Hybrid Lane Detection and Turn Prediction Framework using U-Net-based Lane Marking Visibility and Geometric Curve Analysis

Autonomous driving systems rely heavily on accurate lane detection and turn prediction for safe and reliable navigation. However, faded, occluded, or inconsistent lane markings present significant challenges, especially under varying road conditions. To address these issues, this paper introduces a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 International Conference on Modern Sustainable Systems (CMSS) S. 1194 - 1200
Hauptverfasser: I, Lakshmi Narayana, Vamsi, T. M. N
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 12.08.2025
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Autonomous driving systems rely heavily on accurate lane detection and turn prediction for safe and reliable navigation. However, faded, occluded, or inconsistent lane markings present significant challenges, especially under varying road conditions. To address these issues, this paper introduces a hybrid framework that integrates deep learning with classical vision techniques to enhance lane perception and directional understanding. U-Net, a convolutional neural network architecture, is employed to perform semantic segmentation for lane marking visibility, ensuring robust detection even in degraded scenarios. For straight lanes, a region of interest is extracted, and the Hough Transform is applied to identify solid and dashed lanes based on line continuity and slope filtering. Curved lane detection is achieved by generating a bird's-eye view using homography, followed by binary and HSV thresholding to isolate white and yellow lanes. Polynomial fitting models the lane curvature, and the radius of curvature is computed accordingly. Turn direction is predicted by evaluating the sign of the highest-degree polynomial coefficient. Experimental validation demonstrates that the proposed framework improves both lane boundary detection accuracy and turn prediction reliability. This method provides a balanced trade-off between deep learning precision and classical algorithm efficiency, making it suitable for real-world autonomous vehicle applications.
AbstractList Autonomous driving systems rely heavily on accurate lane detection and turn prediction for safe and reliable navigation. However, faded, occluded, or inconsistent lane markings present significant challenges, especially under varying road conditions. To address these issues, this paper introduces a hybrid framework that integrates deep learning with classical vision techniques to enhance lane perception and directional understanding. U-Net, a convolutional neural network architecture, is employed to perform semantic segmentation for lane marking visibility, ensuring robust detection even in degraded scenarios. For straight lanes, a region of interest is extracted, and the Hough Transform is applied to identify solid and dashed lanes based on line continuity and slope filtering. Curved lane detection is achieved by generating a bird's-eye view using homography, followed by binary and HSV thresholding to isolate white and yellow lanes. Polynomial fitting models the lane curvature, and the radius of curvature is computed accordingly. Turn direction is predicted by evaluating the sign of the highest-degree polynomial coefficient. Experimental validation demonstrates that the proposed framework improves both lane boundary detection accuracy and turn prediction reliability. This method provides a balanced trade-off between deep learning precision and classical algorithm efficiency, making it suitable for real-world autonomous vehicle applications.
Author Vamsi, T. M. N
I, Lakshmi Narayana
Author_xml – sequence: 1
  givenname: Lakshmi Narayana
  surname: I
  fullname: I, Lakshmi Narayana
  email: ilnarayana1226@gmail.com
  organization: Andhra University,Department of CS & SE
– sequence: 2
  givenname: T. M. N
  surname: Vamsi
  fullname: Vamsi, T. M. N
  email: mthalata@gitam.edu
  organization: GITAM Deemed University,Department of CSE,Vizag
BookMark eNo1kMtOwzAURI0ECyj9AyT8AymxHTvNsgq0RUoBKYVt5dg36KqJgxwHlH49j5bVSGc0ZzFX5Nx1Dgi5ZfGMsTi7yzdlqZRUasZjLn8Ym3MpsjMyzdJsLgSTSrI4vSSH9Vh5tLTQDug9BDABO0e1s3Q7eEdfPFg8sqXXLXx1fk-HHt07fY2eIESV7uE032i__y3esMcKGwzjn2cFXQvBo6H54D-BLpxuxh77a3JR66aH6SknpFw-bPN1VDyvHvNFEWEmQiRjnibAJTd1aoEZVUMtuFEJN9aYNM0MrxPGba0rZRnnJk4EaGUqq63UTEzIzdGKALD78NhqP-7-DxHfPTldbg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CMSS66566.2025.11182539
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331565107
EndPage 1200
ExternalDocumentID 11182539
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i93t-50274e252cf7de1c6fef32c642cdcc779c2f412dfab6d122c043ea6cbdad5a13
IEDL.DBID RIE
IngestDate Wed Oct 15 14:21:21 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-50274e252cf7de1c6fef32c642cdcc779c2f412dfab6d122c043ea6cbdad5a13
PageCount 7
ParticipantIDs ieee_primary_11182539
PublicationCentury 2000
PublicationDate 2025-Aug.-12
PublicationDateYYYYMMDD 2025-08-12
PublicationDate_xml – month: 08
  year: 2025
  text: 2025-Aug.-12
  day: 12
PublicationDecade 2020
PublicationTitle 2025 International Conference on Modern Sustainable Systems (CMSS)
PublicationTitleAbbrev CMSS
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.917998
Snippet Autonomous driving systems rely heavily on accurate lane detection and turn prediction for safe and reliable navigation. However, faded, occluded, or...
