DukeMTMCT Results

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


Easy Test Set

Single Camera (all)

Tracker IDF1 IDP IDR MOTA MOTP FAF MT ML FP FN ID Sw. Frag
BIPCC
1. online method using public detections
70.183.660.459.478.70.0966523468,147361,672300801
E. Ristani, F. Solera, R. Zou, R. Cucchiara, C. Tomasi. Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. In ECCV workshop on Benchmarking Multi-Target Tracking, 2016.
DeepCC
2.
89.291.786.787.577.10.051,1032937,28094,399202753
E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
dirBIPCC
3. online method using public detections
70.083.260.459.078.70.1066523471,381361,673298799
Anonymous submission
d_b_v13
4.
89.091.187.088.478.60.051,112837,50984,8387241,954
Anonymous submission
lx_b
5. online method using public detections
70.388.158.561.378.70.0464024726,845382,524246788
Anonymous submission
MFFusion
6. online method using public detections new
86.788.485.084.678.20.081,0922461,155101,871299775
Anonymous submission
MIS_ncku
7. using public detections
88.889.588.290.078.80.061,1481745,15560,487278404
Anonymous submission
MOT_TBA
8. online method
82.486.179.079.680.40.091,0264664,002151,4838751,481
Paper ID 648
mtmct_hxq
9. online method
16.419.414.268.474.10.0381726425,155308,6629184,392
Anonymous submission
MTMCT_PA
10. using public detections
87.587.587.589.178.80.081,1651457,34357,848229376
Anonymous submission
Tracker IDF1 IDP IDR MOTA MOTP FAF MT ML FP FN ID Sw. Frag
MTMCT_s
11. online method using public detections
91.392.889.890.678.30.041,1651132,31466,824178467
Anonymous submission
MTMCT_sp
12. online method using public detections
91.492.990.090.478.20.051,1641234,05467,079214457
Anonymous submission
MTMC_basel
13.
91.391.890.990.778.70.061,1691444,49254,044153456
Anonymous submission
MTMC_CDSC
14. using public detections
77.087.668.670.975.80.0574011038,655268,3986934,717
Y. Tesfaye, E. Zemene, A. Prati, M. Pelillo, M. Shah. Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets. In CoRR, 2017.
mtmc_cg
15. using public detections
49.452.047.183.778.80.059972235,397134,9822,426687
Anonymous submission
MTMC_ReID
16.
89.892.087.788.279.00.051,1231737,91186,958372772
Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
MTMC_ReIDp
17. using public detections
79.289.970.768.877.90.0772614352,408277,7624491,060
Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
MTMC_TBC
18. using public detections
89.290.488.087.878.10.071,1312250,77178,263222833
Anonymous submission
MTMC___DS
19. using public detections
70.884.361.065.275.80.0560311936,956330,3828554,669
Anonymous submission
MYTRACKER
20. online method using public detections
80.387.374.478.378.40.059147235,580193,2534061,116
K. Yoon, Y. Song, M. Jeon. Multiple hypothesis tracking algorithm for multi-target multi-camera tracking with disjoint views. In IET Image Processing, 2018.
Tracker IDF1 IDP IDR MOTA MOTP FAF MT ML FP FN ID Sw. Frag
PT_BIPCC
21. using public detections
71.284.861.459.378.70.0966623468,634361,589290783
A. Maksai, X. Wang, F. Fleuret, P. Fua. Non-Markovian Globally Consistent Multi-Object Tracking. In ICCV, 2017.
SAS
22. using public detections
76.583.970.369.374.80.108138976,059248,2244262,081
Submission id 177
SAS_full
23. using public detections
84.089.479.276.076.00.099507266,783186,9741691,256
Anonymous submission
TAREIDMTMC
24. online method
83.887.680.483.375.50.061,0511744,691131,2203832,428
N. Jiang, S. Bai, Y. Xu, C. Xing, Z. Zhou, W. Wu. Online Inter-Camera Trajectory Association Exploiting Person Re-Identification and Camera Topology. In MM, 2018.

