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

TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
zxbtk17
1. online method using public detections
45.1
±0.0
40.017.7% 31.8% 33,186273,5313,303 (64.1)8,148 (158.1)Public
Anonymous submission
ZM
2. using public detections
43.5
±0.0
32.614.5% 39.9% 25,083284,4059,197 (185.4)8,849 (178.4)Public
Anonymous submission
YOONKJ17
3. online method using public detections
51.4
±0.0
54.021.2% 37.3% 29,051243,2022,118 (37.2)3,072 (54.0)Public
K. Yoon, J. Gwak, Y. Song, Y. Yoon and M. Jeon, "OneShotDA: Online Multi-object Tracker with One-shot-learning-based Data Association," in IEEE Access, 2020.
YoloSort
4. online method using public detections
29.5
±0.0
41.715.0% 36.4% 154,747238,2414,888 (84.6)4,952 (85.7)Public
Anonymous submission
XYHv2
5. online method using public detections
39.9
±0.0
23.89.9% 41.8% 29,713296,70412,900 (272.1)12,911 (272.3)Public
Anonymous submission
wangs
6. online method using public detections
48.5
±0.0
45.018.3% 38.8% 25,428261,7553,233 (60.3)4,941 (92.2)Public
Anonymous submission
UTA
7. using public detections
53.0
±0.0
52.221.7% 31.5% 24,468238,3562,292 (39.7)6,231 (107.9)Public
Anonymous submission
Umot
8. online method
43.9
±0.0
37.815.2% 38.9% 28,596278,6219,363 (185.0)11,371 (224.6)Public
Anonymous submission
TTracker
9. using public detections
46.2
±0.0
44.021.0% 35.6% 44,854254,4384,258 (77.6)6,307 (114.9)Public
Anonymous submission
TTL
10. online method using public detections
52.3
±0.0
51.319.3% 38.2% 21,617244,5012,779 (49.0)4,290 (75.7)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
TT17
11. online method using public detections
54.9
±0.0
63.124.4% 38.1% 20,236233,2951,088 (18.5)2,392 (40.8)Public
TIP-21754-2019
TriplDSort
12. using public detections
50.7
±0.0
50.520.3% 36.6% 51,739222,2124,397 (72.5)7,352 (121.3)Public
Anonymous submission
TrajTrack
13. using public detections
56.0
±0.0
57.222.6% 35.1% 14,378231,2122,546 (43.1)3,452 (58.5)Public
Anonymous submission
track_bnw
14. online method using public detections new
57.9
±0.0
54.724.5% 33.4% 8,250226,8562,196 (36.7)2,859 (47.8)Public
Anonymous submission
track_bin
15. using public detections
57.2
±0.0
54.822.6% 34.9% 9,462229,7922,353 (39.7)3,122 (52.7)Public
Anonymous submission
Tracktorv2
16. online method using public detections
56.3
±0.0
55.121.1% 35.3% 8,866235,4491,987 (34.1)3,763 (64.6)Public
P. Bergmann, T. Meinhardt, L. Leal-Taixé. Tracking without bells and whistles. In ICCV, 2019.
Tracktor17
17. using public detections
53.5
±0.0
52.319.5% 36.6% 12,201248,0472,072 (37.0)4,611 (82.3)Public
P. Bergmann, T. Meinhardt, L. Leal-Taixé. Tracking without bells and whistles. In ICCV, 2019.
TppNoFPN
18. online method using public detections
52.4
±0.0
52.618.5% 37.2% 18,635247,1042,726 (48.5)5,461 (97.2)Public
Anonymous submission
TPM
19. online method using public detections
54.2
±0.0
52.622.8% 37.5% 13,739242,7301,824 (32.0)2,472 (43.4)Public
Anonymous submission
TPbase17
20. online method
43.3
±0.0
48.216.2% 36.6% 49,992265,8154,194 (79.3)12,103 (228.8)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
TOPA
21. online method using public detections
51.8
±0.0
53.419.6% 33.1% 27,603241,5462,668 (46.7)5,790 (101.2)Public
Anonymous submission
TM_track
22. using public detections
41.1
±0.0
32.813.2% 41.3% 27,606287,51117,408 (355.0)15,197 (309.9)Public
Anonymous submission
TLO_MHT
23. online method using public detections
52.9
±0.0
53.320.1% 37.6% 24,142238,8342,565 (44.5)4,101 (71.1)Public
Anonymous submission
TLO17
24. online method using public detections
52.6
±0.0
51.319.5% 38.2% 20,089244,9302,530 (44.7)4,170 (73.7)Public
Anonymous submission
TLMHT
25. online method using public detections
50.6
±0.0
56.517.6% 43.4% 22,213255,0301,407 (25.7)2,079 (37.9)Public
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.
tianyi
26. using public detections
50.0
±0.0
51.020.5% 35.6% 27,839251,1483,312 (59.7)6,234 (112.3)Public
Anonymous submission
TCT4
27. using public detections
50.7
±0.0
50.924.5% 25.6% 46,638224,9556,543 (108.8)7,968 (132.5)Public
Anonymous submission
TCT
28. online method using public detections
47.5
±0.0
49.323.2% 28.8% 52,209238,7165,541 (96.0)7,368 (127.7)Public
Anonymous submission
TAR_1
29. using public detections
51.6
±0.0
41.421.7% 28.7% 33,514235,8593,629 (62.4)5,949 (102.2)Public
Anonymous submission
STRN_MOT17
30. online method using public detections
50.9
±0.0
56.018.9% 33.8% 25,295249,3652,397 (43.0)9,363 (167.8)Public
J. Xu, Y. Cao, Z. Zhang, H. Hu. Spatial-Temporal Relation Networks for Multi-Object Tracking. In ICCV, 2019.
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
STCG17
31. online method using public detections
51.1
±0.0
54.520.4% 38.6% 32,258241,9161,702 (29.8)2,483 (43.5)Public
Anonymous submission
SRPN
32. using public detections
47.8
±0.0
41.417.0% 41.7% 38,279251,9894,325 (78.2)5,355 (96.8)Public
Anonymous submission
SRPN17
33. online method
51.0
±0.0
53.516.8% 35.1% 21,011252,8082,596 (47.0)5,981 (108.4)Public
Anonymous submission
SOTD_MC
34. using public detections
48.4
±0.0
45.519.4% 35.9% 33,525255,0912,531 (46.2)4,944 (90.2)Public
Anonymous submission
SORT17
35. online method using public detections
43.1
±0.0
39.812.5% 42.3% 28,398287,5824,852 (99.0)7,127 (145.4)Public
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.
SNM17
36. online method using public detections
46.8
±0.0
43.416.2% 37.1% 25,104271,0424,213 (81.1)9,891 (190.3)Public
Anonymous submission
SNet_pub
37. online method
51.7
±0.0
53.418.0% 33.5% 26,809243,0662,735 (48.0)6,157 (108.2)Public
Anonymous submission
SMOT_no
38. online method using public detections
52.9
±0.0
54.118.7% 32.8% 26,703236,3462,702 (46.5)6,340 (109.1)Public
Anonymous submission
SMOTe
39. online method using public detections
52.1
±0.0
53.818.4% 33.3% 27,571239,7242,691 (46.8)6,134 (106.7)Public
Anonymous submission
SiaIOU
40. using public detections
48.5
±0.0
48.518.9% 38.8% 26,867260,2783,152 (58.5)4,391 (81.5)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
SFS
41. online method using public detections
50.5
±0.0
52.217.0% 40.8% 30,925245,9222,275 (40.3)5,270 (93.4)Public
Anonymous submission
SCNet
42. using public detections
53.2
±0.0
54.920.0% 32.1% 30,440231,1092,621 (44.4)6,031 (102.2)Public
Anonymous submission
SAS_MOT17
43. using public detections
44.2
±0.0
57.216.1% 44.3% 29,473283,6111,529 (30.7)2,644 (53.2)Public
A. Maksai, P. Fua. Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking. In CVPR, 2019.
RFTracking
