SeC---結合雲端運算與感測網路之應用服務平台---子計畫二：SeC-VS結合雲端運算與視訊感測網路之號誌管控與車輛追蹤研究

Abstract

隨著無線通訊網路技術的進步，加上電子元件價格漸漸的下降以及行車安全問題越 來越受重視，各國政府紛紛投入智慧型運輸系統(Intelligent transportation system, ITS)的 研究。而車載感測網路(Vehicular Sensor Network)與雲端計算(Cloud Computing)的整合， 將會成為實現ITS 的重要架構。 子計畫二的主要研究目標在於利用行車視訊紀錄器及路邊感測器收集視訊資料，再 透過VANET/3G 網路，以無線傳輸方式將經過影像辨識處理過的各項行車特徵資料(如 車道分隔線、車輛種類、車輛速度與車間距離等)傳送至雲端平台處理。透過雲端平台 將收集到的所有行車特徵資料，進一步分析並產生車流估算、路況、車輛找尋、車輛軌 跡與交通事故查詢等各項服務，進而發展出智慧型運輸系統之號誌管控與車輛追蹤等兩 項重要應用。 第一年預計針對車載網路開發一組智慧型行車視訊感測器；並以各項行車影像特徵 資料為基礎，發展車輛定位、車輛軌跡擷取與多項進階型車安全應用等技術。在第二年 的研究中將利用雲端計算發展車載視訊感測網路相關技術，如車流估算系統以及行車軌 跡資料庫；並建立出單一路口的號誌管控模型。第三年將結合雲端車流資訊設計多路口 號誌連鎖演算法以建置動態即時號誌管控系統，除此之外，利用雲端型車軌跡資料庫， 發展車輛追蹤系統，以創造出一個有效且安全的智慧型運輸系統。

Due to the advances on wireless technologies and the dramatic cost down on electronic components, the development of Intelligent Transportation System (ITS) has drawn intensive attention in recent years. The integration of Vehicular Sensor Network and Cloud Computing will be a promising approach for the future ITS. This subproject aims to build a vehicular video sensor network based on cloud computing for traffic signal control and vehicle tracking applications. This is a three-year project: In the first year, we will develop an intelligent video driving logger for vehicles. The developed video driving logger not only can automatically record driving video, but also can count and analyze the vehicles from the video image, and then detect and track the vehicle activities. In the second year, we will investigate traffic flow estimation and vehicle trajectories database based on cloud computing. In addition, we will also develop a traffic signal control model for the isolated intersection. In the last year, based on the traffic data and vehicle trajectories from the cloud, we will develop a dynamic multi-intersection traffic signal control coordination system to ensure the unobstructed road and a vehicle tracking system for the security applications.