EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Topology-Aware Lane Detection with Relational Reasoning and Consistency Constraints

Danyang Dong iD, Qibo Zhang iD, Yihui Zhan iD, Tianqing Su iD, Quanke Su, Samuel S Mao, Yusheng Xiang iD

Sensors · 05.07.2026 · 26 (13) · 4278

DOI: 10.3390/s26134278 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.07.2026. Verfasst von Danyang Dong und 6 weiteren Autor:innen. Beteiligte Einrichtung: Center for Intelligent Autonomous Systems, Nantong University, Nantong 226019, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Provincial Department of Industry and Information Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lane detection is a fundamental perception task for autonomous driving and intelligent transportation systems. Although existing methods have achieved promising performance, many of them mainly focus on individual lane instances and insufficiently exploit the structural relationships among lanes, such as relative ordering, geometric continuity, and spatial parallelism. This limitation may lead to broken lanes, ordering errors, and geometric inconsistencies in complex road scenarios. To address these issues, we propose TPDNet, a topology-aware lane detection framework that incorporates structural reasoning into the detection pipeline at three complementary levels. First, a Topology-aware Perception Reasoner (TPR) is introduced at the feature level to capture relational dependencies among lane features and enhance the representation of global road topology. Second, a Topology-Decoupled Head (TDH) is designed at the prediction level to decouple geometric regression from lane classification, thereby reducing task interference and improving prediction stability. Third, a Topology Consistency Loss (TCL) is formulated as a complementary supervision term to encourage smoothness and ordering consistency in predicted lanes. Extensive experiments on three public benchmarks demonstrate the effectiveness of the proposed method. On CULane, TPDNet achieves an F1@50 of 81.46 with ResNet101 and remains competitive with the strongest compared methods, while showing improved robustness in challenging scenarios such as Curve and Dazzle light. On TuSimple, TPDNet obtains an F1 score of 98.01 among the compared methods, while maintaining competitive accuracy. On CurveLanes, TPDNet achieves an mF1 of 58.74, exceeding the strongest baseline by 4.98 points. These results suggest that topology-aware reasoning can improve the generalization capability of lane detection and help produce more structurally coherent lane predictions under diverse road conditions.

Schlagwörter

Stichwörter der Autor:innen

autonomous drivingdeep learninglane detectionstructural consistencytopology-aware learning

Autor:innen und Institutionen

  • Center for Intelligent Autonomous Systems, Nantong University, Nantong 226019, China.
  • Department of AI, SunnyWay LLC, Suzhou 215000, China.
  • Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511458, China.
  • Department of Mechanical Engineering, University of California at Berkeley, Berkeley, CA 94720, USA.

ORCID-Profile: Danyang Dong, Qibo Zhang, Yihui Zhan, Tianqing Su, Yusheng Xiang

Förderung

  • Jiangsu Provincial Department of Industry and Information Technology

Zitieren

APA

Dong, D., Zhang, Q., Zhan, Y., Su, T., Su, Q., Mao, S. S., & Xiang, Y. (2026). Topology-Aware Lane Detection with Relational Reasoning and Consistency Constraints. Sensors, 26(13), 4278. https://doi.org/10.3390/s26134278

Vancouver

Dong D, Zhang Q, Zhan Y, Su T, Su Q, Mao SS, et al. Topology-Aware Lane Detection with Relational Reasoning and Consistency Constraints. Sensors. 2026;26(13):4278. doi:10.3390/s26134278

BibTeX
@article{Dong2026,
  author = {Dong, Danyang and Zhang, Qibo and Zhan, Yihui and Su, Tianqing and Su, Quanke and Mao, Samuel S and Xiang, Yusheng},
  title = {Topology-Aware Lane Detection with Relational Reasoning and Consistency Constraints},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {4278},
  doi = {10.3390/s26134278}
}
Kostenlos starten →