44. online method using public detections
48.5
±0.0
44.917.7% 38.6% 25,739261,7103,089 (57.6)4,813 (89.8)Public
Anonymous submission
ReTracktor
45. using public detections
55.1
±0.0
52.821.4% 34.9% 15,489235,6942,119 (36.4)4,725 (81.1)Public
Anonymous submission
ResTestV2
46. using public detections
52.0
±0.0
50.919.2% 36.3% 33,320234,4812,836 (48.5)4,835 (82.7)Public
Anonymous submission
Response17
47. using public detections
61.2
±0.0
63.236.7% 22.0% 55,168159,9863,589 (50.1)7,640 (106.6)Public
Anonymous submission
ReID_Seq
48. using public detections
51.4
±0.0
49.220.3% 34.1% 23,045247,8853,226 (57.5)4,148 (74.0)Public
Anonymous submission
RegTL
49. online method using public detections
48.1
±0.0
41.618.1% 39.8% 20,850268,3633,386 (64.6)4,524 (86.3)Public
Anonymous submission
Q_ls
50. online method using public detections
50.2
±0.0
43.619.7% 37.3% 23,143253,1514,414 (80.1)6,112 (110.9)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
QiMOT
51. online method
47.2
±0.0
40.815.5% 39.9% 18,907274,8284,320 (84.2)5,917 (115.4)Public
Anonymous submission
PV
52. online method using public detections
52.8
±0.0
51.819.7% 34.0% 15,884246,9393,711 (66.0)8,757 (155.7)Public
Anonymous submission
PPMOT
53. using public detections
52.4
±0.0
50.822.4% 40.0% 20,176246,1582,224 (39.5)2,769 (49.1)Public
Anonymous submission
PPMOT17
54. online method using public detections
51.5
±0.0
47.821.8% 40.1% 19,821251,4952,492 (45.0)2,986 (53.9)Public
Anonymous submission
PP17
55. online method
52.4
±0.0
50.822.4% 40.0% 20,183245,9982,215 (39.3)2,752 (48.8)Public
Anonymous submission
PointMOT17
56. using public detections
52.2
±0.0
50.822.4% 40.0% 22,012245,2772,134 (37.8)2,652 (46.9)Public
Anonymous submission
PHD_LMP
57.
45.9
±0.0
42.515.5% 37.9% 27,946272,1964,977 (96.2)6,985 (135.0)Public
Anonymous submission
PHD_GSDL17
58. online method
48.0
±0.0
49.617.1% 35.6% 23,199265,9543,998 (75.6)8,886 (168.1)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.
PHD_GM
59. using public detections
48.8
±0.0
43.219.1% 35.2% 26,260257,9714,407 (81.2)6,448 (118.8)Public
R. Sanchez-Matilla, A. Cavallaro. A predictor of moving objects for First-Person vision. In Proceedings of IEEE International Conference Image Processing, 2019.
overlap
60. online method using public detections
51.5
±0.0
55.623.0% 36.1% 38,322233,2751,860 (31.7)2,935 (50.0)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
OTCD_1
61. online method
48.6
±0.0
47.916.2% 41.2% 18,499268,2043,502 (66.7)5,588 (106.5)Public
Q. Liu, B. Liu, Y. Wu, W. Li, N. Yu. Real-Time Online Multi-Object Tracking in Compressed Domain. In IEEE Access, 2019.
OST
62. online method
49.7
±0.0
50.417.0% 36.7% 21,811258,6493,077 (56.8)4,339 (80.1)Public
Anonymous submission
OMHT
63. using public detections
52.6
±0.0
51.919.3% 38.0% 20,153244,9982,552 (45.1)4,148 (73.3)Public
Anonymous submission
OLGT_new
64. online method
45.7
±0.0
49.410.8% 75.5% 6,915298,2881,418 (30.1)3,641 (77.2)Public
Anonymous submission
NOTA
65.
51.3
±0.0
54.517.1% 35.4% 20,148252,5312,285 (41.4)5,798 (105.0)Public
L. Chen, H. Ai, R. Chen, Z. Zhuang. Aggregate Tracklet Appearance Features for Multi-Object Tracking. In IEEE Signal Processing Letters, 2019.
MTDF17
66. using public detections
49.6
±0.0
