MOT16 Results

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


Showing only entries that use public detections!

TrackerAvg RankMOTAIDF1 MTMLFPFNID Sw.FragHzDetector
FullTest
1. online method using public detections new
36.0
-57.8
±34.0
0.70.0% 99.9% 107,344180,34856 (51.6)295 (271.9)236.8Public
Anonymous submission
rookie_ksp
2. using public detections
44.9
24.8
±7.7
11.52.4% 66.1% 1,421132,3613,343 (122.0)4,886 (178.3)19.7Public
Anonymous submission
CMRZF
3. using public detections
33.7
30.4
±10.8
29.42.9% 70.5% 1,421124,4831,030 (32.5)733 (23.1)16.9Public
Anonymous submission
DP_NMS
4. using public detections
30.8
26.2
±9.3
31.24.1% 67.5% 3,689130,557365 (12.9)638 (22.5)5.9Public
H. Pirsiavash, D. Ramanan, C. Fowlkes. Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects. In CVPR, 2011.
JPDA_m
5. using public detections
32.5
26.2
±6.1
0.04.1% 67.5% 3,689130,549365 (12.9)638 (22.5)22.2Public
H. Rezatofighi, A. Milan, Z. Zhang, Q. Shi, A. Dick, I. Reid. Joint Probabilistic Data Association Revisited. In ICCV, 2015.
CppSORT
6. online method using public detections
36.3
31.5
±9.0
27.74.3% 59.9% 3,048120,2781,587 (46.6)2,239 (65.8)687.1Public
S. Murray. Real-Time Multiple Object Tracking - A Study on the Importance of Speed. In arXiv preprint arXiv:1709.03572, 2017.
GMPHD_HDA
7. online method using public detections
31.5
30.5
±6.9
33.44.6% 59.7% 5,169120,970539 (16.0)731 (21.7)13.6Public
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.
SMOT
8. using public detections
51.8
29.7
±7.3
0.05.3% 47.7% 17,426107,5523,108 (75.8)4,483 (109.3)0.2Public
C. Dicle, O. Camps, M. Sznaier. The Way They Move: Tracking Targets with Similar Appearance. In ICCV, 2013.
GM_PHD_N1T
9. online method using public detections
40.6
31.6
±8.6
19.75.5% 55.2% 4,767115,6454,348 (118.9)3,986 (109.0)9.9Public
Anonymous submission
ERCTracker
10. online method using public detections
32.8
32.3
±9.4
29.25.7% 62.1% 1,193121,333953 (28.5)943 (28.2)32.0Public
Anonymous submission
TrackerAvg RankMOTAIDF1 MTMLFPFNID Sw.FragHzDetector
tMOT
11. using public detections
34.5
28.9
±10.5
32.45.8% 63.0% 3,754125,494468 (15.0)694 (22.3)11.8Public
Anonymous submission
GMPHD_AM
12. online method using public detections
36.8
30.6
±6.7
30.25.9% 53.1% 4,982120,698930 (27.5)1,856 (54.9)7.9Public
Anonymous submission
DQNTracker
13. online method using public detections
38.2
33.7
±13.7
31.76.9% 59.3% 5,210113,8651,744 (46.4)4,184 (111.4)9.9Public
Anonymous submission
TBD
14. using public detections
44.7
33.7
±9.2
0.07.2% 54.2% 5,804112,5872,418 (63.2)2,252 (58.9)1.3Public
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.
OVBT
15. online method using public detections
44.7
38.4
±8.8
37.87.5% 47.3% 11,51799,4631,321 (29.1)2,140 (47.1)0.3Public
Y. Ban, S. Ba, X. Alameda-Pineda, R. Horaud. Tracking Multiple Persons Based on a Variational Bayesian Model. In BMTT 2016, .
CEM
16. using public detections
35.3
33.2
±7.9
0.07.8% 54.4% 6,837114,322642 (17.2)731 (19.6)0.3Public
A. Milan, S. Roth, K. Schindler. Continuous Energy Minimization for Multitarget Tracking. In IEEE TPAMI, 2014.
HISP_T
17. online method using public detections
40.3
35.9
±8.5
