臺灣博碩士論文加值系統

本研究中，我們提出了一基於深度學習之戶外停車場多車輛追蹤及辨別方法，此方法共包含了車輛偵測技術、車輛辨別技術以及車輛追蹤技術。首先，我們偵測出停車場中正在移動的車輛；接著，我們給予每台車輛一個專屬的身份，並建立特徵模型；最後，在影像序列中持續偵測並與模型進行配對關聯以達到多車輛追蹤的目標。在車輛偵測技術中，由特徵提取網路、區域建議網路及移動車輛偵測網路三個子網路組成，特徵提取網路融合影像及光流資訊，提取穩定的多階層特徵，經由區域建議網路搜尋出移動車輛的可能所在位置，最後透過移動車輛偵測網路找出移動車輛的所在位置。在車輛辨別技術中，我們設計三胞胎孿生網路來學習，使特徵在高維度空間中的分布，相同的車輛距離很近，不同的車輛距離很遠，並藉由量測彼此的相似性來求得關聯配對，最後透過分類器進行判斷以確保輸入特徵為車輛，而非其他物體或背景。在車輛追蹤技術中，為了使車輛辨別技術能有更多資訊配對關聯車輛，我們基於長短期記憶單元設計一移動預測網路，透過當前偵測車輛的所在位置與長寬資訊以及過去的軌跡資訊預測下一刻車輛可能出現的位置，使關聯及配對時能更穩定。

In this research, we propose a deep learning method based on multi-vehicle tracking and identification in outdoor parking lot. The framework has three parts which consists of vehicle detection, vehicle identification, and vehicle tracking. First, we detect the vehicles that are moving in the parking lot; then, we give each vehicle an identity and build a model; finally, continue to detect the motion vehicles and associate them with the model in the video sequence to achieve multi-vehicle tracking. For the vehicle detection, consist of feature representation, region proposal network, and motion vehicle detection. In the feature representation, merge the information of optical flow and extract the robust multi-layer features to descript the input. In the region proposal network, the network suggests for possible location of the motion vehicles. In the motion vehicle detection, make sure the objects are motion vehicles and their position. For the vehicle identification, we design triple Siamese network to train the appearance model, let the features of the same vehicle approach each other in the high dimensional feature space, and vice versa. At last, use the classifier to check the input image is a vehicle rather than other objects or backgrounds. For the vehicle tracking, we design a prediction network based on the long short term memory(LSTM) units to get more information of vehicle identifications to associate the vehicles. Predict the next position based on the current location and trajectory information of the detected vehicles to make the association and relationship more stable.

摘要 i
Abstract ii
目錄 iii
圖目錄 vi
表目錄 viii
第1章、 緒論 1
1.1 研究背景與動機 1
1.2 研究目標與困難 3
1.3 論文架構 4
第2章、 文獻探討與技術背景 5
2.1 機器學習方法 5
2.1.1 特徵描述方法 5
2.1.1.1 全域外觀特徵 5
2.1.1.2 區域外觀特徵 10
2.1.1.3 全域外觀特徵與區域外觀特徵比較 14
2.1.2 特徵外觀模型 15
2.1.2.1 混合生成式外觀模型 16
2.1.2.2 基於核心之生成式外觀模型(KGAMs) 17
2.1.2.3 基於子空間學習之生成式外觀模型(SLGAMs) 18
2.1.2.4 基於助推之判別式外觀模型(BDAMs) 20
2.1.2.5 基於支持向量基之判別式外觀模型(SDAMs) 22
2.1.2.6 基於隨機學習之判別式外觀模型(RLDAMs) 23
2.1.2.7 基於判別分析之判別式外觀模型(DADAMs) 23
2.1.2.8 基於碼書學習之判別式外觀模型(CLDAMs) 25
2.1.2.9 混合生成判別式外觀模型(HGDAMs) 26
2.2 深度學習方法 27
2.3 機器學習與深度學習比較 29
2.4 物件偵測技術 30
2.5 物件辨別技術 30
2.6 物件追蹤技術 31
第3章、 基於深度學習之戶外停車場多車輛追蹤及辨別方法 33
3.1 系統架構 33
3.2 光流資訊 34
3.3 基於深度學習之移動車輛偵測技術 36
3.3.1 特徵提取網路(Feature Representation) 36
3.3.2 區域建議網路(Region Proposal Network) 38
3.3.3 移動車輛偵測網路(Motion Vehicle Detection) 39
3.3.4 最佳化(Optimization) 40
3.4 基於深度學習之車輛辨別技術 41
3.4.1 特徵模型(Appearance Model) 41
3.4.2 模型更新機制 42
3.5 基於深度學習之車輛追蹤技術 43
3.5.1 移動模型(Motion Model) 43
第4章、 系統實現 45
4.1 系統平台 45
4.2 網路實現 45
4.2.1 車輛偵測技術 46
4.2.2 車輛辨別技術 47
4.2.3 車輛追蹤網路 48
第5章、 實驗結果 49
5.1 資料庫 49
5.2 不同光流下的結果評估 49
5.3 不同融合下的結果評估 50
5.4 車輛偵測的結果評估 51
5.5 車輛辨別的結果評估 52
5.6 車輛追蹤的結果評估 53
第6章、 結論與未來展望 54
6.1 結論 54
6.2 未來展望 54
參考文獻 55

[1]C. Perkins, “Frustrated drivers: There's an app that helps you find street parking,” Mashable, June 04, 2015. [online], Available: http://mashable.com. [Accessed June 05, 2018].