45.218.9% 33.1% 37,124241,7685,567 (97.4)9,260 (162.0)Public
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.
ms_dh
67. using public detections
42.6
±0.0
40.113.6% 40.0% 31,878284,5287,446 (150.2)14,736 (297.3)Public
Anonymous submission
MPNTrack17
68. online method using public detections
55.7
±0.0
59.127.2% 34.4% 25,013223,5311,433 (23.7)3,122 (51.7)Public
Anonymous submission
MOT_TBC
69.
53.9
±0.0
50.020.2% 36.7% 24,584232,6702,945 (50.1)4,612 (78.5)Public
Anonymous submission
MOT_HY
70. online method
47.3
±0.0
49.417.2% 33.8% 46,875246,0614,231 (75.0)8,188 (145.2)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
MOT_BJ
71.
-7.3
±0.0
1.40.0% 99.1% 52,007548,5314,824 (1,734.0)8,621 (3,098.8)Public
Anonymous submission
MOT_AF
72. online method using public detections
53.5
±0.0
55.619.2% 37.6% 12,867247,8161,672 (29.8)3,516 (62.7)Public
Anonymous submission
MOTPP17
73. online method using public detections
52.4
±0.0
50.822.4% 40.0% 19,922246,1832,223 (39.4)2,769 (49.1)Public
Anonymous submission
MOTF17
74.
52.0
±0.0
50.520.1% 40.4% 19,222249,4642,293 (41.1)3,297 (59.1)Public
Anonymous submission
MOTDT17
75. online method using public detections
50.9
±0.0
52.717.5% 35.7% 24,069250,7682,474 (44.5)5,317 (95.7)Public
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.
MOTbyReID
76. online method using public detections
43.6
±0.0
37.117.6% 36.3% 35,725270,03612,347 (236.8)11,408 (218.8)Public
Anonymous submission
MOT17ZH
77. online method using public detections
51.1
±0.0
53.416.7% 35.5% 20,309253,2452,549 (46.2)5,910 (107.2)Public
Anonymous submission
MOLF
78. using public detections
50.9
±0.0
46.718.3% 34.6% 29,398242,8374,535 (79.6)5,343 (93.8)Public
Anonymous submission
MMHT17
79. using public detections
52.8
±0.0
53.320.3% 37.5% 25,401238,4132,596 (45.0)4,103 (71.1)Public
Anonymous submission
MHT_ReID7
80. online method using public detections
46.5
±0.0
46.918.8% 40.3% 22,203276,3743,386 (66.4)8,521 (167.0)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
MHT_DAM
81. using public detections
50.7
±0.0
47.220.8% 36.9% 22,875252,8892,314 (41.9)2,865 (51.9)Public
C. Kim, F. Li, A. Ciptadi, J. Rehg. Multiple Hypothesis Tracking Revisited. In ICCV, 2015.
MHT_bLSTM
82. online method using public detections
47.5
±0.0
51.918.2% 41.7% 25,981268,0422,069 (39.4)3,124 (59.5)Public
C. Kim, F. Li, J. Rehg. Multi-object Tracking with Neural Gating Using Bilinear LSTM. In ECCV, 2018.
MFT
83. online method using public detections
53.1
±0.0
50.120.4% 39.4% 35,295225,6063,681 (61.3)6,271 (104.5)Public
Anonymous submission
MCLT17
84. online method
54.2
±0.0
63.524.0% 38.1% 23,602233,7831,208 (20.6)2,394 (40.9)Public
Anonymous submission
MASS
85. online method using public detections
46.9
±0.0
46.016.9% 36.3% 25,733269,1164,478 (85.6)11,994 (229.3)Public
H. Karunasekera, H. Wang, H. Zhang. Multiple Object Tracking With Attention to Appearance, Structure, Motion and Size. In IEEE Access, 2019.
LT17
86. using public detections
47.7
±0.0
45.217.3% 36.0% 27,856263,0624,042 (75.7)9,183 (172.0)Public
Anonymous submission
LSST17O
87. using public detections
52.7
±0.0
57.917.9% 36.6% 22,512241,9362,167 (37.9)7,443 (130.3)Public
Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
LSST17
