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!

TrackerAvg RankMOTAMOTPFAFMTMLFPFNID Sw.FragHzDetector
MDPNN
1. online method using public detections
23.4
37.6
±12.5
71.71.415.8% 26.8% 7,93329,3971,026 (19.7)2,024 (38.8)1.9Public
A. Sadeghian, A. Alahi, S. Savarese. Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies. In arXiv preprint arXiv:1701.01909, 2017.
JointMC
2. using public detections
20.1
35.6
±18.9
71.91.823.2% 39.3% 10,58028,508457 (8.5)969 (18.1)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.
RAR15pub
3. online method using public detections
20.8
35.1
±12.5
70.91.213.0% 42.3% 6,77132,717381 (8.1)1,523 (32.6)5.4Public
Anonymous ICCV submission
mLK
4. online method using public detections
16.7
35.1
±12.9
71.51.012.3% 38.3% 5,67833,815383 (8.5)1,175 (26.1)1.0Public
Yuan Zhang, Di Xie and Shiliang Pu (Hikvision Research Institute)
TSMLCDEnew
5. using public detections
17.1
34.3
±13.1
71.71.414.0% 39.4% 7,86931,908618 (12.9)959 (20.0)6.5Public
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.
QuadMOT
6. using public detections
20.4
33.8
±14.8
73.41.412.9% 36.9% 7,89832,061703 (14.7)1,430 (29.9)3.7Public
J. Son, M. Baek, M. Cho, B. Han. Multi-Object Tracking with Quadruplet Convolutional Neural Networks. In CVPR, 2017.
NOMT
7. using public detections
15.5
33.7
±16.2
71.91.312.2% 44.0% 7,76232,547442 (9.4)823 (17.5)11.5Public
W. Choi. Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor. In ICCV, 2015.
TDAM
8. online method using public detections
21.4
33.0
±9.8
72.81.713.3% 39.1% 10,06430,617464 (9.2)1,506 (30.0)5.9Public
Y. Min, J. Yunde. Temporal Dynamic Appearance Modeling for Online Multi-Person Tracking. In arXiv:1510.02906, 2015.
HAF
9. using public detections
21.4
33.0
±17.8
71.71.716.4% 44.9% 9,59331,204376 (7.6)804 (16.3)0.6Public
Anonymous submission
CDA_DDALpb
10. online method using public detections
26.3
32.8
±10.6
70.70.99.7% 42.2% 4,98335,690614 (14.7)1,583 (37.8)2.3Public
S. Bae and K. Yoon, Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking, In IEEE TPAMI, 2017.
TrackerAvg RankMOTAMOTPFAFMTMLFPFNID Sw.FragHzDetector
MOTBKCF
11. online method using public detections
23.4
32.4
±15.3
71.71.514.1% 42.0% 8,91232,112501 (10.5)1,058 (22.2)0.2Public
Anonymous submission
MHT_DAM
12. using public detections
21.2
32.4
±15.6
71.81.616.0% 43.8% 9,06432,060435 (9.1)826 (17.3)0.7Public
C. Kim, F. Li, A. Ciptadi, J. Rehg. Multiple Hypothesis Tracking Revisited. In ICCV, 2015.
JAM
13. online method using public detections
24.9
32.0
±14.6
71.21.010.3% 43.6% 5,71435,473562 (13.3)1,217 (28.8)0.0Public
Anonymous submission
CF_MCMC
14. using public detections
33.5
31.4
±11.3
69.81.510.3% 40.9% 8,79832,541814 (17.3)1,711 (36.4)3.2Public
Anonymous submission
MPTCNN
15. online method using public detections
29.7
30.9
±12.9
70.11.39.4% 43.7% 7,37434,623484 (11.1)1,582 (36.2)0.6Public
Anonymous submission
TSSRC_2015
16. online method using public detections
26.8
30.5
±17.1
71.01.814.6% 41.1% 10,65031,445612 (12.5)1,585 (32.5)34.3Public
Anonymous submission
MDP
17. online method using public detections
29.1
30.3
±14.6
71.31.713.0% 38.4% 9,71732,422680 (14.4)1,500 (31.8)1.1Public
Y. Xiang, A. Alahi, S. Savarese. Learning to Track: Online Multi-Object Tracking by Decision Making. In International Conference on Computer Vision (ICCV), 2015.