[2]M.-Y.-I. Idris, Y.-Y. Leng, E.-M. Tamil, N.-M. Noor, and Z. Razak, “Car Park System: A Review of Smart Parking System and its Technology,” Information Technology Journal (ITJ), vol. 8, no. 2, pp. 101-113, 2009.
[3]G. Silveira and E. Malis, “Real-time Visual Tracking under Arbitrary Illumination Changes,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA, June 17-22, 2007.
[4]J. Ho, K.-C. Lee, M.-H. Yang, and D. Kriegman, “Visual tracking using learned linear subspaces,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA, 27 June-2 July, 2004.
[5]Y. Li, “On incremental and robust subspace learning,” Pattern Recognition, vol. 37, no. 7, pp. 1509-1518, 2004.
[6]D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang, “Incremental Learning for Robust Visual Tracking,” International Journal of Computer Vision (IJCV), vol. 77, no. 1-3, pp. 125-141, 2008.
[7]X. Li, W. Hu, Z. Zhang, X. Zhang, and G. Luo, “Robust Visual Tracking Based on Incremental Tensor Subspace Learning,” IEEE International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, 14-21 Oct., 2007.
[8]L. Wen, Z. Cai, Z. Lei, D. Yi, and S. Z. Li, “Online Spatio-temporal Structural Context Learning for Visual Tracking,” European Conference on Computer Vision (ECCV), Florence, Italy, 7-13 Oct., 2012.
[9]W. Hu, X. Li, X. Zhang, X. Shi, S. Maybank, and Z. Zhang, “Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking,” International Journal of Computer Vision (IJCV), vol. 91, no. 3, pp. 303-327, 2011.
[10]T. Wang, I. Y.-H. Gu, and P. Shi, “Object Tracking using Incremental 2D-PCA Learning and ML Estimation,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Honolulu, HI, USA, 15-20 April, 2007.
[11]G. Li, D. Liang, Q. Huang, S. Jiang, and W. Gao, “Object tracking using incremental 2D-LDA learning and Bayes inference,” IEEE International Conference on Image Processing (ICIP), San Diego, CA, USA, 12-15 Oct., 2008.
[12]B. D. Lucas and T. Kanade, “An iterative image registration technique with an application to stereo vision,” International Joint Conference on Artificial Intelligence (IJCAI), San Francisco, CA, USA, 24-28 Aug.,1981.
[13]B. K.-P. Horn and B. G. Schunck, “Determining optical flow,” Artificial Intelligence, vol. 17, no. 1-3, pp. 185-203, 1981.
[14]M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof, “Anisotropic Huber-L1 Optical Flow,” British Machine Vision Conference (BMVC), London, UK, 7-10 Sept., 2009.
[15]I. K. Sethi and R. Jain, “Finding Trajectories of Feature Points in a Monocular Image Sequence,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 9, no. 1, pp. 56-73, 1987.
[16]V. Salari and I.-K. Sethi, “Feature point correspondence in the presence of occlusion,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 12, no. 1, pp. 87-91, 1990.
[17]J. Santner, C. Leistner, A. Saffari, T. Pock, and H. Bischof, “PROST: Parallel robust online simple tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, 13-18 June, 2010.