Multi-Camera

Tracker IDF1 IDP IDR
BIPCC
1. online method using public detections
56.267.048.4
E. Ristani, F. Solera, R. Zou, R. Cucchiara, C. Tomasi. Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. In ECCV workshop on Benchmarking Multi-Target Tracking, 2016.
DeepCC
2.
82.084.479.8
E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
dirBIPCC
3. online method using public detections
52.162.045.0
Anonymous submission
d_b_v13
4.
85.487.483.5
Anonymous submission
lx_b
5. online method using public detections
58.072.648.2
Anonymous submission
MFFusion
6. online method using public detections new
26.527.026.0
Anonymous submission
MIS_ncku
7. using public detections
84.685.384.0
Anonymous submission
MOT_TBA
8. online method
28.529.827.4
Paper ID 648
mtmct_hxq
9. online method
5.97.05.1
Anonymous submission
MTMCT_PA
10. using public detections
72.472.572.4
Anonymous submission
Tracker IDF1 IDP IDR
MTMCT_s
11. online method using public detections
87.488.885.9
Anonymous submission
MTMCT_sp
12. online method using public detections
88.089.486.6
Anonymous submission
MTMC_basel
13.
87.487.887.0
Anonymous submission
MTMC_CDSC
14. using public detections
60.068.353.5
Y. Tesfaye, E. Zemene, A. Prati, M. Pelillo, M. Shah. Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets. In CoRR, 2017.
mtmc_cg
15. using public detections
40.742.838.8
Anonymous submission
MTMC_ReID
16.
83.285.281.2
Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
MTMC_ReIDp
17. using public detections
74.484.466.4
Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
MTMC_TBC
18. using public detections
27.728.127.3
Anonymous submission
MTMC___DS
19. using public detections
54.965.447.3
Anonymous submission
MYTRACKER
20. online method using public detections
65.471.160.6
K. Yoon, Y. Song, M. Jeon. Multiple hypothesis tracking algorithm for multi-target multi-camera tracking with disjoint views. In IET Image Processing, 2018.
Tracker IDF1 IDP IDR
PT_BIPCC
21. using public detections
34.941.630.1
A. Maksai, X. Wang, F. Fleuret, P. Fua. Non-Markovian Globally Consistent Multi-Object Tracking. In ICCV, 2017.
SAS
22. using public detections
38.542.335.4
Submission id 177
SAS_full
23. using public detections
59.963.856.5
Anonymous submission
TAREIDMTMC
24. online method
68.871.866.0
N. Jiang, S. Bai, Y. Xu, C. Xing, Z. Zhou, W. Wu. Online Inter-Camera Trajectory Association Exploiting Person Re-Identification and Camera Topology. In MM, 2018.

Hard Test Set

Single Camera (all)

Tracker IDF1 IDP IDR MOTA MOTP FAF MT ML FP FN ID Sw. Frag
BIPCC
1. online method using public detections
64.581.253.554.677.10.1433810339,599283,3766521,073
E. Ristani, F. Solera, R. Zou, R. Cucchiara, C. Tomasi. Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. In ECCV workshop on Benchmarking Multi-Target Tracking, 2016.
DeepCC
2.
79.087.472.070.075.00.155246643,989170,104236777
E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
dirBIPCC
3. online method using public detections
64.380.353.653.977.10.1633810245,472283,0146531,078
Anonymous submission
d_b_v13
4.
82.390.775.476.276.70.095363824,319144,8139102,024
Anonymous submission
lx_b
5. online method using public detections
64.280.453.453.677.10.1633610745,370285,1926211,049
Anonymous submission
MFFusion
6. online method using public detections new
79.386.673.274.676.30.125525235,193145,514467970
Anonymous submission
MIS_ncku
7. using public detections
80.385.375.978.076.60.145993138,918117,627468627
Anonymous submission
mtmct_hxq
8. online method
49.058.242.466.072.70.084637822,099216,6183,6205,193
Anonymous submission
MTMCT_PA
9. using public detections
80.384.976.277.576.60.156003243,666116,079469572
Anonymous submission
MTMCT_s
10. online method using public detections
83.589.678.279.176.30.106073129,068119,967321512
Anonymous submission
Tracker IDF1 IDP IDR MOTA MOTP FAF MT ML FP FN ID Sw. Frag
MTMCT_sp
11. online method using public detections
83.289.378.078.876.20.116063230,259120,511375580
Anonymous submission
MTMC_basel
12.
83.788.879.178.976.60.136143435,987114,104307602
Anonymous submission
MTMC_CDSC
13. using public detections
65.581.454.759.675.40.093489926,643260,0731,6375,024
Y. Tesfaye, E. Zemene, A. Prati, M. Pelillo, M. Shah. Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets. In CoRR, 2017.
mtmc_cg
14. using public detections
42.147.637.770.776.90.104794429,660177,7121,774821
Anonymous submission
MTMC_ReID
15.
81.289.474.574.776.60.115695730,297149,443521860
Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
MTMC_ReIDp
16. using public detections
71.685.361.760.976.80.1437510440,732237,974572993
Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
MTMC_TBC
17. using public detections
82.490.076.075.276.40.125695232,813143,883298898
Anonymous submission
MTMC___DS
18. using public detections
62.679.451.657.375.30.0931410326,721276,2331,6724,946
Anonymous submission
MYTRACKER
19. online method using public detections
63.573.955.659.676.70.194008055,038231,5271,4681,801
K. Yoon, Y. Song, M. Jeon. Multiple hypothesis tracking algorithm for multi-target multi-camera tracking with disjoint views. In IET Image Processing, 2018.
PT_BIPCC
20. using public detections
65.081.854.054.477.10.1433510440,978283,7046611,054
A. Maksai, X. Wang, F. Fleuret, P. Fua. Non-Markovian Globally Consistent Multi-Object Tracking. In ICCV, 2017.
Tracker IDF1 IDP IDR MOTA MOTP FAF MT ML FP FN ID Sw. Frag
SAS
21. using public detections
65.579.355.859.174.00.1437910239,576251,2569721,855
Submission id 177
SAS_full
22. using public detections
76.889.367.465.475.30.124508735,596210,639267977
Anonymous submission
TAREIDMTMC
23. online method
77.986.670.768.173.50.174984547,777179,0355412,074
N. Jiang, S. Bai, Y. Xu, C. Xing, Z. Zhou, W. Wu. Online Inter-Camera Trajectory Association Exploiting Person Re-Identification and Camera Topology. In MM, 2018.

