YOLOv8-QSD: An Improved Small Object Detection Algorithm for Autonomous Vehicles Based on YOLOv8

As self-driving vehicles become more prevalent, the speed and accuracy of detecting surrounding objects through onboard sensing technology have become increasingly important. The YOLOv8-QSD network is a novel anchor-free driving scene detection network that builds on YOLOv8 and ensures detection acc...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on instrumentation and measurement Ročník 73; s. 1 - 16
Hlavní autori:	Wang, Hai, Liu, Chenyu, Cai, Yingfeng, Chen, Long, Li, Yicheng
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	2-D object detection Accuracy Algorithms Autonomous cars Autonomous driving Commercial vehicles Feature extraction highway traffic Image recognition Location awareness Object detection Object recognition Safety YOLO
ISSN:	0018-9456, 1557-9662
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	As self-driving vehicles become more prevalent, the speed and accuracy of detecting surrounding objects through onboard sensing technology have become increasingly important. The YOLOv8-QSD network is a novel anchor-free driving scene detection network that builds on YOLOv8 and ensures detection accuracy while maintaining efficiency. The network's backbone employs structural reparameterization techniques to transform the diverse branch block (DBB)-based model. To accurately detect small objects, it integrates features of different scales and implements a bidirectional feature pyramid network (BiFPN)-based feature pyramid after the backbone. To address the challenge of long-range detection in driving scenarios, a query-based model with a new pipeline structure is introduced. The test results demonstrate that this algorithm outperforms YOLOv8 on the large-scale small object detection dataset (SODA-A) in terms of both speed and accuracy. With an accuracy rate of 64.5% and reduced computational requirements of 7.1 GFLOPs, it satisfies the speed, precision, and cost-effectiveness requirements for commercial vehicles in high-speed road driving scenarios.
AbstractList	As self-driving vehicles become more prevalent, the speed and accuracy of detecting surrounding objects through onboard sensing technology have become increasingly important. The YOLOv8-QSD network is a novel anchor-free driving scene detection network that builds on YOLOv8 and ensures detection accuracy while maintaining efficiency. The network’s backbone employs structural reparameterization techniques to transform the diverse branch block (DBB)-based model. To accurately detect small objects, it integrates features of different scales and implements a bidirectional feature pyramid network (BiFPN)-based feature pyramid after the backbone. To address the challenge of long-range detection in driving scenarios, a query-based model with a new pipeline structure is introduced. The test results demonstrate that this algorithm outperforms YOLOv8 on the large-scale small object detection dataset (SODA-A) in terms of both speed and accuracy. With an accuracy rate of 64.5% and reduced computational requirements of 7.1 GFLOPs, it satisfies the speed, precision, and cost-effectiveness requirements for commercial vehicles in high-speed road driving scenarios.
Author	Li, Yicheng Chen, Long Wang, Hai Liu, Chenyu Cai, Yingfeng