[18]M. J. Black and P. Anandan, “The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields,” Computer Vision and Image Understanding (CVIU), vol. 63, no. 1, pp.75-104, 1996.
[19]H. S. Sawhney and S. Ayer, “Compact Representations of Videos Through Dominant and Multiple Motion Estimation,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 18, no. 8, pp. 814-830, 1996.
[20]G.-D. Hager and P.-N. Belhumeur, “Efficient region tracking with paramteric models of geometry and illumination,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 20, no. 10, pp. 1025-1039, 1998.
[21]J.-R. Bergen, P.-J. Burt, R. Hingorani, and S. Peleg, “A three-frame algorithm for estimating two-component image motion,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 14, no. 9, pp. 886-896, 1992.
[22]M. Irani, “Multi-frame optical flow estimation using subspace constraints,” IEEE International Conference on Computer Vision (ICCV), Kerkyra, Greece, 20-27 Sept., 1999.
[23]Y. Wu and J. Fan, “Contextual flow,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA, 20-25 June, 2009.
[24]G.-R. Bradski, “Real time face and object tracking as a component of a perceptual user interface,” IEEE Workshop on Applications of Computer Vision (WACV), Princeton, NJ, USA, 19-21 Oct., 1998.
[25]D. Comaniciu, V. Ramesh, and P. Meer, “Kernel-based object tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 25, no. 5, pp. 564-577, 2003.
[26]Q. Zhao, Z. Yang, and H. Tao, “Differential Earth Mover's Distance with Its Applications to Visual Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 32, no. 2, pp. 274-287, 2008.
[27]C. Yang, R. Duraiswami, and L. Davis, “Efficient mean-shift tracking via a new similarity measure,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, 20-25 June, 2005.
[28]B. Georgescu and P. Meer, “Point matching under large image deformations and illumination changes,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 26, no. 6, pp. 674-688, 2004.
[29]S.-T. Birchfield and S. Rangarajan, “Spatiograms versus histograms for region-based tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, 20-25 June, 2005.
[30]A. Adam, E. Rivlin, and I. Shimshoni, “Robust Fragments-based Tracking using the Integral Histogram,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New York, NY, USA, 17-22 June, 2006.
[31]S.-M. S. Nejhum, J. Ho, and M.-H. Yang, “Online visual tracking with histograms and articulating blocks,” Computer Vision and Image Understanding (CVIU), vol. 114, no. 8, pp. 901-914, 2010.
[32]R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural Features for Image Classification,” IEEE Transactions on Systems, Man, and Cybernetics (SMC), vol. 3, no. 6, pp. 610-621, 1973.
[33]I. Haritaoglu and M. Flickner, “Detection and tracking of shopping groups in stores,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Kauai, HI, USA, 8-14 Dec., 2001.
[34]J. Wang and Y. Yagi, “Integrating Color and Shape-Texture Features for Adaptive Real-Time Object Tracking,” IEEE Transactions on Image Processing (TIP), vol. 17, no. 2, pp. 235-240, 2008.
[35]J. Ning, L. Zhang, D. Zhang, and C. Wu, “Robust Object Tracking using Joint Color-Texture Histogram,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 23, no. 7, pp. 1245-1263, 2009.
[36]F. Porikli, O. Tuzel, and P. Meer, “Covariance Tracking using Model Update Based on Lie Algebra,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New York, NY, USA, 17-22 June, 2006.
[37]O. Tuzel, F. Porikli, and P. Meer, “Region Covariance: A Fast Descriptor for Detection and Classification,” European Conference on Computer Vision (ECCV), Graz, Austria, 7-13 May, 2006.
[38]X. Li, W. Hu, Z. Zhang, X. Zhang, M. Zhu, and J. Cheng, “Visual tracking via incremental Log-Euclidean Riemannian subspace learning,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, AK, USA, 23-28 June, 2008.
[39]W. Hu, X. Li, W. Luo, X. Zhang, S. Maybank, and Z. Zhang, “Single and Multiple Object Tracking Using Log-Euclidean Riemannian Subspace and Block-Division Appearance Model,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 34, no. 12, pp. 2420-2440, 2012.
[40]I. Austvoll and B. Kwolek, “Region Covariance Matrix-Based Object Tracking with Occlusions Handling,” International Conference on Computer Vision and Graphics (ICCVG), Warsaw, Poland, 20-22 Sept., 2010.
