2D MOT 2015 Results

Download all results for this benchmark

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

Showing only entries that use public detections!

Tracker	Avg Rank	MOTA	IDF1	MT	ML	FP	FN	ID Sw.	Frag	Hz	Detector
TO 1.	31.1	25.7 ±13.5	32.7	4.3%	57.4%	4,779	40,511	383 (11.2)	600 (17.6)	5.0	Public
TO 1.	S. Manen, R. Timofte, D. Dai, L. Gool. Leveraging single for multi-target tracking using a novel trajectory overlap affinity measure. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), 2016.
SegTrack 2.	37.2	22.5 ±15.2	31.5	5.8%	63.9%	7,890	39,020	697 (19.1)	737 (20.2)	0.2	Public
SegTrack 2.	A. Milan, L. Leal-Taixé, K. Schindler, I. Reid. Joint Tracking and Segmentation of Multiple Targets. In CVPR, 2015.
LINF1 3.	27.7	24.5 ±15.4	34.8	5.5%	64.6%	5,864	40,207	298 (8.6)	744 (21.5)	7.5	Public
LINF1 3.	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.
HAM_SADF 4.	25.3	25.2 ±13.9	37.8	5.7%	58.3%	7,330	38,275	357 (9.5)	745 (19.8)	18.7	Public
HAM_SADF 4.	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.
TFMOT 5.	31.7	23.8 ±11.9	32.3	4.9%	62.0%	4,533	41,873	404 (12.7)	792 (24.9)	11.3	Public
TFMOT 5.	M. Abhijeet Boragule. Joint Cost Minimization for Multi-Object Tracking. In 2017 IEEE International Conference on Advanced Vide and Signale Based Surveillance, 2017.
DCO_X 6.	36.0	19.6 ±14.1	31.5	5.1%	54.9%	10,652	38,232	521 (13.8)	819 (21.7)	0.3	Public
DCO_X 6.	A. Milan, K. Schindler, S. Roth. Multi-Target Tracking by Discrete-Continuous Energy Minimization. In IEEE PAMI, 2016.
NOMT 7.	17.4	33.7 ±16.2	44.6	12.2%	44.0%	7,762	32,547	442 (9.4)	823 (17.5)	11.5	Public
NOMT 7.	W. Choi. Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor. In ICCV, 2015.
TC_SIAMESE 8.	33.8	20.2 ±13.9	32.6	2.6%	67.5%	6,127	42,596	294 (9.6)	825 (26.9)	13.0	Public
TC_SIAMESE 8.	Y. Yoon, Y. Song, K. Yoon, M. Jeon. Online Multiple-Object Tracking using Selective Deep Appearance Matching. In IEEE/IEIE The International Conference on Consumer Electronics (ICCE) Asia, 2018.
MHT_DAM 9.	19.7	32.4 ±15.6	45.3	16.0%	43.8%	9,064	32,060	435 (9.1)	826 (17.3)	0.7	Public
MHT_DAM 9.	C. Kim, F. Li, A. Ciptadi, J. Rehg. Multiple Hypothesis Tracking Revisited. In ICCV, 2015.
CNNEMBED 10.	24.2	23.6 ±14.9	41.0	12.9%	44.1%	14,047	32,398	496 (10.5)	829 (17.5)	1.9	Public
CNNEMBED 10.	Anonymous submission
Tracker	Avg Rank	MOTA	IDF1	MT	ML	FP	FN	ID Sw.	Frag	Hz	Detector
LP_SSVM 11.	28.6	25.2 ±13.7	34.0	5.8%	53.0%	8,369	36,932	646 (16.2)	849 (21.3)	41.3	Public
LP_SSVM 11.	S. Wang, C. Fowlkes. Learning Optimal Parameters for Multi-target Tracking with Contextual Interactions. In International Journal of Computer Vision, 2016.
JPDA_m 12.	27.8	23.8 ±15.1	33.8	5.0%	58.1%	6,373	40,084	365 (10.5)	869 (25.0)	32.6	Public
JPDA_m 12.	H. Rezatofighi, A. Milan, Z. Zhang, Q. Shi, A. Dick, I. Reid. Joint Probabilistic Data Association Revisited. In ICCV, 2015.
TPM 13.	20.1	36.2 ±12.8	43.6	15.4%	42.6%	5,650	33,102	420 (9.1)	928 (20.1)	0.8	Public
TPM 13.	Anonymous submission