EAGS
18. using public detections
23.4
30.0
±15.0
71.41.715.8% 37.7% 9,99431,8941,149 (23.9)1,231 (25.6)192.8Public
#MM-007925 Enhancing Association Graph with Super-voxel for Multi-target Tracking
CNNTCM
19. using public detections
24.3
29.6
±13.9
71.81.311.2% 44.0% 7,78634,733712 (16.4)943 (21.7)1.7Public
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.
SCEA
20. online method using public detections
26.0
29.1
±12.2
71.11.08.9% 47.3% 6,06036,912604 (15.1)1,182 (29.6)6.8Public
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.
TrackerAvg RankMOTAMOTPFAFMTMLFPFNID Sw.FragHzDetector
SiameseCNN
21. using public detections
25.4
29.0
±15.1
71.20.98.5% 48.4% 5,16037,798639 (16.6)1,316 (34.2)52.8Public
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.
TBX
22. using public detections
36.7
27.5
±13.3
70.61.410.4% 45.8% 7,96835,810759 (18.2)1,528 (36.6)0.1Public
R. Henschel, L. Leal-Taixé, B. Rosenhahn, K. Schindler. Tracking with multi-level features. In arXiv:1607.07304, 2016.
LFNF
23. using public detections
28.3
27.1
±11.4
72.10.65.1% 50.9% 3,53440,1441,101 (31.8)1,171 (33.8)4.0Public
Anonymous submission
oICF
24. online method using public detections
33.7
27.1
±14.9
70.01.36.4% 48.7% 7,59436,757454 (11.3)1,660 (41.3)1.4Public
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.
TO
25. using public detections
25.4
25.7
±13.5
72.20.84.3% 57.4% 4,77940,511383 (11.2)600 (17.6)5.0Public
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.
MCFCOS_CNN
26. online method using public detections new
36.6
25.5
±19.6
71.92.19.3% 34.4% 12,34431,3782,064 (42.2)2,618 (53.5)0.5Public
Anonymous submission
2D_SPL
27. using public detections
37.0
25.2
±14.6
71.21.45.1% 50.3% 8,03737,190706 (17.9)1,278 (32.4)0.8Public
Anonymous submission
LP_SSVM
28. using public detections
28.4
25.2
±13.7
71.71.45.8% 53.0% 8,36936,932646 (16.2)849 (21.3)41.3Public
S. Wang, C. Fowlkes. Learning Optimal Parameters for Multi-target Tracking with Contextual Interactions. In International Journal of Computer Vision, 2016.
ELP
29. using public detections
33.6
25.0
±10.8
71.21.37.5% 43.8% 7,34537,3441,396 (35.6)1,804 (46.0)5.7Public
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.
GMC
30. online method using public detections
31.9
25.0
±13.8
70.72.110.5% 44.4% 12,04633,441599 (13.1)1,246 (27.3)28.9Public
Anonymous submission
TrackerAvg RankMOTAMOTPFAFMTMLFPFNID Sw.FragHzDetector
MVM
31. online method using public detections new
37.7
25.0
±11.3
70.90.83.2% 48.7% 4,66640,1181,302 (37.5)2,084 (60.1)13.8Public
Anonymous submission
MTT
32. online method using public detections
35.3
25.0
±13.2
71.11.34.0% 53.0% 7,69137,833569 (14.8)1,218 (31.7)1.9Public
Anonymous submission
AR_WLS
33. using public detections
35.5
24.9
±14.5
71.01.46.1% 52.4% 8,07137,543551 (14.2)1,297 (33.3)2.1Public
Anonymous submission
MPM
34. online method using public detections
37.0
24.8
±10.9
71.20.72.9% 50.2% 4,06140,8461,319 (39.4)2,017 (60.2)8.6Public
Anonymous submission
LINF1
35. using public detections
28.1
24.5
±15.4
71.31.05.5% 64.6% 5,86440,207298 (8.6)744 (21.5)7.5Public
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.
TFMOT
36. online method using public detections
27.6
23.8
±11.9
71.30.84.9% 62.0% 4,53341,873404 (12.7)792 (24.9)11.3Public
