這篇論文主要研究三大主題：物件擷取、臉部辨識與車輛驗證。首先，物件擷取方法採用以模組為基礎的背景去除。不同於以前的方法，我們使用混合式碼簿的背景去除方法，該方法結合混合高斯與碼簿模型。所以我們對於具有陰影雨亮影的動態背景，提出一種橢圓求型式的碼簿，且設計一種修正式的陰影/亮影去除方法克服光影變化。我們提出的方法避免擷取到錯誤前景像素，(例：暗色背景容易受光影變化成為前景)，或是遺失真正的前景像素。最後我們在CVPR 2011年的變化偵測的標竿資料集上，用兩個實驗比較我們的方法與其他的方法。
再來我們提出一個基於外觀的流型臉部辨識。大部分這類的方法使用多張同一個人的照片進行訓練，然而我們通常沒有辦法針對每個人獲得足夠的訓練樣本，這類型的方法會因為不足的訓練樣本而無法有良好的辨識結果。因此，我們應用了可鑑別流型分析(DMMA)方法並提出了加速的方式，我們的快速DMMA方法分為三部分。首先我們將多個人訓練樣本集合起來，在每個人只有一個樣本的狀況下，使用修改型K均值分群法，把集合分成兩群。其二、這兩群的每個樣本，會被切割成無交疊的區塊，每一區塊當作DMMA的一個訓練實體。最後我們重複前兩個步驟並建立二元樹的方式達成快速的DMMA。實驗表明我們的方法可以加速DMMA的運算時間，而正確率只有微量的降低。
第三個主題是在兩個場景下驗證經過的車輛是否為同一台車輛，這個驗證並非一個簡單的問題，這個問題無法藉由特徵匹配的方式來解決。這裡我們提出一個新的稀疏表達(SR)，Boost K-SVD的字典表達車輛並進行車輛驗證，這種方法可以更能有效表達物件。首先我們使用粒子濾波器來挑選初始字基，然後我們令字典呈現近似正交的特性，該特性與具有有限級距特性(RIP)的矩陣相似。最後我們使用鑑別性評斷式決定字基的數量提升驗證的正確率。兩個場景下的車輛樣本對各自經過字典表達後將特徵表達向量串接成一個輸入向量，相同的車輛視為正樣本，不同的車輛視為負樣本。而驗證過程將被簡化為一個二元分類問題。所以我們所提出的Boost K-SVD字典(1)可以產生合適的稀疏表達字典。(2)更快找到初始字基。(3)提升車輛驗證的準確率。

This thesis investigates three research topics: object extraction, face recognition, and vehicle verification. First, we develop an object extraction method based on the model-based background subtraction. Different from previous methods, we introduce a hybrid codebook-based background subtraction method by combining the mixture of Gaussian (MOG) with the codebook (CB) method. The so-called ellipsoid CB model for modeling the dynamic background with highlight and shadow is a modified shadow/highlight removal method which can overcome the influence of illumination change. It can avoid extracting the false foreground pixels (e.g., dark background) or missing the real foreground pixels (e.g., bright foreground). Finally, we show two experiments to compare our method with the others based on the change detection benchmark dataset provided in CVPR 2011.
Second, we propose an appearance-based face recognition method. Most of the appearance-based methods use multiple samples per person for training. However, normally we do not have enough training samples for each person. The appearance-based methods may not work due to insufficient training samples. Therefore, we modify the Discriminative Multi-manifold Analysis (DMMA) method and propose an acceleration method. Our fast DMMA method can be divided into three modules. First, we input the training samples of multiple persons, one person one training sample, and then use a modified of K-means method to identify the similarity of two groups people. Second, these two groups of faces are divided into non-overlapping local patches for the DMMA. Third, we repeat the previous two steps to obtain the binary tree projection matrix of fast DMMA. The accelerated DMMA shows very little accuracy deficiency.