CNNTCM 14.	24.8	29.6 ±13.9	36.8	11.2%	44.0%	7,786	34,733	712 (16.4)	943 (21.7)	1.7	Public
CNNTCM 14.	B. Wang, K. L. Chan, L. Wang, B. Shuai, Z. Zuo, T. Liu, G. Wang. Joint Learning of Convolutional Neural Networks and Temporally Constrained Metrics for Tracklet Association. In DeepVision Workshop (CVPR), 2016.
TSMLCDEnew 15.	19.3	34.3 ±13.1	44.1	14.0%	39.4%	7,869	31,908	618 (12.9)	959 (20.0)	6.5	Public
TSMLCDEnew 15.	B. Wang, G. Wang, K. L. Chan, L. Wang. Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation. In arXiv:1511.06654, 2015.
JointMC 16.	17.5	35.6 ±18.9	45.1	23.2%	39.3%	10,580	28,508	457 (8.5)	969 (18.1)	0.6	Public
JointMC 16.	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.
MCF_PHD 17.	23.7	29.9 ±20.0	38.2	11.9%	44.0%	8,892	33,529	656 (14.4)	989 (21.8)	12.2	Public
MCF_PHD 17.	N. Wojke, D. Paulus. Global data association for the Probability Hypothesis Density filter using network flows. In 2016 IEEE International Conference on Robotics and Automation, ICRA, 2016.
GSCR 18.	34.3	15.8 ±10.5	27.9	1.8%	61.0%	7,597	43,633	514 (17.7)	1,010 (34.8)	28.1	Public
GSCR 18.	L. Fagot-Bouquet, R. Audigier, Y. Dhome, F. Lerasle. Online multi-person tracking based on global sparse collaborative representations. In ICIP, 2015.
CEM 19.	35.3	19.3 ±17.5	0.0	8.5%	46.5%	14,180	34,591	813 (18.6)	1,023 (23.4)	1.1	Public
CEM 19.	A. Milan, S. Roth, K. Schindler. Continuous Energy Minimization for Multitarget Tracking. In IEEE TPAMI, 2014.
MotiCon 20.	38.5	23.1 ±16.4	29.4	4.7%	52.0%	10,404	35,844	1,018 (24.4)	1,061 (25.5)	1.4	Public
MotiCon 20.	L. Leal-Taixé, M. Fenzi, A. Kuznetsova, B. Rosenhahn, S. Savarese. Learning an image-based motion context for multiple people tracking. In CVPR, 2014.
Tracker	Avg Rank	MOTA	IDF1	MT	ML	FP	FN	ID Sw.	Frag	Hz	Detector
LFNF 21.	26.0	31.6 ±12.3	33.1	9.6%	41.7%	5,943	35,095	961 (22.4)	1,106 (25.8)	4.0	Public
LFNF 21.	Sheng H, Hao L, Chen J, et al. Robust Local Effective Matching Model for Multi-Target Tracking. In PCM, 2017
mLK 22.	17.3	35.1 ±12.9	47.5	12.3%	38.3%	5,678	33,815	383 (8.5)	1,175 (26.1)	1.0	Public
mLK 22.	Yuan Zhang, Di Xie and Shiliang Pu (Hikvision Research Institute)
RSCNN 23.	26.0	29.5 ±23.9	37.0	12.9%	36.3%	11,866	30,474	976 (19.4)	1,176 (23.3)	4.0	Public
RSCNN 23.	Heba Mahgoub, Khaled Mostafa, Khaled T. Wassif and Ibrahim Farag, “Multi-Target Tracking Using Hierarchical Convolutional Features and Motion Cues” International Journal of Advanced Computer Science and Applications(IJACSA), 8(11), 2017.
SCEA 24.	27.8	29.1 ±12.2	37.2	8.9%	47.3%	6,060	36,912	604 (15.1)	1,182 (29.6)	6.8	Public
SCEA 24.	J. Yoon, C. Lee, M. Yang, K. Yoon. Online Multi-object Tracking via Structural Constraint Event Aggregation. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
TripBFT15 25.	20.3	37.1 ±15.3	48.4	12.6%	39.7%	8,305	29,732	580 (11.2)	1,193 (23.1)	1.0	Public
TripBFT15 25.	Anonymous submission
SAS_MOT15 26.	36.7	22.2 ±13.8	27.2	3.1%	61.6%	5,591	41,531	700 (21.6)	1,240 (38.3)	8.9	Public
SAS_MOT15 26.	Submission id 177
OMT_DFH 27.	30.3	21.2 ±17.2	37.3	7.1%	46.5%	13,218	34,657	563 (12.9)	1,255 (28.8)	28.6	Public
OMT_DFH 27.	J. Ju, D. Kim, B. Ku, D. Han, H. Ko. Online multi-object tracking with efficient track drift and fragmentation handling. In J. Opt. Soc. Am. A, 2017.
AP_HWDPL_p 28.	14.5	38.5 ±9.9	47.1	8.7%	37.4%	4,005	33,203	586 (12.8)	1,263 (27.5)	6.7	Public
AP_HWDPL_p 28.	C. Long, A. Haizhou, S. Chong, Z. Zijie, B. Bo. Online Multi-Object Tracking with Convolutional Neural Networks. In 2017 IEEE International Conference on Image Processing (ICIP), 2017.
GMPHD 29.	33.7	18.5 ±12.7	28.4	3.9%	55.3%	7,864	41,766	459 (14.3)	1,266 (39.5)	19.8	Public
GMPHD 29.	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.
HybridDAT 30.	17.0	35.0 ±15.0	47.7	11.4%	42.2%	8,455	31,140	358 (7.3)	1,267 (25.7)	4.6	Public
HybridDAT 30.	M. Yang, Y. Jia. A Hybrid Data Association Framework for Robust Online Multi-Object Tracking. In IEEE Transactions on Image Processing, 2016.
Tracker	Avg Rank	MOTA	IDF1	MT	ML	FP	FN	ID Sw.	Frag	Hz	Detector
RMOT 31.	38.1	18.6 ±17.5	32.6	5.3%	53.3%	12,473	36,835	684 (17.1)	1,282 (32.0)	7.9	Public
RMOT 31.	J. Yoon, H. Yang, J. Lim, K. Yoon. Bayesian Multi-Object Tracking Using Motion Context from Multiple Objects. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2015.
SiameseCNN 32.	27.8	29.0 ±15.1	34.3	8.5%	48.4%	5,160	37,798	639 (16.6)	1,316 (34.2)	52.8	Public
SiameseCNN 32.	Laura Leal-Taixé, Cristian Canton-Ferrer, Konrad Schindler. Learning by Tracking: Siamese CNN for Robust Target Association. DeepVision Workshop (CVPR), Las Vegas (Nevada, USA), June 2016.
QuadMOT 33.	21.7	33.8 ±14.8	40.4	12.9%	36.9%	7,898	32,061	703 (14.7)	1,430 (29.9)	3.7	Public
QuadMOT 33.	J. Son, M. Baek, M. Cho, B. Han. Multi-Object Tracking with Quadruplet Convolutional Neural Networks. In CVPR, 2017.
KCF 34.	16.8	38.9 ±14.5	44.5	16.6%	31.5%	7,321	29,501	720 (13.9)	1,440 (27.7)	0.3	Public
KCF 34.	Paper ID 2988
AM 35.	17.9	34.3 ±13.7	48.3	11.4%	43.4%	5,154	34,848	348 (8.0)	1,463 (33.8)	0.5	Public
AM 35.	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.
cf_mdp 36.	16.3	31.4 ±14.7	43.7	16.1%	34.3%	10,118	31,284	718 (14.6)	1,469 (29.9)	450.4	Public
cf_mdp 36.	Anonymous submission
EAMTTpub 37.	34.0	22.3 ±14.2	32.8	5.4%	52.7%	7,924	38,982	833 (22.8)	1,485 (40.6)	12.2	Public
EAMTTpub 37.	R. Sanchez-Matilla, F. Poiesi, A. Cavallaro "Multi-target tracking with strong and weak detections" in BMTT ECCVw 2016
MDP 38.	24.3	30.3 ±14.6	44.7	13.0%	38.4%	9,717	32,422	680 (14.4)	1,500 (31.8)	1.1	Public
MDP 38.	Y. Xiang, A. Alahi, S. Savarese. Learning to Track: Online Multi-Object Tracking by Decision Making. In International Conference on Computer Vision (ICCV), 2015.
Q_cf 39.	23.8	31.6 ±13.5	43.8	16.0%	34.7%	9,711	31,579	742 (15.3)	1,505 (31.0)	1.0	Public
Q_cf 39.	Anonymous submission
TDAM 40.	21.4	33.0 ±9.8	46.1	13.3%	39.1%	10,064	30,617	464 (9.2)	1,506 (30.0)	5.9	Public
TDAM 40.	M. Yang, Y. Jia. Temporal dynamic appearance modeling for online multi-person tracking. In Computer Vision and Image Understanding, 2016.
