Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/13220
Full metadata record
DC FieldValueLanguage
dc.contributor.authorNalçakan, Yağızen_US
dc.contributor.authorBaştanlar, Yalınen_US
dc.date.accessioned2023-03-09T13:32:56Z-
dc.date.available2023-03-09T13:32:56Z-
dc.date.issued2023-
dc.identifier.urihttps://doi.org/10.1007/s11760-023-02512-3-
dc.identifier.urihttps://hdl.handle.net/11147/13220-
dc.description.abstractThe detection of the maneuvers of the surrounding vehicles is important for autonomous vehicles to act accordingly to avoid possible accidents. This study proposes a framework based on contrastive representation learning to detect potentially dangerous cut-in maneuvers that can happen in front of the ego vehicle. First, the encoder network is trained in a self-supervised fashion with contrastive loss where two augmented videos of the same video clip stay close to each other in the embedding space, while augmentations from different videos stay far apart. Since no maneuver labeling is required in this step, a relatively large dataset can be used. After this self-supervised training, the encoder is fine-tuned with our cut-in/lane-pass labeled datasets. Instead of using original video frames, we simplified the scene by highlighting surrounding vehicles and ego-lane. We have investigated the use of several classification heads, augmentation types, and scene simplification alternatives. The most successful model outperforms the best fully supervised model by ∼ 2% with an accuracy of 92.52%en_US
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relation.ispartofSignal Image and Video Processingen_US
dc.rightsinfo:eu-repo/semantics/embargoedAccessen_US
dc.subjectContrastive representation learningen_US
dc.subjectDriver assistance systemsen_US
dc.subjectVehicle maneuver classificationen_US
dc.titleCut-in maneuver detection with self-supervised contrastive video representation learningen_US
dc.typeArticleen_US
dc.authorid0000-0001-8867-842Xen_US
dc.authorid0000-0002-3774-6872en_US
dc.institutionauthorNalçakan, Yağızen_US
dc.institutionauthorBaştanlar, Yalınen_US
dc.departmentİzmir Institute of Technology. Computer Engineeringen_US
dc.identifier.wosWOS:000941308900001en_US
dc.identifier.scopus2-s2.0-85149040846en_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.identifier.doi10.1007/s11760-023-02512-3-
dc.contributor.affiliation01. Izmir Institute of Technologyen_US
dc.contributor.affiliation01. Izmir Institute of Technologyen_US
dc.relation.issn1863-1703en_US
item.grantfulltextembargo_20250701-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.fulltextWith Fulltext-
item.languageiso639-1en-
item.openairetypeArticle-
item.cerifentitytypePublications-
crisitem.author.dept03.04. Department of Computer Engineering-
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Files in This Item:
File Description SizeFormat 
s11760-023-02512-3.pdf
  Until 2025-07-01
Article1.78 MBAdobe PDFView/Open    Request a copy
Show simple item record



CORE Recommender

SCOPUSTM   
Citations

2
checked on Feb 16, 2024

Page view(s)

126
checked on Feb 19, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.