbsre_Q1LUUQ priority: 102 providerName: IEEE
Title	RPEE-Heads Benchmark: A Dataset and Empirical Comparison of Deep Learning Algorithms for Pedestrian Head Detection in Crowds
URI	https://ieeexplore.ieee.org/document/10973050 https://doaj.org/article/6a97eca606fc4b5aae3701d35175c451
Volume	13
WOSCitedRecordID	wos001480472500048&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: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 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: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3BTtwwELUq1EM5VJRSsaUgH3psSjaO7bi3JQRxaNGqaiVu0diewKrd7Go3cEJ8O2MnoOXEhUsOlmU7M5bfG8vzhrGvqBs04EQCkKkk941MDCqV-JAnGZQoGxcThX_qi4vi8tJMN0p9hTdhvTxwb7hjBUajA-LZjcutBECh07EXknDP5TF5Oku12Qim4hlcjJWRepAZoimPJ2VJf0QBYSa_C6mEGI-fQVFU7H9WYiUizNkOez9QQz7pl_SBvcF2l21vCAZ-ZHe_p1WVnJNf1vyE9tf1HFb_fvAJP4WO4Kjj0HpezZezKPzBy6cig3zR8FPEJR_0VK_45P_VYjXrrudrTryVT9FjLOHR8jA8de7iI62Wz1peUqzu13vs71n1pzxPhvoJiRNCdAlYSBurCNIFSEHMA61ODRGOAoiX-Ty1xqNIkVDcSURCe68z5wVYZb2VVnxiW-2ixX3GrdUKfSGJr_ncFJkhWPM5ALFJ6VHBiH17NGW97GUy6hhepKbuLV8Hy9eD5UfsJJj7qWvQuI4N5Pl68Hz9kudHbC84a2M-Q8eVTD-_xuAH7F1YcH_Z8oVtdasbPGRv3W03W6-O4maj76_76iimDD4APiXY9Q
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09b9swECWKtECbIf1KkaRfN3SsEtkUKbObozhwUdcwihTIJhzJU2I0lg1bydQf3yOlGsnQoZtAEBTFd8K9I3nvhPhEeUUGnUwQ-zrJfKUSQ1onPuRJBiXKysVE4Uk-nQ4uL82sS1aPuTBEFC-f0XF4jGf5fuluw1bZSTgtZfvkCP1xKJ3VpWttt1RCDQmj8k5biDufDIuCP4OjwL46lkpL2es98D9Rpv9BXZXoVs6f_-eEXoi9jj_CsAX8pXhE9Suxe09V8LX4_WM2GiVjBm8Dp2yE1wtc__oCQzjDhn1WA1h7GC1W86gOAsW2EiEsKzgjWkEnunoFw5ur5XreXC82wOQWZuQp1vmoIQzPnZt4k6uGeQ0FB_R-sy9-no8uinHSFVlInJSySdBiWlnNfl-ikkxPyOapYVYyQCZvPkut8SRTYlfvFBFTAp_3nZdotfVWWflG7NTLmg4EWJtr8gPFpM5nZtA37Pt8hsiUU3nSeCg-_136ctVqaZQxBklN2SJVBqTKDqlDcRrg2XYNQtixgSEou_-q1GhycshhWOUyqxBJ5mnPS8W0yGWKB9kPsN17X4vY0T_aP4qn44vvk3LydfrtrXgW5tNuuLwTO836lt6LJ-6umW_WH6Lt_QF6_tea
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=RPEE-Heads+Benchmark%3A+A+Dataset+and+Empirical+Comparison+of+Deep+Learning+Algorithms+for+Pedestrian+Head+Detection+in+Crowds&rft.jtitle=IEEE+access&rft.au=Abubaker%2C+Mohamad&rft.au=Alsadder%2C+Zubayda&rft.au=Abdelhaq%2C+Hamed&rft.au=Boltes%2C+Maik&rft.date=2025&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=13&rft.spage=73451&rft.epage=73467&rft_id=info:doi/10.1109%2FACCESS.2025.3563311&rft.externalDocID=10973050
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon