MOT17 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

TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
DS_TW_F
1. online method using public detections
45.7
±27.0
50.910.8% 75.4% 6,528298,3681,329 (28.2)3,180 (67.5)66.9Public
Anonymous submission
OLGT_new
2. online method using public detections
45.7
±22.8
49.410.8% 75.5% 6,915298,2881,418 (30.1)3,641 (77.2)6.1Public
Anonymous submission
DS_MOT
3. online method using public detections
56.1
±15.8
52.721.1% 35.4% 8,866235,4493,609 (61.9)3,777 (64.8)10.0Public
Anonymous submission
Tracktor++v2
4. online method using public detections
56.3
±13.3
55.121.1% 35.3% 8,866235,4491,987 (34.1)3,763 (64.6)1.5Public
P. Bergmann, T. Meinhardt, L. Leal-Taixé. Tracking without bells and whistles. In ICCV, 2019.
track_bnw
5. online method using public detections
56.7
±13.4
52.123.1% 34.5% 8,895233,2062,351 (40.1)3,155 (53.8)0.7Public
Anonymous submission
SRPN17
6. online method using public detections
40.8
±15.2
40.512.0% 48.0% 9,293321,8112,801 (65.2)7,120 (165.7)4.1Public
Anonymous submission
track_bin
7. online method using public detections
57.2
±13.3
54.822.6% 34.9% 9,462229,7922,353 (39.7)3,122 (52.7)0.7Public
Anonymous submission
DGCT
8. using public detections
54.5
±13.1
51.321.0% 35.4% 10,471243,1432,865 (50.3)4,889 (85.9)7.0Public
CJY, HYW, KHW @ HRI-SH
Seq2Seq
9. using public detections
52.7
±12.1
49.417.7% 38.2% 10,819253,8902,396 (43.6)3,374 (61.3)2.6Public
Anonymous submission
LM_NN
10. using public detections
45.1
±13.3
43.214.8% 46.2% 10,834296,4512,286 (48.2)2,463 (51.9)0.9Public
M. Babaee, Z. Li, G. Rigoll. A Dual CNN--RNN for Multiple People Tracking. In Neurocomputing, 2019.
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
Tracktor++
11. online method using public detections
53.5
±14.5
52.319.5% 36.6% 12,201248,0472,072 (37.0)4,611 (82.3)1.5Public
P. Bergmann, T. Meinhardt, L. Leal-Taixé. Tracking without bells and whistles. In ICCV, 2019.
Alex1
12. online method using public detections
56.1
±14.9
55.022.1% 34.9% 12,627232,9562,097 (35.7)3,398 (57.9)22.8Public
Anonymous submission
GNN_tracktor
13. online method using public detections
54.4
±12.9
54.117.8% 37.4% 12,655241,8682,660 (46.6)3,991 (69.9)1.7Public
Anonymous submission
MOT_AF
14. online method using public detections
53.5
±13.4
55.619.2% 37.6% 12,867247,8161,672 (29.8)3,516 (62.7)25.2Public
Anonymous submission
TPM
15. using public detections
54.2
±13.0
52.622.8% 37.5% 13,739242,7301,824 (32.0)2,472 (43.4)0.8Public
Anonymous submission
FAMNet
16. online method using public detections
52.0
±12.0
48.719.1% 33.4% 14,138253,6163,072 (55.8)5,318 (96.6)0.0Public
P. Chu, H. Ling. FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking. In ICCV, 2019.
TrajTrack
17. online method using public detections
56.0
±12.9
57.222.6% 35.1% 14,378231,2122,546 (43.1)3,452 (58.5)1.4Public
Anonymous submission
Lif_T
18. using public detections
60.5
±15.2
65.627.0% 33.6% 14,966206,6191,189 (18.8)3,476 (54.8)0.5Public
Anonymous submission
ReTracktor
19. using public detections
55.1
±14.0
52.821.4% 34.9% 15,489235,6942,119 (36.4)4,725 (81.1)0.8Public
Anonymous submission
PV
20. online method using public detections
52.8
±14.1
51.819.7% 34.0% 15,884246,9393,711 (66.0)8,757 (155.7)3.5Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
Alex
21. online method using public detections
47.6
±14.2
49.813.2% 41.4% 16,028277,1102,731 (53.7)8,481 (166.7)0.2Public
Anonymous submission
CTRACKER
22. online method using public detections
39.4
±13.5
26.113.4% 42.5% 16,249307,90017,592 (387.2)14,508 (319.3)66.9Public
Anonymous submission
AEb
23. using public detections
48.1
±13.6
46.017.7% 39.5% 16,839273,8192,350 (45.7)5,275 (102.5)66.9Public
AEb_O
24. online method using public detections
46.4
±13.9
44.916.5% 41.4% 17,030283,2652,266 (45.5)5,053 (101.5)1.8Public
Anonymous submission
HDTR
25. using public detections
