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 RankMOTAIDF1MTMLFPFNID Sw.FragHzDetector
AFN
1. using public detections
18.0
49.0
±10.2
48.219.1% 35.7% 9,50882,506899 (16.4)1,383 (25.3)0.6Public
Paper ID 4411
AMIR
2. online method using public detections
20.3
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.
AM_ADM
3. online method using public detections
30.0
40.1
±10.1
43.87.1% 46.2% 8,50399,891789 (17.5)1,736 (38.4)5.8Public
Anonymous submission
CDA_DDALv2
4. online method using public detections
27.3
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.
CEM
5. using public detections
34.0
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.
cm_test
6. online method using public detections
30.2
35.4
±20.2
40.36.5% 71.4% 4,427112,889402 (10.6)1,176 (30.9)1.6Public
Anonymous submission
CppSORT
7. online method using public detections
35.3
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.
CSAHD
8. online method using public detections
28.0
43.7
±11.6
45.710.5% 46.1% 8,31893,273984 (20.1)2,164 (44.3)7.0Public
Anonymous submission
DCCRF16
9. online method using public detections
27.7
44.8
±9.8
39.714.1% 42.3% 5,61394,133968 (20.0)1,378 (28.5)0.1Public
H. Zhou, W. Ouyang, J. Cheng, X. Wang, H. Li. Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking. In IEEE Transactions on Circuits and Systems for Video Technology, 2018.
deepS2
10. using public detections
26.1
43.6
±8.1
40.415.4% 41.9% 8,81993,095871 (17.8)851 (17.4)0.7Public
ID 32
TrackerAvg RankMOTAIDF1MTMLFPFNID Sw.FragHzDetector
DMMOT
11. online method using public detections
20.8
46.1
±11.1
54.817.4% 42.7% 7,90989,874532 (10.5)1,616 (31.9)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.
DP_NMS
12. using public detections
29.3
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.
DRT
13. online method using public detections
30.7
34.7
±11.4
41.16.3% 61.8% 6,992111,617460 (11.9)1,127 (29.1)6.2Public
Anonymous submission
DWET
14. online method using public detections
33.3
32.2
±10.4
38.36.2% 63.0% 7,297115,780603 (16.5)1,184 (32.4)11.3Public
Anonymous submission
EAMTT_pub
15. online method using public detections
30.7
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
EDMT
16. using public detections
19.9
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.
eHAF16
17. using public detections
18.4
47.2
±16.8
52.418.6% 42.8% 12,58683,107542 (10.0)787 (14.5)0.5Public
TCSVT-02141-2018
eTC
18. using public detections
15.7
49.2
±9.1
56.117.3% 40.3% 8,40083,702606 (11.2)882 (16.3)0.7Public
Anonymous submission
FWT
19. using public detections
22.0
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. Fusion of Head and Full-Body Detectors for Multi-Object Tracking. In Trajnet CVPRW, 2018.
GCK
20. online method using public detections
40.3
28.7
±8.5
30.63.4% 51.0% 21,436106,4242,217 (53.3)3,277 (78.7)25.1Public
Anonymous submission
TrackerAvg RankMOTAIDF1MTMLFPFNID Sw.FragHzDetector
GCRA
21. using public detections
19.2
48.2
±8.3
48.612.9% 41.1% 5,10488,586821 (16.0)1,117 (21.7)2.8Public
C. Ma, C. Yang, F. Yang, Y. Zhuang, Z. Zhang, H. Jia, X. Xie. Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking. In ICME, 2018.
GMMCP
22. using public detections
35.4
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.
GMPHD_HDA
23. online method using public detections
30.5
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.
GM_PHD_N1T
24. online method using public detections
37.7
33.3
±8.9
25.55.5% 56.0% 1,750116,4523,499 (96.8)3,594 (99.5)9.9Public
N. Baisa, A. Wallace. Development of a N-type GM-PHD Filter for Multiple Target, Multiple Type Visual Tracking. In CoRR, 2017.
HAM_ACT16
25. online method using public detections
26.5
38.1
±8.2
43.37.8% 54.4% 6,976105,434418 (9.9)707 (16.8)8.0Public
HISP_T
26. online method using public detections
36.7
35.9
±8.5
28.97.8% 50.1% 6,412107,9182,594 (63.6)2,298 (56.3)4.8Public
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_T2
27. online method using public detections
35.1
37.2
±8.6
29.77.6% 50.7% 3,323108,8592,370 (58.8)2,234 (55.4)4.8Public
Anonymous submission
INTERA_MOT
28. using public detections
19.2
45.4
±8.6
47.718.1% 38.7% 13,40785,547600 (11.3)930 (17.5)4.3Public
L. Lan, X. Wang, S. Zhang, D. Tao, W. Gao, T. Huang. Interacting Tracklets for Multi-object Tracking. In IEEE Transactions on Image Processing, 2018.
JCmin_MOT
29. online method using public detections
28.5
36.7
±9.1
36.27.5% 54.4% 2,936111,890667 (17.3)831 (21.5)14.8Public
M. Abhijeet Boragule. Joint Cost Minimization for Multi-Object Tracking. In 2017 IEEE International Conference on Advanced Vide and Signale Based Surveillance, 2017.
JCSTD
30. online method using public detections
24.5
47.4
±8.3
41.114.4% 36.4% 8,07686,6381,266 (24.1)2,697 (51.4)8.8Public
Anonymous submission
TrackerAvg RankMOTAIDF1MTMLFPFNID Sw.FragHzDetector
JMC
31. using public detections
20.4
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.
JPDA_m
32. using public detections
30.6
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.
LFNF16
33. using public detections
28.9
43.6
±11.0
41.613.3% 45.7% 6,61695,363836 (17.5)938 (19.7)0.6Public
Sheng H, Hao L, Chen J, et al. Robust Local Effective Matching Model for Multi-Target Tracking. In PCM, 2017
