Department of Computer Science, University of North Carolina at Chapel Hill, NC 27599-3175, USA.
IEEE Trans Vis Comput Graph. 2012 Jun;18(6):890-901. doi: 10.1109/TVCG.2011.116.
There exists a vast amount of geographic information system (GIS) data that model road networks around the world as polylines with attributes. In this form, the data are insufficient for applications such as simulation and 3D visualization-tools which will grow in power and demand as sensor data become more pervasive and as governments try to optimize their existing physical infrastructure. In this paper, we propose an efficient method for enhancing a road map from a GIS database to create a geometrically and topologically consistent 3D model to be used in real-time traffic simulation, interactive visualization of virtual worlds, and autonomous vehicle navigation. The resulting representation provides important road features for traffic simulations, including ramps, highways, overpasses, legal merge zones, and intersections with arbitrary states, and it is independent of the simulation methodologies. We test the 3D models of road networks generated by our algorithm on real-time traffic simulation using both macroscopic and microscopic techniques.
存在大量的地理信息系统 (GIS) 数据，这些数据将世界各地的道路网络表示为带有属性的折线。以这种形式，这些数据对于模拟和 3D 可视化工具等应用程序来说是不够的，随着传感器数据的普及以及政府试图优化其现有物理基础设施，这些应用程序的功能和需求将会不断增强。在本文中，我们提出了一种从 GIS 数据库中增强道路图的有效方法，以创建一个几何和拓扑一致的 3D 模型，用于实时交通模拟、虚拟世界的交互式可视化和自动驾驶车辆导航。所得到的表示形式为交通模拟提供了重要的道路特征，包括匝道、高速公路、天桥、合法合并区以及具有任意状态的交叉口，并且它独立于模拟方法。我们使用宏观和微观技术在实时交通模拟中测试了我们的算法生成的道路网络的 3D 模型。
