Görsel Hedef Takibi Yöntemlerine Genel Bakış

Yıl 2017, Cilt: 7 Sayı: 13, 5 - 16, 30.06.2017

Bahri Maraş , Nafiz Arıca Ayşın Baytan Ertüzün

Öz

Görsel hedef takibi, üzerinde uzun süredir
çalışılmış ve halen araştırma konusu olmaya devam eden önemli bir bilgisayarla
görü problemidir. Hedef takibi problemi, sabit ya da hareketli bir kameradan alınan
video bilgisi üzerinde ilgilenilen nesnenin izlenmesi olarak tanımlanabilir. Araştırma konusu olarak ilgi çekmesinin en önemli nedenleri, takibin
yapıldığı ortam şartlarında ve takip edilecek nesne hareketinde oluşan değişimlerdir.
Başarılı bir hedef takip algoritmasının, ortamda meydana gelen ışık
değişimlerine, görüntü gürültüsüne, düşük karşıtlığa, hedefin ortamdaki diğer
nesnelerle örtüşmesine, hedefi görüntüleyen kameranın istemsiz hareketlerine
vb. karşı gürbüz olması gerekmektedir. Literatürdeki araştırmalar temel olarak
üretici (generative) ve ayırdedici (discriminative) olarak iki başlık altına
toplanmaktadır. Bu makalede her iki yaklaşımı temel alan son yıllarda
geliştirilmiş hedef takibi algoritmaları incelenerek, mevcut yöntemlerin
avantaj ve dezavantajları karşılaştırılmalarla anlatılmaktadır. Ayrıca
çalışmaların başarım değerlendirmesi amacıyla literatürde kullanılan veri
kümeleri ve karşılaştırma metrikleri de açıklanmaktadır.

Anahtar Kelimeler

Bilgisayarla görü, üretici yöntemler, ayırdedici yöntemler, yapılandırılmış destek vektör makineleri, derin öğrenme, Bayesçi yaklaşımlar (Kalman süzgeci parçacık süzgeci vb.), dolanır matris