Tracker	Avg Rank	MOTA	IDF1	MT	ML	FP	FN	ID Sw.	Frag	Hz	Detector
TBX 41.	35.4	27.5 ±13.3	33.8	10.4%	45.8%	7,968	35,810	759 (18.2)	1,528 (36.6)	0.1	Public
TBX 41.	R. Henschel, L. Leal-Taixé, B. Rosenhahn, K. Schindler. Tracking with multi-level features. In arXiv:1607.07304, 2016.
TSDA_OAL 42.	35.2	18.6 ±17.6	36.1	9.4%	42.3%	16,350	32,853	806 (17.3)	1,544 (33.2)	19.7	Public
TSDA_OAL 42.	H. Ko. Online multi-person tracking with two-stage data association and online appearance model learning. In IET Computer Vision, 2017.
DCCRF 43.	25.1	33.6 ±11.0	39.1	10.4%	37.6%	5,917	34,002	866 (19.4)	1,566 (35.1)	0.1	Public
DCCRF 43.	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.
CDA_DDALpb 44.	22.5	32.8 ±10.6	38.8	9.7%	42.2%	4,983	35,690	614 (14.7)	1,583 (37.8)	2.3	Public
CDA_DDALpb 44.	S. Bae and K. Yoon, Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking , In IEEE TPAMI, 2017.
CMOT 45.	25.4	27.6 ±14.0	43.3	10.5%	49.0%	9,451	34,207	800 (18.0)	1,584 (35.7)	5,783.0	Public
CMOT 45.	Anonymous submission
TripT15 46.	24.4	35.7 ±14.9	47.7	11.1%	39.8%	8,729	30,152	655 (12.9)	1,614 (31.7)	1.1	Public
TripT15 46.	Anonymous submission
AMT 47.	18.0	30.4 ±13.6	43.9	15.0%	35.6%	10,391	31,641	725 (14.9)	1,641 (33.8)	296.0	Public
AMT 47.	Anonymous submission
oICF 48.	30.8	27.1 ±14.9	40.5	6.4%	48.7%	7,594	36,757	454 (11.3)	1,660 (41.3)	1.4	Public
oICF 48.	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.
CF_MCMC 49.	26.7	31.4 ±11.3	36.4	10.3%	40.9%	8,798	32,541	814 (17.3)	1,711 (36.4)	3.2	Public
CF_MCMC 49.	Anonymous submission
LP2D 50.	36.7	19.8 ±14.2	0.0	6.7%	41.2%	11,580	36,045	1,649 (39.9)	1,712 (41.4)	112.1	Public
LP2D 50.	MOT baseline: Linear programming on 2D image coordinates.
Tracker	Avg Rank	MOTA	IDF1	MT	ML	FP	FN	ID Sw.	Frag	Hz	Detector
TC_ODAL 51.	45.8	15.1 ±15.0	0.0	3.2%	55.8%	12,970	38,538	637 (17.1)	1,716 (46.0)	1.7	Public
TC_ODAL 51.	S. Bae, K. Yoon. Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning. In CVPR, 2014.
ELP 52.	33.9	25.0 ±10.8	26.2	7.5%	43.8%	7,345	37,344	1,396 (35.6)	1,804 (46.0)	5.7	Public
ELP 52.	N. McLaughlin, J. Martinez Del Rincon, P. Miller. Enhancing Linear Programming with Motion Modeling for Multi-target Tracking. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2015.
YT 53.	38.9	23.5 ±11.6	26.8	4.4%	49.5%	5,537	40,210	1,270 (36.8)	1,817 (52.6)	34.4	Public
YT 53.	Anonymous submission
ALExTRAC 54.	41.3	17.0 ±12.1	17.3	3.9%	52.4%	9,233	39,933	1,859 (53.1)	1,872 (53.5)	3.7	Public
ALExTRAC 54.	A. Bewley, L. Ott, F. Ramos, B. Upcroft. ALExTRAC: Affinity Learning by Exploring Temporal Reinforcement within Association Chains. In International Conference on Robotics and Automation (ICRA), (to appear) 2016.
TBD 55.	46.4	15.9 ±17.6	0.0	6.4%	47.9%	14,943	34,777	1,939 (44.7)	1,963 (45.2)	0.7	Public
TBD 55.	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.
CppSORT 56.	36.3	21.7 ±11.8	26.8	3.7%	49.1%	8,422	38,454	1,231 (32.9)	2,005 (53.6)	1,112.1	Public
