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.	91.3	91.8	90.9	90.7	78.7	0.06	1,169	14	44,492	54,044	153	456
MTMC_basel 1.	Anonymous submission
MTMCT_PA 2.	87.5	87.5	87.5	89.1	78.8	0.08	1,165	14	57,343	57,848	229	376
MTMCT_PA 2.	Anonymous submission
MTMC_ReID 3.	89.8	92.0	87.7	88.2	79.0	0.05	1,123	17	37,911	86,958	372	772
MTMC_ReID 3.	Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
DeepCC 4.	89.2	91.7	86.7	87.5	77.1	0.05	1,103	29	37,280	94,399	202	753
DeepCC 4.	E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
TAREIDMTMC 5.	83.8	87.6	80.4	83.3	75.5	0.06	1,051	17	44,691	131,220	383	2,428
TAREIDMTMC 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.
MOT_TBA 6.	82.0	85.0	79.2	78.0	80.0	0.11	1,018	40	79,402	152,336	803	1,466
MOT_TBA 6.	Paper ID 648
SAS_full 7.	84.0	89.4	79.2	76.0	76.0	0.09	950	72	66,783	186,974	169	1,256
SAS_full 7.	Anonymous submission
MYTRACKER 8.	80.3	87.3	74.4	78.3	78.4	0.05	914	72	35,580	193,253	406	1,116
MYTRACKER 8.	K. Yoon, Y. Song, M. Jeon. Multiple hypothesis tracking algorithm for multi-target multi-camera tracking with disjoint views. In IET Image Processing, 2018.
SAS 9.	76.5	83.9	70.3	69.3	74.8	0.10	813	89	76,059	248,224	426	2,081
SAS 9.	Submission id 177
MTMC_CDSC 10.	77.0	87.6	68.6	70.9	75.8	0.05	740	110	38,655	268,398	693	4,717
MTMC_CDSC 10.	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	MOTA	MOTP	FAF	MT	ML	FP	FN	ID Sw.	Frag
MTMC_ReIDp 11.	79.2	89.9	70.7	68.8	77.9	0.07	726	143	52,408	277,762	449	1,060
MTMC_ReIDp 11.	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 12.	70.8	84.3	61.0	65.2	75.8	0.05	603	119	36,956	330,382	855	4,669
MTMC___DS 12.	Anonymous submission
PT_BIPCC 13.	71.2	84.8	61.4	59.3	78.7	0.09	666	234	68,634	361,589	290	783
PT_BIPCC 13.	A. Maksai, X. Wang, F. Fleuret, P. Fua. Non-Markovian Globally Consistent Multi-Object Tracking. In ICCV, 2017.
BIPCC 14.	70.1	83.6	60.4	59.4	78.7	0.09	665	234	68,147	361,672	300	801
BIPCC 14.	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 15.	70.0	83.2	60.4	59.0	78.7	0.10	665	234	71,381	361,673	298	799
dirBIPCC 15.	Anonymous submission
lx_b 16.	70.3	88.1	58.5	61.3	78.7	0.04	640	247	26,845	382,524	246	788
lx_b 16.	Anonymous submission

