SnowyLane: Robust Lane Detection on Snow-Covered Rural Roads Using Infrastructural Elements
Authors:
- 18 November 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3283-3290
Abstract
Lane detection for autonomous driving in snowcovered environments remains a major challenge due to the frequent absence or occlusion of lane markings. In this paper, we present a novel, robust and realtime capable approach that bypasses the reliance on traditional lane markings by detecting roadside features-specifically vertical roadside posts called delineators-as indirect lane indicators. Our method first perceives these posts, then fits a smooth lane trajectory using a parameterized Bézier curve model, leveraging spatial consistency and road geometry. To support training and evaluation in these challenging scenarios, we introduce SnowyLane, a new synthetic dataset containing 80,000 annotated frames capture winter driving conditions, with varying snow coverage, and lighting conditions. Compared to state-of-the-art lane detection systems, our approach demonstrates significantly improved robustness in adverse weather, particularly in cases with heavy snow occlusion. This work establishes a strong foundation for reliable lane detection in winter scenarios and contributes a valuable resource for future research in all-weather autonomous driving. The dataset is available at https://ekut-es.github.io/snowy-laneKeywords
All Related Versions
This publication has 22 references indexed in Scilit:
- A Robust Lane Detection Algorithm Adaptable to Challenging Weather ConditionsIEEE Access, 2024
- Lane Detection in Autonomous Vehicles: A Systematic ReviewIEEE Access, 2023
- Ultra Fast Structure-Aware Deep Lane Detection2020
- PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection2020
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning2020
- Lane Detection: A Survey with New ResultsJournal of Computer Science and Technology, 2020
- Simulating Photo-realistic Snow and Fog on Existing Images for Enhanced CNN Training and Evaluation2019
- Towards Robust CNN-based Object Detection through Augmentation with Synthetic Rain Variations2019
- Lane Datasets for Lane Detection2019
- Lane detection using spline modelPattern Recognition Letters, 2000