Multi-Camera

Tracker IDF1 IDP IDR
BIPCC
1. online method using public detections
47.359.639.2
E. Ristani, F. Solera, R. Zou, R. Cucchiara, C. Tomasi. Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. In ECCV workshop on Benchmarking Multi-Target Tracking, 2016.
DeepCC
2.
68.575.962.4
E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
dirBIPCC
3. online method using public detections
45.056.337.5
Anonymous submission
d_b_v13
4.
78.586.471.8
Anonymous submission
lx_b
5. online method using public detections
48.360.640.2
Anonymous submission
MFFusion
6. online method using public detections new
30.232.927.8
Anonymous submission
MIS_ncku
7. using public detections
71.776.267.8
Anonymous submission
mtmct_hxq
8. online method
20.123.917.4
Anonymous submission
MTMCT_PA
9. using public detections
65.569.262.2
Anonymous submission
MTMCT_s
10. online method using public detections
77.282.872.2
Anonymous submission
Tracker IDF1 IDP IDR
MTMCT_sp
11. online method using public detections
76.281.771.4
Anonymous submission
MTMC_basel
12.
75.480.071.3
Anonymous submission
MTMC_CDSC
13. using public detections
50.963.242.6
Y. Tesfaye, E. Zemene, A. Prati, M. Pelillo, M. Shah. Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets. In CoRR, 2017.
mtmc_cg
14. using public detections
32.436.629.0
Anonymous submission
MTMC_ReID
15.
74.081.467.8
Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
MTMC_ReIDp
16. using public detections
65.678.156.5
Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
MTMC_TBC
17. using public detections
31.334.228.9
Anonymous submission
MTMC___DS
18. using public detections
47.660.439.3
Anonymous submission
MYTRACKER
19. online method using public detections
50.158.343.9
K. Yoon, Y. Song, M. Jeon. Multiple hypothesis tracking algorithm for multi-target multi-camera tracking with disjoint views. In IET Image Processing, 2018.
PT_BIPCC
20. using public detections
32.941.327.3
A. Maksai, X. Wang, F. Fleuret, P. Fua. Non-Markovian Globally Consistent Multi-Object Tracking. In ICCV, 2017.
Tracker IDF1 IDP IDR
SAS
21. using public detections
33.040.028.1
Submission id 177
SAS_full
22. using public detections
51.760.145.4
Anonymous submission
TAREIDMTMC
23. online method
61.268.055.5
N. Jiang, S. Bai, Y. Xu, C. Xing, Z. Zhou, W. Wu. Online Inter-Camera Trajectory Association Exploiting Person Re-Identification and Camera Topology. In MM, 2018.


Evaluation Measures

Lower is better. Higher is better.
Measure Better Perfect Description
IDF1 higher 100 % ID F1 Score [1]. The ratio of correctly identified detections over the average number of ground-truth and computed detections.
IDP higher 100 % ID Precision [1]. Identification precision is the fraction of computed detections that are correctly identified.
IDR higher 100 % ID Recall [1]. Identification recall is the fraction of ground truth detections that are correctly identified.
MOTA higher 100 % Multiple Object Tracking Accuracy [2]. This measure combines three error sources: false positives, missed targets and identity switches.
MOTP higher 100 % Multiple Object Tracking Precision [2]. 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 [3].
Frag lower 0 The total number of times a trajectory is fragmented (i.e. interrupted during tracking).

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] 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.
[2] Bernardin, K. & Stiefelhagen, R. Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics. Image and Video Processing, 2008(1):1-10, 2008.
[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.