人工智慧於交通安全應用

10.6653/MoCICHE.202202_49(1).0007

謝宗穎；何語萱；鄭又嘉；張仲宇；許聿廷；陳柏華

行人安全 ； 車輛行為 ； 道路分析 ； 影像偵測 ； 聲音偵測 ； Pedestrian safety ； Vehicle safety ； Road Analysis ； Image detection ； Audio detection

土木水利

49卷1期（2022 / 02 / 01）

40 - 48

繁體中文

台灣的混合車流環境衍伸出不少問題，混亂的交通不僅造成運輸效率下降，更使台灣的交通事故死亡率相較於其他已開發國家高出不少。隨著人工智慧的快速發展，影像及聲音偵測技術的用途越來越廣，其中自駕車與交通安全的應用不在少數。如何運用人工智慧技術來改善台灣的交通問題成為政府的一大課題。本研究回顧國內外文獻，首先以行人安全為主題，介紹了處理行人意圖判斷、行人軌跡預測等問題的新方法，並說明車輛可以結合的應用。接著以車輛行為分析為主題，依據車輛異常偵測、路旁車輛狀態分析、車輛違規與車禍偵測等面向描述近年來的研究方法，顯示影像與聲音技術可以協助車輛本身及政府單位對交通安全事件作出即時反應。最後，從巨觀角度，描述社交距離與道路關係、巨觀車流分析中的新技術可以幫助我們得到更全面的分析。期望本研究能激起更多人工智慧結合交通安全的應用，讓台灣的交通更為安全。

Taiwan's mixed traffic environment has caused many problems. The chaotic traffic not only causes a decline in transportation efficiency, but also make Taiwan's traffic fatality rates much higher than that of other developed countries. With the rapid development of artificial intelligence, the use of video and sound detection technology is becoming more and more extensive, and there are many applications for self-driving vehicles and traffic safety. Using artificial intelligence technology to improve Taiwan's transportation problems has become a major issue for the government. This research reviews domestic and foreign literature, firstly, with pedestrian safety as the theme, introduces new methods to deal with problems such as pedestrian intention identification and pedestrian trajectory prediction, and explains the related applications that can be used in vehicles. Next, with the theme of vehicle behavior analysis, based on recent research methods such as vehicle anomaly detection, roadside vehicle status analysis, vehicle violations and car accident detection, etc., the display image and sound technology can assist the vehicle itself and government agencies to respond traffic safety events in real time. Finally, from the macro perspective, describing the relationship between social distance and roads, and the new technology in macro traffic flow analysis can help us get a more comprehensive traffic analysis. It is hoped that this research will stimulate more applications of artificial intelligence combined with traffic safety to make Taiwan's traffic safer.

