视频跟踪算法研究综述

摘要/Abstract

摘要： 在许多计算机视觉应用领域中,视频跟踪是最基本的任务。尽管有了大量的跟踪算法,但是跟踪算法的鲁棒性仍是具有挑战性的问题。物体的突然运动、目标或者背景外观的改变、目标与目标以及目标与背景的遮挡、非刚性物体的结构、摄像机抖动等问题都是视频跟踪算法设计过程中需要考虑的因素。介绍了视频跟踪算法及其研究进展,综述了现有基本的目标跟踪算法分类,详细描述了每种表示方法,并指出其优缺点。进一步讨论了跟踪的重要性问题,包括目标检测、特征选择、贝叶斯跟踪、在线学习跟踪等。

关键词: 视频跟踪,特征选择,贝叶斯跟踪,在线学习

Abstract: Visual tracking is a fundamental task in many computer vision applications,and the robustness problem is still a challenge in spite of the numerous existing visual tracking algorithms．Besides,several circumstance,as the abrupt object motion,the variation of the target or the background,the object-to-object and object-to-scene occlusions,the non-rigid object structures and camera jiggle,can reduce the effectiveness of the designed visual tracking algorithm．This survey described the visual tracking algorithm and its research advance．The existing target tracking algorithms were overviewed,and described each of these algorithms in detail,then,the advantage and disadvantage of each algorithm were analyzed respectively．Furthermore,the important issues related to tracking were discussed,including detection of objects,feature selection,Bayesian tracking,and online learning tracking.

Key words: Visual tracking,Feature selection,Bayesian tracking,Online learning

闫庆森,李临生,徐晓峰,王灿. 视频跟踪算法研究综述[J]. 计算机科学, 2013, 40(Z6): 204-209. https://doi.org/

YAN Qing-sen,LI Lin-sheng,XU Xiao-feng and WANG Can. Survey of Visual Tracking Algorithm[J]. Computer Science, 2013, 40(Z6): 204-209. https://doi.org/

