2D MOT 2015

This benchmark contains video sequences in unconstrained environments filmed with both static and moving cameras. Tracking and evaluation are done in image coordinates.

Jump to download

Training Set

SampleName FPS Resolution Length Tracks Boxes DensityDescriptionSourceRef.
1PETS09-S2L17768x576795 (01:54)1944765.6A widely used sequence showing up to 8 walking pedestrians, partly in unusual patterns.link[1]
2KITTI-13101242x375340 (00:34)427622.2Busy urban environment filmed from a moving carlink[2]
3KITTI-17101224x370145 (00:15)96834.7Walking pedestrians on a sunny day, static cameralink[2]
4ETH-Bahnhof14640x4801000 (01:11)17154155.4Street scene from a moving platformlink[3]
5ETH-Sunnyday14640x480354 (00:25)3018585.2Street scene on a sunny day from a moving platformlink[3]
6ETH-Pedcross214640x480840 (01:00)13362637.5Street scene from a moving platformlink[3]
7TUD-Stadtmitte25640x480179 (00:07)1011566.5A static camera at about 2 meters height shows walking people on the street.link[4]
8TUD-Campus25640x48071 (00:03)83595.1A short sequence with side-view pedestrianslink[5]
9ADL-Rundle-6301920x1080525 (00:18)2450099.5A pedestrian street scene filmed from a low angle.link[6]
10ADL-Rundle-8301920x1080654 (00:22)28678310.4A pedestrian scene filmed at night by a moving cameralink[6]
11Venice-2301920x1080600 (00:20)26714111.9People walking around a large square.link[6]
Total 5503 frm.
(389 s.)
500 39905 7.3

Test Set

SampleName FPS Resolution Length Tracks Boxes DensityDescriptionSourceRef.
1AVG-TownCentre2.51920x1080450 (03:45)226714815.9A pedestrian street filmed from an elevated pointlink[7]
2PETS09-S2L27768x576436 (01:02)42964122.1A crowded scene shown from an elevated viewpoint.link[1]
3KITTI-16101224x370209 (00:21)1717018.1Pedestrians crossing a street filmed from a carlink[2]
4KITTI-19101238x3741059 (01:46)6253435.0A street scene from a moving vehiclelink[2]
5ETH-Jelmoli14640x480440 (00:31)4525375.8Street scene from a moving platformlink[3]
6ETH-Linthescher14640x4801194 (01:25)19789307.5Street scene from a moving platformlink[3]
7ETH-Crossing14640x480219 (00:16)2610034.6Street scene from a moving platformlink[3]
8TUD-Crossing25640x480201 (00:08)1311025.5A road crossing from a side viewlink[5]
9ADL-Rundle-1301920x1080500 (00:17)32930618.6A busy pedestrian street filmed at eye level by a moving cameralink[6]
10ADL-Rundle-3301920x1080625 (00:21)441016616.3A crowded pedestrian street, stationary cameralink[6]
11Venice-1301920x1080450 (00:15)17456310.1People walking around a large square.link[6]
Total 5783 frm.
(607 s.)
721 61440 10.6


Download

Get all data (1.3 GB)
Get detections and labels only (3.7 MB)
Get development kit (0.5 MB)

References:


[1] Ferryman, J. & Shahrokni, A. PETS2009: Dataset and challenge. In 11th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS), 2009.
[2] Geiger, A., Lenz, P. & Urtasun, R. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012.
[3] Ess, A., Leibe, B. & Gool, L.V. Depth and Appearance for Mobile Scene Analysis. In Proceedings of the Eleventh IEEE International Conference on Computer Vision, 2007.
[4] Andriluka, M., Roth, S. & Schiele, B. Monocular 3D Pose Estimation and Tracking by Detection. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010.
[5] Andriluka, M., Roth, S. & Schiele, B. People-Tracking-by-Detection and People-Detection-by-Tracking. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008.
[6] Leal-Taixé, L., Milan, A., Reid, I., Roth, S. & Schindler, K. MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking. arXiv:1504.01942 [cs], 2015., (arXiv: 1504.01942).
[7] Benfold, B. & Reid, I. Guiding Visual Surveillance by Tracking Human Attention. In Proceedings of the British Machine Vision Conference, 2009.