Vehicle-pedestrian Instance Segmentation Algorithm Based on Improved YOLOv8n-seg

In the field of autonomous driving, the rapid and precise perception of the environment, along with effective segmentation of vehicles and pedestrians, is a critical area of research. The complexity of real-world scenes, often characterized by occlusions, can lead to suboptimal segmentation results....

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Engineering letters Ročník 33; číslo 6; s. 1879
Hlavní autori: Fang, Siwen, Zhang, Xinhe, Su, Bochao, Zhu, Wenxuan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Hong Kong International Association of Engineers 01.06.2025
Predmet:
ISSN:1816-093X, 1816-0948
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In the field of autonomous driving, the rapid and precise perception of the environment, along with effective segmentation of vehicles and pedestrians, is a critical area of research. The complexity of real-world scenes, often characterized by occlusions, can lead to suboptimal segmentation results. Moreover, the computational demands of existing models require substantial resources and time for processing image data. In autonomous driving systems, timely perception and decision-making are essential; computational delays can hinder vehicle responsiveness and increase the risk of driving errors. To enhance the performance of vehicle-pedestrian segmentation, this paper proposes a novel single-stage instance segmentation approach based on an improved YOLOv8n-seg model. This improvement involves redesigning the bottleneck module in the core C2f module of YOLOv8n-seg and replacing the feature fusion layer with a Bidirectional Feature Pyramid Network (BiFPN) structure. Evaluations conducted on the Cityscapes dataset demonstrate that our method achieves a 3.1% increase in the mAP50-95mask value and a 1% reduction in FLOPs compared to the original YOLOv8n-seg. Furthermore, experiments on the COCO subset show that our approach achieves a mAP50mask of 55.6%, mAP50-95mask of 34.2%, and significantly improves segmentation performance under various real-world conditions. Consequently, our approach not only enhances segmentation accuracy but also reduces computational complexity, effectively meeting the real-time requirements for vehicle segmentation in autonomous driving applications.
AbstractList In the field of autonomous driving, the rapid and precise perception of the environment, along with effective segmentation of vehicles and pedestrians, is a critical area of research. The complexity of real-world scenes, often characterized by occlusions, can lead to suboptimal segmentation results. Moreover, the computational demands of existing models require substantial resources and time for processing image data. In autonomous driving systems, timely perception and decision-making are essential; computational delays can hinder vehicle responsiveness and increase the risk of driving errors. To enhance the performance of vehicle-pedestrian segmentation, this paper proposes a novel single-stage instance segmentation approach based on an improved YOLOv8n-seg model. This improvement involves redesigning the bottleneck module in the core C2f module of YOLOv8n-seg and replacing the feature fusion layer with a Bidirectional Feature Pyramid Network (BiFPN) structure. Evaluations conducted on the Cityscapes dataset demonstrate that our method achieves a 3.1% increase in the mAP50-95mask value and a 1% reduction in FLOPs compared to the original YOLOv8n-seg. Furthermore, experiments on the COCO subset show that our approach achieves a mAP50mask of 55.6%, mAP50-95mask of 34.2%, and significantly improves segmentation performance under various real-world conditions. Consequently, our approach not only enhances segmentation accuracy but also reduces computational complexity, effectively meeting the real-time requirements for vehicle segmentation in autonomous driving applications.
