應用停走衝擊波模型於遍佈式都會交通偵測

Stop-Go Shockwave Model for Pervasive Urban Traffic Sensing

藍啟瑞(Chi-Jui Lan)

指導教授 ： 易志偉

國立交通大學/資訊學院/網路工程研究所/碩士(2013年)

https://doi.org/10.6842/NCTU.2013.00808

摘要

道路車流量對於交通管理者而言是一個非常重要的資訊，尤其在都會交通網路中遍佈性的車流資訊更可讓交通管理者了解整個都會交通狀態，甚至可以利用即時的車流資訊來改善目前交通品質或者提供給駕駛者即時道路導航。然而目前偵測道路車流的方法為在路口裝置車流感測器或透過影像辨識的方式估算車流量，但這些方法都因為成本的考量，通常只裝設在特定道路路口上，這無法提供給交通管理者在都會全面且具遍佈性的車流資訊。因此本論文提出一名為停走衝擊波模型，此模型是利用車輛在號誌路口前的停走行為來估算目前道路上的車流量甚至是號誌的變換時間。我們利用實測以及模擬資料來驗證我們所提出的停走衝擊波模型之可行性，尤其是在低取樣率的問題下。根據我們的實驗結果，我們發現本模型可以在低取樣率下可以有效的偵測出車流資訊，未來透過群眾外包的方式可達到廣泛的車流資訊偵測。

關鍵字

道路車流 ； 衝擊波

並列摘要

The traffic flow information is very important information for traffic management. Pervasive traffic flow information is helpful for urban traffic manager to understand whole the traffic status and decide a proper traffic assignment to improve traffic quality. Besides, this real-time traffic information is also useful in real-time navigation for drivers. In convention, the traffic flow is detected by loop detectors and vehicle detectors, however, these methods require highly cost on deployment and cannot be pervasively deployed over the road networks and provide traffic flow information. In this work, we propose a stop-go shockwave model which is based on the vehicle movement in front of traffic lights to estimate the traffic flow information and even the traffic light information. The proposed concepts are verified via extensive simulations and field trails, especially on the penetration rate issue. Our results show that shockwave models are useful to extract traffic information with low penetration rate. In the future, the stop-go events can be collected via crowdsourcing to achieve pervasively traffic flow detection.

並列關鍵字

Traffic flow ； Shockwave

參考文獻

[3] X. Wu, H. X. Liu, and D. Gettman, “Identification of oversaturated intersections using high-resolution identification of oversaturated intersections using high-resolution,”

[4] N. Geroliminis and A. Skabardonis, “Identification and analysis of queue spillovers in city street networks,” IEEE Transactions on Intelligent Transportation Systems, vol. pp, no. 99, pp. 1–9, May 2011.

of traffic data obtained via GPS-enabled mobile phones: The mobile century field experiment,” Transportation Research Part C: Emerging Technologies, vol. 18, no. 4, pp. 568–583, Aug 2010.

[6] X. Ban, P. Hao, and Z. Sun, “Real time queue length estimation for signalized intersections using travel times from mobile ensors,” Transportation Research Part C: Emerging Technologies, vol. 19, no. 6, pp. 1133–1156, Dec 2011.

[7] A. Skabardonis and N. Geroliminis, “Real-time monitoring and control on signalized arterials,” Journal of Intelligent ransportation Systems, vol. 12, no. 2, pp. 64–74, Apr 2008.