Third, verifying the same vehicle appearing in two scenes is a nontrivial problem that cannot be solved by corresponding feature matching. Here, we propose a new sparse representation (SR) for vehicle verification using the Boost K-SVD method, which offers more effective object representation. First, we use particle filtering to find the initial atom. Next, we generate the dictionary satisfying the nearly orthonormal property as similar as Restricted Isometry Property. Finally, we use a discrimination criterion to determine the number of atoms for enhanced verification accuracy. The vehicles in two views are subsequently combined and represented as a feature pair, each of which can be either a positive or negative pair. The verification is simplified as a binary classification problem. The contributions of the proposed Boost K-SVD method are (1) generating a proper SR dictionary, (2) finding the initial atom more quickly, and (3) improving verification accuracy.

[1] K. Kim, D. Harwood and L. Davis, "A perturbation method for evaluating background subtraction algorithm," Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2003.
[2] P. N. Belhumeur, J. P. Hespanha and D. J. Kriegman, "Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear NEigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, pp. 711-720, 7 1997.
[3] X. He, S. Yan, Y. Hu, P. Niyogi and H.-J. Zhang, "Face Recognition Using Laplacianfaces," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, pp. 328-340, 3 2005.
[4] X. Tan, S. Chen, Z. H. Zhou and F. Zhang, "Face recognition from a single image per person: A survey," Pattern Recognition, vol. 39, pp. 1725-1745, 9 2006.
[5] J. Wu and Z. H. Zhou, "Face recognition with one training image per person," Pattern Recognition Letters, vol. 23, pp. 1711-1719, 12 2002.
[6] J. Lu, Y. P. Tan and G. Wang, "Discriminative Multimanifold Analysis for Face Recognition from a Single Training Sample per Person," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, pp. 39-51, 1 2013.
[7] J. Lu, Y. P. Tan and G. Wang, "Discriminative Multimanifold Analysis for Face Recognition from a Single Training Sample per Person," IEEE Int. Conf. on Computer Vision, Barcelona, 2011.
[8] T. Bouwmans, "Recently advanced statistical background modeling for foreground detection – A systematic survey," Recent Patents on Computer Science, vol. 4, pp. 147-176, 9 2011.
[9] A. Elgammal, D. Harwood and L. Davis, "Non-parametric model for background subtraction," European Conference on Computer Vision, 2000.
[10] N. Thome and S. Miguet, "A robust appearance model for tracking human motion," IEEE International Conference on Advanced Video and Signal Based Surveillance, Como, 2005.
[11] H. Wang and P. Miller, "Regularized online Mixture of Gaussians for background subtraction," IEEE International Conference on Advanced Video and Signal Based Surveillance, Klagenfurt, 2011.
[12] J. K. Suhr, H. G. Jung and G. Li, "Mixture of Gaussian-based background subtraction for Bayer-pattern Image sequence," IEEE Transactions on Circuits and Systems for Video Technology, vol. 21, pp. 365 - 370, 3 2011.
[13] F. Porikli and O. Tuzel, "Bayesian background modeling for foreground detection," the third ACM international workshop on Video surveillance & sensor networks, 2005.
[14] H. H. Lin, T. L. Liu and J. H. Chuang, "A probabilistic SVM approach for background scene initialization," IEEE International Conference on Image Processing, Rochester, 2002.
[15] J. Wang, G. Bebis, M. Nicolescu, M. Nicolescu and R. Miller, "Improving target detection by coupling it with tracking," Machine Vision and Applications, vol. 20(4), pp. 205-223, 6 2009.
[16] R. H. Evangelio, M. Pätzold and T. Sikora, "Splitting Gaussians in Mixture Models," IEEE Int. Conf. on Advanced Video and Signal-Based Surveillance , Beijing, 2012.
[17] T. Haines and X. Tao, "Background subtraction with dirichlet processes," European Conference on Computer Vision, Florence, 2012.
[18] A. Shimada, D. Arita and R. Taniguchi, "Dynamic control of adaptive mixture-of-Gaussians background model," IEEE International Conference on Video and Signal Based Surveillance, Sydney, 2006.
