SnowyLane: Robust Lane Detection on Snow-covered Rural Roads Using Infrastructural Elements

2025-11-07

AI Summary

To address lane detection failure on snow-covered rural roads caused by missing or occluded lane markings, this paper proposes an implicit, geometry-driven approach that bypasses explicit lane-line detection. Instead, it leverages roadside delineator posts as geometric anchors and integrates parametric Bézier curve modeling with structural road constraints to robustly infer lane centerline trajectories in real time. A deep learning model detects delineator posts, followed by spatial consistency analysis and curve fitting to generate smooth, physically plausible centerlines. To enhance generalization under snowy conditions, we introduce SnowyLane—the first large-scale synthetic dataset specifically designed for snow-affected rural road scenarios. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches across diverse snow coverage levels and illumination conditions, exhibiting exceptional robustness under severe occlusion. This work establishes a new paradigm for all-weather autonomous driving in challenging low-marking environments.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Computer Vision: Large Vision Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Lane detection for autonomous driving in snow-covered 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 Bezier 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-lane

Problem

• Detects lane markings in snow-covered rural roads
• Uses roadside delineators as indirect lane indicators
• Creates synthetic dataset for winter driving conditions

Innovation

• Uses roadside delineators as lane indicators
• Applies Bezier curve model for trajectory fitting
• Introduces synthetic SnowyLane dataset for training