Vision-based mapping of lane semantics and topology for intelligent vehicles
Vision-based mapping of lane semantics and topology for intelligent vehicles
复制标题
DOI：
10.1016/j.jag.2022.102851
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Wei Tian;Xiaozhou Ren;Xianwang Yu;Min-Hsiu Wu;Wenbo Zhao;Qiaosen Li
中科院分区：
文献类型：
--
作者：
Wei Tian;Xiaozhou Ren;Xianwang Yu;Min-Hsiu Wu;Wenbo Zhao;Qiaosen Li
高清地图是智能车辆进行路径测量、规划和导航的必备工具。然而，它的创建仍然是一个持久的挑战，特别是在创建基于视觉传感的地图的语义和拓扑层。然而，目前的语义映射方法没有考虑地图在导航任务中的适用性，而拓扑映射方法面临的问题，有限的位置精度或昂贵的硬件成本。在本文中，我们提出了一个联合映射框架的语义和拓扑层，这是在车道级学习，并基于单目摄像头传感器和车载GPS定位设备。地图管理方法“RoadSegDict”也被提出来支持高效的语义地图更新的众包方式。此外，提出了一种新的数据集，其中包括各种车道结构与详细的语义和拓扑注释。
High-definition map is an essential tool for route measurement, planning and navigation of intelligent vehicles. Yet its creation is still a persisting challenge, especially in creating the semantic and topology layer of the map based on visual sensing. However, current semantic mapping approaches do not consider the map applicability in navigation tasks while the topology mapping approaches face the issues of limited location accuracy or expensive hardware cost. In this paper, we propose a joint mapping framework for both semantic and topology layers, which are learned in a lane-level and based on a monocular camera sensor and an on-board GPS positioning device. A map management approach “RoadSegDict” is also proposed to support the efficient updating of semantic map in a crowdsourced manner. Moreover, a new dataset is proposed, which includes a variety of lane structures with detailed semantic and topology annotations.