A map, as crucial information for downstream applications of an autonomous driving system, is usually represented in lanelines or centerlines. However, existing literature on map learning primarily focuses on either detecting geometry-based lanelines or perceiving topology relationships of centerlines. Both of these methods ignore the intrinsic relationship of lanelines and centerlines, that lanelines bind centerlines. While simply predicting both types of lane in one model is mutually excluded in learning objective, we advocate lane segment as a new representation that seamlessly incorporates both geometry and topology information. Thus, we introduce LaneSegNet, the first end-to-end mapping network generating lane segments to obtain a complete representation of the road structure. Our algorithm features two key modifications. One is a lane attention module to capture pivotal region details within the long-range feature space. Another is an identical initialization strategy for reference points, which enhances the learning of positional priors for lane attention. On the OpenLane-V2 dataset, LaneSegNet outperforms previous counterparts by a substantial gain across three tasks, \textit{i.e.}, map element detection (+4.8 mAP), centerline perception (+6.9 DET$_l$), and the newly defined one, lane segment perception (+5.6 mAP). Furthermore, it obtains a real-time inference speed of 14.7 FPS. Code is accessible at https://github.com/OpenDriveLab/LaneSegNet.

翻译：地图作为自动驾驶系统下游应用的关键信息，通常以车道线或中心线的形式表示。然而，现有地图学习文献主要关注基于几何的车道线检测或中心线拓扑关系感知。这两类方法均忽略了车道线与中心线的内在关联——车道线约束着中心线。若简单地在单一模型中同时预测两种车道类型，其学习目标会相互排斥。为此，我们提出将车道段作为新表征，该表征能够无缝融合几何与拓扑信息。基于此，我们引入LaneSegNet——首个端到端映射网络，通过生成车道段获得道路结构的完整表示。我们的算法具有两项关键改进：一是车道注意力模块，用于捕获长程特征空间中的关键区域细节；二是参考点的同质初始化策略，可增强车道注意力对位置先验的学习。在OpenLane-V2数据集上，LaneSegNet在三个任务中均显著优于先前方法：地图元素检测（+4.8 mAP）、中心线感知（+6.9 DET$_l$）以及新定义的车道段感知任务（+5.6 mAP）。此外，该方法实现了14.7 FPS的实时推理速度。代码开源地址：https://github.com/OpenDriveLab/LaneSegNet。