在十字路口車行分析中，車行軌跡的建模與分類是一個重要的步驟，車行種類的判斷能夠為十字路口的設計提供重要的衡量依據，本篇論文旨在提出一高準確率的車行軌跡分類方法並利用過往的車行軌跡預測片段軌跡未來的行進方向。
本方法首先利用十字路口車行軌跡的起點與終點將軌跡初步分為多種類別，並且分別為每個類別訓練隱馬可夫模型，隱馬可夫模型可以用來做為軌跡判斷的依據並且判斷出不尋常的軌跡，本篇論文利用反覆調整隱馬可夫模型的方式並引入canonical vector的概念，不依靠單一機率做為軌跡分類的唯一評判標準，以提高軌跡分類的準確度。再者，我們提出一個片段軌跡的分類方法，並且利用車行速度與車行方向找出一最相近的軌跡，用以預測片段軌跡未來的行進方向，提供給追蹤器以提升準確率與計算速度。

Currently, most of urban intersections are being installed surveillance cameras, and several vision-based techniques are emerging to exploit and explore the traffic behavior. Vehicle trajectory classification plays an important role in the traffic flow analysis, such as organizing the structure of urban intersections, detecting traffic events, monitoring the abnormal driving activities … and so on. In this thesis, some methods of vehicle trajectory classification and vehicle location prediction are proposed.
For solving the trajectory classification problem within an urban intersection, the training trajectories are roughly categorized using their sources and sinks initially, and for each group of trajectories a statistical model is trained using the Hidden Markov Model (HMM), then iteratively refines all of the models until no trajectory misplaced or accuracy cannot be improved further. Based on these well-trained models, the tracklet of the vehicle can be projected accordingly.
Given an identified prefix trajectory, the most likely model is determined and the most probable template (tracklet) with the highest similarity is selected. This template gives the direction to forecast the next few locations. Finally, the real-time tracking of all vehicle trajectories at urban intersections can be possible with the help of this vehicle location prediction solution.

[1] Guodong Tian, Chunfeng Yuan, Weiming Hu, and Ruiguang Hu, "Discovering and Describing Activities by Trajectory Analysis," IAPR Asian Conference on Pattern Recognition, 2013, pp. 652-656.
[2] Atev Stefan, Osama Masoud, and Nikolaos Papanikolopoulos, "Learning Traffic Patterns at Intersections by Spectral Clustering of Motion Trajectories," International Conference on Intelligent Robots and Systems, 2006, pp. 4851-4856.
[3] Xin Le, Deliang Yang, Yangzhou Chen, and Zhenlong Li, "Traffic flow characteristic analysis at intersections from multi-layer spectral clustering of motion patterns using raw vehicle trajectory," International IEEE Conference on Intelligent Transportation Systems, 2011, pp. 513-519.
[4] Morris Brendan Tran, and Mohan Manubhai Trivedi, "Learning, modeling, and classification of vehicle track patterns from live video," IEEE Transactions on Intelligent Transportation Systems, 2008, vol. 9, pp 425-437.
[5] Cai Yingfeng, Hai Wang, Xiaobo Chen and Haobin Jiang, "Trajectory-based anomalous behaviour detection for intelligent traffic surveillance," IET Intelligent Transport Systems, 2015, vol 9, pp. 810-816.
[6] Jozef Mlıch, and Petr Chmelar, "Trajectory classification based on hidden markov models," Proceedings of International Conference on Computer Graphics and Vision. 2008, pp. 101-105.
[7] Michael Perrone, and Scott Connella, "K-means clustering for hidden Markov models," Proceedings of the International Workshop on Frontiers in Handwriting Recognition, 2000, pp. 229-238.
[8] Sam Hare , Stuart Golodetz , Amir Saffari , Vibhav Vineet, Ming-Ming Cheng, Stephen Hicks and Philip Torr, "Struck: Structured output tracking with kernels," 2011 International Conference on Computer Vision, 2011, pp. 263-270.
[9] Jia Xu, Huchuan Lu, and Ming-Hsuan Yang, "Visual tracking via adaptive structural local sparse appearance model," Computer vision and pattern recognition 2012, pp. 1822-1829.
[10] Kalal Zdenek, Jiri Matas, and Krystian Mikolajczyk, "Pn learning: Bootstrapping binary classifiers by structural constraints," Computer Vision and Pattern Recognition, 2010, pp. 49-56.
[11] Mei Xue, and Haibin Ling, "Robust visual tracking using L1 minimization," International Conference on Computer Vision, 2009, pp. 1436-1443.
 
[12] Sanjeev Arulampalam, Simon Maskell, Neil Gordon, and Tim Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Transactions on signal processing, 2002, vol. 50, pp. 174-188.