Multi-Camera

Tracker	IDF1	IDP	IDR
MOT_TBA 1.	27.8	28.8	26.8
	Paper ID 648
PT_BIPCC 2.	34.9	41.6	30.1
	A. Maksai, X. Wang, F. Fleuret, P. Fua. Non-Markovian Globally Consistent Multi-Object Tracking. In ICCV, 2017.
SAS 3.	38.5	42.3	35.4
	Submission id 177
dirBIPCC 4.	52.1	62.0	45.0
	Anonymous submission
MTMC___DS 5.	54.9	65.4	47.3
	Anonymous submission
BIPCC 6.	56.2	67.0	48.4
	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 7.	58.0	72.6	48.2
	Anonymous submission
SAS_full 8.	59.9	63.8	56.5
	Anonymous submission
MTMC_CDSC 9.	60.0	68.3	53.5
	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.
MYTRACKER 10.	65.4	71.1	60.6
	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
TAREIDMTMC 11.	68.8	71.8	66.0
	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 12.	72.4	72.5	72.4
	Anonymous submission
MTMC_ReIDp 13.	74.4	84.4	66.4
	Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
DeepCC 14.	82.0	84.4	79.8
	E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
MTMC_ReID 15.	83.2	85.2	81.2
	Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
MTMC_basel 16.	87.4	87.8	87.0
	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.	83.7	88.8	79.1	78.9	76.6	0.13	614	34	35,987	114,104	307	602
MTMC_basel 1.	Anonymous submission
MTMCT_PA 2.	80.3	84.9	76.2	77.5	76.6	0.15	600	32	43,666	116,079	469	572
MTMCT_PA 2.	Anonymous submission
MTMC_ReID 3.	81.2	89.4	74.5	74.7	76.6	0.11	569	57	30,297	149,443	521	860
MTMC_ReID 3.	Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
DeepCC 4.	79.0	87.4	72.0	70.0	75.0	0.15	524	66	43,989	170,104	236	777
DeepCC 4.	E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
TAREIDMTMC 5.	77.9	86.6	70.7	68.1	73.5	0.17	498	45	47,777	179,035	541	2,074
TAREIDMTMC 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.
SAS_full 6.	76.8	89.3	67.4	65.4	75.3	0.12	450	87	35,596	210,639	267	977
SAS_full 6.	Anonymous submission
MYTRACKER 7.	63.5	73.9	55.6	59.6	76.7	0.19	400	80	55,038	231,527	1,468	1,801
MYTRACKER 7.	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 8.	71.6	85.3	61.7	60.9	76.8	0.14	375	104	40,732	237,974	572	993
MTMC_ReIDp 8.	Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
SAS 9.	65.5	79.3	55.8	59.1	74.0	0.14	379	102	39,576	251,256	972	1,855
SAS 9.	Submission id 177
MTMC_CDSC 10.	65.5	81.4	54.7	59.6	75.4	0.09	348	99	26,643	260,073	1,637	5,024
MTMC_CDSC 10.	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	MOTA	MOTP	FAF	MT	ML	FP	FN	ID Sw.	Frag
MTMC___DS 11.	62.6	79.4	51.6	57.3	75.3	0.09	314	103	26,721	276,233	1,672	4,946
MTMC___DS 11.	Anonymous submission
dirBIPCC 12.	64.3	80.3	53.6	53.9	77.1	0.16	338	102	45,472	283,014	653	1,078
dirBIPCC 12.	Anonymous submission
BIPCC 13.	64.5	81.2	53.5	54.6	77.1	0.14	338	103	39,599	283,376	652	1,073
BIPCC 13.	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 14.	65.0	81.8	54.0	54.4	77.1	0.14	335	104	40,978	283,704	661	1,054
PT_BIPCC 14.	A. Maksai, X. Wang, F. Fleuret, P. Fua. Non-Markovian Globally Consistent Multi-Object Tracking. In ICCV, 2017.
lx_b 15.	64.2	80.4	53.4	53.6	77.1	0.16	336	107	45,370	285,192	621	1,049
lx_b 15.	Anonymous submission

Multi-Camera

Tracker	IDF1	IDP	IDR
PT_BIPCC 1.	32.9	41.3	27.3
	A. Maksai, X. Wang, F. Fleuret, P. Fua. Non-Markovian Globally Consistent Multi-Object Tracking. In ICCV, 2017.
SAS 2.	33.0	40.0	28.1
	Submission id 177
dirBIPCC 3.	45.0	56.3	37.5
	Anonymous submission
BIPCC 4.	47.3	59.6	39.2
	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 5.	47.6	60.4	39.3
	Anonymous submission
lx_b 6.	48.3	60.6	40.2
	Anonymous submission
MYTRACKER 7.	50.1	58.3	43.9
	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 8.	50.9	63.2	42.6
	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 9.	51.7	60.1	45.4
	Anonymous submission
TAREIDMTMC 10.	61.2	68.0	55.5
	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.
Tracker	IDF1	IDP	IDR
MTMCT_PA 11.	65.5	69.2	62.2
	Anonymous submission
MTMC_ReIDp 12.	65.6	78.1	56.5
	Z. Zhang, J. Wu, X. Zhang, C. Zhang. Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project. In , 2017.
DeepCC 13.	68.5	75.9	62.4
	E. Ristani, C. Tomasi. Features for Multi-Target Multi-Camera Tracking and Re-Identification. In CVPR, 2018.
MTMC_ReID 14.	74.0	81.4	67.8
	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 15.	75.4	80.0	71.3
	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
	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.
	This method used the provided detection set as input.
	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.