Author_xml	– sequence: 1 givenname: Hai orcidid: 0000-0002-9136-8091 surname: Wang fullname: Wang, Hai email: wanghai1019@163.com organization: School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, China – sequence: 2 givenname: Chenyu orcidid: 0009-0004-9552-986X surname: Liu fullname: Liu, Chenyu email: 758273063@qq.com organization: School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, China – sequence: 3 givenname: Yingfeng orcidid: 0000-0002-0633-9887 surname: Cai fullname: Cai, Yingfeng email: caicaixiao0304@126.com organization: Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China – sequence: 4 givenname: Long orcidid: 0000-0002-2079-3867 surname: Chen fullname: Chen, Long email: chenlong@ujs.edu.cn organization: Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China – sequence: 5 givenname: Yicheng orcidid: 0000-0003-2937-7162 surname: Li fullname: Li, Yicheng email: liyucheng070@163.com organization: Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China
BookMark	eNp9kM1PwkAQxTcGEwG9e_Cwiefi7Ee7rTcEP0gwxIAmnurSTqWk7eJuIfG_dwkcjAdPbw7v92bm9UinMQ0ScslgwBgkN4vJ84ADlwMhVAIJnJAuC0MVJFHEO6QLwOIgkWF0RnrOrQFARVJ1ycf7bDrbxcHLfHxLhw2d1BtrdpjTea2ris6Wa8xaOsbWS2kaOqw-jS3bVU0LY-lw25rG1Gbr6BuuyqxCR--087i3HpLPyWmhK4cXR-2T14f7xegpmM4eJ6PhNMh4wtsggwIyCKXKE5VrvpQFj5mKI1bEKpZ-ZDkyBI2FBJS50t7KQxQqi2GZi0T0yfUh19__tUXXpmuztY1fmQoQIuJCeemT6ODKrHHOYpFmZav3n7VWl1XKIN23mfo2032b6bFND8IfcGPLWtvv_5CrA1Ii4i-7VFIKKX4A39h_ww
CODEN	IEIMAO
CitedBy_id	crossref_primary_10_1109_JIOT_2025_3564058 crossref_primary_10_1109_TGRS_2025_3590447 crossref_primary_10_1109_TIM_2024_3522698 crossref_primary_10_1007_s10489_024_06213_3 crossref_primary_10_1007_s11227_025_07822_6 crossref_primary_10_1109_TGRS_2024_3486559 crossref_primary_10_1155_joro_8556780 crossref_primary_10_1038_s41598_025_07021_6 crossref_primary_10_1007_s11227_025_07585_0 crossref_primary_10_1109_TIM_2025_3548792 crossref_primary_10_1088_2631_8695_adf71d crossref_primary_10_1007_s10462_025_11253_3 crossref_primary_10_1109_JSTARS_2025_3551551 crossref_primary_10_1117_1_JEI_34_2_023014 crossref_primary_10_1007_s11760_025_04370_7 crossref_primary_10_1109_TIM_2025_3604925 crossref_primary_10_1109_ACCESS_2024_3515201 crossref_primary_10_1109_ACCESS_2025_3546622 crossref_primary_10_3390_rs16234374 crossref_primary_10_1109_TIM_2025_3559616 crossref_primary_10_1109_TIM_2025_3604122 crossref_primary_10_1109_ACCESS_2025_3551686 crossref_primary_10_1109_TIM_2025_3573344 crossref_primary_10_1109_TGRS_2025_3578800 crossref_primary_10_1007_s11554_024_01592_9 crossref_primary_10_1109_TIM_2025_3544365 crossref_primary_10_1007_s11227_024_06487_x crossref_primary_10_1007_s11760_025_04612_8 crossref_primary_10_1007_s11227_025_07577_0 crossref_primary_10_1038_s41598_025_15975_w crossref_primary_10_1109_TITS_2025_3545942 crossref_primary_10_1007_s11554_025_01682_2 crossref_primary_10_1109_TIM_2024_3522436 crossref_primary_10_1109_LGRS_2025_3550349 crossref_primary_10_1109_TIM_2025_3576955 crossref_primary_10_48084_etasr_11105 crossref_primary_10_1007_s11227_024_06527_6 crossref_primary_10_3389_fpls_2025_1540670 crossref_primary_10_1007_s44443_025_00223_y crossref_primary_10_1109_TCSVT_2024_3519569 crossref_primary_10_1007_s11554_024_01562_1 crossref_primary_10_1109_ACCESS_2025_3585561 crossref_primary_10_1109_TVT_2024_3496513 crossref_primary_10_1109_JSTARS_2025_3528057 crossref_primary_10_1007_s11760_024_03361_4 crossref_primary_10_1109_TIM_2025_3551431 crossref_primary_10_3389_fpls_2025_1617997 crossref_primary_10_35784_iapgos_6968 crossref_primary_10_1038_s41598_025_92148_9 crossref_primary_10_1109_TIM_2025_3561424
Cites_doi	10.1109/CVPRW59228.2023.00564 10.1109/CVPR.2018.00644 10.1109/ICCVW.2019.00030 10.1109/CVPR.2019.00720 10.1109/CVPR46437.2021.01422 10.1007/978-3-319-10602-1_48 10.1109/CVPR.2017.211 10.1007/978-3-319-46448-0_2 10.1016/j.procs.2022.01.135 10.1109/CVPR46437.2021.01074 10.1007/978-3-031-20077-9_31 10.1109/ICCV.2019.00929 10.1109/ICCV.2019.00972 10.1007/978-3-030-01264-9_45 10.1109/TETCI.2023.3235381 10.1609/aaai.v33i01.33019259 10.1109/ICCV.2019.00667 10.1109/tpami.2016.2577031 10.1109/TIM.2022.3158998 10.1109/ICIP46576.2022.9897990 10.1109/TIM.2022.3181903 10.1109/TPAMI.2023.3290594 10.1109/CVPR52688.2022.01330 10.18653/v1/P19-1580 10.1109/TITS.2023.3273286 10.1109/ICCV.2015.169 10.1109/TIM.2021.3052575 10.1109/TIM.2022.3192056 10.3390/electronics12102323 10.1109/CVPR42600.2020.01261 10.1109/ICCV.2017.324 10.1109/TITS.2022.3193909 10.1016/j.eswa.2021.114602 10.1109/CVPR42600.2020.00978 10.1109/ICIP42928.2021.9506347 10.1109/ICCV.2017.322 10.1016/j.autcon.2018.02.009 10.1109/TIM.2022.3196954
