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
MTMC_basel
1. 		91.391.890.990.778.70.061,1691444,49254,044153456
Anonymous submission
MTMCT_PA
2. using public detections 		87.587.587.589.178.80.081,1651457,34357,848229376
Anonymous submission
d_b_v13
3. 		89.091.187.088.478.60.051,112837,50984,8387241,954
Anonymous submission
MTMC_ReID
4. 		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.
DeepCC
5. 		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.
MFFusion
6. online method using public detections 		84.986.683.480.975.60.111,0792381,023120,5413638,089
Anonymous submission
TAREIDMTMC
7. 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.
MOT_TBA
8. online method 		82.085.079.278.080.00.111,0184079,402152,3368031,466
Paper ID 648
SAS_full
9. using public detections 		84.089.479.276.076.00.099507266,783186,9741691,256
Anonymous submission
MYTRACKER
10. 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
SAS
11. using public detections 		76.583.970.369.374.80.108138976,059248,2244262,081
Submission id 177
MTMC_CDSC
12. 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_ReIDp
13. 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___DS
14. using public detections 		70.884.361.065.275.80.0560311936,956330,3828554,669
Anonymous submission
PT_BIPCC
15. 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.
BIPCC
16. 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.
dirBIPCC
17. online method using public detections 		70.083.260.459.078.70.1066523471,381361,673298799
Anonymous submission
lx_b
18. online method using public detections 		70.388.158.561.378.70.0464024726,845382,524246788
Anonymous submission

Multi-Camera

Tracker IDF1 IDP IDR
MFFusion
1. online method using public detections 		26.226.725.7
Anonymous submission
MOT_TBA
2. online method 		27.828.826.8
Paper ID 648
PT_BIPCC
3. 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
4. using public detections 		38.542.335.4
Submission id 177
dirBIPCC
5. online method using public detections 		52.162.045.0
Anonymous submission
MTMC___DS
6. using public detections 		54.965.447.3
Anonymous submission
BIPCC
7. 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.
lx_b
8. online method using public detections 		58.072.648.2
Anonymous submission
SAS_full
9. using public detections 		59.963.856.5
Anonymous submission
MTMC_CDSC
10. 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.
Tracker IDF1 IDP IDR
MYTRACKER
11. 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.
TAREIDMTMC
12. 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.
MTMCT_PA
13. using public detections 		72.472.572.4
Anonymous submission
MTMC_ReIDp
14. 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.
DeepCC
15. 		82.084.479.8
E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
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.
d_b_v13
17. 		85.487.483.5
Anonymous submission
MTMC_basel
18. 		87.487.887.0
Anonymous submission

Hard Test Set

Single Camera (all)

Tracker IDF1 IDP IDR MOTA MOTP FAF MT ML FP FN ID Sw. Frag
MTMC_basel
1. 		83.788.879.178.976.60.136143435,987114,104307602
Anonymous submission
MTMCT_PA
2. using public detections 		80.384.976.277.576.60.156003243,666116,079469572
Anonymous submission
d_b_v13
3. 		82.390.775.476.276.70.095363824,319144,8139102,024
Anonymous submission
MTMC_ReID
4. 		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.
MFFusion
5. online method using public detections 		77.584.571.570.974.50.175244648,584158,1756606,556
Anonymous submission
DeepCC
6. 		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.
TAREIDMTMC
7. 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.
SAS_full
8. using public detections 		76.889.367.465.475.30.124508735,596210,639267977
Anonymous submission
MYTRACKER
9. 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.
MTMC_ReIDp
10. 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.
Tracker IDF1 IDP IDR MOTA MOTP FAF MT ML FP FN ID Sw. Frag
SAS
11. using public detections 		65.579.355.859.174.00.1437910239,576251,2569721,855
Submission id 177
MTMC_CDSC
12. 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___DS
13. using public detections 		62.679.451.657.375.30.0931410326,721276,2331,6724,946
Anonymous submission
dirBIPCC
14. online method using public detections 		64.380.353.653.977.10.1633810245,472283,0146531,078
Anonymous submission
BIPCC
15. 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.
PT_BIPCC
16. 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.
lx_b
17. online method using public detections 		64.280.453.453.677.10.1633610745,370285,1926211,049
Anonymous submission

Multi-Camera

Tracker IDF1 IDP IDR
MFFusion
1. online method using public detections 		29.732.327.4
Anonymous submission
PT_BIPCC
2. 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.
SAS
3. using public detections 		33.040.028.1
Submission id 177
dirBIPCC
4. online method using public detections 		45.056.337.5
Anonymous submission
BIPCC
5. 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.
MTMC___DS
6. using public detections 		47.660.439.3
Anonymous submission
lx_b
7. online method using public detections 		48.360.640.2
Anonymous submission
MYTRACKER
8. 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.
MTMC_CDSC
9. 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.
SAS_full
10. using public detections 		51.760.145.4
Anonymous submission
Tracker IDF1 IDP IDR
TAREIDMTMC
11. 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.
MTMCT_PA
12. using public detections 		65.569.262.2
Anonymous submission
MTMC_ReIDp
13. 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.
DeepCC
14. 		68.575.962.4
E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
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_basel
16. 		75.480.071.3
Anonymous submission
d_b_v13
17. 		78.586.471.8
Anonymous submission

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.



Contact