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 Rank MOTAIDF1MTMLFPFNID Sw.FragHzDetector
DP_NMS
1. using public detections
27.0
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
2. using public detections
27.9
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.
SMOT
3. using public detections
43.4
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.
GMPHD_HDA
4. online method using public detections
27.9
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.
CppSORT
5. online method using public detections
32.4
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.
DWET
6. online method using public detections
30.3
32.2
±10.4
38.36.2% 63.0% 7,297115,780603 (16.5)1,184 (32.4)11.3Public
Anonymous submission
CEM
7. using public detections
31.1
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.
GM_PHD_N1T
8. online method using public detections
34.3
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.
TBD
9. using public detections
38.2
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.
DRT
10. online method using public detections
28.7
35.6
±11.9
44.28.2% 55.6% 12,863104,127517 (12.1)1,439 (33.6)6.2Public
Anonymous submission
TrackerAvg Rank MOTAIDF1MTMLFPFNID Sw.FragHzDetector
LP2D
11. using public detections
29.4
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.
HISP_T
12. online method using public detections
34.3
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.
JCmin_MOT
13. online method using public detections
26.4
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.
LTTSC-CRF
14. using public detections
30.6
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.
YT16
15. online method using public detections new
33.3
37.8
±8.8
31.18.8% 46.1% 4,384106,3652,655 (63.7)2,750 (66.0)12.1Public
Anonymous submission
Q_lc
16. online method using public detections
27.8
37.9
±10.3
48.314.2% 37.9% 19,33393,157697 (14.3)1,918 (39.2)0.3Public
Anonymous submission
GMMCP
17. using public detections
32.8
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.
HAM_ACT16
18. online method using public detections
25.0
38.1
±8.2
43.37.8% 54.4% 6,976105,434418 (9.9)707 (16.8)6.4Public
Y. Yoon, A. Boragule, Y. Song, K. Yoon, M. Jeon. Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering. In arXiv:1805.10916, 2018.
OVBT
19. online method using public detections
36.8
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, .
EAMTT_pub
20. online method using public detections
28.7
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
TrackerAvg Rank MOTAIDF1MTMLFPFNID Sw.FragHzDetector
SDMT
21. online method using public detections
25.5
39.6
±8.3
42.311.7% 49.1% 11,13098,343602 (13.1)772 (16.8)19.8Public
Anonymous submission
TST_PLS
22. online method using public detections
33.3
39.7
±11.1
43.36.7% 47.4% 8,447100,728783 (17.5)1,730 (38.7)0.7Public
Anonymous submission
ReIDT
23. online method using public detections
27.7
40.0
±10.3
43.313.6% 38.1% 17,08891,2411,064 (21.3)2,274 (45.5)6.5Public
Anonymous submission
FullTest
24. online method using public detections
26.1
40.7
±32.6
44.811.6% 42.3% 14,35492,6501,136 (23.1)3,864 (78.6)236.8Public
Anonymous submission
PRT
25. online method using public detections
27.0
40.8
±13.0
44.213.7% 38.3% 15,14391,7921,051 (21.2)2,210 (44.5)6.2Public
Anonymous submission
VOFNet
26. online method using public detections
26.9
40.9
±8.3
46.79.7% 47.0% 4,750102,277684 (15.6)4,310 (98.2)24.9Public
Anonymous submission
LINF1
27. using public detections
24.0
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.
TBNMF16
28. online method using public detections
29.1
42.0
±9.2
37.510.4% 44.9% 4,96699,7781,085 (24.0)1,400 (30.9)4.5Public
Anonymous submission
TTAR
29. using public detections
27.0
42.2
±8.0
37.210.4% 47.8% 4,87299,550909 (20.0)945 (20.8)19.7Public
Anonymous submission
oICF
30. online method using public detections
25.1
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.
TrackerAvg Rank MOTAIDF1MTMLFPFNID Sw.FragHzDetector
SAD_T
31. online method using public detections
27.9
43.4
±16.2
44.011.7% 59.3% 15,34187,086763 (14.6)1,832 (35.1)11.4Public
Anonymous submission
LFNF16
32. using public detections
25.5
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
deepS2
33. using public detections
22.3
43.6
±8.1
40.415.4% 41.9% 8,81993,095871 (17.8)851 (17.4)0.7Public
ID 32
STbase
34. using public detections
25.8
43.7
±9.2
50.815.2% 43.0% 8,89193,036662 (13.5)1,844 (37.7)0.4Public
Anonymous submission
CDA_DDALv2
35. online method using public detections
24.1
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.
QuadMOT16
36. using public detections
24.2
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.
TripletT
37. online method using public detections
22.6
44.6
±9.7
48.812.6% 46.6% 2,72597,948422 (9.1)1,093 (23.6)0.1Public
Anonymous submission
DCCRF16
38. online method using public detections
24.4
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.
EDMT
39. using public detections
16.3
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.
MHT_DAM
40. using public detections
18.3
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 Rank MOTAIDF1MTMLFPFNID Sw.FragHzDetector
STAM16
41. online method using public detections
22.6
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.
JMC
42. using public detections
17.3
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.
NOMT
43. using public detections
13.3
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.
IMWIS
44. using public detections
18.7
47.0
±9.3
41.816.2% 41.4% 4,84290,901868 (17.3)904 (18.0)0.7Public
TCSVT-02160-2018
MCjoint
45. using public detections
14.8
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.
AMIR
46. online method using public detections
17.6
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.
eHAF16
47. using public detections
15.3
47.2
±16.8
52.418.6% 42.8% 12,58683,107542 (10.0)787 (14.5)0.5Public
TCSVT-02141-2018
JCSTD
48. online method using public detections
21.8
47.4
±8.3
41.114.4% 36.4% 8,07686,6381,266 (24.1)2,697 (51.4)8.8Public
Anonymous submission
Adaptation
49. using public detections
11.6
47.6
±10.6
47.417.0% 40.4% 5,78389,168627 (12.3)761 (14.9)2.5Public
Anonymous submission
NLLMPa
50. using public detections
13.6
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.
TrackerAvg Rank MOTAIDF1MTMLFPFNID Sw.FragHzDetector
FWT
51. using public detections
18.3
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. Fusion of Head and Full-Body Detectors for Multi-Object Tracking. In Trajnet CVPRW, 2018.
TripT
52. online method using public detections
16.6
48.1
±8.5
51.915.8% 40.2% 2,82791,210563 (11.3)1,143 (22.9)0.6Public
Anonymous submission
GCRA
53. using public detections
16.1
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, D.Xie. Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking. In ICME 2018.
TripBFT
54. online method using public detections
15.8
48.3
±8.1
50.915.4% 40.1% 2,70691,047543 (10.8)896 (17.9)0.5Public
Anonymous submission
LMP
55. using public detections
12.8
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.
KCF16
56. online method using public detections
18.3
48.8
±9.6
47.215.8% 38.1% 5,87586,567906 (17.3)1,116 (21.2)0.1Public
Paper ID 2988
AFN
57. using public detections
15.3
49.0
±10.2
48.219.1% 35.7% 9,50882,506899 (16.4)1,383 (25.3)0.6Public
Anonymous submission
TPM
58. using public detections
16.9
49.1
±9.1
46.920.0% 38.9% 9,03883,031679 (12.5)850 (15.6)0.8Public
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

(51.4% MOTA)

MOT16-06

MOT16-06

(43.1% MOTA)

MOT16-12

MOT16-12

(37.7% MOTA)

...

...

MOT16-08

MOT16-08

(29.5% MOTA)

MOT16-14

MOT16-14

(23.8% 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.