[19] L. Carminati and J. Benois-Pineau, "Gaussian Mixture Classification for Moving Object Detection in Video Surveillance environment," IEEE International Conference on Image Processing, Genova, 2005.
[20] C. Stauffer and W. Grimson, "Learning patterns of activity using real-time tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22(8), pp. 747-757, 8 2000.
[21] E. Salvador, A. Cavallaro and T. Ebrahimi, "Shadow identification and classification using invariant color models.," IEEE International Conference on Acoustics, Speech, and Signal Processing, Salt Lake City, 2001.
[22] Y. Sheikh, O. Javed and T. Kanade, "Background subtraction for freely moving cameras," IEEE International Conference on Computer Vision, Kyoto, 2009.
[23] R. Cucchiara, C. Grana and M. Piccardi, "Detecting moving objects, ghosts and shadows in video streams," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, pp. 1337 - 1342, 10 2003.
[24] L. Li and M. Leung, "Integrating intensity and texture differences for robust change detection," IEEE Transactions on Image Processing, vol. 11, pp. 105 - 112, 2 2002.
[25] K. Kiratiratanapruk, P. Dubey and S. Siddhichai, "A Gradient-based foreground detection technique for object tracking in a traffic monitoring system," IEEE Conf. on Advanced Video and Signal Based Surveillance, 2005., Como, 2005.
[26] A. Mittal and N. Paragios, "Motion-based background subtraction using adaptive kernel density estimation," IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, 2004.
[27] T. Parag, A. Elgammal and A. Mittal, "A framework for feature selection for background subtraction," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, NewYork, 2006.
[28] K. Kim, T. H. Chalidabhongse, D. Harwood and L. Davis, "Real-time foreground- background segmentation using codebook model," Real-Time Imaging, vol. 11(3), pp. 172-185, 6 2005.
[29] A. Ilyas, M. Scuturici and S. Miguet, "Real-time foreground-background segmentation using a modified codebook model," IEEE International Conference on Advanced Video and Signal Based Surveillance, Genova, 2009.
[30] J. Yao and J. M. Odobez, "Multi-layer background subtraction based on color and texture," IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, 2007.
[31] N. Martel-Brisson and A. Zaccarin, "Learning and removing cast shadows through a multi-distribution approach," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29(7), pp. 1133 - 1146, 7 2007.
[32] M. Xiao, C. Z. Han and L. Zhang, "Moving shadow detection and removal for traffic sequences," International Journal of Automation and Computing, vol. 4(1), p. 38–46, 1 2007.
[33] E. Durucan and T. Ebrahimi, "Change detection and background extraction by linear algebra," Proceedings of the IEEE, vol. 89, pp. 1368 - 1381, 10 2001.
[34] J. Wood, Statistical background models with shadow detection for video based tracking, Institutionen för systemteknik, 2007.
[35] A. Prati, I. Mikic and M. Trivedi, "Detecting moving shadows: Algorithms and evaluation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25(7), pp. 918 - 923, 7 2003.
[36] W. Zhao, R. Chellappa, P. J. Phillips and A. Rosenfeld, "Face recognition: A literature survey," ACM computing surveys (CSUR), vol. 35(4), pp. 399-458, 12 2003.
[37] M. Turk and A. Pentland, "Eigenfaces for Recognition," Journal of Cognitive Neuroscience, vol. 3(1), pp. 71-86, 12 1991.
[38] S. Yan, D. Xu, B. Zhang, H. J. Zhang, Q. Yang and S. Lin, "Graph Embedding and Extensions: A General Framework for Dimensionality Reduction," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29(1), pp. 40-51, 1 2007.
[39] D. Zhang and Z. H. Zhou, "(2D) 2PCA: Two-directional two-dimensional PCA for efficient face representation and recognition," Neurocomputing, Vols. 69(1-3), pp. 224-231, 12 2005.
[40] D. Zhang, S. Chen and Z. H. Zhou, "A New Face Recognition Method Based on SVD Perturbation for Single Example Image per Person," Applied Mathematics and Computation, vol. 163(2), pp. 895-907, 4 2005.
