現在，我們可以看見愈來愈多的監視系統被設置在街頭。似乎用單純以人工的方式從監視系統中找出特定的車輛是愈來愈困難。在本篇文章中，我們提出了一個在不同攝影機下辦識車輛的方法。但是不同攝影機下拍得車輛的影像大小、光線明暗及視角都有所不同，這是我們必須面對的挑戰。我們將辦識車輛的問題轉化為同一台車及不同台車的分類問題。我們提出的方式是藉由加權隨機樹來描述兩張影像中所找到的特徵點。而這些影像描述的資訊用來訓練分類器，例如常見的支援向量機(Support Vector Machine)。我們的貢獻是系統能夠考慮到資料的權重而有效率地建立起隨機樹還有能夠控制系統的錯誤警報次數的能力。

Nowadays, more and more surveillance systems are setup along the streets. It is more and more impractical to rely on humans to find vehicles. We proposed an approach to identify vehicles under non-overlapping cameras. The challenges of vehicle identification are the variation in image size, illumination, and view angles under different cameras. The identification problem is formulated as a same-different classification problem. The proposed approach is based on quantizing the scale-invariant features of image pairs by the weighted random trees. The descriptors of quantized image pairs are used to train a popular classifier such as Support Vector Machine (SVM). The main contributions of this thesis are that it efficiently builds the randomized tree due to the weights of the samples and the control of the false-positive rate of this system.

[1] C.M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
[2] C.J.C. Burges, “A Tutorial on Support Vector Machines for Pattern Recognition”, Data Mining and Knowledge Discovery, Vol. 2, pp. 121-167, 1998.
[3] D.G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision, Vol. 60, No. 2, pp. 91-110, 2004.
[4] D. Pelleg and A. Moore, “X-Means: Extending K-means with Efficient Estimation of the Number of Clusters,” International Conference on Machine Learning, pp.727-734, 2000.
[5] D. Nister and H. Stewenius, “Scalable Recognition with a Vocabulary Tree,” Computer Vision and Pattern Recognition, Vol. 2, pp. 2161-2168, 2006.
[6] D. Huttenlocher, G.. Klanderman, and W.J. Rucklidge, “Comparing Images Using the Hausdorff Distance,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 15, No. 9, pp. 850–863, 1993.
[7] E. Grossmann, “AdaTree: Boosting a Weak Classifier into a Decision Tree,” Computer Vision and Pattern Recognition Workshop, Vol. 6, pp. 105-105, 2004.
[8] E. Nowak and Fr’ed’eric Jurie, “Learning Visual Similarity Measures for Comparing Never Seen Objects,” Computer Vision and Pattern Recognition, pp. 1-8, 2007.
[9] E. Osuna, R. Freund, and F. Girosi, “Training Support Vector Machines: an Application to Face Detection,” Computer Vision and Pattern Recognition, pp. 130-136, 1997.
[10] K. Etemad and R. Chellappa, “Discriminant Analysis for Recognition of Human Face Images,” Journal of the Optical Society of America A, Vol. 14, pp. 1724-1733, 1997.
[11] F. Moosmann, B. Triggs, and F. Jurie, “Fast Discriminative Visual Codebooks Using Randomized Clustering Forests,” Neural Information Processing System, 2006.
[12] G. Csurka, C.R. Dance, L. Fan, J. Willamowski, and C. Bray, “Visual Categorization with Bags of Keypoints,” European Conference on Computer Vision Workshop on Statistical Learning in CV, pp. 59-74, 2004.
[13] H. Lodhi, J.S. Taylor, N. Christianini and C. Watkins, “Text Classification Using String Kernels”, Journal of Machine Learning Research, Vol. 13, pp.419-444, 2001.
[14] J.C. Plat, “Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihod Methods”, Advances in Large Margin Classifiers, pp. 61-74, 1999.
[15] K. Mikolajczyk and C. Schmid, “A Performance Evaluation of Local Descriptors,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 27, No. 10, pp. 1615–1630, 2005.
[16] K. Mikolajczyk and C. Schmid, “Scale and Affine Invariant Interest Point Detectors,” International Journal of Computer Vision, Vol. 60, No. 1, pp. 63-86, 2004
[17] N.M. Nasrabadi and| R.A. King, “Image coding using vector quantization: a review,” IEEE Trans. on Communications, Vol. 36, No. 8, pp. 957-971 ,1988
[18] P. Geurts, D. Ernst, and L. Wehenkel, “Extremely Randomized Trees,” Machine Learning, Vol. 36, No. 1, pp. 3-42, 2006.
[19] P. Viola and M. Jones, “Robust Real-Time Object Detection”, International Journal of Computer Vision, Vol. 57, No 2, pp. 137-154, 2004.
[20] R.O. Duda, P.E. Hart, and D.G.. Stork, Pattern Classification, John Wiley and Sons, 2000.
[21] S. Tong and D. Koller, “Support Vector Machine Active Learning with Applications to Text Classification,” Journal of Machine Learning Research, Vol. 2, pp. 45-66, 2000.
[22] K. Veropoulos, C. Campbell, and N. Cristianini, “Controlling the Sensitivity of Support Vector Machines,” International Joint Conference on Artificial Intelligence, 1999.
[23] Y. Shan, H.S. Sawhney, and R. Kumar, “Unsupervised Learning of Discriminative Edge Measures for Vehicle Matching between Non-Overlapping Cameras,” Pattern Analysis and Machine Intellgence, Vol. 30, No. 4, pp. 700-711, 2008.
[24] Y. Guo, S. Hsu, H.S. Sawhney, R. Kumar, and Y. Shan, “Robust Object Matching for Persistent Tracking with Heterogeneous Features,” IEEE Trans. Pattern Analysis and Machine Intelligenc, Vol. 29, pp. 824-839, 2007.
[25] Y. Guo, Y. Shan, H.S. Sawhney, and R. Kumar, “PEET: Prototype Embedding and Embedding Transition for Matching Vehicles over Disparate Viewpoints,” Computer Vision and Pattern Recognition, pp. 1-8, 2007.
[26] Z. Tu, “Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering,” International Conference on Computer Vision, Vol. 2, pp. 1589-1596, 2005.