Kaynakça

• [1] A.W. M. Smeulders, D. M. Chu, R. Cucchiara, S. Calderara, A. Dehghan, and M. Shah. “Visual Tracking: An Experimental Survey. PAMI, 36(7):1442–1468, 2014.
• [2] Y. Wu, J. Lim, and M.-H. Yang. “Online Object Tracking: A Benchmark. In CVPR, 2013.
• [3] K. Briechle and U. D. Hanebeck, “Template Matching Using Fast Normalized Cross Correlation,” in Proc. SPIE, vol. 4387. 2001, pp. 95–102.
• [4] S. Baker and I. Matthews, “Lucas-Kanade 20 Years on: A Unifying Framework,” IJCV, vol. 56, no. 3, pp. 221–255, 2004.
• [5] H. T. Nguyen and A. W. M. Smeulders, “Fast Occluded Object Tracking By A Robust Appearance Filter,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 26, no. 8, pp. 1099–1104, Aug. 2004.
• [6] A. Adam, E. Rivlin, and I. Shimshoni, “Robust Fragments-Based Tracking Using The Integral Histogram,” in Proc. IEEE CVPR, Washington, DC, USA, 2006.
• [7] D. L. Shaul Oron, Aharon Bar-Hillel, and S. Avidan, “Locally Orderless Tracking,” in Proc. IEEE CVPR, Providence, RI, USA, 2012.
• [8] D. Comaniciu, V. Ramesh, and P. Meer, “Real-time Tracking of Non-rigid Objects Using Mean Shift,” in Proc. IEEE CVPR, Hilton Head Island, SC, USA, 2000. 53_MST
• [9] Maraş, Bahri, Nafiz Arica, and Ayşın Baytan Ertüzün. "Object tracking by combining tracking-by-detection and marginal particle filter." Signal Processing and Communication Application Conference (SIU), 2016 24th. IEEE, 2016.
• [10] D. A. Ross, J. Lim, and R. S. Lin, “Incremental Learning For Robust Visual Tracking,” IJCV, vol. 77, no. 1–3, pp. 125–141, 2008.
• [11] E. Maggio and A. Cavallaro, “Tracking By Sampling Trackers,” in Proc. IEEE ICCV, Barcelona, Spain, 2011, pp. 1195–1202.
• [12] X. Jia, H. Lu, and M.-H. Yang, “Visual Tracking Via Adaptive Structural Local Sparse Appearance Model,” in Proc. IEEE Conf. Comput.Vis. Pattern Recognit., 2012, pp. 1822–1829.
• [13] J. Kwon and F. C. Park, “Visual Tracking Via Geometric Particle Filtering on the Affine Group With Optimal Importance Functions,” in Proc. IEEE CVPR, Miami, FL, USA, 2009. 56_TAG
• [14] J. Kwon and K. M. Lee, “Tracking of a Non-Rigid Object Via Patch-based Dynamic Appearance Modeling and Adaptive Basin Hopping Monte Carlo sampling,” in Proc. IEEE CVPR, Miami, FL, USA, 2009.
• [15] L. Cehovin, M. Kristan, and A. Leonardis, “An Adaptive Coupled-layer Visual Model For Robust Visual Tracking,” in Proc.
• [16] X. Mei and H. Ling, “Robust Visual Tracking Using L1 Minimization,” in Proc. IEEE 12th ICCV, Kyoto, Japan, 2009.
• [17] F. Porikli. “Integral Histogram: A Fast Way To Extract Histograms In Cartesian Spaces.” In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2005.
• [18] Y. Rubner, C. Tomasi, and L. Guibas. “The Earth Mover’s Distance As a Metric For Image Retrieval.” Int. Journal of Computer Vision (IJCV), 40(2):91–121, 2000.
• [19] S. S. Boltz, F. Nielsen, “Earth Mover Distance On Superpixels,” ICIP, 2010.
• [20] M. Isard and A. Blake, “A Mixed-State Condensation Tracker With automatic Model-Switching,” in Proc. 6th ICCV, Bombay, India, 1998.
• [21] Schmidt, M. (2005). “Least Squares Optimization With L1-norm Regularization,” Technical report, CS542B Project Report.
• [22] H. T. Nguyen and A. W. M. Smeulders, “Robust Track Using Foreground-background Texture Discrimination,” IJCV, vol. 68, no. 3, pp. 277–294, 2006.
• [23] B. Babenko, M.-H. Yang, and S. Belongie, “Visual Tracking With Online Multiple Instance Learning,” in Proc. IEEE CVPR, Miami, FL, USA, 2009.
• [24] Z. Kalal, J. Matas, and K. Mikolajczyk, “P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints,” in Proc. IEEE CVPR, San Francisco, CA, USA, 2010.
• [25] J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. “Exploiting The Circulant Structure of Tracking-by-Detection With Kernels,” In ECCV, 2012.
• [26] J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. “Highspeed Tracking With Kernelized Correlation Filters,” PAMI, 2014.
• [27] S. Hare, A. Saffari, and P. H. Torr. “Struck: Structured Output Tracking With Kernels,” in ICCV, 2011.
• [28] S. Hare, S. Golodetz, A. Saffari, V. Vineet, M. M. Cheng, S. L. Hicks, P. H. S. Torr, "Struck: Structured Output Tracking with Kernels", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015.