0.07.8% 50.1% 6,406107,9052,592 (63.5)2,299 (56.3)4.8Public
Anonymous submission
EAMTT_pub
18. online method using public detections
33.1
38.8
±8.5
42.47.9% 49.1% 8,114102,452965 (22.0)1,657 (37.8)11.8Public
R. Sanchez-Matilla, F. Poiesi, A. Cavallaro "Multi-target tracking with strong and weak detections" in BMTT ECCVw 2016
GMMCP
19. using public detections
36.7
38.1
±7.8
35.58.6% 50.9% 6,607105,315937 (22.2)1,669 (39.5)0.5Public
A. Dehghan, S. Assari, M. Shah.. GMMCP-Tracker:Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking. In CVPR, 2015.
LP2D
20. using public detections
32.3
35.7
±10.1
34.28.7% 50.7% 5,084111,163915 (23.4)1,264 (32.4)49.3Public
MOT baseline: Linear programming on 2D image coordinates.
TrackerAvg RankMOTAIDF1 MTMLFPFNID Sw.FragHzDetector
DeepAC
21. online method using public detections
33.2
38.8
±9.3
33.19.1% 42.8% 5,444103,1742,886 (66.5)6,592 (151.9)21.1Public
Anonymous submission
GMCSS
22. online method using public detections
36.8
38.3
±9.0
44.79.4% 46.6% 16,49195,303735 (15.4)2,122 (44.5)0.4Public
Anonymous submission
LTTSC-CRF
23. using public detections
35.1
37.6
±9.9
42.19.6% 55.2% 11,969101,343481 (10.8)1,012 (22.8)0.6Public
N. Le, A. Heili, M. Odobez. Long-Term Time-Sensitive Costs for CRF-Based Tracking by Detection. In ECCVw, 2016.
CDA_DDALv2
24. online method using public detections
28.3
43.9
±7.8
45.110.7% 44.4% 6,45095,175676 (14.1)1,795 (37.6)0.5Public
S. Bae and K. Yoon, Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking, In IEEE TPAMI, 2017.
oICF
25. online method using public detections
29.8
43.2
±10.2
49.311.3% 48.5% 6,65196,515381 (8.1)1,404 (29.8)0.4Public
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.
LINF1
26. using public detections
28.3
41.0
±9.5
45.711.6% 51.3% 7,89699,224430 (9.4)963 (21.1)4.2Public
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.
SLT
27. online method using public detections
34.3
41.5
±10.4
41.611.7% 37.0% 8,07496,9561,705 (36.4)3,170 (67.7)9.6Public
Anonymous submission
dmot
28. using public detections
29.8
40.7
±8.3
40.612.0% 44.1% 9,31997,992773 (16.7)1,106 (23.9)6.6Public
Anonymous submission
HSFSC
29. online method using public detections
29.5
43.3
±9.1
41.612.0% 43.9% 5,55896,996874 (18.7)1,482 (31.7)3.0Public
Anonymous submission
SAC
30. online method using public detections
29.2
44.6
±9.2
42.712.1% 43.6% 3,92996,285795 (16.8)1,414 (30.0)1.1Public
Anonymous submission
TrackerAvg RankMOTAIDF1 MTMLFPFNID Sw.FragHzDetector
TBSS
31. online method using public detections
29.3
44.6
±9.3
42.612.3% 43.9% 4,13696,128790 (16.7)1,419 (30.0)3.0Public
Anonymous submission
oBot
32. online method using public detections
32.5
42.5
±20.4
40.812.6% 40.7% 10,42092,8921,559 (31.8)1,639 (33.4)2.3Public
Anonymous BMVC submission
ARM16
33. using public detections
32.0
35.3
±7.7
40.312.8% 38.5% 23,52092,1712,334 (47.2)3,516 (71.1)5.9Public
Anonymous submission
HFCLP
34. using public detections
29.5
42.7
±7.6
35.112.9% 40.2% 8,50294,2661,676 (34.7)1,792 (37.1)19.7Public
Anonymous submission
GCRA
35. using public detections new
17.8
48.2
±8.3
48.612.9% 41.1% 5,10488,586821 (16.0)1,117 (21.7)2.8Public
Anonymous submission
STFP
36. online method using public detections
37.8
39.8
±8.9