[41]V. Arsigny, P. Fillard, X. Pennec, and N. Ayache, “Geometric Means in a Novel Vector Space Structure on Symmetric Positive‐Definite Matrices,” SIAM Journal on Matrix Analysis and Applications, vol. 29, no. 1, pp. 328-347, 2007.
[42]Y. Wu, J. Cheng, J. Wang, and H. Lu, “Real-time visual tracking via Incremental Covariance Tensor Learning,” IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan, 29 Sept.-2 Oct., 2009.
[43]Y. Wu, J. Cheng, J. Wang, H. Lu, J. Wang, H. Ling, E. Blasch, and L. Bai, “Real-Time Probabilistic Covariance Tracking With Efficient Model Update,” IEEE Transactions on Image Processing (TIP), vol. 21, no. 5, pp. 2824-2837, 2012.
[44]X. Hong, H. Chang, S. Shan, B. Zhong, X. Chen, and W. Gao, “Sigma Set Based Implicit Online Learning for Object Tracking,” IEEE Signal Processing Letters, vol. 17, no. 9, pp. 807-810, 2010.
[45]C. He, Y.-F. Zheng, and S.-C. Ahalt, “Object tracking using the Gabor wavelet transform and the golden section algorithm,” IEEE Transactions on Multimedia, vol. 4, no. 4, pp. 528-538, 2002.
[46]M. Li, Z. Zhang, K. Huang, and T. Tan, “Robust visual tracking based on simplified biologically inspired features,” IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, 7-10 Nov., 2009.
[47]N. Paragios and R. Deriche, “Geodesic active contours and level sets for the detection and tracking of moving objects,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 22, no. 3, pp. 266-280, 2000.
[48]D. Cremers, “Dynamical statistical shape priors for level set-based tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 28, no. 8, pp. 1262-1273, 2006.
[49]M. S. Allili and D. Ziou, “Object of Interest segmentation and Tracking by Using Feature Selection and Active Contours,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA, 17-22 June, 2007.
[50]N. Vaswani, Y. Rathi, A. Yezzi, and A. Tannenbaum, “Deform PF-MT: Particle Filter With Mode Tracker for Tracking Nonaffine Contour Deformations,” IEEE Transactions on Image Processing (TIP), vol. 19, no. 4, pp. 841-857, 2009.
[51]X. Sun, H. Yao, and S. Zhang, “A novel supervised level set method for non-rigid object tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, USA, 20-25 June, 2011.
[52]Z. Lin, L. S. Davis, D. Doermann, and D. DeMenthon, “Hierarchical Part-Template Matching for Human Detection and Segmentation,” International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, 14-21 Oct., 2007.
[53]X. Ren and J. Malik, “Tracking as Repeated Figure/Ground Segmentation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA, 17-22 June, 2007.
[54]S. Wang, H. Lu, F. Yang, and M.-H. Yang, “Superpixel tracking,” IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 6-13 Nov., 2011.
[55]H. Zhou, Y, Yuan, and C. Shi, “Object tracking using SIFT features and mean shift,” Computer Vision and Image Understanding (CVIU), vol. 113, no. 3, pp. 345-352, 2009.
[56]F. Tang and H. Tao, “Probabilistic Object Tracking With Dynamic Attributed Relational Feature Graph,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVC), vol. 18, no. 8, pp. 1064-1074, 2008.
[57]J. Sivic, F. Schaffalitzky, and A. Zisserman, “Object Level Grouping for Video Shots,” International Journal of Computer Vision (IJCV), vol. 67, no. 2, pp. 189-210, 2006.
[58]S. Tran and L. Davis, “Robust Object Tracking with Regional Affine Invariant Features,” IEEE International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, 14-21 Oct., 2007.
[59]W. He, T. Yamashita, H. Lu, and S. Lao, “SURF Tracking,” IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan, 29 Sept.-2 Oct., 2009.
[60]Z. Kim, “Real time object tracking based on dynamic feature grouping with background subtraction,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, AK, USA, 23-28 June, 2008.
[61]R.-T. Collins, Y. Liu, and M. Leordeanu, “Online selection of discriminative tracking features,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 27, no. 10, pp. 1631-1643, 2005.
[62]X. Liu and T. Yu, “Gradient Feature Selection for Online Boosting,” IEEE International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, 14-21 Oct., 2007.