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/TIM.2024.3379090
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1557-9662
EndPage	16
ExternalDocumentID	10_1109_TIM_2024_3379090 10474434
Genre	orig-research
GrantInformation_xml	– fundername: Key Research and Development Program of Jiangsu Province grantid: BE2020083-3 – fundername: National Natural Science Foundation of China grantid: 52225212; U20A20333; 52072160 funderid: 10.13039/501100001809
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 85S 8WZ 97E A6W AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 TWZ VH1 VJK AAYXX CITATION 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c292t-c0f0c0547d97da2b4f2817861f87848171de1e0aef40e4d7a54725e37c80bd393
IEDL.DBID	RIE
ISICitedReferencesCount	159
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001197885000014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9456
IngestDate	Mon Jun 30 08:28:23 EDT 2025 Sat Nov 29 08:08:25 EST 2025 Tue Nov 18 22:28:51 EST 2025 Wed Aug 27 01:42:30 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c292t-c0f0c0547d97da2b4f2817861f87848171de1e0aef40e4d7a54725e37c80bd393
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-2937-7162 0000-0002-2079-3867 0000-0002-9136-8091 0009-0004-9552-986X 0000-0002-0633-9887
PQID	3033623703
PQPubID	85462
PageCount	16
ParticipantIDs	proquest_journals_3033623703 crossref_primary_10_1109_TIM_2024_3379090 ieee_primary_10474434 crossref_citationtrail_10_1109_TIM_2024_3379090
PublicationCentury	2000
PublicationDate	20240000 2024-00-00 20240101
PublicationDateYYYYMMDD	2024-01-01
PublicationDate_xml	– year: 2024 text: 20240000
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on instrumentation and measurement
PublicationTitleAbbrev	TIM
PublicationYear	2024
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 ref34 Jocher (ref14) 2022 ref36 ref31 ref11 ref33 ref10 ref32 Chen (ref30); 33 ref2 ref1 ref17 ref39 ref16 ref38 ref19 ref18 ref24 ref23 ref26 ref25 ref20 ref42 ref41 ref22 ref21 Zhu (ref37) ref28 Ge (ref15) 2021 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40
References_xml	– volume: 33 start-page: 5621 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref30 article-title: RepPoints V2: Verification meets regression for object detection – ident: ref10 doi: 10.1109/CVPRW59228.2023.00564 – ident: ref32 doi: 10.1109/CVPR.2018.00644 – ident: ref41 doi: 10.1109/ICCVW.2019.00030 – ident: ref37 article-title: Deformable DETR: Deformable transformers for end-to-end object detection publication-title: arXiv:2010.04159 – ident: ref25 doi: 10.1109/CVPR.2019.00720 – ident: ref38 doi: 10.1109/CVPR46437.2021.01422 – ident: ref42 doi: 10.1007/978-3-319-10602-1_48 – ident: ref17 doi: 10.1109/CVPR.2017.211 – ident: ref9 doi: 10.1007/978-3-319-46448-0_2 – ident: ref1 doi: 10.1016/j.procs.2022.01.135 – ident: ref12 doi: 10.1109/CVPR46437.2021.01074 – ident: ref39 doi: 10.1007/978-3-031-20077-9_31 – ident: ref24 doi: 10.1109/ICCV.2019.00929 – ident: ref35 doi: 10.1109/ICCV.2019.00972 – ident: ref33 doi: 10.1007/978-3-030-01264-9_45 – ident: ref2 doi: 10.1109/TETCI.2023.3235381 – ident: ref26 doi: 10.1609/aaai.v33i01.33019259 – ident: ref34 doi: 10.1109/ICCV.2019.00667 – ident: ref7 doi: 10.1109/tpami.2016.2577031 – ident: ref21 doi: 10.1109/TIM.2022.3158998 – ident: ref29 doi: 10.1109/ICIP46576.2022.9897990 – ident: ref5 doi: 10.1109/TIM.2022.3181903 – volume-title: Ultralytics/YOLOv5: v7. 