47.413.0% 41.4% 12,11896,755950 (20.2)2,630 (56.0)0.4Public
Anonymous submission
RAR16pub
37. online method using public detections
26.2
45.9
±9.7
48.813.2% 41.9% 6,87191,173648 (13.0)1,992 (39.8)0.9Public
Anonymous ICCV submission
MOT_M_hun
38. using public detections
31.0
39.0
±10.3
47.513.7% 40.1% 15,34595,029843 (17.6)1,790 (37.4)1.2Public
Anonymous submission
EMOT
39. online method using public detections
29.3
43.0
±8.8
49.213.8% 42.7% 9,52193,672712 (14.6)1,903 (39.1)0.4Public
Anonymous submission
AMIR
40. online method using public detections
19.2
47.2
±7.7
46.314.0% 41.6% 2,68192,856774 (15.8)1,675 (34.1)1.0Public
A. Sadeghian, A. Alahi, S. Savarese. Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies. In ICCV, 2017.
TrackerAvg RankMOTAIDF1 MTMLFPFNID Sw.FragHzDetector
DCCRF16
41. online method using public detections
27.5
44.8
±9.5
39.714.1% 42.3% 5,61394,125968 (20.0)1,378 (28.5)0.1Public
Anonymous submission
JCSTD
42. online method using public detections
25.1
47.4
±8.3
41.114.4% 36.4% 8,07786,6311,266 (24.1)2,696 (51.4)3.3Public
Anonymous submission
PRMOT
43. using public detections
33.3
43.1
±9.3
44.814.5% 41.8% 10,49592,1741,145 (23.2)1,999 (40.4)0.6Public
Anonymous submission
QuadMOT16
44. using public detections
28.8
44.1
±9.4
38.314.6% 44.9% 6,38894,775745 (15.5)1,096 (22.8)1.8Public
J. Son, M. Baek, M. Cho, B. Han. Multi-Object Tracking with Quadruplet Convolutional Neural Networks. In CVPR, 2017.
STAM16
45. online method using public detections
26.8
46.0
±9.1
50.014.6% 43.6% 6,89591,117473 (9.5)1,422 (28.4)0.2Public
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 arXiv preprint arXiv:1708.02843, 2017.
RMFP
46. online method using public detections
32.0
43.4
±9.2
50.414.9% 44.0% 7,55995,015682 (14.2)1,999 (41.7)0.3Public
Anonymous submission
OVMOT
47. online method using public detections
32.5
41.9
±8.8
50.115.0% 43.0% 10,71294,510626 (13.0)2,008 (41.7)0.4Public
Anonymous submission
STbase
48. using public detections new
29.8
43.7
±9.2
50.815.2% 43.0% 8,89193,036662 (13.5)1,844 (37.7)0.4Public
Anonymous submission
overMOT
49. online method using public detections
29.6
43.7
±9.3
50.815.2% 43.0% 8,89193,036662 (13.5)1,844 (37.7)0.4Public
Anonymous submission
MOTDT
50. online method using public detections
19.1
47.6
±8.2
50.915.2% 38.3% 9,25385,431792 (14.9)1,858 (35.0)20.6Public
Anonymous submission
TrackerAvg RankMOTAIDF1 MTMLFPFNID Sw.FragHzDetector
NOSVM
51. using public detections
29.8
43.6
±9.4
51.115.3% 42.8% 9,10692,991718 (14.7)2,084 (42.5)0.4Public
Anonymous submission
HAF16
52. using public detections
21.5
45.7
±8.9
47.215.4% 41.4% 10,03888,319660 (12.8)985 (19.1)0.7Public
Anonymous submission
PSMT
53. using public detections
32.6
43.9
±9.3
50.715.4% 42.8% 9,10992,271944 (19.1)2,036 (41.2)0.3Public
Anonymous submission
JMC
54. using public detections
18.8
46.3
±9.0
46.315.5% 39.7% 6,37390,914657 (13.1)1,114 (22.2)0.8Public
S. Tang, B. Andres, M. Andriluka, B. Schiele. Multi-Person Tracking by Multicuts and Deep Matching. In BMTT, 2016.
NHL
55. using public detections
32.2
45.1
±8.5
32.315.9% 37.3% 12,60585,6911,747 (33.0)2,033 (38.4)0.3Public
Anonymous submission
MHT_DAM
56. using public detections