88. online method using public detections
54.7
±0.0
62.320.4% 40.1% 26,091228,4341,243 (20.9)3,726 (62.6)Public
Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
LSMT
89. online method
51.9
±0.0
53.517.4% 35.0% 18,672250,6622,257 (40.6)5,733 (103.2)Public
Anonymous submission
Lif_T
90. online method using public detections
60.5
±0.0
65.627.0% 33.6% 14,966206,6191,189 (18.8)3,476 (54.8)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
lbc_mot
91. using public detections
49.8
±0.0
52.320.3% 36.2% 20,963259,5382,638 (48.9)5,303 (98.2)Public
Anonymous submission
Lab031
92. using public detections
46.9
±0.0
48.117.7% 36.1% 31,634263,9383,795 (71.3)10,498 (197.3)Public
Anonymous submission
KVIOU
93. using public detections
46.6
±0.0
44.017.3% 38.1% 34,838262,0084,379 (81.8)7,844 (146.4)Public
Anonymous submission
JOINT_TRAC
94. online method
29.4
±0.0
34.512.6% 42.3% 132,192260,8085,397 (100.4)10,704 (199.0)Public
Anonymous submission
JDT
95. online method
47.4
±0.0
50.116.8% 37.2% 26,910267,3312,760 (52.5)6,211 (118.0)Public
Anonymous submission
jCC
96. using public detections
51.2
±0.0
54.520.9% 37.0% 25,937247,8221,802 (32.1)2,984 (53.2)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.
JBNOT
97. online method using public detections
52.6
±0.0
50.819.7% 35.8% 31,572232,6593,050 (51.9)3,792 (64.5)Public
R. Henschel, Y. Zou, B. Rosenhahn. Multiple People Tracking using Body and Joint Detections. In CVPRW, 2019.
ISE_MOT17R
98. online method using public detections
60.1
±0.0
56.428.5% 28.1% 23,168199,4832,556 (39.5)3,182 (49.2)Public
MIFT
ISE_MOT
99.
58.6
±0.0
54.727.0% 29.8% 23,033208,0452,368 (37.5)3,247 (51.4)Public
Anonymous submission
ISDH_HDAv2
100. using public detections
54.5
±0.0
65.926.4% 32.1% 46,693207,0933,010 (47.6)6,000 (94.8)Public
MM-008988/ IEEE Transactions on Multimedia
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
IOU17
101. using public detections
45.5
±0.0
39.415.7% 40.5% 19,993281,6435,988 (119.6)7,404 (147.8)Public
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.
IDGA
102. online method using public detections
52.6
±0.0
61.323.6% 40.2% 29,049236,8301,402 (24.2)2,613 (45.0)Public
Anonymous submission
HTBT
103. online method using public detections
52.3
±0.0
54.522.5% 36.4% 28,743238,2681,959 (33.9)2,973 (51.5)Public
Anonymous submission
HISP_T17
104. using public detections
44.6
±0.0
38.815.1% 38.8% 25,478276,39510,617 (208.1)7,487 (146.8)Public
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.
HISP_DAL17
105. online method using public detections
45.4
±0.0
39.914.8% 39.2% 21,820277,4738,727 (171.7)7,147 (140.6)Public
N. Baisa. Robust Online Multi-target Visual Tracking using a HISP Filter with Discriminative Deep Appearance Learning. In CoRR, 2019.
HDTR
106. online method using public detections
54.1
±0.0
48.423.3% 34.8% 18,002238,8181,895 (32.9)2,693 (46.7)Public
HAM_SADF17
107. using public detections
48.3
±0.0
51.117.1% 41.7% 20,967269,0381,871 (35.8)3,020 (57.7)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.
GOTURN_3B
108. online method
44.3
±0.0
38.513.0% 43.2% 30,302279,1444,861 (96.2)5,277 (104.4)Public
Anonymous submission
GoturnM17
109. online method using public detections
38.3
±0.0
25.79.4% 47.1% 55,381282,67010,328 (207.0)9,849 (197.4)Public
