Kim Young-Duk, Son Guk-Jin, Song Chan-Ho, Kim Hee-Kang
Center for Future Automotive Convergence Research, DGIST, 333 Techno Jungang-daero, Hyeonpung-myeon, Dalseong-gun, Daegu 711-873, Korea.
Sensors (Basel). 2018 Mar 11;18(3):837. doi: 10.3390/s18030837.
Recently, radar technology has attracted attention for the realization of an intelligent transportation system (ITS) to monitor, track, and manage vehicle traffic on the roads as well as adaptive cruise control (ACC) and automatic emergency braking (AEB) for driving assistance of vehicles. However, when radar is installed on roads or in tunnels, the detection performance is significantly dependent on the deployment conditions and environment around the radar. In particular, in the case of tunnels, the detection accuracy for a moving vehicle drops sharply owing to the diffuse reflection of radio frequency (RF) signals. In this paper, we propose an optimal deployment condition based on height and tilt angle as well as a noise-filtering scheme for RF signals so that the performance of vehicle detection can be robust against external conditions on roads and in tunnels. To this end, first, we gather and analyze the misrecognition patterns of the radar by tracking a number of randomly selected vehicles on real roads. In order to overcome the limitations, we implement a novel road watch module (RWM) that is easily integrated into a conventional radar system such as Delphi ESR. The proposed system is able to perform real-time distributed data processing of the target vehicles by providing independent queues for each object of information that is incoming from the radar RF. Based on experiments with real roads and tunnels, the proposed scheme shows better performance than the conventional method with respect to the detection accuracy and delay time. The implemented system also provides a user-friendly interface to monitor and manage all traffic on roads and in tunnels. This will accelerate the popularization of future ITS services.
最近，雷达技术因实现智能交通系统（ITS）而备受关注，该系统用于监测、跟踪和管理道路上的车辆交通以及车辆驾驶辅助的自适应巡航控制（ACC）和自动紧急制动（AEB）。然而，当雷达安装在道路或隧道中时，检测性能很大程度上取决于雷达周围的部署条件和环境。特别是在隧道中，由于射频（RF）信号的漫反射，移动车辆的检测精度会急剧下降。在本文中，我们提出了基于高度和倾斜角度的最优部署条件以及射频信号的噪声过滤方案，以便车辆检测性能能够在道路和隧道的外部条件下保持稳健。为此，首先，我们通过在真实道路上跟踪大量随机选择的车辆来收集和分析雷达的误识别模式。为了克服这些限制，我们实现了一种新颖的道路监测模块（RWM），它可以轻松集成到诸如德尔福ESR之类的传统雷达系统中。所提出的系统能够通过为来自雷达射频的每个信息对象提供独立队列来对目标车辆进行实时分布式数据处理。基于在真实道路和隧道上的实验，所提出的方案在检测精度和延迟时间方面比传统方法表现出更好的性能。所实现的系统还提供了一个用户友好的界面来监测和管理道路和隧道中的所有交通。这将加速未来智能交通系统服务的普及。
