根據統計資料顯示，目前全世界汽車約有七億輛左右，按全世界人口平均約九人就有一輛汽車。隨著汽車的普及化，各國交通運輸相關單位也開始注重交通資訊方面的蒐集及提供。本研究發展汽車的再辨識技術，此技術可以提供許多應用。在短程應用方面，可以從事車輛大範圍的追蹤，協助治安偵防、交流量監控以及號誌控制等；而在長程應用方面，可以蒐集路段的交通參數，如旅行時間、路佔率、交流量以及平均車流速度等，提供給運輸業者或是交通局做長期的規劃及決策所使用。
本研究提出用影像來從事汽車的再辨識。而使用影像有以下好處：硬體架設方便，只需要架設路口監視器即可，並且影像可以提供非常多額外的資訊，像是車輛顏色、車輛長度或是車輛型號等。此系統軟體部份由二大步驟所組成，分別是車輛偵測及車輛匹配。
在車輛偵測的部份是採用建立高斯混合背景模型(Gaussian Mixture Background Model)找出畫面上的前景物。再利用隨機決策森林(Random Forest)有效的將前景物進行分類，主要分成三個類別，分別為小型車(包含轎車和箱型車等)、大型車(包含公車及卡車)以及非汽車類。接著利用粒子群聚最佳化(Particle Swarm Optimization)做車輛的追蹤，目的是要確保系統不會將相同車輛重覆儲存。接著利用Time Window的限制，從上游資料庫中找出可能與下游車輛相似的候選車輛，最後透過二分圖匹配(Bipartite Matching)，將下游車輛與上游的候選車輛做匹配，即可辨識出哪些車輛通過上／下游。最後統計有通過上／下游的車輛，計算這些車輛配對的相對應關係，得到此路段的交通參數。

This paper proposed a vision-based vehicle re-identfication (VRI) system. The objective of this system is automatically get the road traffic parameters. In the short term, the proposed system can track vehicle under wide range of area, investigate and prevent security, and control traffic signal; in the long term, the proposed system can collect road traffic parameters, e.g, travel time, road accounting rate, traffic flow and average speed.
Using gaussian mixture background model (GMBM) to get foreground and classify foreground into three groups: small car, large car and non-car by random forest (RF). Tracking vehicle using particle swarm optimization to avoid store the same vehicle in the database again. Then regarding the vehicle matching as bipartite matching, and combining time window constrant to reduce matching time. Based on matching pairs, the traffic parameters are computed. The results show that this method can perform well under different time, weather and road type.

[Bre01] L. Breiman, and A. Cutler, “Random forests,” Machine Learning, Vol. 45, pp. 5-32, 2001.

[Dal05] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” IEEE International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, 2005.

[Zha07] J. Zhang, M. Marszalek, S. Lazebnik, and C. Schmid, “Local feature and kernels for classification of texture and object categories: a comprehensive study,” Internal Journal of Computer Vision, vol. 73, no. 2, pp. 213-238, 2007.

[Ken95] J. Kennedy and R. C. Eberhart, “Particle swarm optimization,” IEEE Internal Conference on Neural Networks, vol. 4, pp. 1942-1948, 1995.

[Van10] K. Van De Sande, T. Gevers, and C. Snoek, “Evaluating color descriptors for object and scene recognition,” IEEE Transation Pattern Analysis and Matching Intelligence, vol. 32, no. 9, pp. 1582–1596, 2010.

[Li05] Z.Li-Ping, Y.Huan-Jun, and H.Shang-Xu, ”Optimal choice of parameters for particle swarm optimization,” Journal of Zhejiang University: Science, vol 6, pp. 528-534, 2005.

[Mas01] O. Masoud, Papanikolopoulos, and P. Nikolaos, ”A novel method for tracking and counting pedestrians in real-time using a single camera,” IEEE Transactions on Vehicular Technology,vol.50, no.5,pp. 1267-1278, 2001.

[Kob07] T. Kobayashi, K. Nakagawa, J. Imae and Z. Guisheng, “Real time object tracking on video image sequence using particle swarm optimization,” International Conference on Control Automation and Systems, 2007,.

[Yuh08] Y. Zheng and Y. Meng, ”Swarming particles with multi feature model for free-selected object tracking,” Intelligent Robots and Systems, 2008.

[Hum83] R.A. Hummel , and S.W. Zucker, ”On the foundations of relaxation labeling processes,” IEEE Transation Pattern Analysis and Machine Intelligence, pp. 267-287, 1983.

[Mic96] M. Isard and A. Blake, “Contour tracking by stochastic propagation of conditional density,” Proceedings European Conference on Computer Vision, vol. 1, pp. 343-456, 1996.

[Jun06] J. Cho, S. Jin, X. Pham, J. Jeon, J. Byun and H. Kang, ”A real-time object tracking system using a particle filter,” IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2822-2827, 2006.