54.1
±11.4
48.423.3% 34.8% 18,002238,8181,895 (32.9)2,693 (46.7)1.8Public
M. Babaee, A. Athar, G. Rigoll. Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification. In arXiv preprint arXiv:1811.04091, 2018.
GMPHD_N1Tr
26. online method using public detections
42.1
±13.2
33.911.9% 42.7% 18,214297,64610,698 (226.4)10,864 (229.9)9.9Public
N. Baisa, A. Wallace. Development of a N-type GM-PHD filter for multiple target, multiple type visual tracking. In Journal of Visual Communication and Image Representation, 2019.
GM_PHD
27. online method using public detections
42.1
±13.2
33.911.9% 42.7% 18,214297,64610,698 (226.4)10,864 (229.9)9.9Public
Anonymous submission
OTCD_1
28. online method using public detections
48.6
±13.7
47.916.2% 41.2% 18,499268,2043,502 (66.7)5,588 (106.5)15.5Public
Q. Liu, B. Liu, Y. Wu, W. Li, N. Yu. Real-Time Online Multi-Object Tracking in Compressed Domain. In IEEE Access, 2019.
TppNoFPN
29. using public detections
52.4
±15.3
52.618.5% 37.2% 18,635247,1042,726 (48.5)5,461 (97.2)4.2Public
Anonymous submission
LSMT
30. online method using public detections
51.9
±12.0
53.517.4% 35.0% 18,672250,6622,257 (40.6)5,733 (103.2)8.9Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
D_SST_V1
31. online method using public detections
42.7
±13.9
46.111.8% 44.4% 18,861298,9895,531 (117.7)13,775 (293.0)2.3Public
Anonymous submission
QiMOT
32. online method using public detections
47.2
±13.1
40.815.5% 39.9% 18,907274,8284,320 (84.2)5,917 (115.4)1.8Public
Anonymous submission
GM_PHD_D
33. online method using public detections
44.0
±13.8
34.214.8% 39.4% 19,135283,53013,556 (272.5)13,821 (277.8)9.9Public
Anonymous submission
GMPHD_DAL
34. online method using public detections
44.4
±13.9
36.214.9% 39.4% 19,170283,38011,137 (223.7)13,900 (279.3)3.4Public
N. Baisa. Online Multi-object Visual Tracking using a GM-PHD Filter with Deep Appearance Learning. In 2019 22th International Conference on Information Fusion (FUSION), 2019.
MOTF17
35. using public detections
52.0
±13.2
50.520.1% 40.4% 19,222249,4642,293 (41.1)3,297 (59.1)2.2Public
Anonymous submission
UNS20
36. online method using public detections
46.5
±13.6
47.716.3% 43.1% 19,283280,7881,967 (39.2)3,103 (61.8)12.2Public
Anonymous submission
PPMOT17
37. using public detections
51.5
±13.0
47.821.8% 40.1% 19,821251,4952,492 (45.0)2,986 (53.9)35.5Public
Anonymous submission
PP17
38. using public detections
51.5
±13.0
47.821.8% 40.1% 19,821251,4952,492 (45.0)2,986 (53.9)1.9Public
Anonymous submission
MOTPP17
39. using public detections
52.4
±15.4
50.822.4% 40.0% 19,922246,1832,223 (39.4)2,769 (49.1)35.5Public
Anonymous submission
IOU17
40. using public detections
45.5
±13.6
39.415.7% 40.5% 19,993281,6435,988 (119.6)7,404 (147.8)1,522.9Public
E. Bochinski, V. Eiselein, T. Sikora. High-Speed Tracking-by-Detection Without Using Image Information. In International Workshop on Traffic and Street Surveillance for Safety and Security at IEEE AVSS 2017, 2017.
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
TLO17
41. online method using public detections
52.6
±12.9
51.319.5% 38.2% 20,089244,9302,530 (44.7)4,170 (73.7)25.2Public
Anonymous submission
TARCA
42. online method using public detections
55.9
±13.3
58.124.2% 35.9% 20,141227,1511,784 (29.9)3,741 (62.6)6.9Public
Anonymous submission
NOTA
43. using public detections
51.3
±11.7
54.517.1% 35.4% 20,148252,5312,285 (41.4)5,798 (105.0)17.8Public
L. Chen, H. Ai, R. Chen, Z. Zhuang. Aggregate Tracklet Appearance Features for Multi-Object Tracking. In IEEE Signal Processing Letters, 2019.
OMHT
44. online method using public detections
52.6
±12.9
51.919.3% 38.0% 20,153244,9982,552 (45.1)4,148 (73.3)37.2Public
Anonymous submission
PPMOT
45. using public detections
52.4
±13.4
50.822.4% 40.0% 20,176246,1582,224 (39.5)2,769 (49.1)2.3Public
Anonymous submission
TT17
46. using public detections
54.9
±12.8
63.124.4% 38.1% 20,236233,2951,088 (18.5)2,392 (40.8)2.5Public
TIP-21754-2019
DTBasline
47. online method using public detections
51.1
±11.7
53.416.7% 35.5% 20,309253,2452,549 (46.2)5,910 (107.2)22.2Public
Anonymous submission
MOT17ZH
48. online method using public detections
51.1
±13.7
53.416.7% 35.5% 20,309253,2452,549 (46.2)5,910 (107.2)3.7Public
Anonymous submission
GMOT
49. using public detections
55.4
±12.2
57.922.7% 34.7% 20,608229,5111,403 (23.7)2,765 (46.6)5.9Public
LXD, KHW @ HRI-SH
E2EM
50. online method using public detections
47.5
±14.5
48.816.5% 37.5% 20,655272,1873,632 (70.2)12,712 (245.6)29.6Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
RegTL
51. using public detections
48.1
±13.7
41.618.1% 39.8% 20,850268,3633,386 (64.6)4,524 (86.3)17.8Public
Anonymous submission
lbc_mot
52. using public detections
49.8
±14.3
52.320.3% 36.2% 20,963259,5382,638 (48.9)5,303 (98.2)66.9Public
Anonymous submission
HAM_SADF17
53. online method using public detections
48.3
±13.2
51.117.1% 41.7% 20,967269,0381,871 (35.8)3,020 (57.7)5.0Public
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.
CASC_MOT
54. online method using public detections
42.3
±12.8
46.89.1% 44.1% 21,035300,7973,616 (77.4)16,656 (356.7)11.4Public
Anonymous submission
DCORV2
55. online method using public detections
45.5
±13.9
36.114.6% 40.4% 21,161282,9013,592 (72.0)7,696 (154.4)35.5Public
Anonymous submission
DSA_MOT17
56. online method using public detections
45.0
±12.6
43.615.8% 39.2% 21,442286,4822,491 (50.6)3,824 (77.7)9.9Public
Anonymous submission
TTL
57. online method using public detections
52.3
±12.9
51.319.3% 38.2% 21,617244,5012,779 (49.0)4,290 (75.7)21.5Public
Anonymous submission
OST
58. using public detections
49.7
±14.0
50.417.0% 36.7% 21,811258,6493,077 (56.8)4,339 (80.1)1.7Public
Anonymous submission
HISP_DAL17
59. online method using public detections
45.4
±13.9
39.914.8% 39.2% 21,820277,4738,727 (171.7)7,147 (140.6)3.2Public
N. Baisa. Robust Online Multi-target Visual Tracking using a HISP Filter with Discriminative Deep Appearance Learning. In CoRR, 2019.
PointMOT17
60. using public detections
52.2
±13.3
50.822.4% 40.0% 22,012245,2772,134 (37.8)2,652 (46.9)2.2Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
TLO_MHT
61. online method using public detections
53.3
±12.9
53.320.0% 38.7% 22,161238,9592,434 (42.2)4,089 (70.9)2.0Public
Anonymous submission
MHT_ReID7
62. using public detections
46.5
±13.7
46.918.8% 40.3% 22,203276,3743,386 (66.4)8,521 (167.0)1.6Public
Anonymous submission
TLMHT
63. using public detections
50.6
±12.5
56.517.6% 43.4% 22,213255,0301,407 (25.7)2,079 (37.9)2.6Public
H. Sheng, J. Chen, Y. Zhang, W. Ke, Z. Xiong, J. Yu. Iterative Multiple Hypothesis Tracking with Tracklet-level Association. In IEEE Transactions on Circuits and Systems for Video Technology, 2018.
GF
64. online method using public detections
45.0
±13.9
39.115.0% 39.0% 22,387277,33510,397 (204.5)7,421 (145.9)9.9Public
Anonymous submission
AFN17
65. using public detections
51.5
±13.0
46.920.6% 35.5% 22,391248,4202,593 (46.3)4,308 (77.0)1.8Public
H. Shen, L. Huang, C. Huang, W. Xu. Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking. In CoRR, 2018.
LSST17O
66. online method using public detections
52.7
±13.3
57.917.9% 36.6% 22,512241,9362,167 (37.9)7,443 (130.3)1.8Public
Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
DeepMP17
67. using public detections
50.4
±13.1
52.318.8% 38.7% 22,535255,3561,868 (34.1)3,473 (63.4)7.4Public
MHT_DAM
68. using public detections
50.7
±13.7
47.220.8% 36.9% 22,875252,8892,314 (41.9)2,865 (51.9)0.9Public
C. Kim, F. Li, A. Ciptadi, J. Rehg. Multiple Hypothesis Tracking Revisited. In ICCV, 2015.
UTA
69. online method using public detections
53.1
±11.7
54.421.5% 31.8% 22,893239,5342,251 (39.1)6,192 (107.6)5.0Public
Anonymous submission
ISE_MOT
