Visual Tracker Benchmark---by香蕉麦乐迪

Visual Tracker Benchmark

Y. Wu, J. Lim, and M. Yang测试了29个公开的visual tracker，按年代顺序排列如下：

感谢各位作者都提供了各种方法的源代码：点击下面的www

感谢梳理的作者：Y. Wu, J. Lim, and M. Yang. Object tracking benchmark.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9):1834–1848, Sept 2015.2,5,6

NAME	CODE	REFERENCE
CPF	CPF	P. Pe ́rez, C. Hue, J. Vermaak, and M. Gangnet. Color-Based Probabilistic Tracking. In ECCV, 2002.（基于颜色概率）
KMS	KMS	D. Comaniciu, V. Ramesh, and P. Meer. Kernel-Based Object Tracking. PAMI, 25(5):564–577, 2003.（基于核）
SMS	SMS	R. Collins. Mean-shift Blob Tracking through Scale Space. In CVPR, 2003.（均值漂移）
VR-V	VIVID/VR	R. T. Collins, Y. Liu, and M. Leordeanu. Online Selection of Discriminative Tracking Features. PAMI, 27(10):1631–1643, 2005. [www]  * We also evaluated four other trackers included in the VIVID tracker suite. (PD-V, RS-V, MS-V, and TM-V).（在线选择有判别力的跟踪特征）
Frag	Frag	A. Adam, E. Rivlin, and I. Shimshoni. Robust Fragments-based Tracking using the Integral Histogram. In CVPR, 2006. [www]（基于积分直方图的鲁棒性碎片跟踪）
OAB	OAB	H. Grabner, M. Grabner, and H. Bischof. Real-Time Tracking via On-line Boosting. In BMVC, 2006. [www]（基于在线boosting的实时跟踪）
IVT	IVT	D. Ross, J. Lim, R.-S. Lin, and M.-H. Yang. Incremental Learning for Robust Visual Tracking. IJCV, 77(1):125–141, 2008. [www]（具有鲁棒性的增量学习视觉跟踪）
SemiT	SBT	H. Grabner, C. Leistner, and H. Bischof. Semi-supervised On-Line Boosting for Robust Tracking. In ECCV, 2008. [www]（半监督的在线boosting鲁棒跟踪）
MIL	MIL	B. Babenko, M.-H. Yang, and S. Belongie. Visual Tracking with Online Multiple Instance Learning. In CVPR, 2009. [www]（基于多实例学习的视觉跟踪）
BSBT	BSBT	S. Stalder, H. Grabner, and L. van Gool. Beyond Semi-Supervised Tracking: Tracking Should Be as Simple as Detection, but not Simpler than Recognition. In ICCV Workshop, 2009. [www]（超越半监督跟踪：跟踪应该跟检测一样简单，但比识别麻烦）
TLD	TLD	Z. Kalal, J. Matas, and K. Mikolajczyk. P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints. In CVPR, 2010. [www]（基于结构约束的二分类）
VTD	–	J. Kwon and K. M. Lee. Visual Tracking Decomposition. In CVPR, 2010. [www]（视觉跟踪分解）
CXT	CXT	T. B. Dinh, N. Vo, and G. Medioni. Context Tracker: Exploring supporters and distracters in unconstrained environments. In CVPR, 2011. [www]（无约束环境中探索 supporters and distracters）
LSK	LSK	B. Liu, J. Huang, L. Yang, and C. Kulikowsk. Robust Tracking using Local Sparse Appearance Model and K-Selection. In CVPR, 2011. [www]（基于局域稀疏外观模型和k选择的鲁棒性跟踪）
Struck	Struck	S. Hare, A. Saffari, and P. H. S. Torr. Struck: Structured Output Tracking with Kernels. In ICCV, 2011. [www]（基于核的结构输出跟踪）
VTS	–	J. Kwon and K. M. Lee. Tracking by Sampling Trackers. In ICCV, 2011. [www]（通过采样跟踪器跟踪）
ASLA	ASLA	X. Jia, H. Lu, and M.-H. Yang. Visual Tracking via Adaptive Structural Local Sparse Appearance Model. In CVPR, 2012. [www]（基于自适应的结构化局部稀疏外观模型的视觉跟踪）
DFT	DFT	L. Sevilla-Lara and E. Learned-Miller. Distribution Fields for Tracking. In CVPR, 2012.[www]（跟踪分布）
L1APG	L1APG	C. Bao, Y. Wu, H. Ling, and H. Ji. Real Time Robust L1 Tracker Using Accelerated Proximal Gradient Approach. In CVPR, 2012. [www]（基于加速概率梯度方法的实时鲁棒性L1跟踪方法）
LOT	LOT	S. Oron, A. Bar-Hillel, D. Levi, and S. Avidan. Locally Orderless Tracking. In CVPR, 2012. [www]（局域无序跟踪）
MTT	MTT	T.Zhang, B. Ghanem,S. Liu,and N. Ahuja. Robust Visual Tracking via Multi-task Sparse Learning. In CVPR, 2012. [www]（基于多任务稀疏学习的鲁棒性视觉跟踪）
ORIA	ORIA	Y. Wu, B. Shen, and H. Ling. Online Robust Image Alignment via Iterative Convex Optimization. In CVPR, 2012. [www]（基于迭代凸优化的在线鲁棒图像匹配）
SCM	SCM	W. Zhong, H. Lu, and M.-H. Yang. Robust Object Tracking via Sparsity-based Collaborative Model. In CVPR, 2012. [www]（基于稀疏协同模型的鲁棒性目标跟踪）
CSK	CSK	F. Henriques, R. Caseiro, P. Martins, and J. Batista. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. In ECCV, 2012. [www]（在基于检测的跟踪中，使用核探索循环结构）
CT	CT	K. Zhang, L. Zhang, and M.-H. Yang. Real-time Compressive Tracking. In ECCV, 2012.[www]（实时压缩跟踪）
LSHT	LSHT	S. He, Q. Yang, R. W. H. Lau, J. Wang, and M.-H. Yang. [www]
LSS	LSS	D. Wang, H. Lu, and M.-H. Yang. Least Soft-thresold Squares Tracking. In CVPR, 2013.（最小软阈值平方跟踪）