Joint Cost Minimization for Multi-Object Tracking
JCM_MOT
37. online method using public detections
28.6
23.8
±12.0
71.30.84.9% 62.0% 4,53341,873404 (12.7)792 (24.9)11.3Public
Joint Cost Minimization for Multi-Object Tracking
JPDA_m
38. using public detections
31.9
23.8
±15.1
68.21.15.0% 58.1% 6,37340,084365 (10.5)869 (25.0)32.6Public
H. Rezatofighi, A. Milan, Z. Zhang, Q. Shi, A. Dick, I. Reid. Joint Probabilistic Data Association Revisited. In ICCV, 2015.
MTTCNN
39. using public detections
36.1
23.5
±15.3
71.40.92.6% 54.0% 5,44840,802739 (22.0)1,208 (36.0)1.9Public
Anonymous submission
A_TKF
40. online method using public detections new
36.1
23.5
±13.3
70.51.66.4% 48.3% 9,02337,304696 (17.7)1,453 (37.0)180.7Public
Anonymous submission
TrackerAvg RankMOTAMOTPFAFMTMLFPFNID Sw.FragHzDetector
MotiCon
41. using public detections
42.5
23.1
±16.4
70.91.84.7% 52.0% 10,40435,8441,018 (24.4)1,061 (25.5)1.4Public
L. Leal-Taixé, M. Fenzi, A. Kuznetsova, B. Rosenhahn, S. Savarese. Learning an image-based motion context for multiple people tracking. In CVPR, 2014.
Otakudj
42. online method using public detections
36.8
23.0
±14.0
70.72.217.8% 19.6% 12,76729,9144,625 (90.1)3,524 (68.7)11.6Public
Anonymous submission
SegTrack
43. using public detections
36.6
22.5
±15.2
71.71.45.8% 63.9% 7,89039,020697 (19.1)737 (20.2)0.2Public
A. Milan, L. Leal-Taixé, K. Schindler, I. Reid. Joint Tracking and Segmentation of Multiple Targets. In CVPR, 2015.
EAMTTpub
44. online method using public detections
39.4
22.3
±14.2
70.81.45.4% 52.7% 7,92438,982833 (22.8)1,485 (40.6)12.2Public
R. Sanchez-Matilla, F. Poiesi, A. Cavallaro "Multi-target tracking with strong and weak detections" in BMTT ECCVw 2016
PAOT
45. online method using public detections
40.3
21.7
±11.8
71.21.53.7% 49.1% 8,42238,4541,231 (32.9)2,005 (53.6)1,112.1Public
Thesis available in August 2017
OMT_DFH
46. online method using public detections
38.4
21.2
±17.2
69.92.37.1% 46.5% 13,21834,657563 (12.9)1,255 (28.8)28.6Public
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.
OLTT
47. using public detections
40.4
21.0
±12.7
71.21.43.3% 54.4% 8,37639,368794 (22.1)1,199 (33.4)10.9Public
Anonymous submission
simRNN
48. using public detections
47.0
20.3
±12.0
71.01.65.0% 54.8% 9,40638,588966 (26.0)1,464 (39.4)0.4Public
Anonymous submission
LP2D
49. using public detections
37.8
19.8
±14.2
71.22.06.7% 41.2% 11,58036,0451,649 (39.9)1,712 (41.4)112.1Public
MOT baseline: Linear programming on 2D image coordinates.
DCO_X
50. using public detections
40.4
19.6
±14.1
71.41.85.1% 54.9% 10,65238,232521 (13.8)819 (21.7)0.3Public
A. Milan, K. Schindler, S. Roth. Multi-Target Tracking by Discrete-Continuous Energy Minimization. In IEEE PAMI, 2016.
TrackerAvg RankMOTAMOTPFAFMTMLFPFNID Sw.FragHzDetector
CEM
51. using public detections
42.3
19.3
±17.5
70.72.58.5% 46.5% 14,18034,591813 (18.6)1,023 (23.4)1.1Public
A. Milan, S. Roth, K. Schindler. Continuous Energy Minimization for Multitarget Tracking. In IEEE TPAMI, 2014.
RNN_LSTM
52. online method using public detections
42.3
19.0
±15.2
71.02.05.5% 45.6% 11,57836,7061,490 (37.0)2,081 (51.7)165.2Public
A. Milan, S. Rezatofighi, A. Dick, I. Reid, K. Schindler. Online Multi-Target Tracking using Recurrent Neural Networks. In AAAI, 2017.
RMOT
53. online method using public detections
45.2
18.6
±17.5