[63]Q. Yu, T. B. Dinh, and G. Medioni, “Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers,” European Conference on Computer Vision (ECCV), Marseille, France, 12-18 Oct., 2008.
[64]H. T. Nguyen and A. Smeulders, “Tracking Aspects of the Foreground against the Background,” European Conference on Computer Vision (ECCV), Prague, Czech Republic, 11-14 May, 2004.
[65]B. Babenko, M.-H. Yang, and S. Belongie, “Visual tracking with online Multiple Instance Learning,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA, 20-25 June 2009.
[66]H. Grabner and H. Bischof, “On-line Boosting and Vision,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New York, NY, USA, 17-22 June, 2006.
[67]N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, 20-25 June, 2005.
[68]T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 24, no. 7, pp. 971-987, 2002.
[69]S. E. Palmer, Vision Science: Photons to Phenomenology. MIT, US: The MIT Press, 1999.
[70]K. Toyama and G.-D. Hager, “Incremental focus of attention for robust visual tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, 18-20 June, 1996.
[71]V. Mahadevan and N. Vasconcelos, “Saliency-based discriminant tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA, 20-25 June, 2009.
[72]M. Yang, J. Yuan, and Y. Wu, “Spatial selection for attentional visual tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA, 17-22 June, 2007.
[73]F. Yang, H. Lu, and Y.-W. Chen, “Human Tracking by Multiple Kernel Boosting with Locality Affinity Constraints,” Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand, 8-12 Nov., 2010.
[74]S. J. McKenna, Y. Raja, and S. Gong, “Tracking colour objects using adaptive mixture models,” Image and Vision Computing, vol. 17, no. 3-4, pp. 225-231, 1999.
[75]C. Stauffer and W.-E.-L. Grimson, “Learning patterns of activity using real-time tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 22, no. 8, pp. 747-757, 2000.
[76]B. Han and L. Davis, “On-line density-based appearance modeling for object tracking,” IEEE International Conference on Computer Vision (ICCV), Beijing, China, 17-21 Oct., 2005.
[77]T. Yu and Y. Wu, “Differential Tracking based on Spatial-Appearance Model (SAM),” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New York, NY, USA, 17-22 June, 2006.
[78]H. Wang, D. Suter, K. Schindler, and C. Shen, “Adaptive Object Tracking Based on an Effective Appearance Filter,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 29, no. 9, pp. 1661-1667, 2007.
[79]I. Leichter, M. Lindenbaum, and E. Rivlin, “Mean Shift tracking with multiple reference color histograms,” Computer Vision and Image Understanding (CVIU), vol. 114, no. 3, pp. 400-408, 2010.
[80]R.-T. Collins, “Mean-shift blob tracking through scale space,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Madison, WI, USA, 18-20 June, 2003.
[81]Q. A. Nguyen, A. Robles-Kelly, and C. Shen, “Kernel-based Tracking from a Probabilistic Viewpoint,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA, 17-22 June, 2007.
[82]A. Yilmaz, “Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA, 17-22 June, 2007.
[83]C. Shen, M.-J. Brooks, and A. van den Hengel, “Fast global kernel density mode seeking with application to localization and tracking,” IEEE Transactions on Image Processing (TIP), vol. 16, no. 5, pp. 1457-1469, 2007.
[84]M. J. Black and A. D. Jepson, “EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation,” International Journal of Computer Vision (IJCV), vol. 26, no. 1, pp. 63-84, 1998.
[85]Skocaj and Leonardis, “Weighted and robust incremental method for subspace learning,” IEEE International Conference on Computer Vision (ICCV), Nice, France, 13-16 Oct., 2003.
[86]A. Levey and M. Lindenbaum, “Sequential Karhunen-Loeve basis extraction and its application to images,” IEEE Transactions on Image Processing (TIP), vol. 9, no. 8, pp. 1371-1374, 2000.
[87]M. Brand, “Incremental Singular Value Decomposition of Uncertain Data with Missing Values,” European Conference on Computer Vision (ECCV), Copenhagen, Denmark, 28–31 May, 2002.
[88]Q. Wang, F. Chen, W. Xu, and M.-H. Yang, “Object Tracking via Partial Least Squares Analysis,” IEEE Transactions on Image Processing (TIP), vol. 21, no. 21, pp. 4454-4465, 2012.
[89]H. Lim, O.I. Camps, M. Sznaier, and V.-I. Morariu, “Dynamic Appearance Modeling for Human Tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New York, NY, USA, 17-22 June, 2006.
