CAREER: Sensor Fusion for Multi-Modal Traffic Sensing

该项目的目标是为全面实时监测整个城市街道和高速公路的交通状况奠定基础。最终目标：一种可扩展的、基于模型的传感器融合系统，能够合并来自大量异质和地理上不同的传感器的数据，并保持对所感知和推断的交通状况的一致看法。全市范围内对当前交通状况的详细和准确的查看使交通运输的广泛应用得到改善。以可承受的成本实现这一目标的关键是找到从现有传感器基础设施中提取更多信息的方法。通过与芝加哥市、NAVTEQ、GCM Travel和芝加哥运输机构的合作，PI可以访问芝加哥地区的数据，这些数据来自传感设备，包括地下磁环以及公共汽车、城市车辆和众包GPS轨迹。补充这些来源的是来自安全、闯红灯和其他交通摄像头的机会主义视频源，以及基于无线电频率发射器的车辆重新识别。随着日益严重的拥堵、不断上涨的燃料价格和全球变暖的威胁，提高我们交通系统效率的需求从未像现在这样迫切。对交通状况的全面感知和推断将帮助出行者做出更好的出行决策，并帮助交通工程师识别和解决问题。该项目将研究与公共服务和开源软件开发相结合。PI正在与当地一所高中合作，接待交通传感研究实习生，该项目的结果被用于UIC的交通传感研究生课程。

The objective of this project is to lay the foundation for comprehensive real-time monitoring of traffic conditions throughout our urban streets and highways. The end goal: a scalable, model-based sensor fusion system capable of merging data from a large number of heterogeneous and geographically diverse sensors, and maintaining a coherent view of sensed, and inferred, traffic conditions. A city-wide, detailed and accurate view of current traffic conditions enables improvements in a wide range of applications in transportation. A key to achieving this goal affordabily is to find ways to extract more information from existing sensor infrastructure. Through collaborations with the City of Chicago, NAVTEQ, GCM Travel and the Chicago Transit Agency, the PI has access to Chicago-area data from sensing modalities including underground magnetic loops as well as bus, city-vehicle and crowd-sourced GPS traces. Complementing these sources are opportunistic video feeds from security, red-light and other traffic cameras, as well as vehicle re-identification based on radio frequency transmitters. With increasing congestion, rising fuel prices, and the threat of global warming, the need for improving the efficiency of our transportation systems has never been greater. Comprehensive sensing and inference of traffic conditions will help travelers make better travel decisions and help traffic engineers identify and fix problems. This project combines research with public service and open-source software development. The PI is partnering with a local high-school to host traffic sensing research interns, and the results from this project are used in a graduate course on transportation sensing at UIC.