人工智慧之交通事件影像偵測模式與實域驗證

AN AI-BASED IMAGE-DETECTION MODEL AND FIELD TEST FOR DETECTING TRAFFIC INCIDENTS

吳沛儒(Pei-Ju Wu)；陳其華(Chi-Hwa Chen)；蘇昭銘(Jau-Ming Su)；吳東凌(Tung-Ling Wu)；黃啟倡(Chi-Chang Huang)；鍾俊魁(Jiun-Kuei Jung)；何毓芬(Yu-Fen Ho)

交通事件 ； 交通管理 ； 人工智慧 ； 單次多重目標檢測器 ； 深度神經網路 ； Traffic incident ； Traffic management ； Artificial intelligence ； Single shot multibox detector ； Deep neural network

運輸計劃季刊

48卷3期（2019 / 09 / 30）

159 - 177

繁體中文

交通事件之確認與通報為交通管理之重要議題，往往耗費人力資源以及相互溝通確認時間。雖然人工智慧日益蓬勃發展，但卻鮮少研究透過人工智慧處理交通事件辨析之議題。因此，本研究旨在發展以人工智慧為基礎的影像偵測模式，透過交通事件之自動化偵測，以提升交通管理效率。具體而言，本研究建構單次多重目標推測器之深度神經網路，以偵測交通事件。為了測試本方法之效果，本研究以高雄市一個交叉路口作為實測場域。實測分析結果顯示，本研究提出之交通事件單次多重目標推檢測器模式可以成功地偵測交通事件，並可同時偵測車速與車輛數。再者，本研究示範如何將人工智慧為基礎之交通事件影像偵測技術應用於實體交通環境上。本開創性研究提供清楚的指引，讓交通管理單位可以透過人工智慧技術去偵測交通事件，對於交通管理具有高價值貢獻。

The detection and reporting of traffic incidents is of major importance to all those involved in traffic management, as it results in increased labor and prolonged periods of complex communication. However, few studies have explored how these pressures might be relieved through the use of artificial intelligence (AI). Accordingly, this study aims to develop an AI-based image-detection model, the Single Shot MultiBox Detector (SSD) with a deep neural network, which will detect and report traffic incidents automatically, and thus enhance the efficiency of traffic management. This study used the field case of a real intersection in Kaohsiung City, Taiwan, to test the effectiveness of the proposed approach, and the results indicated that the proposed traffic-incident SSD model was successful not only in identifying traffic incidents, but also in monitoring key background traffic parameters such as the numbers and speeds of vehicles on the road. This pioneering research also demonstrates how AI-based image-detection technology for traffic incidents could be installed in the physical environment, and provides clear and valuable guidance to traffic managers interested in utilizing AI technology in their field.

