Improving Yolo Detection Performance of Autonomous Vehicles in Adverse Weather Conditions Using Metaheuristic Algorithms

dc.authorid ozcan, ibrahim/0000-0001-9471-5119
dc.authorid ALTUN, Prof. Dr. Yusuf/0000-0002-2099-0959
dc.authorid PARLAK (PhD), CEVAHIR/0000-0002-5500-7379
dc.authorscopusid 57225723807
dc.authorscopusid 25031391400
dc.authorscopusid 55807221400
dc.authorwosid özcan, ibrahim/IAP-0607-2023
dc.authorwosid PARLAK (PhD), Cevahir/ABA-4914-2021
dc.authorwosid ALTUN, Prof. Dr. Yusuf/AAA-9929-2020
dc.contributor.author Ozcan, Ibrahim
dc.contributor.author Parlak, Cevahir
dc.contributor.author Altun, Yusuf
dc.contributor.author Parlak, Cevahir
dc.contributor.other Bilgisayar Mühendisliği Bölümü
dc.date.accessioned 2025-01-11T13:03:29Z
dc.date.available 2025-01-11T13:03:29Z
dc.date.issued 2024
dc.department Fenerbahçe University en_US
dc.department-temp [Ozcan, Ibrahim] Kutahya Dumlupinar Univ, Dept Comp Usage, TR-43020 Kutahya, Turkiye; [Altun, Yusuf] Duzce Univ, Dept Comp Engn, TR-81620 Duzce, Turkiye; [Parlak, Cevahir] Fenerbahce Univ, Dept Comp Engn, TR-43020 Istanbul, Turkiye en_US
dc.description ozcan, ibrahim/0000-0001-9471-5119; ALTUN, Prof. Dr. Yusuf/0000-0002-2099-0959; PARLAK (PhD), CEVAHIR/0000-0002-5500-7379 en_US
dc.description.abstract Despite the rapid advances in deep learning (DL) for object detection, existing techniques still face several challenges. In particular, object detection in adverse weather conditions (AWCs) requires complex and computationally costly models to achieve high accuracy rates. Furthermore, the generalization capabilities of these methods struggle to show consistent performance under different conditions. This work focuses on improving object detection using You Only Look Once (YOLO) versions 5, 7, and 9 in AWCs for autonomous vehicles. Although the default values of the hyperparameters are successful for images without AWCs, there is a need to find the optimum values of the hyperparameters in AWCs. Given the many numbers and wide range of hyperparameters, determining them through trial and error is particularly challenging. In this study, the Gray Wolf Optimizer (GWO), Artificial Rabbit Optimizer (ARO), and Chimpanzee Leader Selection Optimization (CLEO) are independently applied to optimize the hyperparameters of YOLOv5, YOLOv7, and YOLOv9. The results show that the preferred method significantly improves the algorithms' performances for object detection. The overall performance of the YOLO models on the object detection for AWC task increased by 6.146%, by 6.277% for YOLOv7 + CLEO, and by 6.764% for YOLOv9 + GWO. en_US
dc.description.sponsorship Duzce University Scientific Research Projects Coordination Office [BAP-2020.06.01.1060] en_US
dc.description.sponsorship This research was funded by Duzce University Scientific Research Projects Coordination Office with the Scientific Research Project grant number BAP-2020.06.01.1060. en_US
dc.description.woscitationindex Science Citation Index Expanded
dc.identifier.citation 1
dc.identifier.doi 10.3390/app14135841
dc.identifier.issn 2076-3417
dc.identifier.issue 13 en_US
dc.identifier.scopus 2-s2.0-85198479179
dc.identifier.scopusquality Q1
dc.identifier.uri https://doi.org/10.3390/app14135841
dc.identifier.uri https://hdl.handle.net/20.500.14627/278
dc.identifier.volume 14 en_US
dc.identifier.wos WOS:001269153900001
dc.identifier.wosquality Q1
dc.language.iso en en_US
dc.publisher Mdpi en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.scopus.citedbyCount 9
dc.subject Aro en_US
dc.subject Cleo en_US
dc.subject Dawn Dataset en_US
dc.subject Deep Learning en_US
dc.subject Gwo en_US
dc.subject Object Detection en_US
dc.subject Rtts Dataset en_US
dc.subject Yolov5 en_US
dc.subject Yolov7 en_US
dc.subject Yolov9 en_US
dc.title Improving Yolo Detection Performance of Autonomous Vehicles in Adverse Weather Conditions Using Metaheuristic Algorithms en_US
dc.type Article en_US
dc.wos.citedbyCount 6
dspace.entity.type Publication
relation.isAuthorOfPublication d57697e4-e3d0-4c57-bb5c-4b92ceb92d1a
relation.isAuthorOfPublication.latestForDiscovery d57697e4-e3d0-4c57-bb5c-4b92ceb92d1a
relation.isOrgUnitOfPublication 85e04a04-fb9d-4894-961f-e92f27bb6cb6
relation.isOrgUnitOfPublication.latestForDiscovery 85e04a04-fb9d-4894-961f-e92f27bb6cb6

Files