[90]T.-J. Chin and D. Suter, “Incremental Kernel Principal Component Analysis,” IEEE Transactions on Image Processing (TIP), vol. 16, no. 6, pp. 1662-1674, 2007.
[91]X. Mei and H. Ling, “Robust visual tracking using l_1 minimization,” IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan, 29 Sept.-2 Oct., 2009.
[92]X. Jia, H. Lu, and M.-H. Yang, “Visual tracking via adaptive structural local sparse appearance model,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, 16-21 June, 2012.
[93]T. Zhang, B. Ghanem, S. Liu, and N. Ahuja, “Robust visual tracking via multi-task sparse learning,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, 16-21 June, 2012.
[94]H. Li, C. Shen, and Q. Shi, “Real-time visual tracking using compressive sensing,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, USA, 20-25 June, 2011.
[95]K. Zhang, L. Zhang, and M.-H. Yang, “Real-time compressive tracking,” European conference on Computer Vision (ECCV), Florence, Italy, 7-13 Oct., 2012.
[96]C. Bao, Y. Wu, H. Ling, and H. Ji, “Real time robust L1 tracker using accelerated proximal gradient approach,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, 16-21 June, 2012.
[97]X. Li, A. Dick, C. Shen, A. van den Hengel, and H. Wang, “Incremental Learning of 3D-DCT Compact Representations for Robust Visual Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 35, no. 4, pp. 863-881, 2012.
[98]X. Li, C. Shen, Q. Shi, A. Dick, and A. van den Hengel, “Non-sparse linear representations for visual tracking with online reservoir metric learning,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, 16-21 June, 2012.
[99]J. Fan, M. Yang, and Y. Wu, “A bi-subspace model for robust visual tracking,” IEEE International Conference on Image Processing (ICIP), San Diego, CA, USA, 12-15 Oct., 2008.
[100]K.-C. Lee and D. Kriegman, “Online learning of probabilistic appearance manifolds for video-based recognition and tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, 20-25 June, 2005.
[101]J. Kwon and K. M. Lee, “Visual tracking decomposition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, 13-18 June, 2010.
[102]H. Grabner, M. Grabner, and H. Bischof, “Real-time Tracking via On-line Boosting,” British Machine Vision Conference (BMVC), Edinburgh, Scotland, 4-7 Sept., 2006.
[103]S. Avidan, “Ensemble Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 29, no. 2, pp. 261-271, 2007.
[104]X. Zhu, “Semi-supervised learning literature survey,” Computer Sciences, vol. 37, no. 1, pp. 63-77, 2008.
[105]H. Grabner, C. Leistner, and H. Bischof, “Semi-supervised On-Line Boosting for Robust Tracking,” European Conference on Computer Vision (ECCV), Marseille, France, 12-18 Oct., 2008.
[106]R. Liu, J. Cheng, and H. Lu, “A robust boosting tracker with minimum error bound in a co-training framework,” IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan, 29 Sept.-2 Oct., 2009.
[107]K. Zhang and H. Song, “Real-time visual tracking via online weighted multiple instance learning,” Pattern Recognition, vol. 46, no. 1, pp. 397-411, 2013.
[108]M. Li, J. T. Kwok, and B.-L. Lu, “Online multiple instance learning with no regret,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, 13-18 June, 2010.
[109]B. Zeisl, C. Leistner, A. Saffari, and H. Bischof, “On-line semi-supervised multiple-instance boosting,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, 13-18 June, 2010.
[110]G. Li, Q. Huang, L. Qin, and S. Jiang, “SSOCBT: A Robust Semisupervised Online CovBoost Tracker That Uses Samples Differently,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 23, no. 4, pp. 695-709, 2013.
[111]S. Avidan, “Support vector tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 26, no. 8, pp. 1064-1072, 2004.
[112]O. Williams, A. Blake, and R. Cipolla, “Sparse Bayesian learning for efficient visual tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 27, no. 8, pp. 1292-1304, 2005.
[113]M. Tian, W. Zhang, and F. Liu, “On-Line Ensemble SVM for Robust Object Tracking,” Asian Conference on Computer Vision (ACCV), Tokyo, Japan, 18-22 Nov., 2007.
[114]S. Hare, A. Saffari, and P. H. S. Torr, “Struck: Structured output tracking with kernels,” IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 6-13 Nov., 2011.