[41] T. K. Kim and J. Kittler, "Locally linear discriminant analysis for multimodally distributed classes for face recognition with a single model image," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 27(3), pp. 318-327, 3 2005.
[42] J. Arróspide and L. Salgado, "Log-Gabor Filters for Image-Based Vehicle Verification," IEEE Trans. on Image Processing, vol. 22(6), pp. 2286-2295, 2 2013.
[43] Y. Li, B. Li and T. Bin, "Vehicle detection based on the AND–OR graph for congested traffic conditions," IEEE Transactions on Intelligent Transportation Systems, vol. 14(2), pp. 984-993, 6 2013.
[44] J. M. Guo, H. Prasetyo and K. Wong, "Vehicle Verification Using Gabor Filter Magnitude with Gamma Distribution Modeling," IEEE Signal Processing Letters, vol. 21(5), pp. 600-604, 3 2014.
[45] L. Cao, F. Luo, L. Chen, H. Wang, C. Wang and R. Ji, "Weakly supervised vehicle detection in satellite images via multi-instance discriminative learning," Pattern Recognition, vol. 64, pp. 417-424, 4 2017.
[46] Z. Y. Zhou, T. M. Deng and X. Y. Lv, "Study for vehicle recognition and classification based on Gabor wavelets transform & HMM," Int.l Conference on Consumer Electronics, Communications and Networks, XianNing, 2011.
[47] S. L. Chang, L. S. Chen, ,. Y. C. Chung and S. W. Chen, "Automatic License Plate Recognition," IEEE Trans. on Intelligent Transportation Systems, vol. 5(1), pp. 42-53, 2004.
[48] L. C. Chen, J. W. Hsieh, Y. Yan and D. Y. Chen, "Vehicle make and model recognition using sparse representation and symmetrical SURFs," Pattern Recognition, vol. 48(6), pp. 1979-1998, 6 2015.
[49] Y. Guo, Y. Shan, H. Sawhney and R. Kumar, "PEET: Prototype Embedding and Embedding Transition for Matching Vehicles over Disparate Viewpoints," IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, 2007.
[50] Y. Shan, H. S. Sawhney and R. Kumar, "Unsupervised learning of discriminative edge measures for vehicle matching between nonoverlapping cameras," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 30(4), pp. 700-711, 4 2008.
[51] Y. Shan, H. S. Sawhney and R. Kumar, "Vehicle identification between non-overlapping cameras without direct feature matching," IEEE International Conference on Computer Vision, Beijing, 2005.
[52] R. Rubinstein, T. Peleg and M. Elad, "Analysis K-SVD: A Dictionary-Learning Algorithm for the Analysis Sparse Model," IEEE Trans. on Signal Processing, vol. 61(3), pp. 661-677, 2012.
[53] R. Rubinstein, M. Zibulevsky and M. Elad, "Efficient implementation of the K-SVD algorithm using batch orthogonal matching pursuit," CS Technion, vol. 40(8), pp. 1-15, 2008.
[54] Y. Amidi and M. T. Sadeghi, "Face verification using sparse representations," in International Symposium on Telecommunications, Tehran, 2012.
[55] C. H. Duan, C. K. Chiang and S. H. Lai, "Face Verification With Local Sparse Representation," IEEE Signal Processing Letters, vol. 20(2), pp. 177-180, 2013.
[56] J. Mairal, F. Bach, J. Ponce and G. Sapiro, "Online Dictionary Learning for Sparse Coding," International Conference on Machine Learning, New York, 2009.
[57] I. T. Jolliffe, "A note on the use of principal components in regression," Applied Statistics, vol. 31, pp. 300-303, 1982.
[58] D. D. Lee and S. Seung, "Learning the parts of objects by non-negative matrix factorization," Nature, vol. 40, pp. 788-791, 1999.
[59] M. Isard and A. Blake, "Condensation—conditional density propagation for visual tracking," International Journal of Computer Vision, vol. 29(1), pp. 5-28, 8 1998.
[60] C. Shan, T. Tan and Y. Wei, "Real-time hand tracking using a mean shift embedded particle filter," Pattern Recognition, vol. 40(7), pp. 1958-1970, 7 2007.
[61] I. C. Chang and S. Y. Lin, "3D human motion tracking based on a progressive particle filter," Pattern Recognition, vol. 43(10), pp. 3621-3635, 10 2010.
[62] S. Julier and J. Uhlmann, "A New Extension of the Kalman Filter to Nonlinear Systems," International Symposium on Aerospace/Defense Sensing, Simulations and Controls, 1997.
[63] T. D. Gamage, J. G. Samarawickrama and A. A. Pasqual, "GPU based non-overlapping multi-camera vehicle tracking," Int. Conference on Information and Automation for Sustainability, 2014.
[64] W. Jiang, C. Xiao and H. Jin, "Vehicle tracking with non-overlapping views for multi-camera surveillance system," IEEE International Conference on High Performance Computing and Communications & Embedded and Ubiquitous Computing, Zhangjiajie, 2013.
[65] X. Wang, C. Zhang and Z. Zhang, "Boosted multi-task learning for face verification with applications to web image and video search," IEEE Conference on Computer Vision and Pattern Recognition, Miami, 2009.
[66] L. E. Shafey , R. Wallace and S. Marcel, "Face Verification using Gabor Filtering and Adapted Gaussian Mixture Models," Proceedings of the International Conference of the Biometrics Special Interest Group, Darmstadt, 2012.
[67] M. Kan, D. Xu and S. Shan, "Learning prototype hyperplanes for face verification in the wild," IEEE Transactions on Image Processing, vol. 22(8), pp. 3310-3316, 8 2013.
[68] Y. Wong, M. T. Harandi and C. Sanderson, "On robust biometric identity verification via sparse encoding of faces: Holistic vs local approaches," in International Joint Conference on Neural Networks, Brisbane, 2012.
[69] E. Ahmed, M. Jonse and T. K. Marks, "An improved deep learning architecture for person re-identification," IEEE Conference on Computer Vision and Pattern Recognition, Boston, 2015.
[70] W. J. Scheirer, M. J. Wilber, M. Eckmann and T. E. Boult, "Good recognition is non-metric," Pattern Recognition, vol. 47(8), pp. 2721-2731, 8 2014.
[71] Z. Yang and E. Oja, "Quadratic nonnegative matrix factorization," Pattern Recognition, vol. 45(4), pp. 1500-1510, 4 2012.
[72] M. Narasimha and A. Peterson, "On the Computation of the Discrete Cosine Transform," IEEE Transactions on Communications, vol. 26(6), pp. 934-946, 6 1978.
[73] E. Michael, Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing, NewYork: Springer-Verlag, 2010.
[74] X. Zhao, Z. He, S. Zhang and D. Liang, "Robust pedestrian detection in thermal infrared imagery using a shape distribution histogram feature and modified sparse representation classification," Pattern Recognition, vol. 48(6), pp. 1947-1960, 6 2015.
[75] Y. Xie, W. Zhang, Y. Qu and Y. Zhang, "Discriminative subspace learning with sparse representation view-based model for robust visual tracking," Pattern Recognition, vol. 47(3), pp. 1383-1394, 3 2014.
[76] J. Wright, A. Y. Yang, A. Ganesh, S. Sastry and Y. Ma, "Robust Face Recognition via Sparse Representation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31(2), pp. 210-227, 2008.
[77] Y. Xu, Z. Zhang, G. Lu and J. Yang, "Approximately symmetrical face images for image preprocessing in face recognition and sparse representation based classification," Pattern Recognition, vol. 54, pp. 68-82, 6 2016.
[78] X. Peng, L. Zhang, Z. Yi and K. K. Tan, "Learning locality-constrained collaborative representation for robust face recognition," Pattern Recognition, vol. 47(9), pp. 2794-2806, 9 2014.
[79] E. J. Candès, "The restricted isometry property and its implications for compressed sensing," Comptes Rendus Mathematique, Vols. 346(9-10), pp. 589-592, 5 2008.
