CVPR 2019 Detection Challenge

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.

Jump to download

Training Set

SampleName FPS Resolution Length Tracks Boxes DensityDescriptionSourceRef.
1CVPR19-01251920x1080429 (00:17)902621961.1Crowded indoor train station.link[?]
2CVPR19-02251920x10802782 (01:51)29519975271.8Crowded indoor train station.link[?]
3CVPR19-05251920x10803315 (02:13)1251815068245.9Crowded square by night time.link[?]
4CVPR19-03251920x8802405 (01:36)754414734172.4People leaving entrance of stadium by night time, elevated viewpoint.link[?]
Total 8931 frm.
(357 s.)
2390 1455773 163.0

Test Set

SampleName FPS Resolution Length Tracks Boxes DensityDescriptionSourceRef.
1CVPR19-04251920x10802080 (01:23)756425216204.4Crowded square by night time.link[?]
2CVPR19-07251920x1080585 (00:23)1254051169.2Crowded indoor train station.link[?]
3CVPR19-06251920x7341008 (00:40)340197382195.8A pedestrian street scene.link[?]
4CVPR19-08251920x734806 (00:32)271140261174.0A pedestrian street scene.link[?]
Total 4479 frm.
(178 s.)
1492 803370 179.4


Download

Get all data (5.3 GB)
Get detections and labels only (12.7 MB)
Get development kit (0.5 MB)