参考文献

[1] Yilmaz A,Javed O,Shah M．Object Tracking:A Survey[J]．ACM Journal of Computing Surveys,2006,38(4):1-45
[2] Cannons K．A Review of Visual Tracking[R]．Canada:Department of Computer Science and Engineering and the Centre for Vision Research,2008
[3] Yang Han-xuan,Shao Ling,Zheng Feng,et al．Recent advance s and trends in visual tracking:A review[J]．Neurocomputing,2011,4(6):3823-3831
[4] 蔡荣太,吴元昊,王明佳,等．视频目标跟踪算法综述[J]．视频技术应用与工程,2010,4(12):135-142
[5] Collins R,et al．A system for video surveillance and monitoring:VSAM final report[R]．Technical Report CMU-RI-TR-00-12．Carnegie Mellon University,2000
[6] Haritaoglu I,Harwood D,Davis L．W4:real-time surveillance of people and their activities[J]．IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8):809-830
[7] Remaining P I,Tan T’Baker K．Mufti—agent visual surveillance of dynamic scenes[J]．Image and Vision Computing,1998,16(8):529-532
[8] Cannons K,Wildes R．Spatiotemporal oriented energy features for visual tracking[C]∥Asian Conference on Computer Vision,2007．Tokyo,Japan:ACCV,2007:532-543
[9] Fieguth P,Terzopoulos D．Color-based tracking of heads andother mobile objects at video frame rates[C]∥Conference on Computer Vision and Pattern Recognition,1997．San Juan,Puerto Rico:CVPR,1997:21-27
[10] Wren C,Zarbayejani A A,Pentland A．Pfinder:Real-time tracking of the human body[J].IEEE Trans．Patt.Analy.Mach.Intell.,1997,9(7):780-785
[11] Stauffer C,Grimson W．Learning patterns of activity using real-time tracking[J]．PAMI,2000,2(8):747-757
[12] Elgammal A,Harwood D,Davis L.Non-parametric model forbackground subtraction[C]∥European Conference on Compu-ter Vision,2000.Dublin,Ireland:ECCV,2000:751-767
[13] Liyuan L,Andmaylor L．Integrating intensity and texture diff-erences for robust change detection[J]．IEEE Trans．Image Process．,2002,1(2):105-112
[14] Shen Y,Hu W,Liu J,et al．Efficient background subtraction for real-time tracking in embedded camera networks[C]∥Procee-dings of the 10th ACM Conference on Embedded Network Sensor Systems．ACM,2012:295-308
[15] Deriche R,Faugeras O．Tracking line segments[J].IVC,1991,8(4):261-270
[16] Koller D,Daniilidis K,Nagel H.Model-based object tracking in monocular image sequences of road trcaing scenes[J]．IJCV,1993,0(3):257-281
[17] Huttenlocher D,Noh J,Rucklidge W.Tracking non-rigid objects in complex scenes[C]∥International Conference on Computer Vision,1993．Berlin,Germany:ICCV,1993:93-101
[18] Canny J．A computational approach to edge detection[J]．PAMI,1986,8(6):679-698
[19] Nalwa V S,Binford T O．On detecting edges[J]．PAMI,1986,8(6):699-714
[20] Iverson L A,Zucker S W．Logical/Linear operators for image curves[J]．PAMI,1995,7(10):982-996
[21] Harris C,Stephens M.Combined corner and edge detector[C]∥The Fourth Alvey Vision Conference,1988．Berlin,Germany:Springer,1988:147-152
[22] Lowe D G．Object recognition from local scale-invariant features[C]∥International Conference on Computer Vision,1999.Kerkyra,Corfu,Greece:ICCV,1999:24-27
[23] Bay H,Tuytelaars T,Van Gool L．SURF:Speeded up robust features[C]∥European Conference on Computer Vision,2006.Graz,Austria:ECCV,2006:118-127
[24] Comaniciu D,Amesh R,Meer V P.Kernel-based object tracking[J].IEEE Trans．Patt．Analy．Mach．Intell．,2003,5(5):564-575
[25] Manjunath B,Ma W．Texture features for browsing and retrie-val of image data[J]．IEEE Trans．Pattern Anal．Mach．Intell．,1996,8(8):837-842
[26] Ojala T,Pietikainen M,Maenpaa T．Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]．IEEE Trans．Pattern Anal．Mach．Intell．,2002,4(7):972-987
[27] Dalal N,Trigges B．Histograms of oriented gradients for human detection[C]∥Conference on Computer Vision and Pattern Re-cognition,2005．San Diego,CA,USA:CVPR,2005
[28] Black M J,Jepson A D．Eigen Tracking:robust matching and tracking of articulated objects using a view-based representation[J]．IJCV,1998,6(1):63-84
[29] Hager G D,Belhumeur P N．Efficient region tracking with parametric models of geometry and illumination[J]．PAMI,1998,0(10):1025-1039
[30] Ross D A,Lim J,Lin R S,et al．Incremental learning for robust visual tracking[J]．International Journal of Computer Vision,2008,7(1):125-141
[31] Moreno-Noguer F,Sanfeliu A,Samaras D．Dependent multiple cue integration for robust tracking[J]．Pattern Analysis and Machine Intelligence,IEEE Transactions on,2008,30(4):670-685
[32] Eshel R,Moses Y．Tracking in a dense crowd using multiplecameras[J]．International journal of computer vision,2010,88(1):129-143
[33] Glocker B,Heibel T H,Navab N．TriangleFlow:Optical Flow with Triangulation-Based Higher-Order Likelihoods[C]∥European Conference on Computer Vision,2010．Crete,Greece:ECCV,2010:272-285
[34] Bar-Shalom Y,Fortmann T E,Cable P G．Tracking and data association[J]．The Journal of the Acoustical Society of America,1990,87:9-18
[35] Maskell S,Gordon N．A tutorial on particle filters for on-line nonlinear non-Gaussian Bayesian tracking[C]∥Target Trac-king:Algorithms and Applications．2001:1-15
[36] Broida T,Chellappa R．Estimation of object motion parameters from noisy images[J]．IEEE Trans.Patt．Analy．Mach．Intell．,1986,8(1):90-99