70. online method using public detections
58.6
±10.5
54.727.0% 29.8% 23,033208,0452,368 (37.5)3,247 (51.4)16.3Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
ReID_Seq
71. online method using public detections
51.4
±12.7
49.220.3% 34.1% 23,045247,8853,226 (57.5)4,148 (74.0)14.0Public
Anonymous submission
Q_ls
72. online method using public detections
50.2
±14.4
43.619.7% 37.3% 23,143253,1514,414 (80.1)6,112 (110.9)1.8Public
Anonymous submission
ISE_MOT17R
73. online method using public detections
60.1
±11.0
56.428.5% 28.1% 23,168199,4832,556 (39.5)3,182 (49.2)7.2Public
MIFT
PHD_GSDL17
74. online method using public detections
48.0
±13.6
49.617.1% 35.6% 23,199265,9543,998 (75.6)8,886 (168.1)6.7Public
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.
GNNMOT
75. online method using public detections
42.0
±12.8
29.312.0% 50.0% 23,294299,6944,377 (93.4)3,847 (82.1)177.6Public
Anonymous submission
MCLT17
76. using public detections
54.2
±12.3
63.524.0% 38.1% 23,602233,7831,208 (20.6)2,394 (40.9)66.9Public
Anonymous submission
GM_PHD
77. online method using public detections
36.4
±14.1
33.94.1% 57.3% 23,723330,7674,607 (111.3)11,317 (273.5)38.4Public
V. Eiselein, D. Arp, M. Pätzold, T. Sikora. Real-time Multi-Human Tracking using a Probability Hypothesis Density Filter and multiple detectors. In 9th IEEE International Conference on Advanced Video and Signal-Based Surveillance, 2012.
FFT
78. online method using public detections
56.5
±15.7
51.026.2% 26.7% 23,746215,9715,672 (91.9)5,474 (88.7)1.8Public
Anonymous submission
GMPHDOGM17
79. online method using public detections
49.9
±13.6
47.119.7% 38.0% 24,024255,2773,125 (57.1)3,540 (64.6)30.7Public
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.
MOTDT17
80. online method using public detections
50.9
±11.9
52.717.5% 35.7% 24,069250,7682,474 (44.5)5,317 (95.7)18.3Public
C. Long, A. Haizhou, Z. Zijie, S. Chong. Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identification. In ICME, 2018.
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
FWT
81. using public detections
51.3
±13.1
47.621.4% 35.2% 24,101247,9212,648 (47.2)4,279 (76.3)0.2Public
R. Henschel, L. Leal-Taixé, D. Cremers, B. Rosenhahn. Fusion of Head and Full-Body Detectors for Multi-Object Tracking. In Trajnet CVPRW, 2018.
MOT_TBC
82. using public detections
53.9
±15.7
50.020.2% 36.7% 24,584232,6702,945 (50.1)4,612 (78.5)6.7Public
Anonymous submission
DualAtte
83. online method using public detections
48.4
±14.5
43.717.6% 39.0% 24,915262,6543,423 (64.0)5,192 (97.1)0.3Public
Anonymous submission
MPNTrack17
84. using public detections
55.7
±13.2
59.127.2% 34.4% 25,013223,5311,433 (23.7)3,122 (51.7)4.2Public
Anonymous submission
AM_ADM17
85. online method using public detections
48.1
±13.8
52.113.4% 39.7% 25,061265,4952,214 (41.8)5,027 (94.9)5.7Public
S. Lee, M. Kim, S. Bae, Learning Discriminative Appearance Models for Online Multi-Object Tracking with Appearance Discriminability Measures, In IEEE Access, 2018.
ZM
86. online method using public detections
43.5
±13.9
32.614.5% 39.9% 25,083284,4059,197 (185.4)8,849 (178.4)14.4Public
Anonymous submission
SNM17
87. online method using public detections
46.8
±13.8
43.416.2% 37.1% 25,104271,0424,213 (81.1)9,891 (190.3)0.8Public
Anonymous submission
STRN_MOT17
88. online method using public detections
50.9
±11.6
56.018.9% 33.8% 25,295249,3652,397 (43.0)9,363 (167.8)13.8Public
J. Xu, Y. Cao, Z. Zhang, H. Hu. Spatial-Temporal Relation Networks for Multi-Object Tracking. In ICCV, 2019.
MOCL
89. online method using public detections new
49.5
±14.0
43.420.7% 35.6% 25,373254,1315,164 (94.0)5,787 (105.3)148.0Public
ECCV-20/4696
MMHT17
90. online method using public detections
52.8
±12.9
53.320.3% 37.5% 25,401238,4132,596 (45.0)4,103 (71.1)37.2Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
wangs
91. online method using public detections
48.5
±14.2
45.018.3% 38.8% 25,428261,7553,233 (60.3)4,941 (92.2)66.9Public
Anonymous submission
CGHA_MOT
92. online method using public detections
41.2
±14.1
44.08.3% 45.9% 25,462299,1127,294 (155.2)18,655 (397.0)11.4Public
Anonymous submission
HISP_T17
93. online method using public detections
44.6
±14.2
38.815.1% 38.8% 25,478276,39510,617 (208.1)7,487 (146.8)4.7Public
N. Baisa. Online Multi-target Visual Tracking using a HISP Filter. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,, 2018.
DEEP_TAMA
94. online method using public detections
50.3
±13.3
53.519.2% 37.5% 25,479252,9962,192 (39.7)3,978 (72.1)1.5Public
Y. Yoon, D. Kim, K. Yoon, Y. Song, M. Jeon. Online Multiple Pedestrian Tracking using Deep Temporal Appearance Matching Association. In arXiv:1907.00831, 2019.
EDA_GNN
95. online method using public detections
45.5
±13.8
40.515.6% 40.6% 25,685277,6634,091 (80.5)5,579 (109.8)39.3Public
Paper ID 2713
MASS
96. online method using public detections
46.9
±14.1
46.016.9% 36.3% 25,733269,1164,478 (85.6)11,994 (229.3)17.1Public
H. Karunasekera, H. Wang, H. Zhang. Multiple Object Tracking With Attention to Appearance, Structure, Motion and Size. In IEEE Access, 2019.
RFTracking
97. online method using public detections
48.5
±14.8
44.917.7% 38.6% 25,739261,7103,089 (57.6)4,813 (89.8)66.9Public
Anonymous submission
GMPHD_SHA
98. online method using public detections
43.7
±12.5
39.211.7% 43.0% 25,935287,7583,838 (78.3)5,056 (103.2)9.2Public
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.
jCC
99. using public detections
51.2
±14.5
54.520.9% 37.0% 25,937247,8221,802 (32.1)2,984 (53.2)1.8Public
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.
MHT_bLSTM
100. using public detections
47.5
±12.6
51.918.2% 41.7% 25,981268,0422,069 (39.4)3,124 (59.5)1.9Public
C. Kim, F. Li, J. Rehg. Multi-object Tracking with Neural Gating Using Bilinear LSTM. In ECCV, 2018.
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
LSST17
101. using public detections
54.7
±12.9
62.320.4% 40.1% 26,091228,4341,243 (20.9)3,726 (62.6)1.5Public
Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
DMAN
102. online method using public detections
48.2
±12.3
55.719.3% 38.3% 26,218263,6082,194 (41.2)5,378 (100.9)0.3Public
J. Zhu, H. Yang, N. Liu, M. Kim, W. Zhang, M. Yang. Online Multi-Object Tracking with Dual Matching Attention Networks. In ECCV, 2018.
PHD_GM
103. online method using public detections
48.8
±13.4
43.219.1% 35.2% 26,260257,9714,407 (81.2)6,448 (118.8)22.3Public
R. Sanchez-Matilla, A. Cavallaro. A predictor of moving objects for First-Person vision. In Proceedings of IEEE International Conference Image Processing, 2019.
DeepMOTRPN
104. online method using public detections
48.1
±14.5
43.017.6% 38.6% 26,490262,5783,696 (69.1)5,353 (100.1)4.9Public
Anonymous submission
SMOT_no
105. online method using public detections
52.9
±12.3
54.118.7% 32.8% 26,703236,3462,702 (46.5)6,340 (109.1)4.9Public
Anonymous submission
ENFT17
106. using public detections
52.8
±13.1
57.123.1% 36.8% 26,754237,9091,667 (28.8)2,557 (44.2)0.5Public
BUAA
SNet_pub
107. online method using public detections
51.7
±12.0
53.418.0% 33.5% 26,809243,0662,735 (48.0)6,157 (108.2)4.9Public
Anonymous submission
SiaIOU
108. using public detections
48.5
±16.7
48.518.9% 38.8% 26,867260,2783,152 (58.5)4,391 (81.5)8.3Public
Anonymous submission
JDT
109. online method using public detections
47.4
±12.2
50.116.8% 37.2% 26,910267,3312,760 (52.5)6,211 (118.0)35.1Public
Anonymous submission
CRF_TRA
110. using public detections
53.1
±12.2
53.724.2% 30.7% 27,194234,9912,518 (43.2)4,918 (84.3)1.4Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
SMOTe
111. online method using public detections
52.1
±12.1
53.818.4% 33.3% 27,571239,7242,691 (46.8)6,134 (106.7)1.0Public
Anonymous submission
TOPA
112. online method using public detections
51.8
±13.5