1. 吳熙仁,陳穆臻(2017)。濃霧中前車緊急煞車時道路駕駛人對前車相對速度感知與反應時間不確性之關聯 — 以海森堡不確定性原理觀點。運輸計畫季刊，46(2)，117-140。
   連結：
2. 吳繼虹,鍾易詩,陳菀蕙,張勝雄,周文靜(2016)。號誌化四岔路口闖紅燈機車事故之人為失誤因子分析。運輸學刊，28(4)，397-427。
   連結：
3. 張旗晏,鍾易詩,馮正民(2017)。動作想像能力與客觀時間提示對道路穿越行為之影響分析：以臺灣年長行人為實證對象。運輸學刊，29(2)，211-232。
   連結：
4. Abbas, S.A.,Zisserman, A.(2019).A geometric approach to obtain a bird’s eye view from an image.Proceedings of the 2019 International Conference on Computer Vision Workshop, ICCVW 2019
5. Bewley, A.,Ge, Z.,Ott, L.,Ramos, F.,Upcroft, B.(2016).Simple online and realtime tracking.Proceedings of the Int. Conf. Image Process. ICIP, Vol. 2016-August
6. Cristani, M.,Del Bue, A.,Murino, V.,Setti, F.,Vinciarelli, A.(2020).The visual social distancing problem.IEEE Access,8,126876-126886.
7. Foggia, P.,Petkov, N.,Saggese, A.,Strisciuglio, N.,Vento, M.(2016).Audio surveillance of roads: A system for detecting anomalous sounds.IEEE Trans. Intell. Transp. Syst.,17(1),279-288.
8. Guo, Y.,Sayed, T.,Zaki, M.H.(2020).Examining two-wheelers’ overtaking behavior and lateral distance choices at a shared roadway facility.J. Transp. Saf. Secur.,12(8),1046-1066.
9. He, K.,Gkioxari, G.,Dollár, P.,Girshick, R.(2020).Mask R-CNN.IEEE Trans Pattern Anal. Mach Intell.,42(2),386-397.
10. Hsieh, M.-H.(2015)。國立臺灣大學土木工程學研究所。
11. Ionescu, R.T.,Smeureanu, S.,Alexe, B.,Popescu, M.(2017).Unmasking the abnormal events in video.Proc. IEEE Int. Conf. Comput. Vis.
12. Li, S.,Fan, X.,Zhang, Y.,Trappe, W.,Lindqvist, J.,Howard, R.E.(2017).Auto++: Detecting cars using embedded microphones in real-time.Proceedings of the ACM Interact Wearable Ubiquitous Technol,1(70)
13. Liang, J., Jiang, L., Niebles, J.C., Hauptmann, A., and Fei-Fei, L. (2019). Peeking into the future: Predicting future person activities and locations in videos. Computer Vision and Pattern Recognition, https://next.cs.cmu.edu.
14. Liu, B.(2020).Spatiotemporal relationship reasoning for pedestrian intent prediction.IEEE Robot. Autom. Lett.,5(2),3485-3492.
15. Liu, Z.(2020).CVPR 2020 paperCVPR 2020 paper,Computer Vision Foundation.
16. Makansi, O.,Cicek, Ö.,Buchicchio, K.,Brox, T.(2020).,未出版
17. Manh, H.,Alaghband, G.(2020).,未出版
18. Mehran, R.,Oyama, A.,Shah, M.(2010).Abnormal crowd be-havior detection using social force model.Conference on Computer Vision and Pattern Recognition (CVPR)
19. Minaee, S.,Boykov, Y.,Porikli, F.,Plaza, A.,Kehtarnavaz, N.,Terzopoulos, D.(2020).,未出版
20. Mnasri, Z.,Rovetta, S.,Masulli, F.(2020).Audio surveillance of roads using deep learning and autoencoder-based sample weight initialization.Proceedings of the 20th IEEE Mediterranean Electrotechnical Conference, MELECON 2020
21. Mohamed, A.,Qian, K.,Elhoseiny, M.,Claudel, C.(2020).,未出版
22. Raghavendra, R.,Del Bue, A.,Cristani, M.,Murino, V.(2011).Abnormal crowd behavior detection by social force opti-mization.Lecture Notes in Computer Science,7065,134-145.
23. Rasouli, A.,Kotseruba, I.,Kunic, T.,Tsotsos, J.(2019).PIE: A large-scale dataset and models for pedestrian intention estimation and trajectory prediction.Proceedings of the IEEE International Conference on Computer Vision, Vol. 2019-October
24. Ravanbakhsh, M.,Nabi, M.,Sangineto, E.,Marcenaro, L.,Regazzoni, C.,Sebe, N.(2018).Abnormal event detection in videos using generative adversarial nets.Abnormal event detection in videos using generative adversarial nets. Proceedings of the International Conference on Image Processing, ICIP, Feb. 2018, vol. 2017-September
25. Redmon, J.,Farhadi, A.(2018).,未出版
26. Rovetta, S.,Mnasri, Z.,Masulli, F.(2020).Detection of hazard-ous road events from audio streams: An ensemble outlier detection approach.IEEE Conference on Evolving and Adaptive Intelligent Systems
27. Sammarco, M.,Detyniecki, M.(2019).Car accident detection and reconstruction through sound analysis with crashzam.Com-munications in Computer and Information Science,992,159-180.
28. Saunier, N.,Sayed, T.(2006).A feature-based tracking algorithm for vehicles in intersections.Third Canadian Conference on Computer and Robot Vision, CRV 2006
29. Saunier, N.,Sayed, T.(2007).Automated analysis of road safety with video data.Transp. Res. Rec.,2019,57-64.
30. Siebert, F.W.,Lin, H.(2020).Detecting motorcycle helmet use with deep learning.Accid. Anal. Prev.,134,105319.
31. Yao, Y.,Wang, X.,Xu, M.,Pu, Z.,Atkins, E.,Crandall, D.(2020).,未出版
32. Yao, Y.,Xu, M.,Wang, Y.,Crandall, D.J.,Atkins, E.M.(2019).Unsupervised Traffic Accident Detection in First-Person Videos.IEEE Int. Conf. Intell. Robot. Syst.
33. 許添本,溫谷琳,張哲寧,陳俊嘉,林瑩潔,張開國,葉祖宏,孔垂昌,黃明正(2019)。,交通部運輸研究所。
34. 溫基信,王宏生,黃家耀,蘇志文,周業凱,楊植竣,張開國,葉祖宏,孔垂昌,黃明正(2020).路口無人機交通攝影及衝突分析技術開發.交通部運輸研究所.