Anonymous submission
GNNT
110. online method
-523.7
±0.0
9.033.6% 27.2% 3,318,414185,81915,019 (223.9)4,763 (71.0)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
GNNMOT
111. online method using public detections
42.0
±0.0
29.312.0% 50.0% 23,294299,6944,377 (93.4)3,847 (82.1)Public
Anonymous submission
GM_PHD_D
112. using public detections
44.0
±0.0
34.214.8% 39.4% 19,135283,53013,556 (272.5)13,821 (277.8)Public
Anonymous submission
GM_PHD
113. online method using public detections
42.1
±0.0
33.911.9% 42.7% 18,214297,64610,698 (226.4)10,864 (229.9)Public
Anonymous submission
GM_PHD
114. online method using public detections
36.4
±0.0
33.94.1% 57.3% 23,723330,7674,607 (111.3)11,317 (273.5)Public
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.
GMPHD_SHA
115. using public detections
43.7
±0.0
39.211.7% 43.0% 25,935287,7583,838 (78.3)5,056 (103.2)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.
GMPHD_Rd17
116. using public detections
46.8
±0.0
54.119.7% 33.3% 38,452257,6783,865 (71.1)8,097 (149.0)Public
N. Baisa. Occlusion-robust Online Multi-object Visual Tracking using a GM-PHD Filter with a CNN-based Re-identification. In , 2019.
GMPHD_N1Tr
117. using public detections
42.1
±0.0
33.911.9% 42.7% 18,214297,64610,698 (226.4)10,864 (229.9)Public
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.
GMPHD_KCF
118. using public detections
39.6
±0.0
36.68.8% 43.3% 50,903284,2285,811 (117.1)7,414 (149.4)Public
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.
GMPHD_DAL
119. online method using public detections
44.4
±0.0
36.214.9% 39.4% 19,170283,38011,137 (223.7)13,900 (279.3)Public
N. Baisa. Online Multi-object Visual Tracking using a GM-PHD Filter with Deep Appearance Learning. In 22nd International Conference on Information Fusion, 2019.
GMPHDOGM17
120. online method
49.9
±0.0
47.119.7% 38.0% 24,024255,2773,125 (57.1)3,540 (64.6)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.
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
GMOT
121. using public detections
55.4
±0.0
57.922.7% 34.7% 20,608229,5111,403 (23.7)2,765 (46.6)Public
LXD, KHW @ HRI-SH
GLMBS3
122. online method
38.0
±0.0
32.39.3% 52.8% 38,874304,0166,963 (151.0)3,927 (85.2)Public
Anonymous submission
GF
123. online method
45.0
±0.0
39.115.0% 39.0% 22,387277,33510,397 (204.5)7,421 (145.9)Public
Anonymous submission
FWT
124. online method using public detections
51.3
±0.0
47.621.4% 35.2% 24,101247,9212,648 (47.2)4,279 (76.3)Public
R. Henschel, L. Leal-Taixé, D. Cremers, B. Rosenhahn. Fusion of Head and Full-Body Detectors for Multi-Object Tracking. In Trajnet CVPRW, 2018.
FPSN
125.
44.9
±0.0
48.416.5% 35.8% 33,757269,9527,136 (136.8)14,491 (277.8)Public
S. Lee, E. Kim. Multiple Object Tracking via Feature Pyramid Siamese Networks. In IEEE ACCESS, 2018.
FFT
126. using public detections
56.5
±0.0
51.026.2% 26.7% 23,746215,9715,672 (91.9)5,474 (88.7)Public
Anonymous submission
FAMNet
127. using public detections
52.0
±0.0
48.719.1% 33.4% 14,138253,6163,072 (55.8)5,318 (96.6)Public
P. Chu, H. Ling. FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking. In ICCV, 2019.
eTC17
128. using public detections
51.9
±0.0
58.123.1% 35.5% 36,164232,7832,288 (38.9)3,071 (52.3)Public