53.419.6% 33.1% 27,603241,5462,668 (46.7)5,790 (101.2)443.9Public
Anonymous submission
TM_track
113. online method using public detections
41.1
±14.9
32.813.2% 41.3% 27,606287,51117,408 (355.0)15,197 (309.9)2.5Public
Anonymous submission
cascademot
114. online method using public detections
41.8
±16.0
34.215.2% 38.7% 27,816288,76811,535 (236.3)14,800 (303.2)17.8Public
Anonymous submission
tianyi
115. using public detections
50.0
±13.7
51.020.5% 35.6% 27,839251,1483,312 (59.7)6,234 (112.3)5.9Public
Anonymous submission
LT17
116. online method using public detections
47.7
±16.6
45.217.3% 36.0% 27,856263,0624,042 (75.7)9,183 (172.0)7.2Public
Anonymous submission
PHD_LMP
117. online method using public detections
45.9
±13.1
42.515.5% 37.9% 27,946272,1964,977 (96.2)6,985 (135.0)29.4Public
Anonymous submission
SORT17
118. online method using public detections
43.1
±13.3
39.812.5% 42.3% 28,398287,5824,852 (99.0)7,127 (145.4)143.3Public
A. Bewley, Z. Ge, L. Ott, F. Ramos, B. Upcroft. Simple online and realtime tracking. In 2016 IEEE International Conference on Image Processing (ICIP), 2016.
Umot
119. online method using public detections
43.9
±13.8
37.815.2% 38.9% 28,596278,6219,363 (185.0)11,371 (224.6)19.7Public
Anonymous submission
HTBT
120. using public detections
52.3
±13.3
54.522.5% 36.4% 28,743238,2681,959 (33.9)2,973 (51.5)0.4Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
DAM_MOT
121. online method using public detections
47.0
±12.6
48.716.9% 38.1% 28,933267,8962,140 (40.7)2,756 (52.5)18.7Public
Multi Object Tracking using Deep Structural Cost Minimization in Data Association
IDGA
122. using public detections
52.6
±13.4
61.323.6% 40.2% 29,049236,8301,402 (24.2)2,613 (45.0)59.2Public
Anonymous submission
YOONKJ17
123. online method using public detections
51.4
±13.5
54.021.2% 37.3% 29,051243,2022,118 (37.2)3,072 (54.0)3.4Public
K. YOON, J. GWAK, Y. SONG, Y. YOON, M. JEON. OneShotDA: Online Multi-object Tracker with One-shot-learning-based Data Association. In IEEE Access, 2020.
MOLF
124. online method using public detections
50.9
±12.3
46.718.3% 34.6% 29,398242,8374,535 (79.6)5,343 (93.8)30.5Public
Anonymous submission
SAS_MOT17
125. using public detections
44.2
±12.2
57.216.1% 44.3% 29,473283,6111,529 (30.7)2,644 (53.2)4.8Public
A. Maksai, P. Fua. Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking. In CVPR, 2019.
CMT
126. using public detections
51.8
±12.9
60.719.6% 42.8% 29,528240,9601,217 (21.2)2,008 (35.0)6.5Public
#Submission: TIP-21190-2019
XYHv2
127. online method using public detections
39.9
±12.4
23.89.9% 41.8% 29,713296,70412,900 (272.1)12,911 (272.3)7.8Public
Anonymous submission
DAIST_
128. online method using public detections
52.1
±12.5
53.819.7% 33.6% 29,931237,9132,689 (46.5)5,600 (96.8)6.9Public
Anonymous submission
AReid17
129. online method using public detections
51.4
±12.2
53.919.2% 32.3% 30,079241,3642,993 (52.3)6,373 (111.4)33.7Public
Anonymous submission
dcor
130. online method using public detections
45.0
±14.2
34.015.4% 38.2% 30,231275,2654,801 (93.7)8,498 (165.9)44.4Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
GOTURN_3B
131. online method using public detections
44.3
±13.7
38.513.0% 43.2% 30,302279,1444,861 (96.2)5,277 (104.4)48.6Public
Anonymous submission
DAN__test
132. using public detections
43.0
±14.7
43.313.5% 40.0% 30,367283,5337,576 (152.3)14,990 (301.3)1.8Public
Anonymous submission
SCNet
133. online method using public detections
53.2
±15.4
54.920.0% 32.1% 30,440231,1092,621 (44.4)6,031 (102.2)1.0Public
Anonymous submission
2MPT
134. using public detections
48.1
±14.2
52.917.4% 39.6% 30,650260,1331,860 (34.5)2,784 (51.7)2.7Public
Anonymous submission
EAMTT
135. online method using public detections
42.6
±13.3
41.812.7% 42.7% 30,711288,4744,488 (91.8)5,720 (117.0)12.0Public
R. Sanchez-Matilla, F. Poiesi, A. Cavallaro. Online Multi-target Tracking with Strong and Weak Detections. In Computer Vision -- ECCV 2016 Workshops, 2016.
