在許多國家違規停車被認為是一個交通問題。違章停車不僅導致交通擁堵，還會造成事故。在過去，解決違規停車的方法通常是人工取締和影像識別。前一種方法不能覆蓋大片區域。後一種方法有成本高和影像品質差（如雨天）的問題。因此，本論文設計了一個基於機車軌跡的非法停車檢測系統建立更有效和低成本的檢測方法。

由於行動裝置和網路技術的發展，許多機車騎士使用導航應用到達目的地。
這些導航產生的軌跡被用來考察當時的道路交通狀況。此系統處理軌跡並檢測軌跡是否因 違規停車車輛而有不自然的車道切換行為。模擬結果顯示，該系統可以成功檢測出90.28% 的違規停車 。

In many countries, illegal parking is considered a traffic problem. Illegal parking not only leads to traffic jams but also causes accidents. In the past, the solutions for illegal parking were manual proscription and image recognition. The former method cannot cover a large area. The latter method typically has the poor image quality problem (e.g., rainy days). Therefore, this thesis designs an illegal parking detection system based on scooters' trajectories for establishing more efficient and low cost detection methods.

Many scooter riders use navigation applications due to the advances in mobile devices and internet technologies. The trajectories produced by these navigations are used to examine the traffic conditions of the road at that time. The system processes the trajectories and detects whether the trajectories have unnatural lane switching behavior because of illegally parked vehicles (IPVs). The simulation results show that the system can detect 90.28% of the IPVs successfully.

[1] S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” 2016.
[2] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” 2020.
[3] L. Rabiner and B. Juang, “An introduction to hidden markov models,” IEEE ASSP Magazine, vol. 3, no. 1, pp. 4–16, 1986.
[4] P. Newson and J. Krumm, “Hidden markov map matching through noise and sparseness,” in Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ser. GIS ’09, 2009, p. 336343.
[5] Y.-L. Hsueh and H.-C. Chen, “Map matching for low-sampling-rate gps trajectories by exploring real-time moving directions,” Information Sciences, vol. 433-434, pp. 55–69, 2018.
[6] J. D. Lafferty, A. McCallum, and F. C. N. Pereira, “Conditional random fields: Probabilistic models for segmenting and labeling sequence data,” in Proceedings of the Eighteenth International Conference on Machine Learning, ser. ICML ’01. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 2001, p. 282289.
[7] M. Xu, Y. Du, J. Wu, Y. Zhou, and Y. Xiao, “Map matching based on conditional random fields and route preference mining for uncertain trajectories,” CoRR, vol. abs/1410.4461, 2014. [Online]. Available: http://arxiv.org/abs/1410.4461
[8] “Probe vehicle data.” [Online]. Available:
https://www.c-roads-germany.de/english/ c-its-services/pvd/
[9] Z. He, G. Qi, L. Lu, and Y. Chen, “Network-wide identification of turn-level intersection congestion using only low-frequency probe vehicle data,” Transportation Research Part C: Emerging Technologies, vol. 108, pp. 320–339, 2019. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0968090X18312543
[10] A. Keler, J. M. Krisp, and L. Ding, “Detecting vehicle traffic patterns in urban environments using taxi trajectory intersection points,” Geo-spatial Information Science, vol. 20, no. 4, pp.333–344, 2017. [Online]. Available: https://doi.org/10.1080/10095020.2017.1399672
[11] “Open street map,”[EB/OL], https://www.openstreetmap.org/#map=8/23. 611/120.768.
[12] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “Ssd: Single shot multibox detector,” Lecture Notes in Computer Science, p. 2137, 2016. [Online]. Available: http://dx.doi.org/10.1007/978-3-319-46448-0_2
[13] T. Kanungo, D. Mount, N. Netanyahu, C. Piatko, R. Silverman, and A. Wu, “An efficient k- means clustering algorithm: analysis and implementation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 881–892, 2002.
[14] X. Xie, C. Wang, S. Chen, G. Shi, and Z. Zhao, “Real-time illegal parking detection system based on deep learning,” in Proceedings of the 2017 International Conference on Deep Learning Technologies, ser. ICDLT ’17. New York, NY, USA: Association for Computing Machinery, 2017, p. 2327. [Online]. Available: https://doi.org/10.1145/3094243.3094261
[15] J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” 2018.
[16] W. Chen and C. K. Yeo, “Unauthorized parking detection using deep networks at real time,” in 2019 IEEE International Conference on Smart Computing (SMARTCOMP), Conference Proceedings, pp. 459–463.
[17] Z. Yin, H. Xiong, X. Zhou, D. W. Goldberg, D. Bennett, and C. Zhang, “A deep learning based illegal parking detection platform,” in Proceedings of the 3rd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, ser. GeoAI 2019. New York, NY, USA: Association for Computing Machinery, 2019, p. 3235. [Online]. Available: https://doi.org/10.1145/3356471.3365233
[18] T. He, J. Bao, R. Li, S. Ruan, Y. Li, C. Tian, and Y. Zheng, “Detecting vehicle illegal parking events using sharing bikes’ trajectories,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ser. KDD ’18. New York, NY, USA: Association for Computing Machinery, 2018, p. 340349. [Online]. Available: https://doi.org/10.1145/3219819.3219887
[19] P. A. Lopez, M. Behrisch, L. Bieker-Walz, J. Erdmann, Y.-P. Flötteröd, R. Hilbrich,
L. Lücken, J. Rummel, P. Wagner, and E. Wießner, “Microscopic traffic simulation using sumo,” in The 21st IEEE International Conference on Intelligent Transportation Systems, 2018.
[20] A. Wegener, M. Piórkowski, M. Raya, H. Hellbrück, S. Fischer, and J.-P. Hubaux, “Traci: An interface for coupling road traffic and network simulators,” in Proceedings of the 11th Communications and Networking Simulation Symposium, Apr. 2008, pp. 155–163.
[21] O. U. government information about the Global Positioning System (GPS) and related topics, “Gps accuracy,” 2020. [Online]. Available: https://www.gps.gov/systems/gps/ performance/accuracy/