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.
ENFT17
129.
52.8
±0.0
57.123.1% 36.8% 26,754237,9091,667 (28.8)2,557 (44.2)Public
BUAA
eHAF17
130. using public detections
51.8
±0.0
54.723.4% 37.9% 33,212236,7721,834 (31.6)2,739 (47.2)Public
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.
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
EDMT17
131. using public detections
50.0
±0.0
51.321.6% 36.3% 32,279247,2972,264 (40.3)3,260 (58.0)Public
J. Chen, H. Sheng, Y. Zhang, Z. Xiong. Enhancing Detection Model for Multiple Hypothesis Tracking. In BMTT-PETS CVPRw, 2017.
EDA_GNN
132. online method
45.5
±0.0
40.515.6% 40.6% 25,685277,6634,091 (80.5)5,579 (109.8)Public
Paper ID 2713
EAMTT
133. using public detections
42.6
±0.0
41.812.7% 42.7% 30,711288,4744,488 (91.8)5,720 (117.0)Public
R. Sanchez-Matilla, F. Poiesi, A. Cavallaro. Online Multi-target Tracking with Strong and Weak Detections. In Computer Vision -- ECCV 2016 Workshops, 2016.
E2EM
134.
47.5
±0.0
48.816.5% 37.5% 20,655272,1873,632 (70.2)12,712 (245.6)Public
Anonymous submission
D_SST_V1
135.
42.7
±0.0
46.111.8% 44.4% 18,861298,9895,531 (117.7)13,775 (293.0)Public
Anonymous submission
DualAtte
136. online method
48.4
±0.0
43.717.6% 39.0% 24,915262,6543,423 (64.0)5,192 (97.1)Public
Anonymous submission
DTBasline
137. online method using public detections
51.1
±0.0
53.416.7% 35.5% 20,309253,2452,549 (46.2)5,910 (107.2)Public
Anonymous submission
DS_TW_F
138.
45.7
±0.0
50.910.8% 75.4% 6,528298,3681,329 (28.2)3,180 (67.5)Public
Anonymous submission
DS_MOT
139. using public detections
56.1
±0.0
52.721.1% 35.4% 8,866235,4493,609 (61.9)3,777 (64.8)Public
Anonymous submission
DSA_MOT17
140. using public detections
45.0
±0.0
43.615.8% 39.2% 21,442286,4822,491 (50.6)3,824 (77.7)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
DMAN
141. using public detections
48.2
±0.0
55.719.3% 38.3% 26,218263,6082,194 (41.2)5,378 (100.9)Public
J. Zhu, H. Yang, N. Liu, M. Kim, W. Zhang, M. Yang. Online Multi-Object Tracking with Dual Matching Attention Networks. In ECCV, 2018.
DGCT
142. using public detections
54.5
±0.0
51.321.0% 35.4% 10,471243,1432,865 (50.3)4,889 (85.9)Public
CJY, HYW, KHW @ HRI-SH
DEEP_TAMA
143. online method using public detections
50.3
±0.0
53.519.2% 37.5% 25,479252,9962,192 (39.7)3,978 (72.1)Public
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.
DeepMP17
144. using public detections
50.4
±0.0
52.318.8% 38.7% 22,535255,3561,868 (34.1)3,473 (63.4)Public
DeepMOTRPN
145. online method using public detections
48.1
±0.0
43.017.6% 38.6% 26,490262,5783,696 (69.1)5,353 (100.1)Public
Anonymous submission
dcor
146. using public detections
45.0
±0.0
34.015.4% 38.2% 30,231275,2654,801 (93.7)8,498 (165.9)Public
Anonymous submission
DCORV2
147. using public detections
45.5
±0.0
36.114.6% 40.4% 21,161282,9013,592 (72.0)7,696 (154.4)Public
Anonymous submission
DAN__test
148. using public detections
43.0
±0.0
43.313.5% 40.0% 30,367283,5337,576 (152.3)14,990 (301.3)Public
Anonymous submission
DAM_MOT
149. using public detections
47.0
±0.0
48.716.9% 38.1% 28,933267,8962,140 (40.7)2,756 (52.5)Public
Multi Object Tracking using Deep Structural Cost Minimization in Data Association
DAIST_
150. using public detections
52.1
±0.0
