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_CDSC 1.	77.0	87.6	68.6	70.9	75.8	0.05	740	110	38,655	268,398	693	4,717
MTMC_CDSC 1.	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.
PT_BIPCC 2.	71.2	84.8	61.4	59.3	78.7	0.09	666	234	68,634	361,589	290	783
PT_BIPCC 2.	Anonymous submission
BIPCC 3.	70.1	83.6	60.4	59.4	78.7	0.09	665	234	68,147	361,672	300	801
BIPCC 3.	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 4.	70.0	83.2	60.4	59.0	78.7	0.10	665	234	71,381	361,673	298	799
dirBIPCC 4.	Anonymous submission
lx_b 5.	70.3	88.1	58.5	61.3	78.7	0.04	640	247	26,845	382,524	246	788
lx_b 5.	Anonymous submission

Multi-Camera

Tracker	IDF1	IDP	IDR
PT_BIPCC 1.	34.9	41.6	30.1
	Anonymous submission
dirBIPCC 2.	52.1	62.0	45.0
	Anonymous submission
BIPCC 3.	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 4.	58.0	72.6	48.2
	Anonymous submission
MTMC_CDSC 5.	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.

Hard Test Set

Single Camera (all)

Tracker	IDF1	IDP	IDR	MOTA	MOTP	FAF	MT	ML	FP	FN	ID Sw.	Frag
MTMC_CDSC 1.	65.5	81.4	54.7	59.6	75.4	0.09	348	99	26,643	260,073	1,637	5,024
MTMC_CDSC 1.	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.
dirBIPCC 2.	64.3	80.3	53.6	53.9	77.1	0.16	338	102	45,472	283,014	653	1,078
dirBIPCC 2.	Anonymous submission
BIPCC 3.	64.5	81.2	53.5	54.6	77.1	0.14	338	103	39,599	283,376	652	1,073
BIPCC 3.	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 4.	65.0	81.8	54.0	54.4	77.1	0.14	335	104	40,978	283,704	661	1,054
PT_BIPCC 4.	Anonymous submission
lx_b 5.	64.2	80.4	53.4	53.6	77.1	0.16	336	107	45,370	285,192	621	1,049
lx_b 5.	Anonymous submission

Multi-Camera

Tracker	IDF1	IDP	IDR
PT_BIPCC 1.	32.9	41.3	27.3
	Anonymous submission
dirBIPCC 2.	45.0	56.3	37.5
	Anonymous submission
BIPCC 3.	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.
lx_b 4.	48.3	60.6	40.2
	Anonymous submission
MTMC_CDSC 5.	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.

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.