0-YOLOv5 Sota Realtime Instance Segmentation year: 2022 ident: ref14 – ident: ref16 doi: 10.1109/TPAMI.2023.3290594 – ident: ref27 doi: 10.1109/CVPR52688.2022.01330 – ident: ref31 doi: 10.18653/v1/P19-1580 – ident: ref4 doi: 10.1109/TITS.2023.3273286 – ident: ref6 doi: 10.1109/ICCV.2015.169 – ident: ref18 doi: 10.1109/TIM.2021.3052575 – ident: ref22 doi: 10.1109/TIM.2022.3192056 – ident: ref11 doi: 10.3390/electronics12102323 – ident: ref19 doi: 10.1109/CVPR42600.2020.01261 – ident: ref28 doi: 10.1109/ICCV.2017.324 – ident: ref23 doi: 10.1109/TITS.2022.3193909 – year: 2021 ident: ref15 article-title: YOLOx: Exceeding YOLO series in 2021 publication-title: arXiv:2107.08430 – ident: ref20 doi: 10.1016/j.eswa.2021.114602 – ident: ref36 doi: 10.1109/CVPR42600.2020.00978 – ident: ref13 doi: 10.1109/ICIP42928.2021.9506347 – ident: ref8 doi: 10.1109/ICCV.2017.322 – ident: ref40 doi: 10.1016/j.autcon.2018.02.009 – ident: ref3 doi: 10.1109/TIM.2022.3196954
SSID	ssj0007647
Score	2.6808
Snippet	As self-driving vehicles become more prevalent, the speed and accuracy of detecting surrounding objects through onboard sensing technology have become...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	2-D object detection Accuracy Algorithms Autonomous cars Autonomous driving Commercial vehicles Feature extraction highway traffic Image recognition Location awareness Object detection Object recognition Safety YOLO
Title	YOLOv8-QSD: An Improved Small Object Detection Algorithm for Autonomous Vehicles Based on YOLOv8
URI	https://ieeexplore.ieee.org/document/10474434 https://www.proquest.com/docview/3033623703
Volume	73
WOSCitedRecordID	wos001197885000014&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1557-9662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007647 issn: 0018-9456 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB4BolI50JaCWB6VD730ENaxvXHc21JAVGrZVtCKnlLHGQPSkkW7WX5_x04WrVQVqafkMLaifPZ84_E8AN4Tx2UulYPECeESYgiZWOPLJPfKKotG0DM2m9AXF_n1tfnWJavHXBhEjMFneBRe411-NXHz4Crrh7ICSkm1CqtaZ22y1pPa1ZlqC2SmtIPJLFjcSXLTv_r8lU6CQh1JqQ0P6neJg2JTlb80caSXs1f_-WGvYbOzI9mwBf4NrGC9BRtL1QW34EWM7nSzt_D71-jL6DFPvl-efGTDmrWeBKzY5b0dj9moDM4YdoJNjMuq2XB8M5neNbf3jExaNpw3IfNhMp-xn3gbw-jYMZFfxUi0nXkbfpydXn06T7rWCoSJEU3iuOeOrDVdGV1ZUSov8lTnWepzHQrs67TCFLlFrziqSlsSFQOU2uW8rKSRO7BWT2rcBebTzBssOQrv1EB5k5WY2Zy0F3Jnpe5Bf_GzC9fVHQ_tL8ZFPH9wUxA8RYCn6ODpwYenEQ9tzY1nZLcDHEtyLRI9OFgAWnS7clYQXRNfS1Jye_8Ytg8vw-ytj-UA1prpHA9h3T02d7Ppu7jg_gBJONBz
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Nb9MwFH-CAWIc-BhDKwzwgQuHrI7txjG3wpg20bWgFTROwXGe2aQuRW26v59nJ50qIZA4JYfnJPIvfr_n5_cB8IY4LnOpHCROCJcQQ8jEGl8muVdWWTSCrrHZhB6P8_Nz87lLVo-5MIgYg8_wINzGs_xq7lbBVdYPZQWUkuo23BkoJXibrnWjeHWm2hKZKa1hMgzWp5Lc9Kcnp7QXFOpASm14UMAbLBTbqvyhiyPBHD36z097DA87S5INW-ifwC2sd-DBRn3BHbgX4zvd8in8-D4ZTa7z5MvZ4Ts2rFnrS8CKnV3Z2YxNyuCOYYfYxMismg1nP-eLy-biipFRy4arJuQ-zFdL9g0vYiAde0_0VzESbZ-8C1-PPk4_HCddcwVCxYgmcdxzR_aaroyurCiVF3mq8yz1uQ4l9nVaYYrcolccVaUtiYoBSu1yXlbSyGewVc9r3APm08wbLDkK79RAeZOVmNmc9BdyZ6XuQX892YXrKo-HBhizIu5AuCkIniLAU3Tw9ODtzYhfbdWNf8juBjg25FokerC_BrTo1uWyIMImxpak5p7_ZdhruH88PR0Vo5PxpxewHd7Uelz2YatZrPAl3HXXzeVy8Sr-fL8BTQTTug
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=YOLOv8-QSD%3A+An+Improved+Small+Object+Detection+Algorithm+for+Autonomous+Vehicles+Based+on+YOLOv8&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Wang%2C+Hai&rft.au=Liu%2C+Chenyu&rft.au=Cai%2C+Yingfeng&rft.au=Chen%2C+Long&rft.date=2024&rft.pub=IEEE&rft.issn=0018-9456&rft.volume=73&rft.spage=1&rft.epage=16&rft_id=info:doi/10.1109%2FTIM.2024.3379090&rft.externalDocID=10474434
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9456&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9456&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9456&client=summon