53.819.7% 33.6% 29,931237,9132,689 (46.5)5,600 (96.8)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
CTRACKER
151. online method using public detections
39.4
±0.0
26.113.4% 42.5% 16,249307,90017,592 (387.2)14,508 (319.3)Public
Anonymous submission
CRF_TRA
152. online method using public detections
53.1
±0.0
53.724.2% 30.7% 27,194234,9912,518 (43.2)4,918 (84.3)Public
Anonymous submission
CoCT
153. using public detections
50.1
±0.0
55.623.9% 35.4% 49,887229,3912,075 (35.0)4,304 (72.5)Public
Anonymous submission
cnt_klt
154. online method
48.0
±0.0
57.819.0% 31.6% 63,207228,7831,215 (20.4)4,134 (69.5)Public
Anonymous submission
CMT
155. using public detections
51.8
±0.0
60.719.6% 42.8% 29,528240,9601,217 (21.2)2,008 (35.0)Public
#Submission: TIP-21190-2019
CGHA_MOT
156. using public detections
41.2
±0.0
44.08.3% 45.9% 25,462299,1127,294 (155.2)18,655 (397.0)Public
Anonymous submission
CASC_MOT
157. using public detections
42.3
±0.0
46.89.1% 44.1% 21,035300,7973,616 (77.4)16,656 (356.7)Public
Anonymous submission
cascademot
158. online method
41.8
±0.0
34.215.2% 38.7% 27,816288,76811,535 (236.3)14,800 (303.2)Public
Anonymous submission
c3d_Track
159.
41.5
±0.0
40.210.7% 48.5% 33,332292,9313,890 (80.9)11,454 (238.2)Public
Anonymous submission
baitrack
160. online method
37.6
±0.0
20.321.0% 30.9% 99,085244,0018,808 (155.2)6,708 (118.2)Public
Anonymous submission
TrackerMOTAIDF1MTMLFPFNID Sw.FragDetector
AReid17
161.
51.4
±0.0
53.919.2% 32.3% 30,079241,3642,993 (52.3)6,373 (111.4)Public
Anonymous submission
AM_ADM17
162. online method using public detections
48.1
±0.0
52.113.4% 39.7% 25,061265,4952,214 (41.8)5,027 (94.9)Public
S. Lee, M. Kim, S. Bae, Learning Discriminative Appearance Models for Online Multi-Object Tracking with Appearance Discriminability Measures, In IEEE Access, 2018.
Alex1
163. using public detections
56.1
±0.0
55.022.1% 34.9% 12,627232,9562,097 (35.7)3,398 (57.9)Public
Anonymous submission
Alex
164. using public detections
47.6
±0.0
49.813.2% 41.4% 16,028277,1102,731 (53.7)8,481 (166.7)Public
Anonymous submission
AFN17
165. using public detections
51.5
±0.0
46.920.6% 35.5% 22,391248,4202,593 (46.3)4,308 (77.0)Public
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.
AEb_O
166. using public detections
46.4
±0.0
44.916.5% 41.4% 17,030283,2652,266 (45.5)5,053 (101.5)Public
Anonymous submission
AEb
167. using public detections
48.1
±0.0
46.017.7% 39.5% 16,839273,8192,350 (45.7)5,275 (102.5)Public
K. Ho, J. Keuper, M. Keuper. Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts. In , 2020.
98K
168. using public detections
40.8
±0.0
37.015.6% 38.1% 32,312298,1743,514 (74.5)4,991 (105.8)Public
Anonymous submission
2MPT
169. using public detections
48.1
±0.0
52.917.4% 39.6% 30,650260,1331,860 (34.5)2,784 (51.7)Public
Anonymous submission
SequencesFramesTrajectoriesBoxes
21177572355564228

Difficulty Analysis

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

MOT17-01-DPM

MOT17-01-DPM

(0.0% MOTA)

MOT17-08-FRCNN

MOT17-08-FRCNN

(0.0% MOTA)

MOT17-12-SDP

MOT17-12-SDP

(0.0% MOTA)

...

...

MOT17-06-DPM

MOT17-06-DPM

(0.0% MOTA)

MOT17-14-SDP

MOT17-14-SDP

(0.0% 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.

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.