测试得到的结果，这里我只给出前7：

Benchmark Results

SRER evaluation results on the TB-50 dataset. Each entry contains the average overlap in percent and the average number of failures in 1000 frames at the overlap threshold 0.5. The trackers are ordered by the average overlap scores, and the top 5 methods in each attribute are denoted by different colors: red, green, blue, cyan, and magenta.

All

BC

DEF

FM

IPR

IV

LR

MB

OCC

OPR

OV

SV

STRUCK

57.5 / 3.6

59.3 / 3.3

52.4 / 4.6

55.6 / 3.8

57.0 / 3.4

59.0 / 3.3

59.1 / 3.9

59.9 / 2.8

55.9 / 4.1

57.3 / 3.7

58.9 / 3.4

57.8 / 3.6

SCM

54.4 / 4.1

61.3 / 2.9

51.5 / 4.8

42.8 / 6.5

51.8 / 4.3

61.1 / 3.1

61.7 / 2.5

45.2 / 5.9

56.8 / 3.8

57.0 / 3.8

56.4 / 4.5

55.8 / 3.9

ASLA

53.2 / 4.1

59.2 / 3.0

50.5 / 4.5

42.0 / 6.5

52.1 / 4.1

59.6 / 3.0

59.3 / 2.3

44.6 / 5.9

56.0 / 3.8

56.3 / 3.7

55.3 / 4.3

54.0 / 3.9

CSK

52.4 / 4.9

55.9 / 4.2

48.1 / 5.7

45.8 / 5.8

52.4 / 4.7

56.2 / 4.3

55.0 / 4.8

50.6 / 5.1

52.7 / 5.1

53.3 / 4.9

53.2 / 4.9

52.0 / 5.0

L1APG

50.8 / 4.8

54.8 / 4.2

44.6 / 5.8

44.6 / 6.0

52.0 / 4.5

52.9 / 4.7

59.5 / 3.2

49.2 / 5.2

50.9 / 4.8

50.9 / 5.0

55.5 / 4.4

51.0 / 4.7

OAB

50.3 / 5.3

50.1 / 5.1

46.0 / 6.0

47.4 / 5.7

51.0 / 4.9

48.3 / 5.8

56.2 / 4.5

49.9 / 5.1

49.2 / 5.6

49.2 / 5.6

50.0 / 5.6

50.8 / 5.1

VTD

49.3 / 5.2

55.1 / 4.2

46.2 / 5.5

41.7 / 6.8

50.2 / 4.6

53.7 / 4.6

47.1 / 5.6

43.5 / 6.3

52.3 / 4.9

53.7 / 4.6

51.5 / 5.4

48.9 / 5.4