JBNOT
136. using public detections
52.6
±12.3
50.819.7% 35.8% 31,572232,6593,050 (51.9)3,792 (64.5)5.4Public
R. Henschel, Y. Zou, B. Rosenhahn. Multiple People Tracking using Body and Joint Detections. In CVPRW, 2019.
Lab031
137. using public detections
46.9
±16.2
48.117.7% 36.1% 31,634263,9383,795 (71.3)10,498 (197.3)9.4Public
Anonymous submission
ms_dh
138. online method using public detections
42.6
±14.6
40.113.6% 40.0% 31,878284,5287,446 (150.2)14,736 (297.3)4.0Public
Anonymous submission
STCG17
139. using public detections
51.1
±12.9
54.520.4% 38.6% 32,258241,9161,702 (29.8)2,483 (43.5)66.9Public
Anonymous submission
EDMT17
140. using public detections
50.0
±13.9
51.321.6% 36.3% 32,279247,2972,264 (40.3)3,260 (58.0)0.6Public
J. Chen, H. Sheng, Y. Zhang, Z. Xiong. Enhancing Detection Model for Multiple Hypothesis Tracking. In BMTT-PETS CVPRw, 2017.
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
98K
141. using public detections
40.8
±17.2
37.015.6% 38.1% 32,312298,1743,514 (74.5)4,991 (105.8)17.7Public
Anonymous submission
zxbtk17
142. online method using public detections
45.1
±14.7
40.017.7% 31.8% 33,186273,5313,303 (64.1)8,148 (158.1)8.3Public
Anonymous submission
eHAF17
143. using public detections
51.8
±13.2
54.723.4% 37.9% 33,212236,7721,834 (31.6)2,739 (47.2)0.7Public
H. Sheng, Y. Zhang, J. Chen, Z. Xiong, J. Zhang. Heterogeneous Association Graph Fusion for Target Association in Multiple Object Tracking. In IEEE Transactions on Circuits and Systems for Video Technology, 2018.
ResTestV2
144. using public detections
52.0
±16.4
50.919.2% 36.3% 33,320234,4812,836 (48.5)4,835 (82.7)66.9Public
Anonymous submission
c3d_Track
145. online method using public detections
41.5
±13.7
40.210.7% 48.5% 33,332292,9313,890 (80.9)11,454 (238.2)22.2Public
Anonymous submission
TAR_1
146. online method using public detections
51.6
±11.9
41.421.7% 28.7% 33,514235,8593,629 (62.4)5,949 (102.2)5.6Public
Anonymous submission
SOTD_MC
147. online method using public detections
48.4
±15.0
45.519.4% 35.9% 33,525255,0912,531 (46.2)4,944 (90.2)67.0Public
Anonymous submission
FPSN
148. online method using public detections
44.9
±13.9
48.416.5% 35.8% 33,757269,9527,136 (136.8)14,491 (277.8)10.1Public
S. Lee, E. Kim. Multiple Object Tracking via Feature Pyramid Siamese Networks. In IEEE ACCESS, 2018.
KVIOU
149. online method using public detections
46.6
±14.2
44.017.3% 38.1% 34,838262,0084,379 (81.8)7,844 (146.4)29.6Public
Anonymous submission
MFT
150. online method using public detections
53.1
±16.1
50.120.4% 39.4% 35,295225,6063,681 (61.3)6,271 (104.5)0.7Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
MOTbyReID
151. online method using public detections
43.6
±13.7
37.117.6% 36.3% 35,725270,03612,347 (236.8)11,408 (218.8)2.5Public
Anonymous submission
eTC17
152. using public detections
51.9
±12.4
58.123.1% 35.5% 36,164232,7832,288 (38.9)3,071 (52.3)0.7Public
G. Wang, Y. Wang, H. Zhang, R. Gu, J. Hwang. Exploit the connectivity: Multi-object tracking with trackletnet. In Proceedings of the 27th ACM International Conference on Multimedia, 2019.
MTDF17
153. online method using public detections
49.6
±13.9
45.218.9% 33.1% 37,124241,7685,567 (97.4)9,260 (162.0)1.2Public
Z. Fu, F. Angelini, J. Chambers, S. Naqvi. Multi-Level Cooperative Fusion of GM-PHD Filters for Online Multiple Human Tracking. In IEEE Transactions on Multimedia, 2019.
SRPN
154. online method using public detections
47.8
±13.2
41.417.0% 41.7% 38,279251,9894,325 (78.2)5,355 (96.8)11.8Public
Anonymous submission
overlap
155. using public detections
51.5
±13.1
55.623.0% 36.1% 38,322233,2751,860 (31.7)2,935 (50.0)66.9Public
Anonymous submission
GMPHD_Rd17
156. online method using public detections
46.8
±14.7
54.119.7% 33.3% 38,452257,6783,865 (71.1)8,097 (149.0)30.8Public