CppSORT 56.	S. Murray. Real-Time Multiple Object Tracking - A Study on the Importance of Speed. In arXiv preprint arXiv:1709.03572, 2017.
AMIR15 57.	17.3	37.6 ±12.5	46.0	15.8%	26.8%	7,933	29,397	1,026 (19.7)	2,024 (38.8)	1.9	Public
AMIR15 57.	A. Sadeghian, A. Alahi, S. Savarese. Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies. In ICCV, 2017.
RNN_LSTM 58.	40.3	19.0 ±15.2	17.1	5.5%	45.6%	11,578	36,706	1,490 (37.0)	2,081 (51.7)	165.2	Public
RNN_LSTM 58.	A. Milan, S. Rezatofighi, A. Dick, I. Reid, K. Schindler. Online Multi-Target Tracking using Recurrent Neural Networks. In AAAI, 2017.
SMOT 59.	46.4	18.2 ±10.3	0.0	2.8%	54.8%	8,780	40,310	1,148 (33.4)	2,132 (62.0)	2.7	Public
SMOT 59.	C. Dicle, O. Camps, M. Sznaier. The Way They Move: Tracking Targets with Similar Appearance. In ICCV, 2013.
PHD_GSDL 60.	29.3	30.5 ±14.9	38.8	7.6%	41.2%	6,534	35,284	879 (20.6)	2,208 (51.9)	8.2	Public
PHD_GSDL 60.	Z. Fu, P. Feng, F. Angelini, J. Chambers, S. Naqvi. Particle PHD Filter based Multiple Human Tracking using Online Group-Structured Dictionary Learning. In IEEE Access, 2018.
Tracker	Avg Rank	MOTA	IDF1	MT	ML	FP	FN	ID Sw.	Frag	Hz	Detector
MTSTracker 61.	34.2	20.6 ±18.2	31.9	9.0%	36.9%	15,161	32,212	1,387 (29.2)	2,357 (49.5)	19.3	Public
MTSTracker 61.	F. Nguyen Thi Lan Anh, F. Bremond. Multi-Object Tracking using Multi-Channel Part Appearance Representation. In International conference on Advanced video and Signal Based Surveillance, 2017.
SNM 62.	26.7	31.3 ±16.5	38.2	12.6%	35.4%	8,903	32,393	926 (19.6)	2,382 (50.4)	14.8	Public
SNM 62.	Anonymous submission
Stitiching 63.	29.5	29.3 ±25.1	42.6	11.8%	34.1%	9,555	32,018	1,877 (39.2)	2,428 (50.7)	4.8	Public
Stitiching 63.	Anonymous submission
Otakudj 64.	30.4	29.2 ±13.9	42.2	12.3%	33.8%	9,558	32,008	1,924 (40.2)	2,463 (51.4)	0.6	Public
Otakudj 64.	Anonymous submission
ARMS 65.	25.8	30.1 ±13.4	43.3	11.8%	33.8%	9,117	32,042	1,785 (37.3)	2,483 (51.9)	1.7	Public
ARMS 65.	Anonymous submission
LDCT 66.	34.7	4.7 ±41.3	16.8	11.4%	32.5%	14,066	32,156	12,348 (259.1)	2,918 (61.2)	20.7	Public
LDCT 66.	F. Solera, S. Calderara, R. Cucchiara. Learning to Divide and Conquer for Online Multi-Target Tracking. In ICCV, 2015
DP_NMS 67.	37.5	14.5 ±14.5	19.7	6.0%	40.8%	13,171	34,814	4,537 (104.7)	3,090 (71.3)	444.8	Public
DP_NMS 67.	H. Pirsiavash, D. Ramanan, C. Fowlkes. Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects. In CVPR, 2011.
Bar_dist 68.	34.8	18.0 ±16.0	17.6	5.7%	35.9%	10,019	36,222	4,161 (101.4)	5,043 (122.9)	2,891.5	Public
Bar_dist 68.	Anonymous submission

Benchmark Statistics

Sequences	Frames	Trajectories	Boxes
11	5783	721	61440

Difficulty Analysis

Sequence difficulty (from easiest to hardest, measured by average MOTA)

TUD-Crossing

(63.8% MOTA)

PETS09-S2L2

(42.5% MOTA)

ETH-Jelmoli

(38.4% MOTA)

...

Venice-1

(21.8% MOTA)

ADL-Rundle-1

(16.5% 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
	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]	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.