Author Zhang, Xinhe
Su, Bochao
Zhu, Wenxuan
Fang, Siwen
Author_xml – sequence: 1
  givenname: Siwen
  surname: Fang
  fullname: Fang, Siwen
– sequence: 2
  givenname: Xinhe
  surname: Zhang
  fullname: Zhang, Xinhe
– sequence: 3
  givenname: Bochao
  surname: Su
  fullname: Su, Bochao
– sequence: 4
  givenname: Wenxuan
  surname: Zhu
  fullname: Zhu, Wenxuan
BookMark eNo9jstqwzAUREVJoWmafzB0bZAlWb5apqGPgMGFPmhXQY8bx8WWXUvJ91fQ0tUczmJmrsnCjx4vyLKAQuZUCVj8M_-4IusQOkOFqHipaLkkz-947GyP-YQOQ5w77bOdD1F7i9kLtgP6qGM3-mzTt-PcxeOQ3emALktqN0zzeE782dTNGXwesL0hlwfdB1z_5Yq8Pdy_bp_yunncbTd1PhVQxhwQuKPOVBwUMwpkoSsNlTTKGI4HQOTWCFtKgUlQZ4UzDJKRjAJaxlfk9rc3Xfg-pev7r_E0-zS554xxKaSCiv8AMTVPYg
ContentType Journal Article
Copyright Copyright International Association of Engineers 2025
Copyright_xml – notice: Copyright International Association of Engineers 2025
DBID 7SC
7TB
8FD
FR3
JQ2
KR7
L7M
L~C
L~D
DatabaseName Computer and Information Systems Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Engineering Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle Civil Engineering Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Civil Engineering Abstracts
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1816-0948
GroupedDBID 29G
2WC
5GY
5VS
7SC
7TB
8FD
AAKPC
ABDBF
ACIWK
ACUHS
ADMLS
ALMA_UNASSIGNED_HOLDINGS
EOJEC
ESX
FR3
I-F
JQ2
KQ8
KR7
L7M
L~C
L~D
MK~
OBODZ
OK1
OVT
P2P
TR2
TUS
~8M
ID FETCH-LOGICAL-p185t-8e83d0db73892b9861a7a876b9bb3ef8ee3cb4c564ebb30dc4db28b4c6208ec23
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001506721900013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1816-093X
IngestDate Mon Jun 30 07:22:44 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 6
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-p185t-8e83d0db73892b9861a7a876b9bb3ef8ee3cb4c564ebb30dc4db28b4c6208ec23
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
PQID 3223646987
PQPubID 2049041
ParticipantIDs proquest_journals_3223646987
PublicationCentury 2000
PublicationDate 2025-06-01
PublicationDateYYYYMMDD 2025-06-01
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-06-01
  day: 01
PublicationDecade 2020
PublicationPlace Hong Kong
PublicationPlace_xml – name: Hong Kong
PublicationTitle Engineering letters
PublicationYear 2025
Publisher International Association of Engineers
Publisher_xml – name: International Association of Engineers
SSID ssib044735905
ssj0000314636
Score 2.3161726
Snippet In the field of autonomous driving, the rapid and precise perception of the environment, along with effective segmentation of vehicles and pedestrians, is a...
SourceID proquest
SourceType Aggregation Database
StartPage 1879
SubjectTerms Complexity
Instance segmentation
Modules
Pedestrians
Perception
Performance enhancement
Real time
Title Vehicle-pedestrian Instance Segmentation Algorithm Based on Improved YOLOv8n-seg
URI https://www.proquest.com/docview/3223646987
Volume 33
WOSCitedRecordID wos001506721900013&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: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1816-0948
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044735905
  issn: 1816-093X
  databaseCode: M~E
  dateStart: 20060101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV07b9swECaaoEM7BOkLTZMWGoouBgGZlERyTAMHHVw7QJzUnQxRPD-AhHb9SD3lt-dIUZaCAEU7dCGI0wOEvhPveLzjR8hnaVTKjVFUpyBoIvKcasg4ZUyCdnm6sS8fu-6KXk8Oh-oipBWtPJ2AsFZut2rxX6FGGYLtSmf_Ae7dS1GAfQQdW4Qd278C_hqmTkQXYMCTclifEeBLAy5hchuKjWzr9GYyX87W09vWVzRlxm0blCEG7P_sd_t30tIVTB7F7uvTC1s3vhCoLh-pAs-z33V12S4cPZzZ6U6FLjdeq-bFNJ_Xd3rhD7DbTVDYEItgaZ0zVa5PHwUxG_rlsyTDCBsxSPQu8HnlCYHRGDVl5fGb1RRdnpURVLE53zqu9NqSVbv3vf7o_KrbHQ06w8GXxS_qOMbcXnwgXNkjezx2PAvf7zvV3JM4CmYV5j5vxXnbnaXm1uvVKJ-Ya--DDA7JQVg8RKcl6K_IM7CvycsGKG_IxVP4owr-qAl_tIM_8vBHKKrgjxrwvyVX553B2TcaWDPoAn2vNZUguYmNFuiKMq1k1s5FjjZPK605jCUAL3RSpFkCKIhNkRjNJEoyFksoGH9H9u3cwnsSpZJnwuCamokxut0yN7zN9DiLpYFUFckROak-yCj8AasRWgieOV5S8eHPl4_Ji1qHTsj-ermBj-R5cbeerZafPDoPUQxdsg
linkProvider ISSN International Centre
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=Vehicle-pedestrian+Instance+Segmentation+Algorithm+Based+on+Improved+YOLOv8n-seg&rft.jtitle=Engineering+letters&rft.au=Fang%2C+Siwen&rft.au=Zhang%2C+Xinhe&rft.au=Su%2C+Bochao&rft.au=Zhu%2C+Wenxuan&rft.date=2025-06-01&rft.pub=International+Association+of+Engineers&rft.issn=1816-093X&rft.eissn=1816-0948&rft.volume=33&rft.issue=6&rft.spage=1879&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1816-093X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1816-093X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1816-093X&client=summon