LINF1
34. using public detections
26.8
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.
LMP
35. using public detections
15.5
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.
LP2D
36. using public detections
31.4
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.
LTTSC-CRF
37. using public detections
33.8
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.
MCjoint
38. using public detections
17.4
47.1
±10.8
52.320.4% 46.9% 6,70389,368370 (7.3)598 (11.7)0.6Public
}@article{DBLP:journals/corr/KeuperTYABS16, author = {Margret Keuper and Siyu Tang and Zhongjie Yu and Bjoern Andres and Thomas Brox and Bernt Schiele}, title = {A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects}, journal = {CoRR}, volume = {abs/1607.06317}, year = {2016}, url = {http://arxiv.org/abs/1607.06317}, timestamp = {Wed, 07 Jun 2017 14:41:31 +0200}, biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/KeuperTYABS16}, bibsource = {dblp computer science bibliography, http://dblp.org} }
MHT_bLSTM6
39. using public detections
27.8
42.1
±9.7
47.814.9% 44.4% 11,63793,172753 (15.4)1,156 (23.6)1.8Public
C. Kim, F. Li, J. Rehg. Multi-object Tracking with Neural Gating Using Bilinear LSTM. In ECCV, 2018.
MHT_DAM
40. using public detections
21.3
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.
TrackerAvg RankMOTAIDF1MTMLFPFNID Sw.FragHzDetector
MOTDT
41. online method using public detections
20.5
47.6
±8.2
50.915.2% 38.3% 9,25385,431792 (14.9)1,858 (35.0)20.6Public
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.
MTDF
42. online method using public detections
30.2
45.7
±11.2
40.114.1% 36.4% 12,01884,9701,987 (37.2)3,377 (63.2)1.5Public
Anonymous submission
NLLMPa
43. using public detections
16.3
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.
NOMT
44. using public detections
16.4
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.
oICF
45. online method using public detections
28.3
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.
OVBT
46. online method using public detections
40.7
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, .
PDetTracId
47. online method using public detections
21.7
49.7
±9.4
46.816.7% 37.3% 4,39386,2411,040 (19.7)3,652 (69.3)2.4Public
Anonymous submission
PRT
48. online method using public detections
30.7
40.8
±13.0
44.213.7% 38.3% 15,14391,7921,051 (21.2)2,210 (44.5)6.2Public
Anonymous submission
QuadMOT16
49. using public detections
27.6
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.
RAR16pub
50. online method using public detections
26.4
45.9
±9.7
48.813.2% 41.9% 6,87191,173648 (13.0)1,992 (39.8)0.9Public
K. Fang, Y. Xiang, X. Li, S. Savarese. Recurrent Autoregressive Networks for Online Multi-Object Tracking. In The IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.
TrackerAvg RankMOTAIDF1MTMLFPFNID Sw.FragHzDetector
RC_cluster
51. using public detections new
11.2
53.8
±8.7
46.921.6% 36.9% 4,76478,948518 (9.1)795 (14.0)8.5Public
Anonymous submission
SMOT
52. using public detections
48.0
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.
STAM16
53. online method using public detections
26.0
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 2017 IEEE International Conference on Computer Vision (ICCV), 2017.
TBD
54. using public detections
42.0
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.
TBNMF16
55. online method using public detections
32.0
42.0
±9.2
37.510.4% 44.9% 4,96699,7781,085 (24.0)1,400 (30.9)4.5Public
Anonymous submission
TBSS
56. online method using public detections
28.0
44.6
±9.3
42.612.3% 43.9% 4,13696,128790 (16.7)1,419 (30.0)3.0Public
X. Zhou, P. Jiang, Z. Wei, H. Dong, F. Wang. Online Multi-Object Tracking with Structural Invariance Constraint. In BMVC, 2018.
TDP
57. online method using public detections
34.1
33.9
±10.2
40.46.2% 62.2% 6,709113,249480 (12.7)1,105 (29.2)9.7Public
Anonymous submission
TLMHT
58. using public detections
16.3
48.7
±8.6
55.315.7% 44.5% 6,63286,504413 (7.9)642 (12.2)4.8Public
TCSVT-02160-2018
TPM
59. using public detections
20.3
49.1
±9.1
46.920.0% 38.9% 9,03883,031679 (12.5)850 (15.6)0.8Public
Anonymous submission
TripBFT
60. online method using public detections
19.3
48.3
±8.1
50.915.4% 40.1% 2,70691,047543 (10.8)896 (17.9)0.5Public
Anonymous submission
TrackerAvg RankMOTAIDF1MTMLFPFNID Sw.FragHzDetector
TripT
61. online method using public detections
19.8
48.1
±8.5
51.915.8% 40.2% 2,82791,210563 (11.3)1,143 (22.9)0.6Public
Anonymous submission
TSN
62. using public detections
21.2
48.2
±8.7
45.719.9% 38.9% 8,44785,315665 (12.5)829 (15.6)0.8Public
Anonymous submission
TST_PLS
63. online method using public detections
35.8
39.7
±11.1
43.36.7% 47.4% 8,447100,728783 (17.5)1,730 (38.7)4.0Public
Anonymous submission
YT16
64. online method using public detections
35.8
37.8
±8.8
31.18.8% 46.1% 4,384106,3652,655 (63.7)2,750 (66.0)12.1Public
Anonymous submission

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

(52.1% MOTA)

MOT16-06

MOT16-06

(43.1% MOTA)

MOT16-07

MOT16-07

(37.7% MOTA)

...

...

MOT16-08

MOT16-08

(29.4% MOTA)

MOT16-14

MOT16-14

(23.5% 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.