[37] Beymer D,Konolige K．Real-time tracking of multiple people using continuous detection[C]∥IEEE Frame Rate Workshop．1999
[38] Lao Y,Zhu J,Zheng Y．Sequential particle generation for visual tracking[J]．IEEE Transactions on Circuits and Systems for Video Technology,2009,19(9):1365-1378
[39] Isard M,Blake A．Contour tracking by stochastic propagation of conditional density[C]∥Computer Vision-ECCV’96．1996:343-356
[40] Nummiaro K,Koller-Meier E,Van Gool L．An adaptive color-based particle filter[J]．Image and Vision Computing,2003,21(1):99-110
[41] Wang E,Silva J,Carin L．Compressive particle filtering for target tracking[C]∥Statistical Signal Processing,SSP’09．IEEE/SP 15th Workshop on．IEEE,2009:233-236
[42] Comaniciu D,Ramesh V,Meer P．Real-time tracking of non-rigid objects using mean shift:Computer Vision and Pattern Recognition,2000[C]∥Proceedings．IEEE Conference on．IEEE,2000,2:142-149
[43] Leung A P,Gong S．Mean shift tracking with random sampling:Proc[C]∥BMVC．2005:729-738
[44] Hager G D,Dewan M,Stewart C V．Multiple kernel trackingwith SSD:Computer Vision and Pattern Recognition,2004[C]∥Proceedings of the 2004IEEE Computer Society Conference on．IEEE,2004,1:I-790-I-797
[45] Collins R T．Mean-shift blob tracking through scale space:Computer Vision and Pattern Recognition,2003[C]∥Proceedings．2003IEEE Computer Society Conference on．IEEE,2003,2:II-234-240
[46] 匡金骏,柴毅,熊庆宇．结合标准对冲与核函数稀疏分类的目标跟踪[J].光学精密工程,2012,0(11):2540-2547
[47] Matthews L,Ishikawa T,Baker S．The template update problem[J]．PAMI,2004,6(6):810-815
[48] Porikli F,Tuzel O,Meer P．Covariance tracking using model update based on lie algebra:Computer Vision and Pattern Recognition,2006[C]∥IEEE Computer Society Conference on．IEEE,2006,1:728-735
[49] Adam A,Rivlin E,Shimshoni I．Robust fragments-based tr-acking using the integral histogram:Computer Vision and Pattern Recognition,2006[C]∥IEEE Computer Society Conference on．IEEE,2006,1:798-805
[50] Kwon J,Lee K M．Visual tracking decomposition:Computer Vision and Pattern Recognition(CVPR),2010[C]∥IEEE Conference on．IEEE,2010:1269-1276
[51] Avidan S．Ensemble tracking[J].PAMI,2007,29(2):261-271
[52] Babenko B,Yang M H,Belongie S．Robust object tracking with online multiple instance learning[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1619-1632
[53] Breitenstein M D,Reichlin F,Leibe B,et al．Robust tracking-by-detection using a detector confidence particle filter:Computer Vision,2009[C]∥IEEE 12th International Conference on．IEEE,2009:1515-1522
[54] Collins R T,Liu Yan-xi,Leordeanu M．Online selection of discriminative tracking features[J]．IEEE Trans．Pattern Anal．Mach．Intell.,2004,27(10):1631-1643
[55] Grabner H,Bischof H．On-line boosting and vision:Computer Vision and Pattern Recognition,2006[C]∥IEEE Computer Society Conference on．IEEE,2006,1:260-267
[56] Grabner H,Grabner M,Bischof H．Real-time tracking via on-line boosting[C]∥Proc．BMVC．2006,1:47-56
[57] Grabner H,Leistner C,Bischof H．Semi-supervised on-line boosting for robust tracking[C]∥Computer Vision-ECCV 2008．2008:234-247
[58] Kalal Z,Matas J,Mikolajczyk K．Pn learning:Bootstrapping binary classifiers by structural constraints[C]∥Computer Vision and Pattern Recognition(CVPR),2010．IEEE Conference on．IEEE,2010:49-56
[59] Donoho D．Compressed sensing[J]．IEEE Trans．Inform．Theory,2006,2:1289-1306
[60] Candès E．Compressive Sampling[J]．Int．Congress of Mathe-matics,2006,3(4):1433-1452
[61] Candès E,Wakin M．An introduction to compressive sampling[J]．IEEE Signal Processing Magazine,2008,25(2):21-30
[62] Liu B,Yang L,Huang J,et al．Robust and fast collaborative tracking with two stage sparse optimization[C]∥Computer Vision-ECCV 2010．2010:624-637
[63] Mei X,Ling H．Robust visual tracking using L1minimization:Computer Vision[C]∥IEEE 12th International Conference on,2009．IEEE,2009:1436-1443
[64] Mei X,Ling H,Wu Y,et al．Minimum error bounded efficient L1tracker with occlusion detection[C]∥Computer Vision and Pattern Recognition(CVPR),2011．IEEE Conference on．IEEE,2011:1257-1264
[65] Liu B,Huang J,Yang L,et al．Robust tracking using local sparse appearance model and k-selection[C]∥Computer Vision and Pattern Recognition(CVPR),2011．IEEE Conference on．IEEE,2011:1313-1320
[66] Wang Q,Chen F,Xu W,et al．Online discriminative objecttracking with local sparse representation[C]∥Applications of Computer Vision(WACV),2012．IEEE Workshop on．IEEE,2012:425-432
[67] Zhang K,Zhang L,Yang M H．Real-time Compressive Tracking[C]∥ECCV．2012
[68] Zhong W,Lu H,Yang M H．Robust object tracking via sparsity-based collaborative model[C]∥Computer Vision and Pattern Recognition(CVPR),2012．IEEE Conference on．IEEE,2012:1838-1845
[69] Chen Feng,Wang Qing,Wang Song,et al．Object tracking via appearance modeling and sparse representation[J]．Image and Vision Computing,2011(29):787-796
[70] Pan S J,Yang Q．A survey on transfer learning[J]．IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359
[71] Koller D,Friedman N．Probabilistic graphical models:principles and techniques[M]．Boston:MIT press,2009:2-10

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed