2D MOT 2015 Results

Click on a measure to sort the table accordingly. See below for a more detailed description.


Showing only entries that use public detections!


Benchmark Statistics

TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
HOHOTRACK
1. using public detections
26.8
±0.0
32.928.6% 16.9% 18,99424,5491,411 (23.5)3,417 (56.9)Public
Anonymous submission
DP_NMS
2. using public detections
14.5
±0.0
19.76.0% 40.8% 13,17134,8144,537 (104.7)3,090 (71.3)Public
H. Pirsiavash, D. Ramanan, C. Fowlkes. Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects. In CVPR, 2011.
LDCT
3. online method using public detections
4.7
±0.0
16.811.4% 32.5% 14,06632,15612,348 (259.1)2,918 (61.2)Public
F. Solera, S. Calderara, R. Cucchiara. Learning to Divide and Conquer for Online Multi-Target Tracking. In ICCV, 2015
INARLA
4.
34.7
±0.0
42.112.5% 30.0% 9,85529,1581,112 (21.2)2,848 (54.2)Public
H. Wu, Y. Hu, K. Wang, H. Li, L. Nie, H. Cheng. Instance-aware representation learning and association for online multi-person tracking. In Pattern Recognition, 2019.
HSJ_Sia
5. online method using public detections
20.9
±0.0
29.24.0% 51.6% 6,45740,4771,695 (49.7)2,734 (80.1)Public
Anonymous submission
STRN
6. online method using public detections
38.1
±0.0
46.611.5% 33.4% 5,45131,5711,033 (21.2)2,665 (54.8)Public
J. Xu, Y. Cao, Z. Zhang, H. Hu. Spatial-Temporal Relation Networks for Multi-Object Tracking. In ICCV, 2019.
KCF_Simple
7. using public detections
18.3
±0.0
25.12.6% 49.8% 8,97639,8051,436 (40.8)2,634 (74.8)Public
Anonymous submission
SNM
8. online method using public detections
31.3
±0.0
38.212.6% 35.4% 8,90332,393926 (19.6)2,382 (50.4)Public
Anonymous submission
MTSTracker
9. online method using public detections
20.6
±0.0
31.99.0% 36.9% 15,16132,2121,387 (29.2)2,357 (49.5)Public
F. Nguyen Thi Lan Anh, F. Bremond. Multi-Object Tracking using Multi-Channel Part Appearance Representation. In International conference on Advanced video and Signal Based Surveillance, 2017.
PHD_GSDL
10. using public detections
30.5
±0.0
38.87.6% 41.2% 6,53435,284879 (20.6)2,208 (51.9)Public
Z. Fu, P. Feng, F. Angelini, J. Chambers, S. Naqvi. Particle PHD Filter based Multiple Human Tracking using Online Group-Structured Dictionary Learning. In IEEE Access, 2018.
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
SMOT
11. online method
18.2
±0.0
0.02.8% 54.8% 8,78040,3101,148 (33.4)2,132 (62.0)Public
C. Dicle, O. Camps, M. Sznaier. The Way They Move: Tracking Targets with Similar Appearance. In ICCV, 2013.
SMOTe
12. online method using public detections
28.0
±0.0
45.415.0% 30.8% 15,88127,372977 (17.6)2,106 (38.0)Public
Anonymous submission
RNN_LSTM
13.
19.0
±0.0
17.15.5% 45.6% 11,57836,7061,490 (37.0)2,081 (51.7)Public
A. Milan, S. Rezatofighi, A. Dick, I. Reid, K. Schindler. Online Multi-Target Tracking using Recurrent Neural Networks. In AAAI, 2017.
BiGRU1
14. using public detections
26.1
±0.0
32.26.5% 48.8% 5,76138,948719 (19.6)2,046 (55.9)Public
Anonymous submission
AMIR15
15. using public detections
37.6
±0.0
46.015.8% 26.8% 7,93329,3971,026 (19.7)2,024 (38.8)Public
A. Sadeghian, A. Alahi, S. Savarese. Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies. In ICCV, 2017.
CppSORT
16. using public detections
21.7
±0.0
26.83.7% 49.1% 8,42238,4541,231 (32.9)2,005 (53.6)Public
S. Murray. Real-Time Multiple Object Tracking - A Study on the Importance of Speed. In arXiv preprint arXiv:1709.03572, 2017.
TBD
17. using public detections
15.9
±0.0
0.06.4% 47.9% 14,94334,7771,939 (44.7)1,963 (45.2)Public
A. Geiger, M. Lauer, C. Wojek, C. Stiller, R. Urtasun. 3D Traffic Scene Understanding from Movable Platforms. In Pattern Analysis and Machine Intelligence (PAMI), 2014.
FP_H
18.
23.4
±0.0
33.73.7% 55.9% 5,78240,719538 (16.0)1,875 (55.6)Public
Anonymous submission
ALExTRAC
19. using public detections
17.0
±0.0
17.33.9% 52.4% 9,23339,9331,859 (53.1)1,872 (53.5)Public
A. Bewley, L. Ott, F. Ramos, B. Upcroft. ALExTRAC: Affinity Learning by Exploring Temporal Reinforcement within Association Chains. In International Conference on Robotics and Automation (ICRA), (to appear) 2016.
EDA_GNN
20. using public detections
21.8
±0.0
27.89.0% 40.2% 11,97034,5871,488 (34.0)1,851 (42.4)Public
Paper ID 2713
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
GMMA_intp
21. online method
27.3
±0.0
36.66.5% 43.1% 7,84835,817987 (23.7)1,848 (44.3)Public
Y. Song, Y. Yoon, K. Yoon, M. Jeon. Online and Real-Time Tracking with the GMPHD Filter using Group Management and Relative Motion Analysis. In Proc. IEEE Int. Workshop Traffic Street Surveill. Safety Secur. (AVSS), 2018.
ELP
22.
25.0
±0.0
26.27.5% 43.8% 7,34537,3441,396 (35.6)1,804 (46.0)Public
N. McLaughlin, J. Martinez Del Rincon, P. Miller. Enhancing Linear Programming with Motion Modeling for Multi-target Tracking. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2015.
DPT
23. using public detections
16.1
±0.0
27.55.0% 50.3% 10,33040,1541,076 (31.1)1,794 (51.8)Public
Tracktor15
24. using public detections
44.1
±0.0
46.718.0% 26.2% 6,47726,5771,318 (23.2)1,790 (31.5)Public
P. Bergmann, T. Meinhardt, L. Leal-Taixé. Tracking without bells and whistles. In ICCV, 2019.
RKCF
25. online method using public detections
16.8
±0.0
29.05.5% 50.1% 10,33639,805980 (27.8)1,750 (49.7)Public
Anonymous submission
PoMOT
26. using public detections
16.7
±0.0
28.85.0% 50.3% 10,18540,025968 (27.8)1,748 (50.2)Public
Anonymous submission
TC_ODAL
27. online method using public detections
15.1
±0.0
0.03.2% 55.8% 12,97038,538637 (17.1)1,716 (46.0)Public
S. Bae, K. Yoon. Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning. In CVPR, 2014.
LP2D
28. online method using public detections
19.8
±0.0
0.06.7% 41.2% 11,58036,0451,649 (39.9)1,712 (41.4)Public
MOT baseline: Linear programming on 2D image coordinates.
CF_MCMC
29. online method using public detections
31.4
±0.0
36.410.3% 40.9% 8,79832,541814 (17.3)1,711 (36.4)Public
Anonymous submission
DCOR
30. online method using public detections
22.4
±0.0
24.73.3% 57.4% 5,60341,410634 (19.4)1,686 (51.7)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
oICF
31.
27.1
±0.0
40.56.4% 48.7% 7,59436,757454 (11.3)1,660 (41.3)Public
H. Kieritz, S. Becker, W. Hübner, M. Arens. Online Multi-Person Tracking using Integral Channel Features. In IEEE Advanced Video and Signal-based Surveillance (AVSS) 2016, 2016.
FFT15
32. using public detections
46.3
±0.0
48.829.1% 23.2% 9,87021,9131,232 (19.1)1,638 (25.5)Public
Anonymous submission
TLO15
33. online method using public detections
40.0
±0.0
44.317.1% 28.8% 9,34926,3281,207 (21.1)1,624 (28.4)Public
Anonymous submission
MMHT15
34. online method using public detections
29.8
±0.0
38.012.1% 38.0% 10,54831,3901,189 (24.3)1,612 (33.0)Public
Anonymous submission
CDA_DDALpb
35. using public detections
32.8
±0.0
38.89.7% 42.2% 4,98335,690614 (14.7)1,583 (37.8)Public
S. Bae and K. Yoon, Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking , In IEEE TPAMI, 2017.
DCCRF
36. online method using public detections
33.6
±0.0
39.110.4% 37.6% 5,91734,002866 (19.4)1,566 (35.1)Public
H. Zhou, W. Ouyang, J. Cheng, X. Wang, H. Li. Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking. In IEEE Transactions on Circuits and Systems for Video Technology, 2018.
TSDA_OAL
37. online method using public detections
18.6
±0.0
36.19.4% 42.3% 16,35032,853806 (17.3)1,544 (33.2)Public
H. Ko. Online multi-person tracking with two-stage data association and online appearance model learning. In IET Computer Vision, 2017.
DEEPDA_MOT
38. using public detections
22.5
±0.0
25.96.4% 62.0% 7,34639,0921,159 (31.9)1,538 (42.3)Public
K. Yoon, D. Kim, Y. Yoon, M. Jeon. Data Association for Multi-Object Tracking via Deep Neural Networks. In Sensors, 2019.
TBX
39. using public detections
27.5
±0.0
33.810.4% 45.8% 7,96835,810759 (18.2)1,528 (36.6)Public
R. Henschel, L. Leal-Taixé, B. Rosenhahn, K. Schindler. Tracking with multi-level features. In arXiv:1607.07304, 2016.
RAR15pub
40. using public detections
35.1
±0.0
45.413.0% 42.3% 6,77132,717381 (8.1)1,523 (32.6)Public
K. Fang, Y. Xiang, X. Li, S. Savarese. Recurrent Autoregressive Networks for Online Multi-Object Tracking. In The IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
CRFTrack_
41. online method
40.0
±0.0
49.623.0% 28.6% 10,29525,917658 (11.4)1,508 (26.1)Public
Anonymous submission
TBSS15
42. using public detections
29.2
±0.0
37.26.8% 43.8% 6,06836,779649 (16.2)1,508 (37.6)Public
X. Zhou, P. Jiang, Z. Wei, H. Dong, F. Wang. Online Multi-Object Tracking with Structural Invariance Constraint. In BMVC, 2018.
TDAM
43. online method using public detections
33.0
±0.0
46.113.3% 39.1% 10,06430,617464 (9.2)1,506 (30.0)Public
M. Yang, Y. Jia. Temporal dynamic appearance modeling for online multi-person tracking. In Computer Vision and Image Understanding, 2016.
MDP
44. using public detections
30.3
±0.0
44.713.0% 38.4% 9,71732,422680 (14.4)1,500 (31.8)Public
Y. Xiang, A. Alahi, S. Savarese. Learning to Track: Online Multi-Object Tracking by Decision Making. In International Conference on Computer Vision (ICCV), 2015.
EAMTTpub
45.
22.3
±0.0
32.85.4% 52.7% 7,92438,982833 (22.8)1,485 (40.6)Public
R. Sanchez-Matilla, F. Poiesi, A. Cavallaro "Multi-target tracking with strong and weak detections" in BMTT ECCVw 2016
AM
46. online method using public detections
34.3
±0.0
48.311.4% 43.4% 5,15434,848348 (8.0)1,463 (33.8)Public
Q. Chu, W. Ouyang, H. Li, X. Wang, B. Liu, N. Yu. Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism. In 2017 IEEE International Conference on Computer Vision (ICCV), 2017.
KCF
47. using public detections
38.9
±0.0
44.516.6% 31.5% 7,32129,501720 (13.9)1,440 (27.7)Public
P. Chu, H. Fan, C. Tan, H. Ling. Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment. In WACV, 2019.
SORT_Y
48. using public detections
45.9
±0.0
47.220.5% 27.0% 6,24725,6691,346 (23.1)1,436 (24.7)Public
Anonymous submission
QuadMOT
49.
33.8
±0.0
40.412.9% 36.9% 7,89832,061703 (14.7)1,430 (29.9)Public
J. Son, M. Baek, M. Cho, B. Han. Multi-Object Tracking with Quadruplet Convolutional Neural Networks. In CVPR, 2017.
TLO
50. online method using public detections
41.3
±0.0
46.115.7% 34.5% 8,00027,210852 (15.3)1,405 (25.2)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
SRPN
51. online method
31.0
±0.0
30.712.6% 41.7% 10,24131,0991,062 (21.5)1,370 (27.7)Public
Anonymous submission
GMPHD_OGM
52.
30.7
±0.0
38.811.5% 38.1% 6,50235,0301,034 (24.1)1,351 (31.4)Public
Y. Song, K. Yoon, Y. Yoon, K. Yow, M. Jeon. Online Multi-Object Tracking with GMPHD Filter and Occlusion Group Management. In IEEE Access, 2019.
SiameseCNN
53. online method
29.0
±0.0
34.38.5% 48.4% 5,16037,798639 (16.6)1,316 (34.2)Public
Laura Leal-Taixé, Cristian Canton-Ferrer, Konrad Schindler. Learning by Tracking: Siamese CNN for Robust Target Association. DeepVision Workshop (CVPR), Las Vegas (Nevada, USA), June 2016.
TENSOR
54. using public detections
24.3
±0.0
24.15.5% 46.6% 6,64438,5821,271 (34.2)1,304 (35.1)Public
X. Shi, H. Ling, Y. Pang, W. Hu, P. Chu, J. Xing. Rank-1 Tensor Approximation for High-Order Association in Multi-target Tracking. In IJCV, 2019.
AdTobKF
55. using public detections
24.8
±0.0
34.54.0% 52.0% 6,20139,321666 (18.5)1,300 (36.1)Public
K. Loumponias, A. Dimou, N. Vretos, P. Daras. Adaptive Tobit Kalman-Based Tracking. In 2018 14th International Conference on Signal-Image Technology \& Internet-Based Systems (SITIS), 2018.
RMOT
56. using public detections
18.6
±0.0
32.65.3% 53.3% 12,47336,835684 (17.1)1,282 (32.0)Public
J. Yoon, H. Yang, J. Lim, K. Yoon. Bayesian Multi-Object Tracking Using Motion Context from Multiple Objects. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2015.
dSRPN15
57. online method
33.3
±0.0
32.79.3% 43.7% 7,82532,211919 (19.3)1,276 (26.8)Public
Anonymous submission
CRF_RNN15
58. using public detections
38.9
±0.0
49.320.9% 29.4% 10,66926,291591 (10.3)1,270 (22.2)Public
Anonymous submission
HybridDAT
59. online method using public detections
35.0
±0.0
47.711.4% 42.2% 8,45531,140358 (7.3)1,267 (25.7)Public
M. Yang, Y. Jia. A Hybrid Data Association Framework for Robust Online Multi-Object Tracking. In IEEE Transactions on Image Processing, 2016.
GMPHD
60. using public detections
18.5
±0.0
28.43.9% 55.3% 7,86441,766459 (14.3)1,266 (39.5)Public
Y. Song, M. Jeon. Online Multiple Object Tracking with the Hierarchically Adopted GM-PHD Filter using Motion and Appearance. In IEEE/IEIE The International Conference on Consumer Electronics (ICCE) Asia, 2016.
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
ISE_MOT15R
61.
46.7
±0.0
51.629.4% 25.7% 11,00320,839878 (13.3)1,265 (19.1)Public
MIFT
AP_HWDPL_p
62. using public detections
38.5
±0.0
47.18.7% 37.4% 4,00533,203586 (12.8)1,263 (27.5)Public
C. Long, A. Haizhou, S. Chong, Z. Zijie, B. Bo. Online Multi-Object Tracking with Convolutional Neural Networks. In 2017 IEEE International Conference on Image Processing (ICIP), 2017.
OMT_DFH
63. using public detections
21.2
±0.0
37.37.1% 46.5% 13,21834,657563 (12.9)1,255 (28.8)Public
J. Ju, D. Kim, B. Ku, D. Han, H. Ko. Online multi-object tracking with efficient track drift and fragmentation handling. In J. Opt. Soc. Am. A, 2017.
SAS_MOT15
64. using public detections
22.2
±0.0
27.23.1% 61.6% 5,59141,531700 (21.6)1,240 (38.3)Public
A. Maksai, P. Fua. Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking. In CVPR, 2019.
Goturn15
65. online method using public detections
23.9
±0.0
22.33.6% 66.4% 7,02138,750965 (26.1)1,237 (33.5)Public
Anonymous submission
SCEA
66.
29.1
±0.0
37.28.9% 47.3% 6,06036,912604 (15.1)1,182 (29.6)Public
J. Yoon, C. Lee, M. Yang, K. Yoon. Online Multi-object Tracking via Structural Constraint Event Aggregation. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
RSCNN
67. online method using public detections
29.5
±0.0
37.012.9% 36.3% 11,86630,474976 (19.4)1,176 (23.3)Public
Heba Mahgoub, Khaled Mostafa, Khaled T. Wassif and Ibrahim Farag, “Multi-Target Tracking Using Hierarchical Convolutional Features and Motion Cues” International Journal of Advanced Computer Science and Applications(IJACSA), 8(11), 2017.
mLK
68. online method
35.1
±0.0
47.512.3% 38.3% 5,67833,815383 (8.5)1,175 (26.1)Public
Yuan Zhang, Di Xie and Shiliang Pu (Hikvision Research Institute)
DAC_min
69. online method using public detections
28.3
±0.0
38.39.8% 45.5% 8,39635,122543 (12.7)1,162 (27.1)Public
MR
70. using public detections
36.6
±0.0
47.233.1% 21.5% 16,69621,428850 (13.1)1,156 (17.8)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
MHTREID15
71. online method using public detections
40.0
±0.0
49.429.7% 24.4% 12,78023,378684 (11.0)1,112 (17.9)Public
Anonymous submission
LFNF
72. online method
31.6
±0.0
33.19.6% 41.7% 5,94335,095961 (22.4)1,106 (25.8)Public
Sheng H, Hao L, Chen J, et al. Robust Local Effective Matching Model for Multi-Target Tracking. In PCM, 2017
siam
73. online method using public detections
33.0
±0.0
36.28.9% 43.3% 5,10135,190853 (20.0)1,078 (25.2)Public
Anonymous submission
MPNTrack15
74.
48.3
±0.0
56.532.2% 24.3% 9,64021,629504 (7.8)1,074 (16.6)Public
Anonymous submission
MotiCon
75.
23.1
±0.0
29.44.7% 52.0% 10,40435,8441,018 (24.4)1,061 (25.5)Public
L. Leal-Taixé, M. Fenzi, A. Kuznetsova, B. Rosenhahn, S. Savarese. Learning an image-based motion context for multiple people tracking. In CVPR, 2014.
Lif_T
76. online method using public detections
52.5
±0.0
60.033.8% 25.8% 6,83721,610730 (11.3)1,047 (16.2)Public
Anonymous submission
HAM_INTP15
77. online method
28.6
±0.0
41.410.0% 44.0% 7,48535,910460 (11.1)1,038 (25.0)Public
Y. Yoon, A. Boragule, Y. Song, K. Yoon, M. Jeon. Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering. In IEEE AVSS, 2018.
DeepMP
78. online method
40.5
±0.0
28.816.8% 35.2% 6,27929,654599 (11.6)1,034 (20.0)Public
Anonymous submission
CEM
79. online method
19.3
±0.0
0.08.5% 46.5% 14,18034,591813 (18.6)1,023 (23.4)Public
A. Milan, S. Roth, K. Schindler. Continuous Energy Minimization for Multitarget Tracking. In IEEE TPAMI, 2014.
GSCR
80. online method
15.8
±0.0
27.91.8% 61.0% 7,59743,633514 (17.7)1,010 (34.8)Public
L. Fagot-Bouquet, R. Audigier, Y. Dhome, F. Lerasle. Online multi-person tracking based on global sparse collaborative representations. In ICIP, 2015.
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
MCF_PHD
81. using public detections
29.9
±0.0
38.211.9% 44.0% 8,89233,529656 (14.4)989 (21.8)Public
N. Wojke, D. Paulus. Global data association for the Probability Hypothesis Density filter using network flows. In 2016 IEEE International Conference on Robotics and Automation, ICRA, 2016.
JointMC
82. using public detections
35.6
±0.0
45.123.2% 39.3% 10,58028,508457 (8.5)969 (18.1)Public
M. Keuper, S. Tang, B. Andres, T. Brox, B. Schiele. Motion Segmentation amp; Multiple Object Tracking by Correlation Co-Clustering. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018.
TSMLCDEnew
83. using public detections
34.3
±0.0
44.114.0% 39.4% 7,86931,908618 (12.9)959 (20.0)Public
B. Wang, G. Wang, K. L. Chan, L. Wang. Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation. In arXiv:1511.06654, 2015.
CNNTCM
84.
29.6
±0.0
36.811.2% 44.0% 7,78634,733712 (16.4)943 (21.7)Public
B. Wang, K. L. Chan, L. Wang, B. Shuai, Z. Zuo, T. Liu, G. Wang. Joint Learning of Convolutional Neural Networks and Temporally Constrained Metrics for Tracklet Association. In DeepVision Workshop (CVPR), 2016.
SLTV15
85. using public detections
27.6
±0.0
40.37.2% 51.9% 6,58137,566358 (9.2)884 (22.7)Public
Gwangju Institute of Science and Technology(GIST), Machine Learning and Vision Laboratory
JPDA_m
86. online method using public detections
23.8
±0.0
33.85.0% 58.1% 6,37340,084365 (10.5)869 (25.0)Public
H. Rezatofighi, A. Milan, Z. Zhang, Q. Shi, A. Dick, I. Reid. Joint Probabilistic Data Association Revisited. In ICCV, 2015.
MHT__ReID
87. online method using public detections
33.0
±0.0
46.417.6% 42.6% 8,72532,046421 (8.8)851 (17.8)Public
Anonymous submission
LP_SSVM
88. online method
25.2
±0.0
34.05.8% 53.0% 8,36936,932646 (16.2)849 (21.3)Public
S. Wang, C. Fowlkes. Learning Optimal Parameters for Multi-target Tracking with Contextual Interactions. In International Journal of Computer Vision, 2016.
MHT_DAM
89. online method using public detections
32.4
±0.0
45.316.0% 43.8% 9,06432,060435 (9.1)826 (17.3)Public
C. Kim, F. Li, A. Ciptadi, J. Rehg. Multiple Hypothesis Tracking Revisited. In ICCV, 2015.
TC_SIAMESE
90. using public detections
20.2
±0.0
32.62.6% 67.5% 6,12742,596294 (9.6)825 (26.9)Public
Y. Yoon, Y. Song, K. Yoon, M. Jeon. Online Multiple-Object Tracking using Selective Deep Appearance Matching. In IEEE/IEIE The International Conference on Consumer Electronics (ICCE) Asia, 2018.
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
NOMT
91.
33.7
±0.0
44.612.2% 44.0% 7,76232,547442 (9.4)823 (17.5)Public
W. Choi. Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor. In ICCV, 2015.
DCO_X
92. using public detections
19.6
±0.0
31.55.1% 54.9% 10,65238,232521 (13.8)819 (21.7)Public
A. Milan, K. Schindler, S. Roth. Multi-Target Tracking by Discrete-Continuous Energy Minimization. In IEEE PAMI, 2016.
TFMOT
93. online method using public detections
23.8
±0.0
32.34.9% 62.0% 4,53341,873404 (12.7)792 (24.9)Public
M. Abhijeet Boragule. Joint Cost Minimization for Multi-Object Tracking. In 2017 IEEE International Conference on Advanced Vide and Signale Based Surveillance, 2017.
DSA_MOT
94.
29.4
±0.0
41.29.2% 50.2% 7,70535,364329 (7.8)789 (18.6)Public
Anonymous submission
HAM_SADF
95. using public detections
25.2
±0.0
37.85.7% 58.3% 7,33038,275357 (9.5)745 (19.8)Public
Y. Yoon, A. Boragule, Y. Song, K. Yoon, M. Jeon. Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering. In IEEE AVSS, 2018.
LINF1
96. online method using public detections
24.5
±0.0
34.85.5% 64.6% 5,86440,207298 (8.6)744 (21.5)Public
L. Fagot-Bouquet, R. Audigier, Y. Dhome, F. Lerasle. Improving Multi-Frame Data Association with Sparse Representations for Robust Near-Online Multi-Object Tracking. In ECCV, 2016.
SegTrack
97. online method using public detections
22.5
±0.0
31.55.8% 63.9% 7,89039,020697 (19.1)737 (20.2)Public
A. Milan, L. Leal-Taixé, K. Schindler, I. Reid. Joint Tracking and Segmentation of Multiple Targets. In CVPR, 2015.
UN_DAM
98. online method using public detections
29.7
±0.0
41.49.2% 49.9% 7,61035,269318 (7.5)674 (15.8)Public
Multi Object Tracking using Deep Structural Cost Minimization in Data Association
TO
99. online method using public detections
25.7
±0.0
32.74.3% 57.4% 4,77940,511383 (11.2)600 (17.6)Public
S. Manen, R. Timofte, D. Dai, L. Gool. Leveraging single for multi-target tracking using a novel trajectory overlap affinity measure. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), 2016.
JPDA_OP
100. online method
3.6
±0.0
7.50.4% 96.1% 1,02458,18929 (5.5)119 (22.5)Public
Anonymous submission
SequencesFramesTrajectoriesBoxes
11578372161440

Difficulty Analysis

Sequence difficulty (from easiest to hardest, measured by average MOTA)

TUD-Crossing

TUD-Crossing

(0.0% MOTA)

PETS09-S2L2

PETS09-S2L2

(0.0% MOTA)

ETH-Jelmoli

ETH-Jelmoli

(0.0% MOTA)

...

...

KITTI-19

KITTI-19

(0.0% MOTA)

Venice-1

Venice-1

(0.0% MOTA)


Evaluation Measures

Lower is better. Higher is better.
Measure Better Perfect Description
Avg Rank lower 1 This is the rank of each tracker averaged over all present evaluation measures.
MOTA higher 100 % Multiple Object Tracking Accuracy [1]. This measure combines three error sources: false positives, missed targets and identity switches.
MOTP higher 100 % Multiple Object Tracking Precision [1]. The misalignment between the annotated and the predicted bounding boxes.
IDF1 higher 100 % ID F1 Score [2]. The ratio of correctly identified detections over the average number of ground-truth and computed detections.
FAF lower 0 The average number of false alarms per frame.
MT higher 100 % Mostly tracked targets. The ratio of ground-truth trajectories that are covered by a track hypothesis for at least 80% of their respective life span.
ML lower 0 % Mostly lost targets. The ratio of ground-truth trajectories that are covered by a track hypothesis for at most 20% of their respective life span.
FP lower 0 The total number of false positives.
FN lower 0 The total number of false negatives (missed targets).
ID Sw. lower 0 The total number of identity switches. Please note that we follow the stricter definition of identity switches as described in [3].
Frag lower 0 The total number of times a trajectory is fragmented (i.e. interrupted during tracking).
Hz higher Inf. Processing speed (in frames per second excluding the detector) on the benchmark.

Legend

Symbol Description
online method This is an online (causal) method, i.e. the solution is immediately available with each incoming frame and cannot be changed at any later time.
using public detections This method used the provided detection set as input.
new This entry has been submitted or updated less than a week ago.

References:


[1] Bernardin, K. & Stiefelhagen, R. Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics. Image and Video Processing, 2008(1):1-10, 2008.
[2] Ristani, E., Solera, F., Zou, R., Cucchiara, R. & Tomasi, C. Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. In ECCV workshop on Benchmarking Multi-Target Tracking, 2016.
[3] Li, Y., Huang, C. & Nevatia, R. Learning to associate: HybridBoosted multi-target tracker for crowded scene. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009.