Datasets for Lane Detection in Autonomous Driving: A Comprehensive Review
Jörg Gamerdinger, Sven Teufel, Oliver Bringmann
TL;DR
This survey addresses the problem of selecting appropriate lane-detection datasets for robust autonomous-driving development. It systematically catalogs and analyzes 31 public lane-detection datasets, focusing on sensors, annotation types, and environmental diversity to reveal strengths and gaps. The work highlights OpenLane/OpenDenseLane as strong candidates for high-robustness, discusses the limitations of synthetic data, and emphasizes the need for broader adverse-weather coverage and 3D ground truth. The findings provide actionable guidance for researchers to choose datasets aligned with their modality and weather requirements, ultimately advancing reliable lane-detection systems.
Abstract
Accurate lane detection is essential for automated driving, enabling safe and reliable vehicle navigation in a variety of road scenarios. Numerous datasets have been introduced to support the development and evaluation of lane detection algorithms, each differing in terms of the amount of data, sensor types, annotation granularity, environmental conditions, and scenario diversity. This paper provides a comprehensive review of over 30 publicly available lane detection datasets, systematically analysing their characteristics, advantages and limitations. We classify these datasets based on key factors such as sensor resolution, annotation types and diversity of road and weather conditions. By identifying existing challenges and research gaps, we highlight opportunities for future dataset improvements that can further drive innovation in robust lane detection. This survey serves as a resource for researchers seeking appropriate datasets for lane detection, and contributes to the broader goal of advancing autonomous driving.