SourceID ieee
SourceType Publisher
StartPage 1194
SubjectTerms Accuracy
Autonomous vehicles
Bird's-Eye View
Curve Fitting
Deep learning
Homography
Hough Transform
Lane detection
Lane Marking Visibility
Polynomials
Predictive models
Reliability
Roads
Semantic segmentation
Transforms
Turn Prediction
U-Net
Title Hybrid Lane Detection and Turn Prediction Framework using U-Net-based Lane Marking Visibility and Geometric Curve Analysis
URI https://ieeexplore.ieee.org/document/11182539
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwMhECW28eBJjTV-h4NX2oVll-VcrT3UpknV9NawMJge3Jq6bVJ_vTt0V-PBgzcCDCQzITPAezOE3Gbep1qBZFJYxyRozrRXjhmuc2VzmUkbLD1S43E2m-lJTVYPXBgACOAz6GIz_OW7pV3jU1mPYzScxLpFWkqlO7JWjdnike71H6fTFOOT6tonkm4z-1fdlOA2Bof_3PCIdH4IeHTy7VqOyR4UJ-RzuEV6FR2ZAugdlAFEVVBTOIr16isB_HQJfYMGckUR1_5Kn9kYSoYeqxZHig4OvCxqeOw2rPMAyzcssWVpf73aAG1SlnTIdHD_1B-yunQCW-i4ZAleNkEkwlZ6B25TDz4WNkWDWKuUtsJLLpw3eeq4EDaSMZjU5s64xPD4lLSLZQFnhDqRmcSb6phWkRM4MJGvYiATIwM2j6w4Jx1U2_x9lxtj3mjs4o_-S3KAxsFXWS6uSLtcreGa7NtNufhY3QSLfgH6faZE
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBT2pWPFtDl5TN9lnztVacbsUWqW3kk0m0oNbqdtC_fXuxF3FgwdvIU-YIcwk-b58hFwn1kYyhoAFQhsWgORM2tgwxWUe6zxIAu08ncZZlkwmcliT1R0XBgAc-Aw6WHRv-Waul3hVdsMxGw59uUm2UDqrpmvVqC3uyZvuYDSKMEOpDn4i7DT9fymnuMDR2_vnkvuk_UPBo8Pv4HJANqA4JB_9NRKsaKoKoLdQOhhVQVVhKCrWVwPw2cXV9RrQFUVk-wt9YhmUDGNWPRxJOtjwPKsBsms3zz3MX1FkS9PucrEC2nxa0iaj3t2422e1eAKbSb9kIR43QYRCV5YHriML1hc6QpdoHcdSCxtwYazKI8OF0F7gg4p0bpQJFfePSKuYF3BMqBGJCq2qNmqVO4EB5dkqC1I-cmBzT4sT0kazTd--fseYNhY7_aP-iuz0x4N0mj5kj2dkFx2Fd7RcnJNWuVjCBdnWq3L2vrh03v0Ezi2pjQ
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%3Abook&rft.genre=proceeding&rft.title=2025+International+Conference+on+Modern+Sustainable+Systems+%28CMSS%29&rft.atitle=Hybrid+Lane+Detection+and+Turn+Prediction+Framework+using+U-Net-based+Lane+Marking+Visibility+and+Geometric+Curve+Analysis&rft.au=I%2C+Lakshmi+Narayana&rft.au=Vamsi%2C+T.+M.+N&rft.date=2025-08-12&rft.pub=IEEE&rft.spage=1194&rft.epage=1200&rft_id=info:doi/10.1109%2FCMSS66566.2025.11182539&rft.externalDocID=11182539