[80] J. Mairal, I. Paris, F. Bach and J. Ponce, "Sparse modeling for image and vision processing," Journal Foundations and Trends® in Computer Graphics and Vision, vol. 8, pp. 85-283, 12 2014.
[81] A. Schick, M. Bäuml and R. Stiefelhagen, "Improving foreground segmentations with probabilistic superpixel Markov random fields," IEEE Conference on Computer Vision and Pattern Recognition Workshops, Providence, 2012.
[82] M. Hofmann, P. Tiefenbacher and G. Rigoll, "Background segmentation with feedback: The Pixel-Based Adaptive Segmenter," IEEE Conference on Computer Vision and Pattern Recognition Workshops, Providence, 2012.
[83] Y. Nonaka, A. Shimada, H. Nagahara and R.-i. Taniguchi, "Evaluation report of integrated background modeling based on spatio-temporal features," IEEE Conf. on Computer Vision and Pattern Recognition Workshops, Providence, 2012.
[84] Z. Zivkovic and F. Van Der Heijden, "Efficient adaptive density estimation per image pixel for the task of background subtraction," Pattern Recognition Letters, vol. 27(7), pp. 773-780, 5 2006.
[85] A. Morde, X. Ma and S. Guler, "Learning a background model for change detection," IEEE Conference on Computer Vision and Pattern Recognition Workshops, Providence, 2012.
[86] R. H. Evangelio and T. Sikora, "Complementary background models for the detection of static and moving objects in crowded environments," IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Klagenfurt, 2011.
[87] P. Phillips, H. Moon, S. Rizvi and P. Rauss, "The FERET evaluation methodology for face-recognition algorithms," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22(10), pp. 1090-1104, 10 2000.
[88] A. Martinez and R. Benavente, "The AR Face Database," CVC Tech. Report #24, 1998.
[89] B. Fei and J. Liu, "Binary tree of SVM: a new fast multiclass training and classification algorithm," IEEE Transactions on Neural Networks, vol. 17(3), pp. 696-704, 5 2006.
[90] G. Guo, S. Li and K. Chan, "Face recognition by support vector machines," IEEE Int. Conference on Automatic Face and Gesture Recognition, Grenoble, 2000.
[91] X. Tan, S. Chen, Z.-H. Zhou and F. Zhang, "Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft k-NN ensemble," IEEE Transactions on Neural Networks, vol. 16(4), pp. 875 - 886, 2005.
[92] S. Chen, D. Zhang and Z.-H. Zhou, "Enhanced (PC)2A for face recognition with one training image per person," Pattern Recognition Letters, vol. 25(10), pp. 1173-1181, 7 2004.
[93] B. Efron, T. Hastie, I. Johnstone and R. Tibshirani, "Least Angle Regression," The Annals of Statistics, vol. 32, no. 2, pp. 407-499, 2004.
[94] S. G. Mallat and Z. Zhang , "Matching pursuits with time-frequency dictionaries," IEEE Transactions on Signal Processing, vol. 41(12), pp. 3397-3415, 1993.
[95] R. Tibshirani, "Regression Shrinkage and Selection Via the Lasso," Journal of the Royal Statistical Society, pp. 267-288, 1994.
[96] J. Lu, G. Wang and W. Deng, "Reconstruction-based metric learning for unconstrained face verification," IEEE Transactions on Information Forensics and Security, vol. 10(1), pp. 79-89, 2015.
[97] L. Wolf, T. Hassner and Y. Taigman, "Similarity scores based on background samples," Asian Conference on Computer Vision, Xian, 2009.
[98] L. Maddalena and A. Petrosino, "A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications," IEEE Transactions on Image Processing, vol. 17(7), pp. 1168-1177, 2008.
[99] A. Shimada, D. Arita and R.-i. Taniguchi, "Dynamic Control of Adaptive Mixture-of-Gaussian Background Model," IEEE International Conference on Video and Signal Based Surveillance, Sydney, 2006.