[Hof12] A. Hofleitner, R. Herring, P. Abbeel, and A. Bayen, “Learning the dynamics of arterial traffic from probe data using a dynamic Bayesian network,” IEEE Transaction Intelligent Transportation System, vol. 13, no. 4, pp. 1679–1693, 2012.

[Ndo11] M. Ndoye, V. Totten, J. Krogmeier, and D. Bullock, “Sensing and signal processing for vehicle reidentification and travel time estimation,” IEEE Transaction Intelligent Transportation System, vol. 12, no. 1, pp. 119–131, 2011.

[Sor11] F. Soriguera and F. Robuste, “Requiem for freeway travel time estimation methods based on blind speed interpolations between point measurements,” IEEE Transaction Intelligent Transportation System, vol. 12, no. 1, pp. 291–297, 2011.

[Cel13] H. B. Celikoglu, “Flow-based freeway travel-time estimation: A comparative evaluation within dynamic path loading,” IEEE Transaction Intelligent Transportation System, vol. 14, no. 2, pp. 772–781, 2013.

[Lin11] W. Lin and D. Tong, “Vehicle re-identification with dynamic time windows for vehicle passage time estimation,” IEEE Transaction Intelligent Transportation System, vol. 12, no. 4, pp. 1057–1063, 2011.

[Wan14] J. Wang, N. Indra-Payoong, A. Sumalee, and S. Panwai, “Vehicle reidentification with self-adaptive time windows for real-time travel time estimation,” IEEE Transaction Intelligent Transportation System, vol. 15, no. 2, pp. 540–552, 2014.

[Bay08] H. Bay, A. Ess, T. Tuytelaars, and “Speeded-Up Robust Features (SURF),” International Journal of Computer Vision, vol. 110, no. 3, pp. 346-359, 2008

[Qua10] S. Quayle, P. Koonce, D. DePencier, and D. M. Bullock, “Arterial performance measures with media access control readers: Portland, Oregon, pilot study,” Transportation Research Record, vol. 2192, pp. 185–193, 2010.

[Cha04] S. Chang, L. Chen, Y. Chung, and S. Chen, “Automatic license plate recognition,” IEEE Transaction Intelligent Transportation System, vol. 5, no. 1, pp. 42–53, 2004.

[Ros06] G. Rose, “Mobile phones as traffic probes: Practices, prospects and issues,”
Transportation Review, vol. 26, no. 3, pp. 275–291, 2006.

[Sun99] C. Sun and S. G. Ritchie, “Individual vehicle speed estimation using single
loop inductive waveforms,” Journal of Transportation Engineering, vol. 125, no. 6, pp. 531–538, 1999.

[Coi02] B. Coifman, “Estimating travel times and vehicle trajectories on freeways using dual loop detectors,” Transportation Research, vol. 36, no. 4, pp. 351– 364, 2002.

[Kam05] S. Kamijo, T. Kawahara, and M. Sakauchi, “Vehicle sequence image matching for travel time measurement between intersections,” IEEE International Conference System, vol. 2, pp. 1359–1364, 2005.

[Sun12] A. Sumalee, J. Wang, K. Jedwanna, and S. Suwansawat, “Probabilistic fusion of vehicle features for re-identification and travel time estimation using video image data,” Transportation Research Record, vol. 2308, pp. 73–82, 2012.

[Mal09] C. Mallikarjuna, A. Phanindra, and K. Rao, “Traffic data collection under mixed traffic conditions using video image processing,” Journal of Transportation Engineering, vol. 135, no. 4, pp. 174-182, 2009.

[Che03] T. Chen, ” An automatic bi-directional passing-people counting method based on color image processing,” IEEE 2003 International Carnahan Conference on Security Technology, pp.200-207, 2003.

[Zha95] X. Zhang, and G. Sexton, “Automatic pedestrian counting using image processing techniques,” Electronics Letters, vol. 31 , no. 11 , pp.863 – 865, 1995.

[Bro00] A. Broggi, M. Bertozzi, A. Fascioli ,and M. Sechi, "Shape-based pedestrian detection," IEEE on Intelligent Vehicles Symposium IV, pp.215 - 220, 2000.

[Xia95] X. Zhang, and G. Sexton, “A new method for pedestrian counting,” Fifth International Conference on Image Processing and its Applications, pp. 208-212, 1995.

[Dai00] D. Dailey, F. Cathey, and S. Pumrin, "An algorithm to estimate mean traffic speed using un-calibrated cameras," IEEE Trans. on Intelligent Transportation Systems, vol. 1, no. 2, pp. 98–107, 2000.

[Kwo99] J. Kwow, “Moderating the outputs of support vector machine classifiers,” IEEE Transaction On neural networks, vol. 10, no. 5, 1999.

[Fre97] Y. Freund, and R. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of Computer and System Sciences, pp. 119-139, 1997.

[Dia06] R. Díaz-Uriarte, and S. Andres, “Gene selection and classification of microarray data using random forest,” BMC bioinformatics, 2006.