[115]R. Yao, Q. Shi, C. Shen, Y. Zhang, and A. van den Hengel, “Robust Tracking with Weighted Online Structured Learning,” European Conference on Computer Vision (ECCV), Florence, Italy, 7-13 Oct., 2012.
[116]Y. Bai and M. Tang, “Robust tracking via weakly supervised ranking SVM,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, 16-21 June, 2012.
[117]F. Tang, S. Brennan, Q. Zhao, and H. Tao, “Co-Tracking Using Semi-Supervised Support Vector Machines,” IEEE International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, 14-21 Oct., 2007.
[118]H. Lu, W. Zhang, and Y.-W. Chen, “On Feature Combination and Multiple Kernel Learning for Object Tracking,” Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand, 8-12 Nov., 2010.
[119]L. Breiman, “Random Forests,” Machine Learning, vol. 46, no. 1, pp. 5-32, 2001.
[120]J. Shotton, M. Johnson, and R. Cipolla, “Semantic texton forests for image categorization and segmentation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, AK, USA, 23-28 June, 2008.
[121]V. Lepetit and P. Fua, “Keypoint recognition using randomized trees,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 28, no. 9, pp 1465-1479, 2006.
[122]M. Ozuysal, M. Calonder, V. Lepetit, and P. Fua, “Fast Keypoint Recognition Using Random Ferns,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 32, no. 3, pp. 448-461, 2010.
[123]A. Saffari, C. Leistner, J. Santner, M. Godec, and H. Bischof, “On-line Random Forests,” IEEE International Conference on Computer Vision Workshops (ICCV Workshops), Kyoto, Japan, 27 Sept.-4 Oct., 2009.
[124]M. Godec, C. Leistner, A. Saffari, and H. Bischof, “On-Line Random Naive Bayes for Tracking,” International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, 23-26 Aug., 2010.
[125]R.-S. Lin, M.-H. Yang, and S.-E. Levinson, “Object tracking using incremental Fisher discriminant analysis,” International Conference on Pattern Recognition (ICPR), Cambridge, UK, 26 Aug., 2004.
[126]H. T. Nguyen and A. W. M. Smeulders, “Robust Tracking Using Foreground-Background Texture Discrimination,” International Journal of Computer Vision (IJCV), vol. 69, no. 3, pp. 277-293, 2006.
[127]X. Wang, G. Hua, and T. X. Han, “Discriminative Tracking by Metric Learning,” European Conference on Computer Vision (ECCV), Heraklion, Crete, Greece, 5-11 Sept., 2010.
[128]N. Jiang, W. Liu, H. Su, and Y. Wu, “Tracking low resolution objects by metric preservation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, USA, 20-25 June, 2011.
[129]N. Jiang, W. Liu, and Y. Wu, “Order determination and sparsity-regularized metric learning adaptive visual tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, 16-21 June, 2012.
[130]Z. Xu, P. Shi, and X. Xu, “Adaptive Subclass Discriminant Analysis Color Space Learning for Visual Tracking,” Pacific-Rim Conference on Multimedia (PCM), Tainan, Taiwan, 9-13 Dec., 2008.
[131]X. Zhang, W. Hu, S. Maybank, and X. Li, “Graph Based Discriminative Learning for Robust and Efficient Object Tracking,” IEEE International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, 14-21 Oct., 2007.
[132]Y. Zha, Y. Yang, and D. Bi, “Graph-based transductive learning for robust visual tracking,” Pattern Recognition, vol. 43, no. 1, pp. 187-196, 2010.
[133]F. Yang, H. Lu, W. Zhang, and G. Yang, “Visual tracking via bag of features,” International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, 23-26 Aug., 2010.
[134]J. Gall, N. Razavi, and L. V. Gool, “On-line Adaption of Class-specific Codebooks for Instance Tracking,” British Machine Vision Conference (BMVC), Wales, UK, 30 Aug.-2 Sept., 2010.
[135]M. Andriluka, S. Roth, and B. Schiele, “People-tracking-by-detection and people-detection-by-tracking,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, AK, USA, 23-28 June, 2008.
[136]I. Ulusoy and C.M. Bishop, “Generative versus discriminative methods for object recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, 20-25 June, 2005.
[137]B.-M. Kelm, C. Pal, and A. McCallum, “Combining Generative and Discriminative Methods for Pixel Classification with Multi-Conditional Learning,” International Conference on Pattern Recognition (ICPR), Hong Kong, China, 20-24 Aug., 2006.