1. 汪進財,邱孟佑(2010)。以車流狀態為基礎之高速公路旅行時間預測模式。運輸學刊，22(3)，261-284。
   連結：
2. 卓訓榮,賴芳瑜,羅仕京(2001)。以位勢理論構建三維度車流模式之基礎研究。運輸計劃季刊，30(2)，303-321。
   連結：
3. 邱裕鈞,謝志偉(2012)。混合車流格位傳遞模式之建立與驗證。運輸學刊，24(2)，245-276。
   連結：
4. 許添本,鄭雅文(2001)。具備預測機制的追撞事件偵測新演算模式之研發。運輸計劃季刊，30(3)，539-575。
   連結：
5. 許鉅秉,吳熙仁,蔡孟釗(2016)。自動公路系統發生事件下自動駕駛車輛於鄰近混合車道跟車邏輯之研究。運輸計劃季刊，45(2)，133-163。
   連結：
6. Anuar, K.,Cetin, M(2017).Estimating Freeway Traffic Volume Using Shockwaves and Probe Vehicle Trajectory Data.Transportation Research Procedia,22,183-192.
7. Aslam, B.,Amjad, F.,Zou, C. C.(2012).Optimal Roadside Units Placement in Urban Areas for Vehicular Networks.2012 IEEE Symposium on Computers and Communications (ISCC)
8. Canaud, M.,Faouzi, N.-E. E.(2015).ECOSTAND: Towards a Standard Methodology for Environmental Evalualion uf ITS.Transporlutiun Research Procediu,6,377-390.
9. Coifman, B.,Wu, M.,Redmill, K.,Thornton, D. A.(2016).Collecting Ambient Vehicle Trajectories from an Instrumented Probe Vehicle: High Quality Data for Microscopic Traffic Flow Studies.Transportation Research Part C: Emerging Technologies,72,254-271.
10. Comert, G.(2013).Effect of Stop Line Detection in Queue Length Estimation at Traffic Signals from Probe Vehicles Data.European Journal of Operational Research,226(1),67-76.
11. Farradyne, P. B.(2005).Farradyne, P. B., "Use of Unmanned Aerial Vehicles in Traffic Surveillanceand Traffic Management Technical Memorandum'', Florida Department Of Transportation ITS Section Office of Traffic Engineering and Operations, 2005..
12. Gu, Y.,Hsu, L. T.,Kamijo, S.(2018).Towards Lane-Level Traffic Monitoring in Urban Environment Using Precise Probe Vehicle Data Derived from Three-Dimensional Map Aided Differential GNSS.IATSS Research,42(4),248-258.
13. Guido, G.,Gallelli, V.,Rogano, D.,Vitale, A.(2016).Evaluating the Accuracy of Vehicle Tracking Data Obtained from Unmanned Aerial Vehicles.International Journal of Transportation Science and Technology,5(3),136-151.
14. Hansen, R. L.(2016).Traffic Monitoring Using UAV Technology.The American Surveyor,13(5),30-35.
15. Hart, W. S.,Gharaibeh, N. G.(2011).Use of Micro Unmanned Aerial Vehicles in Roadside Condition Surveys.T&DI Proceedings
16. Hsieh, J. W.,Yu, S. H.,Chen. Y. S.,Hu, W. F(2006).Automatic Traffic Surveillance System for Vehicle Tracking and Classification.IEEE Transactions on Intelligent Transportation Systems,7(2),175-187.
17. Ito, H.,Suga, Y.,Higashi, T.,Asakura, Y.(2009).An Improved Methodology to Generate a Digital Road Network Using Location Positioning Data of Probe Vehicles.IFAC Proceedings Volumes,42(15),292-297.
18. Iton, H.,Suga, Y.,Higashi, T.,Asakura, Y.(2006).Generating a Road Map Based on Location Positioning Data of Probe Vehicles.IFAC Proceedings Volumes,39(12),567-572.
19. Li, J.,Henk, van Z.,Liu, C.,Lu, S.(2011).Monitoring Travel Times in an Urban Network Using Video, GPS and Bluetooth.Procedia - Social and Behavioral Sciences,20,630-637.
20. Luo, Z.,Jodoin, P.,Su, S.,Li, S.,Larochelle, H.(2018).Traffic Analytics with Low-Frame-Rate Videos.IEEE Transactions on Circuits and Systems for Video Technology,28(4),878-891.
21. Menouar, H.,Guvenc, I.,Akkaya, K.,Uluagac, A. S.,Kadri, A.,Tuncer, A.(2017).UAV-Enabled Intelligent Transportation Systems for the Smart City: Applications and Challenges.IEEE Communications Magazine,55(3),22-28.
22. Mussone. L.,Matteucci, M.,Bassani, M.,Rizzi, D(2011).Traffic Analysis in Roundabout Intersections by Image Processing.IFAC Proceedings Volumes,44(1),14922-14927.
23. Rathinam, S.,Kim, Z. W.,Sengupta, R.(2008).Vision-Based Monitoring of Locally Linear Structures Using an Unmanned Aerial Vehicle.Journal of Infrastructure Systems,14(1),52-63.
24. Sekine, T.(2014).Utilization of Probe Powered Two-Wheeler Vehicles to Realize a Safe Mobile Society.IATSS Research,38(1),58-70.
25. Seo, T.,Kusakabe, T.,Asakura, Y.(2015).Estimation of Flow and Density Using Probe Vehicles with Spacing Measurement Equipment.Transportation Research Part C: Emerging Technologies,53,134-150.
26. Son, S.,Back, Y.(2015).Design and Implementation of Real-Time Vehicular Camera for Driver Assistance and Traffic Congestion Estimation.Sensors,15(8),20204-20231.
27. Xu, Y.,Yu, G.,Wang, Y.,Wu, X.,Ma, Y.(2017).Car Detection from Low-Altitude UAV Imagery with the Faster R-CNN.Journal of Advanced Transportation,2017,1-10.
28. 張瓊文,林豐博,曾平毅,蘇振維(2010)。雪山隧道內車流特性與容量之分析。中國土木水利工程學刊，22(3)，333-340。
29. 陳一昌,林亨杰,許添本(2009).道路交通事故事件偵測與影像分析.臺北市:交通部運輸研究所.
30. 詹富翔,陳玉亭,向宇,陳柏瑋,孫民(2017)。預測於行車紀錄影像中的事故。電工通訊季刊，3，110-122。

1. 蘇昭銘,簡君麟,鍾俊魁,黃啟倡,張和盛,林良泰,吳東凌,吳沛儒,何毓芬(2020)。建構交通事件之人工智慧物件偵測邏輯與實證研究。運輸學刊，32(3)，299-320。
2. 謝宗穎,鄭又嘉,陳柏華,張仲宇,何語萱,朱致遠(2022)。人工智慧於交通運輸潛在應用之回顧。土木水利，49(1)，49-57。