建構交通事件之人工智慧物件偵測邏輯與實證研究

The Development of AI Object-detection Logics and an Empirical Study for Traffic Incident

吳沛儒(Pei-Ju Wu) ； 蘇昭銘(Jau-Ming Su) ； 吳東凌(Tung-Ling Wu) ； 林良泰(Liang-Tay Lin) ； 黃啟倡(Chi-Chang Huang) ； 鍾俊魁(Jiun-Kuei Jung) ； 張和盛(Ho-Sheng Chang) ； 何毓芬(Yu-Fen Ho) ； 簡君麟(Chun-Lin Chien)

《運輸學刊》 32卷3期 (2020/09) Pp. 299-320

https://doi.org/10.6383/JCIT.202009_32(3).0003

摘要

道路交通事件資訊整合與發布平台可有效地讓交控中心即時地執行交通管理並讓用路人藉由重新規劃路徑以提升便利性。目前人工智慧技術被廣泛應用在各個領域，但鮮少研究致力於在交通事件偵測領域上之應用。因此，本研究嘗試發展一套人工智慧深度學習物件偵測演算邏輯，包括紅線違停、異常停留、路口溢流、逆向行駛等常見交通事件，用以自動化偵測與辨識交通事件。實證分析結果顯示，異常停留之整體準確率為73.33%、紅線違規停車之整體準確率為95.95%%、路口溢流偵測之整體準確率為99.40%、逆向行駛之整體準確率為39.28%。本研究進而探究人工智慧交通事件偵測準確率不盡理想之結果，研擬精進模式準確率之方法。

關鍵字

交通事件 ； 交通管理 ； 人工智慧 ； 深度學習 ； 物件偵測

並列摘要

The integration and announcement platform of road traffic incidents can allow traffic control centers to effectively implement real-time traffic management and enhance travelers' trips by rerouting them where necessary. Nevertheless, there are not enough studies that can fully explain how artificial intelligence (AI) can be utilized to make a positive difference in this industry. In order to fill this need, this study has devised AI logics of object detection, along with a deep learning neural network, in order to identify and record traffic misdemeanors. This can then enable the traffic department to efficiently control and monitor how motorists behave while driving. Factors that will be monitored in the proposed AI-based traffic incident logics are illegal parking along a red line, parking violations, intersection overflows, and driving in the wrong direction. In order to test the effectiveness of this AI-based method, a field case was conducted with the following results. The empirical results reveal that the overall accuracy of parking violations is 73.33%, the overall accuracy of illegal parking along a red line is 95.95%, the overall accuracy of intersection overflows is 99.40%, and the overall accuracy of driving in the wrong direction is 39.28%. This study further examines which components of the AI traffic incident detection might be inexact and outlines potential approaches that could enhance the accuracy of these models.

並列關鍵字

Traffic incident ； Traffic management ； Artificial intelligence ； Object detection ； Deep learning

參考文獻

陳一昌、林亨杰、許添本、孫瑀、林俊良、孫將瓴、陳煒騰、曾乙庭、林楷閔 (2009)，道路交通事故事件偵測與影像分析，交通部運輸研究所委託研究。

吳炳飛、瞿忠正、陳昭榮、王晉元、古閔宇、劉治君、高志忠、楊錚諺、鐘孟良、蕭文淵、劉育均、曹瑞和、李霞 (2009)，影像式車輛偵測器擴充模組研發－事件偵測功能模組研發與試作，交通部運輸研究所委託研究。

吳沛儒、陳其華、蘇昭銘、吳東凌、黃啟倡、鍾俊魁、何毓芬 (2019)，「人工智慧之交通事件影像偵測模式與實域驗證」，運輸計劃季刊，第四十八卷第三期，頁 159-178。

CEDR (2011), Best Practice in European Traffic Incident Management, Research Report, Conference of European Directors of Roads, Belgium.

FHWA (2007), Intelligent Transportation Systems for Traffic Incident Management, FHWA-JPO-07-001, Federal Highway Administration, Department of Transportation, Washington.