Lane detection is a critical function for autonomous driving. With the recent development of deep learning and the publication of camera lane datasets and benchmarks, camera lane detection networks (CLDNs) have been remarkably developed. Unfortunately, CLDNs rely on camera images which are often distorted near the vanishing line and prone to poor lighting condition. This is in contrast with Lidar lane detection networks (LLDNs), which can directly extract the lane lines on the bird's eye view (BEV) for motion planning and operate robustly under various lighting conditions. However, LLDNs have not been actively studied, mostly due to the absence of large public lidar lane datasets. In this paper, we introduce KAIST-Lane (K-Lane), the world's first and the largest public urban road and highway lane dataset for Lidar. K-Lane has more than 15K frames and contains annotations of up to six lanes under various road and traffic conditions, e.g., occluded roads of multiple occlusion levels, roads at day and night times, merging (converging and diverging) and curved lanes. We also provide baseline networks we term Lidar lane detection networks utilizing global feature correlator (LLDN-GFC). LLDN-GFC exploits the spatial characteristics of lane lines on the point cloud, which are sparse, thin, and stretched along the entire ground plane of the point cloud. From experimental results, LLDN-GFC achieves the state-of-the-art performance with an F1- score of 82.1%, on the K-Lane. Moreover, LLDN-GFC shows strong performance under various lighting conditions, which is unlike CLDNs, and also robust even in the case of severe occlusions, unlike LLDNs using the conventional CNN. The K-Lane, LLDN-GFC training code, pre-trained models, and complete development kits including evaluation, visualization and annotation tools are available at https://github.com/kaist-avelab/k-lane.

翻译：车道检测是自动驾驶的关键功能。随着深度学习技术的近期发展以及相机车道数据集与基准的发布，相机车道检测网络（CLDN）取得了长足进步。然而，CLDN依赖相机图像，而相机图像在消失线附近常存在畸变问题，且易受不良光照条件影响。相比之下，激光雷达车道检测网络（LLDN）可直接在鸟瞰视角（BEV）下提取车道线用于运动规划，并在多种光照条件下稳健运行。但受限于缺乏大规模公开激光雷达车道数据集，LLDN尚未得到充分研究。本文提出KAIST-Lane（K-Lane），这是全球首个且规模最大的面向城市道路与高速公路的公开激光雷达车道数据集。K-Lane包含超过1.5万帧数据，针对多种道路与交通场景（如多遮挡等级的道路、昼夜路况、汇入与分流路段、弯道）标注了最多六条车道线。我们还提出了基于全局特征关联器的激光雷达车道检测网络（LLDN-GFC）作为基线模型。LLDN-GFC充分利用点云中车道线的空间特性——稀疏、纤细且沿整个点云地平面延展。实验结果表明，LLDN-GFC在K-Lane上达到了82.1%的F1分数，实现了当前最优性能。与CLDN不同，LLDN-GFC在各类光照条件下均展现出强劲性能；即便在严重遮挡情况下，其鲁棒性也优于采用传统CNN的LLDN。K-Lane数据集、LLDN-GFC训练代码、预训练模型及包含评估、可视化和标注工具的完整开发套件均已开源发布于https://github.com/kaist-avelab/k-lane。