N. Baisa. Occlusion-robust Online Multi-object Visual Tracking using a GM-PHD Filter with a CNN-based Re-identification. In , 2019.
GLMBS3
157. using public detections
38.0
±13.7
32.39.3% 52.8% 38,874304,0166,963 (151.0)3,927 (85.2)4.9Public
Anonymous submission
SFS
158. online method using public detections
50.0
±12.2
51.819.2% 33.6% 44,810234,5502,993 (51.2)6,858 (117.4)0.9Public
Anonymous submission
TTracker
159. online method using public detections
46.2
±14.0
44.021.0% 35.6% 44,854254,4384,258 (77.6)6,307 (114.9)29.6Public
Anonymous submission
TCT4
160. online method using public detections
50.7
±15.4
50.924.5% 25.6% 46,638224,9556,543 (108.8)7,968 (132.5)14.1Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
ISDH_HDAv2
161. online method using public detections
54.5
±14.5
65.926.4% 32.1% 46,693207,0933,010 (47.6)6,000 (94.8)3.6Public
MM-008988/ IEEE Transactions on Multimedia
MOT_HY
162. using public detections
47.3
±121.2
49.417.2% 33.8% 46,875246,0614,231 (75.0)8,188 (145.2)2.0Public
Anonymous submission
CoCT
163. online method using public detections
50.1
±12.2
55.623.9% 35.4% 49,887229,3912,075 (35.0)4,304 (72.5)57.8Public
Anonymous submission
TPbase17
164. online method using public detections
43.3
±15.0
48.216.2% 36.6% 49,992265,8154,194 (79.3)12,103 (228.8)22.2Public
Anonymous submission
GMPHD_KCF
165. online method using public detections
39.6
±13.5
36.68.8% 43.3% 50,903284,2285,811 (117.1)7,414 (149.4)3.3Public
T. Kutschbach, E. Bochinski, V. Eiselein, T. Sikora. Sequential Sensor Fusion Combining Probability Hypothesis Density and Kernelized Correlation Filters for Multi-Object Tracking in Video Data. In International Workshop on Traffic and Street Surveillance for Safety and Security at IEEE AVSS 2017, 2017.
TriplDSort
166. using public detections
50.7
±15.3
50.520.3% 36.6% 51,739222,2124,397 (72.5)7,352 (121.3)0.6Public
Anonymous submission
MOT_BJ
167. online method using public detections
-7.3
±23.5
1.40.0% 99.1% 52,007548,5314,824 (1,734.0)8,621 (3,098.8)0.0Public
Anonymous submission
TCT
168. online method using public detections
47.5
±27.1
49.323.2% 28.8% 52,209238,7165,541 (96.0)7,368 (127.7)14.1Public
Anonymous submission
Response17
169. using public detections
61.2
±14.3
63.236.7% 22.0% 55,168159,9863,589 (50.1)7,640 (106.6)5.9Public
Anonymous submission
GoturnM17
170. online method using public detections
38.3
±9.0
25.79.4% 47.1% 55,381282,67010,328 (207.0)9,849 (197.4)11.8Public
Anonymous submission
TrackerMOTAIDF1MTML FPFNID Sw.FragHzDetector
cnt_klt
171. using public detections
48.0
±11.8
57.819.0% 31.6% 63,207228,7831,215 (20.4)4,134 (69.5)59.2Public
Anonymous submission
baitrack
172. using public detections
37.6
±19.4
20.321.0% 30.9% 99,085244,0018,808 (155.2)6,708 (118.2)6.4Public
Anonymous submission
JOINT_TRAC
173. using public detections
29.4
±17.6
34.512.6% 42.3% 132,192260,8085,397 (100.4)10,704 (199.0)66.9Public
Anonymous submission
YoloSort
174. online method using public detections
29.5
±24.1
41.715.0% 36.4% 154,747238,2414,888 (84.6)4,952 (85.7)14.4Public
Anonymous submission
GNNT
175. online method using public detections
-523.7
±1,341.9
9.033.6% 27.2% 3,318,414185,81915,019 (223.9)4,763 (71.0)7.6Public
Anonymous submission
SequencesFramesTrajectoriesBoxes
21177572355564228

Difficulty Analysis

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

MOT17-03-SDP

MOT17-03-SDP

(66.8% MOTA)

MOT17-03-FRCNN

MOT17-03-FRCNN

(59.7% MOTA)

MOT17-03-DPM

MOT17-03-DPM

(51.7% MOTA)

...

...

MOT17-14-DPM

MOT17-14-DPM

(21.3% MOTA)

MOT17-14-FRCNN

MOT17-14-FRCNN

(20.6% MOTA)


Evaluation Measures

Lower is better. Higher is better.
Measure Better Perfect Description
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. The frequency is provided by the authors and not officially evaluated by the MOTChallenge.

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.