[138]M. Yang, Z. Fan, J. Fan, and Y. Wu, “Tracking Nonstationary Visual Appearances by Data-Driven Adaptation,” IEEE Transactions on Image Processing (TIP), vol. 18, no. 7, pp. 1633-1644, 2009.
[139]H. Grabner, P. M. Roth, and H. Bischof, “Eigenboosting: Combining Discriminative and Generative Information,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA, 17-22 June, 2007
[140]M. Everingham and A. Zisserman, “Identifying individuals in video by combining 'generative' and discriminative head models,” IEEE International Conference on Computer Vision (ICCV), Beijing, China, 17-21 Oct., 2005.
[141]Y. Lei, X. Ding, and S. Wang, “Visual Tracker Using Sequential Bayesian Learning: Discriminative, Generative, and Hybrid,” IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, vol. 38, no. 6, pp. 1578-1591, 2008.
[142]Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[143]A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” International Conference on Neural Information Processing Systems (NIPS), Nevada, NV, USA, 3-8 Dec., 2012.
[144]K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” International Conference on Learning Representations (ICLR), San Diego, CA, USA,7-9 May, 2015
[145]R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA, 23-28 June, 2014.
[146]R. Girshick, “Fast R-CNN,” IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7-13 Dec., 2015.
[147]S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” Neural Information Processing Systems (NIPS), Montreal, QC, Canada, 7-15 Dec., 2015.
[148]J. E. Espinosa, S. A. Velastin, and J. W. Branch, “Vehicle Detection Using Alex Net and Faster R-CNN Deep Learning Models: A Comparative Study,” International Visual Informatics Conference (IVIC), Bangi, Selangor, Malaysia, 28-30 Nov., 2017.
[149]M. Koestinger, M. Hirzer, P. Wohlhart, P. Roth, and H. Bischof, “Large scale metric learning from equivalence constraints,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, 16-21 June, 2012.
[150]Z. Li, S. Chang, F. Liang, T. Huang, L. Cao, and J. Smith, “Learning locally-adaptive decision functions for person verification,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, 25-27 June, 2013.
[151]N. Martinel, C. Micheloni, and G. Feresti, “Saliency weighted features for person re-identification,” European Conference on Computer Vision (ECCV), Zurich, Switzerland, 6-7 and 12 Sept., 2014.
[152]E. Ahmed, M. Jones, and T. K. Marks, “An improved deep learning architecture for person re-identification,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7-12 June, 2015.
[153]X. Qian, Y. Fu, Y.-G. Jiang, T. Xiang, and X. Xue, “Multi-scale Deep Learning Architectures for Person Re-identification,” IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22-29 Oct., 2017.
[154]S.-H. Bae and K.-J. Yoon, “Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. PP, no. 99, pp. 1-1, 2017.
[155]R. E. Kalman, “A New Approach to Linear Filtering and Prediction Problems,” Basic Engineering, vol. 82, no. 1, pp. 35-45, 1960.
[156]M. Isard and A. Blake, “Condensation-conditional density propagation for tracking,” International Journal of Computer Vision (IJCV), vol. 29, no. 1, pp. 2-28, 1998.
[157]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, 2002.
[158]C. Shen, M. Brooks, and A. van den Hengel, “Augmented particle filtering for efficient visual tracking,” IEEE International Conference on Image Processing (ICIP), Genova, Italy, 14 Sept., 2005.
[159]A. Sadeghian, A. Alahi, and Savarese, “Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies,” arXiv preprint arXiv:1701.01909, 2017.
[160]B. D. Lucas and T. Kanade, “An iterative image registration technique with an application to stereo vision,” International Joint Conference on Artificial Intelligence (IJCAI), Vancouver, BC, Canada, 24-28 Aug., 1981.
[161]G. Farnebäck, “Two-Frame Motion Estimation Based on Polynomial Expansion,” Scandinavian Conference on Image Analysis (SCIA), Halmstad, Sweden, 29 June-2 July, 2003.
[162]S. Baker, D. Scharstein, J. P. Lewis, S. Roth, M. J. Black, and R. Szeliski, “A Database and Evaluation Methodology for Optical Flow,” International Journal of Computer Vision (IJCV), vol. 92, no. 1, pp. 1-31, 2011.