21.4
45.8
±8.9
46.116.2% 43.2% 6,41291,758590 (11.9)781 (15.7)0.8Public
C. Kim, F. Li, A. Ciptadi, J. Rehg. Multiple Hypothesis Tracking Revisited. In ICCV, 2015.
IMWIS
57. using public detections
20.3
47.0
±9.3
41.816.2% 41.4% 4,84290,901868 (17.3)904 (18.0)0.7Public
Anonymous submission
STMOT
58. using public detections
25.1
45.4
±9.2
53.316.3% 42.8% 8,07190,883561 (11.2)1,548 (30.9)0.3Public
Anonymous submission
ONEEC
59. online method using public detections
23.5
45.3
±9.5
53.716.3% 42.4% 8,42390,821550 (11.0)1,574 (31.4)0.3Public
Anonymous submission
ASSMOT
60. using public detections
18.2
46.0
±9.3
54.416.6% 42.7% 8,04589,959538 (10.6)1,623 (32.0)0.4Public
Anonymous submission
TrackerAvg RankMOTAIDF1 MTMLFPFNID Sw.FragHzDetector
NLLMPa
61. using public detections
15.3
47.6
±10.6
47.317.0% 40.4% 5,84489,093629 (12.3)768 (15.0)8.3Public
E. Levinkov, J. Uhrig, S. Tang, M. Omran, E. Insafutdinov, A. Kirillov, C. Rother, T. Brox, B. Schiele, B. Andres. Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications. In CVPR, 2017.
EDMT
62. using public detections
18.1
45.3
±9.1
47.917.0% 39.9% 11,12287,890639 (12.3)946 (18.3)1.8Public
J. Chen, H. Sheng, Y. Zhang, Z. Xiong. Enhancing Detection Model for Multiple Hypothesis Tracking. In BMTT-PETS CVPRw, 2017.
EAGS16
63. using public detections
13.0
47.4
±10.4
50.117.3% 42.7% 8,36986,931575 (11.0)913 (17.5)197.3Public
#PR-D-17-01373# Enhancing Association Graph with Super-voxel for Multi-target Tracking
DMMOT
64. online method using public detections
17.2
46.1
±11.1
54.817.4% 42.7% 7,90989,874532 (10.5)1,616 (31.9)0.5Public
Anonymous submission
HCC
65. using public detections
10.7
49.3
±10.2
50.717.8% 39.9% 5,33386,795391 (7.5)535 (10.2)0.8Public
Anonymous submission
LMP
66. using public detections
13.3
48.8
±9.8
51.318.2% 40.1% 6,65486,245481 (9.1)595 (11.3)0.5Public
S. Tang, M. Andriluka, B. Andres, B. Schiele. Multiple People Tracking with Lifted Multicut and Person Re-identification. In CVPR, 2017.
NOMT
67. using public detections
14.8
46.4
±9.9
53.318.3% 41.4% 9,75387,565359 (6.9)504 (9.7)2.6Public
W. Choi. Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor. In ICCV, 2015.
FWT
68. using public detections
19.3
47.8
±9.4
44.319.1% 38.2% 8,88685,487852 (16.0)1,534 (28.9)0.6Public
R. Henschel, L. Leal-Taixé, D. Cremers, B. Rosenhahn. A Novel Multi-Detector Fusion Framework for Multi-Object Tracking. In arXiv preprint arXiv:1705.08314, 2017.
MCjoint
69. using public detections
16.8
47.1
±10.8
52.320.4% 46.9% 6,70389,368370 (7.3)598 (11.7)0.6Public
M. Keuper, S. Tang, Z. Yu, B. Andres, T. Brox, B. Schiele. A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects. In CoRR, 2016.

Due to a minor bug in the export script, all results were re-evaluated on April 11, 2016. Here is the old snapshot of the leaderboard.


Benchmark Statistics

SequencesFramesTrajectoriesBoxes
75919759182326

Difficulty Analysis

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

MOT16-03

MOT16-03

(51.6% MOTA)

MOT16-06

MOT16-06

(44.2% MOTA)

MOT16-07

MOT16-07

(38.5% MOTA)

...

...

MOT16-08

MOT16-08

(29.5% MOTA)

MOT16-14

MOT16-14

(24.7% 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.