• [30] J. Zhang, S. Ma, and S. Sclaroff. “MEEM: Robust Tracking Via Multiple Experts Using Entropy Minimization,” in ECCV, 2014.
• [31] K. Simonyan and A. Zisserman,”Very Deep Convolutional Networks For Large-scale Image Recognition,” ICLR, 2015.
• [32] H. Li, Y. Li, and F. Porikli,”Deeptrack: Learning Discriminative Feature Representations By Convolutional Neural Networks For Visual Tracking,” in BMVC, 2014.
• [33] Welling M. “Fisher Linear Discriminant Analysis,” notes for Linear Discriminant Analysis.
• [34] Grabner H., Grabner M., Bischof H. “Proceedings of the British Machine Vision Conference” (BMVC'06), Vol. 1 (2006), pp. 47-56.
• [35] Antoine Bordes, Leon Bottou, Patrick Gallinari, Jason Weston, “Solving Multiclass Support Vector Machines With LaRank,” Proceedings of The 24 th International Conference on Machine Learning, p. 89-96, June 20-24, 2007, Corvalis, Oregon , USA.
• [36] J. C. Platt, “Fast Training of Support Vector Machines Using Sequential Minimal Optimization,” MIT Press, 1999, pp. 185–208.
• [37] Zabih, R., Woodfill, J.,”Non-parametric Local Transforms For Computing Visual Correspondence,” In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 801, Springer, Heidelberg (1994)
• [38] Maji, S., Berg, A.C.,” Max-margin Additive Classifiers For Detection,” In: CVPR (2009)
• [39] D. Ramanan,” Dual Coordinate Solvers For Large-scale Structural SVMs,” in http://arxiv.org/abs/1312.1743, 2014.
• [40] Grandvalet, Y., Bengio, Y.,” Semi-supervised Learning By Entropy Minimization,” in: NIPS (2005)
• [41] Alov300.org, ‘Amsterdam Library of Ordinary Videos for Evaluating Visual Trackers Robustness’. [Online] . Available: /http://www.alov300.org/.
• [42] Cvlab.hanyang.ac.krz, ‘Visual Tracker Benchmark’. [Online].Available:http://cvlab.hanyang.ac.krz/tracker_benchmark/datasets.html
• [43] Ri.cmu.edu, ‘Lucas-Kanade 20 Years On’. [Online]. Available:http://www.ri.cmu.edu/research_project_detail.html?project_id=515&menu_id=261
• [44] Cs.technion.ac.il, ‘Fragtrack-Robust Fragments-based Tracking Using the Integral Histogram’. [Online]. Available:http://www.cs.technion.ac.il/~amita/fragtrack/fragtrack.htm
• [45] Eng.tau.ac.il, ‘Locally Orderless Tracking’. [Online]. Available:http://www.eng.tau.ac.il/~oron/LOT/LOT.html
• [46] Cs.toronto.edu, ‘Incremental Learning for Robust Visual Tracking’. [Online]. Available: http://www.cs.toronto.edu/~dross/ivt
• [47] Cv.snu.ac.kr, ‘Tracking by Sampling Trackers’. [Online]. Available: http://cv.snu.ac.kr/research/~vts/
• [48] Faculty.ucmerced.edu, ‘Visual Tracking via Adaptive Structural Local Sparse Appearance Model’. [Online]. Available:http://faculty.ucmerced.edu/mhyang/project/cvpr12_jia_project.htm
• [49] Cv.snu.ac.kr, ‘Tracking of a Non-Rigid Object via Patch-based Dynamic Appearance Modeling and Adaptive Basin Hopping Monte Carlo Sampling’. [Online].Available:http://cv.snu.ac.kr/research/~bhmctracker/
• [50] Vicos.si, ‘Visual Tracking using Global and Local Visual Information’. [Online]. Available: http://www.vicos.si/Research/LocalGlobalTracking
• [51] Dabi.temple.edu, ‘L1 Tracker’ . [Online]. Available: http://www.dabi.temple.edu/~hbling/code_data. htm#L1_Tracker
• [52] Vision.ucsd.edu, ‘Tracking with Online Multiple Instance Learning’. [Online]. Available: http://vision.ucsd.edu/~bbabenko/project_miltrack.html
• [53] Github.com, ‘Tracking, Learning and Detection’. [Online].Available:https://github.com/mrgloom/openTLD-1/find/master
• [54] Robots.ox.ac.uk, ‘Kernelized Correlation Filters’. [Online].Available:http://www.robots.ox.ac.uk/~joao/circulant/
• [55] Samhare.net, ‘Struck:Structured Output Tracking with Kernels’.[Online].Available:http://www.samhare.net/research/struck
• [56] Comp.polyu.edu.hk, ‘Object Tracking via Dual Linear Structured SVM and Explicit Feature Map’. [Online]. Available:http://www4.comp.polyu.edu.hk/~cslzhang/DLSSVM/DLSSVM.htm
• [57] Cs-people.bu.edu, ‘MEEM: Robust Tracking via Multiple Experts using Entropy Minimization’. [Online].Available:http://cspeople.bu.edu/jmzhang/MEEM/MEEM.html
• [58] Sites.google.com, ‘Hierarchical Convolutional Features for Visual Tracking’. [Online]. Available: https://sites.google.com/site/chaoma99/iccv15-tracking