69.62.25.3% 53.3% 12,47336,835684 (17.1)1,282 (32.0)7.9Public
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.
TSDA_OAL
54. online method using public detections
41.5
18.6
±17.6
69.72.89.4% 42.3% 16,35032,853806 (17.3)1,544 (33.2)19.7Public
H. Ko. Online multi-person tracking with two-stage data association and online appearance model learning. In IET Computer Vision, 2017.
GMPHD_15
55. online method using public detections
38.4
18.5
±12.7
70.91.43.9% 55.3% 7,86441,766459 (14.3)1,266 (39.5)19.8Public
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
56. using public detections
48.4
18.2
±10.3
71.21.52.8% 54.8% 8,78040,3101,148 (33.4)2,132 (62.0)2.7Public
C. Dicle, O. Camps, M. Sznaier. The Way They Move: Tracking Targets with Similar Appearance. In ICCV, 2013.
ALExTRAC
57. using public detections
47.7
17.0
±12.1
71.21.63.9% 52.4% 9,23339,9331,859 (53.1)1,872 (53.5)3.7Public
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.
GMCSS
58. online method using public detections
50.8
16.7
±14.7
69.22.24.0% 55.1% 12,54338,102562 (14.8)1,619 (42.6)1.5Public
Anonymous submission
TBD
59. using public detections
50.1
15.9
±17.6
70.92.66.4% 47.9% 14,94334,7771,939 (44.7)1,963 (45.2)0.7Public
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.
GSCR
60. online method using public detections
40.2
15.8
±10.5
69.41.31.8% 61.0% 7,59743,633514 (17.7)1,010 (34.8)28.1Public
L. Fagot-Bouquet, R. Audigier, Y. Dhome, F. Lerasle. Online multi-person tracking based on global sparse collaborative representations. In ICIP, 2015.
TrackerAvg RankMOTAMOTPFAFMTMLFPFNID Sw.FragHzDetector
SSM_DPM
61. online method using public detections
38.5
15.1
±20.5
70.43.211.4% 44.5% 18,31933,193621 (13.5)1,229 (26.7)28.9Public
Anonymous submission
TC_ODAL
62. online method using public detections
52.8
15.1
±15.0
70.52.23.2% 55.8% 12,97038,538637 (17.1)1,716 (46.0)1.7Public
S. Bae, K. Yoon. Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning. In CVPR, 2014.
DP_NMS
63. using public detections
43.9
14.5
±13.9
70.82.36.0% 40.8% 13,17134,8144,537 (104.7)3,090 (71.3)444.8Public
H. Pirsiavash, D. Ramanan, C. Fowlkes. Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects. In CVPR, 2011.
FOT
64. online method using public detections
34.3
10.8
±17.0
71.42.115.4% 29.7% 12,05631,35711,373 (232.3)3,341 (68.2)96.4Public
Anonymous submission
cuMOT
65. online method using public detections
40.6
5.0
±11.3
68.10.51.1% 77.8% 2,98754,604789 (70.9)1,176 (105.7)28.9Public
Anonymous submission
LDCT
66. online method using public detections
38.1
4.7
±41.3
71.72.411.4% 32.5% 14,06632,15612,348 (259.1)2,918 (61.2)20.7Public
F. Solera, S. Calderara, R. Cucchiara. Learning to Divide and Conquer for Online Multi-Target Tracking. In ICCV, 2015

Benchmark Statistics

SequencesFramesTrajectoriesBoxes
11578372161440

Difficulty Analysis

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

TUD-Crossing

TUD-Crossing

(60.5% MOTA)

PETS09-S2L2

PETS09-S2L2

(40.9% MOTA)

ETH-Jelmoli

ETH-Jelmoli

(36.3% MOTA)

...

...

Venice-1

Venice-1

(20.3% MOTA)

ADL-Rundle-1

ADL-Rundle-1

(13.2% 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.
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 [2].
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] 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.