MOT Challenge

MOT17-01-DPM

MOT17-03-DPM

MOT17-06-DPM

MOT17-07-DPM

MOT17-08-DPM

MOT17-12-DPM

MOT17-14-DPM

MOT17-01-FRCNN

MOT17-03-FRCNN

MOT17-06-FRCNN

MOT17-07-FRCNN

MOT17-08-FRCNN

MOT17-12-FRCNN

MOT17-14-FRCNN

MOT17-01-SDP

MOT17-03-SDP

MOT17-06-SDP

MOT17-07-SDP

MOT17-08-SDP

MOT17-12-SDP

MOT17-14-SDP

Benchmark:

MOT17 |

Short name:

CRF_TRA_17

Detector:

Public

Description:

n/a

Reference:

Jun xiang, Chao Ma, Guohan Xu, Jianhua Hou, End-to-End Learning Deep CRF models for Multi-Object Tracking. In IEEE Transactions on Circuits and Systems for Video Technology, 2020

Last submitted:

June 20, 2019 (1 year ago)

Published:

January 17, 2019 at 15:12:54 CET

Submissions:

Project page / code:

n/a

Open source:

Yes

Hardware:

Runtime:

1.4 Hz

Benchmark performance:

Sequence	MOTA	IDF1	HOTA	MOTP	MT	ML	FP	FN	Rcll	Prcn	AssA	DetA	AssRe	AssPr	DetRe	DetPr	LocA	FAF	ID Sw.	Frag
MOT17	53.1	53.7	42.2	76.1	571 (24.2)	724 (30.7)	27,194	234,991	58.4	92.4	41.7	43.1	45.1	73.4	46.2	73.1	79.4	1.5	2,518 (43.2)	4,918 (84.3)

Detailed performance:

Sequence	MOTA	IDF1	HOTA	MOTP	MT	ML	FP	FN	Rcll	Prcn	AssA	DetA	AssRe	AssPr	DetRe	DetPr	LocA	FAF	ID Sw.	Frag
MOT17-01-DPM	47.6	63.0	47.7	73.1	8	7	484	2,889	55.2	88.0	57.5	39.9	61.9	74.8	43.1	68.7	76.8	1.1	9	44
MOT17-01-FRCNN	32.3	47.5	39.9	76.6	7	7	1,166	3,182	50.7	73.7	47.1	34.0	49.6	78.6	40.7	59.3	79.7	2.6	20	39
MOT17-01-SDP	43.7	51.7	42.0	73.6	10	4	1,399	2,189	66.1	75.3	43.9	40.5	48.9	72.6	50.4	57.5	77.6	3.1	42	90
MOT17-03-DPM	54.7	55.1	41.9	75.6	32	27	4,138	42,949	59.0	93.7	40.3	44.0	42.6	74.3	46.5	74.0	78.9	2.8	284	562
MOT17-03-FRCNN	60.7	59.1	46.1	77.1	44	22	3,267	37,709	64.0	95.3	44.5	48.3	48.2	73.5	51.1	76.2	80.2	2.2	209	380
MOT17-03-SDP	76.3	59.6	49.2	77.4	83	14	2,572	21,867	79.1	97.0	41.2	59.0	44.0	72.2	62.6	76.8	80.4	1.7	395	722
MOT17-06-DPM	46.5	59.4	44.2	75.2	40	101	511	5,732	51.4	92.2	51.1	38.4	54.5	76.5	40.6	72.9	78.5	0.4	57	158
MOT17-06-FRCNN	55.4	61.2	48.4	77.3	81	42	1,535	3,629	69.2	84.2	47.7	49.5	63.3	62.0	56.6	68.8	79.9	1.3	88	216
MOT17-06-SDP	59.0	63.8	48.4	75.9	104	59	1,295	3,433	70.9	86.6	47.6	49.3	58.0	66.2	56.0	68.4	79.3	1.1	108	177
MOT17-07-DPM	45.2	49.7	38.0	75.3	9	17	840	8,330	50.7	91.1	38.6	37.7	40.4	77.2	40.1	72.1	78.5	1.7	82	193
MOT17-07-FRCNN	39.6	41.7	32.7	73.1	6	12	994	9,051	46.4	88.8	32.8	33.6	34.8	74.0	36.0	68.7	77.1	2.0	154	310
MOT17-07-SDP	52.1	49.6	38.7	74.3	17	11	1,039	6,912	59.1	90.6	35.6	42.4	38.2	72.2	45.8	70.3	78.1	2.1	140	265
MOT17-08-DPM	31.7	43.3	35.9	79.3	15	34	978	13,374	36.7	88.8	45.1	28.6	47.1	80.5	30.4	73.5	81.5	1.6	67	84
MOT17-08-FRCNN	26.0	31.6	27.5	77.6	8	38	385	15,159	28.2	93.9	34.5	22.1	36.1	80.5	22.8	76.0	81.1	0.6	81	113
MOT17-08-SDP	30.0	32.4	26.9	75.5	9	34	760	13,856	34.4	90.5	28.2	26.1	29.5	76.1	27.4	72.0	79.0	1.2	167	233
MOT17-12-DPM	45.7	56.6	44.4	78.7	18	39	346	4,329	50.1	92.6	51.7	38.2	53.8	81.7	40.6	75.2	81.5	0.4	35	54
MOT17-12-FRCNN	41.4	55.1	41.0	76.6	13	42	479	4,572	47.2	89.5	47.7	35.4	51.2	76.4	38.0	71.9	79.7	0.5	24	51
MOT17-12-SDP	44.1	57.6	43.6	75.7	18	31	890	3,913	54.9	84.2	49.3	38.8	52.7	76.2	43.5	66.8	79.2	1.0	45	74
MOT17-14-DPM	31.2	43.3	31.2	74.8	14	73	909	11,721	36.6	88.2	35.6	27.6	37.7	74.2	29.1	70.1	77.8	1.2	91	158
MOT17-14-FRCNN	28.9	39.6	29.2	69.3	11	62	1,869	11,033	40.3	79.9	30.3	28.4	33.4	64.4	30.9	61.2	73.7	2.5	231	527
MOT17-14-SDP	42.2	49.0	34.0	69.8	24	48	1,338	9,162	50.4	87.4	33.8	34.6	36.6	65.5	37.4	64.8	74.8	1.8	189	468

Raw data:

download

TransCtr

CRF_TRA_17

AFN17

CRF_TRA_17: