MOT20

Pedestrian Detection Challenge. This benchmark contains 8 challenging video sequences (4 train, 4 test) in unconstrained environments. Tracking and evaluation are done in image coordinates. All sequences have been annotated with high accuracy, strictly following a well-defined protocol.

Training Set

Sample	Name	FPS	Resolution	Length	Tracks	Boxes	Density	Description	Source	Ref.
	MOT20-05	25	1654x1080	3315 (02:13)	1211	751330	226.6	Crowded square by night time.	link	[1]
	MOT20-03	25	1173x880	2405 (01:36)	735	356728	148.3	People leaving entrance of stadium by night time, elevated viewpoint.	link	[1]
	MOT20-02	25	1920x1080	2782 (01:51)	296	202215	72.7	Crowded indoor train station.	link	[1]
	MOT20-01	25	1920x1080	429 (00:17)	90	26647	62.1	Crowded indoor train station.	link	[1]
	Total			8931 frm. (357 s.)	2332	1336920	149.7

Test Set

Sample	Name	FPS	Resolution	Length	Tracks	Boxes	Density	Description	Source	Ref.
	MOT20-08	25	1920x734	806 (00:32)	279	145301	180.3	A pedestrian street scene.	link	[1]
	MOT20-07	25	1920x1080	585 (00:23)	126	41096	70.2	Crowded indoor train station.	link	[1]
	MOT20-06	25	1920x734	1008 (00:40)	368	207543	205.9	A pedestrian street scene.	link	[1]
	MOT20-04	25	1545x1080	2080 (01:23)	728	371525	178.6	Crowded square by night time.	link	[1]
	Total			4479 frm. (178 s.)	1501	765465	170.9

Download