This thesis has proposed a system for multi-camera vehicle identification in tunnel surveillance videos. As vehicles drive through a tunnel, they appear in all surveillance cameras. By applying the proposed algorithms, vehicles from different cameras can be identified.
In the beginning, vehicles are detected with Haar-like feature detector and transformed to a visual feature vector using OpponentSIFT descriptor in an individual camera video. After the system collects a set of vehicles in multiple cameras for a while, the proposed Spatiotemporal Successive Dynamic Programming (S2DP) algorithm is applied to identify vehicles across two cameras by considering the ordering constraint in a tunnel.
Usually there are two major requirements in a multi-camera traffic system, real-time tracking and offline identification. Therefore, two algorithms are proposed for the two purposes, respectively. The Real-Time RT algorithm gives an assignment strategy for fast candidate selection and can be used in multi-camera tracking-by-identification. Another algorithm is the Offline Refinement OR that refines the result of the S2DP using Hungarian algorithm that achieves better performance. Meanwhile, practical issues such as initialization problem and error handling are taken into consideration in our proposed system.
Comprehensive experiments on every part of the system are provided using three manually labeled tunnel surveillance datasets. The three datasets include not only labeled vehicles, but also miss detected vehicles and order-changed vehicles. The
64
proposed RT and OR algorithms demonstrate good performance on different datasets, and both outperform state-of-the-art algorithms.
Mixing information from more than two cameras is left for future work. A miss-detected vehicle in one camera can be recovered using the information from the cameras in behind. Alarms can be triggered if one vehicle is miss-detected in consecutive cameras, since vehicles must pass all cameras. In addition, we would like to extend the multi-camera vehicle identification system to regular highway traffic in the future.
65
Johannesson and A. Radmanesh, "Video-Based Automatic Incident Detection for Smart Roads: The Outdoor Environmental Challenges Regarding False Alarms,"
IEEE Transactions on Intelligent Transportation Systems, vol. 9, no. 2, pp.
349-360, Jun. 2008.
[3] P. Dollar, C. Wojek, B. Schiele and P. Perona, "Pedestrian Detection: An Evaluation of the State of the Art," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 4, pp. 743-761, Apr. 2012.
[4] T. Gandhi and M. M. Trivedi, "Pedestrian Protection Systems: Issues, Survey, and Challenges," IEEE Transactions on Intelligent Transportation Systems, vol.
8, no. 3, pp. 413-130, Sep. 2007.
[5] C. Rougier, J. Meunier, A. St-Arnaud and J. Rousseau, "Robust Video Surveillance for Fall Detection Based on Human Shape Deformation," IEEE Transactions on Circuits and Systems for Video Technology, vol. 21, no. 5, pp.
611-622, May 2011.
[6] R. S. Feris, B. Siddiquie, J. Petterson, Y. Zhai, A. Datta, L. M. Brown and S.
Pankanti, "Large-Scale Vehicle Detection, Indexing, and Search in Urban Surveillance Videos," IEEE Transactions on Multimedia, vol. 14, no. 1, pp.
28-42, Feb. 2012.
66
[7] B. T. Morris and M. M. Trivedi, "Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach,"
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 11,
pp. 2287-2301, Nov. 2012.
[8] I. Saleemi, L. Hartung and M. Shah, "Scene Understanding by Statistical Modeling of Motion Patterns," in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2010.
[9] R. R. Cabrera, T. Tuytelaars and L. Van Gool, "Efficient Multi-Camera Vehicle Detection, Tracking, and Identification in a Tunnel Surveillance Application,"
Computer Vision and Image Understanding, vol. 116, no. 6, pp. 742-753, Jun.
2012.
[10] R. R. Cabrera, T. Tuytelaars and L. Van Gool, "Efficient Multi-Camera Detection, Tracking, and Identification Using a Shared Set of Haar-Features," in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2011.
[11] P. Viola and M. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," in Proc. IEEE CS. Conf. Computer Vision and Pattern Recognition, 2001.
[12] N. Buch, S. A. Velastin and J. Orwell, "A Review of Computer Vision Techniques for the Analysis of Urban Traffic," IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 3, pp. 920-939, Sep. 2011.
[13] J. Zhang, F. Y. Wang, K. Wang, W. H. Lin and C. Chen, "Data-Driven Intelligent Transportation Systems: A Survey," IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 4, pp. 1624-1639, Dec. 2011.
[14] S. Atev, G. Miller and N. P. Papanikolopoulos, "Clustering of Vehicle
67
Trajectories," IEEE Transactions on Intelligent Transportation Systems, vol. 11, no. 3, pp. 647-657, Sep. 2010.
[15] M. Piccardi, "Background subtraction techniques: a review," in Proc. IEEE Int'l Conf. Systems, Man, Cybernetics, 2004.
[16] S. Brutzer, B. Hoferlin and G. Heidemann, "Evaluation of Background Subtraction Techniques for Video Surveillance," in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2011.
[17] C. Stauffer and W. E. L. Grimson, "Adaptive Background Mixture Models for Real-Time Tracking," in Proc. IEEE CS. Conf. Computer Vision and Pattern Recognition, 1999.
[18] N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," in Proc. IEEE CS. Conf. Computer Vision and Pattern Recognition, 2005.
[19] M. D. Breitenstein, F. Reichlin, B. Leibe, E. Koller-Meier and L. Van Gool,
"Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.
33, no. 9, pp. 1820-1833, Sep. 2011.
[20] C. R. Wren, A. Azarbayejani, T. Darrell and A. P. Pentland, "Pfinder: Real-Time Tracking of the Human Body," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 780-785, Jul. 1997.
[21] M. S. Arulampalam, S. Maskell, N. Gordon and T. Clapp, "A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking," IEEE Transactions on Signal Processing, vol. 50, no. 2, pp. 174-188, Feb. 2002.
[22] X. Wang, "Intelligent Multi-Camera Video Surveillance: A Review," Pattern
68
Recognition Letters, vol. 34, no. 1, pp. 3-19, Jan. 2013.
[23] G. Lian, J. H. Lia, C. Y. Suen and P. Chen, "Matching of Tracked Pedestrians Across Disjoint Camera Views Using CI-DLBP," IEEE Transactions on Circuits and Systems for Video Technology, vol. 22, no. 7, pp. 1087-1099, Jul. 2012.
[24] K. E. A. van de Sande, T. Gevers and C. G. M. Snoek, "Evaluating Color Descriptors for Object and Scene Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 9, pp. 1582-1596, Sep. 2010.
[25] D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints,"
International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, Nov. 2004.
[26] E. Rublee, V. Rabaud, K. Konolige and G. Bradski, "ORB: An efficient alternative to SIFT or SURF," in Proc. IEEE Int'l Conf. Computer Vision, 2011.
[27] E. Rosten and T. Drummond, "Machine Learning for High-Speed Corner Detection," in Proc. European Conference on Computer Vision, 2006.
[28] M. Calonder, V. Lepetit, C. Strecha and P. Fua, "BRIEF: Binary Robust Independent Elementary Features," in Proc. European Conference on Computer Vision, 2010.
[29] H. W. Kuhn, "The Hungarian Method for the Assignment Problem," Naval Research Logistics Quarterly, vol. 2, pp. 83-97, 1955.
[30] P. F. Felzenszwalb and R. Zabih, "Dynamic Programming and Graph Algorithms in Computer Vision," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 4, pp. 721-740, Apr. 2011.
[31] "Taiwan Area National Freeway Bureau, MOTC," [Online]. Available:
http://www.freeway.gov.tw.