Fair: A simple baseline for multi-object tracking

TUD-Crossing


Benchmark:

Short name:

Fair

Detector:

Private

Description:

n/a

Reference:

Y. Zhang, C. Wang, X. Wang, W. Zeng, W. Liu. FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking. In arXiv preprint arXiv:2004.01888, 2020.

Last submitted:

August 02, 2020 (5 months ago)

Published:

May 16, 2020 at 05:52:27 CET

Submissions:

3

Project page / code:

Open source:

Yes

Hardware:

RTX2080ti

Runtime:

30.5 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201560.664.776.5343 (47.6)79 (11.0)7,85415,78574.385.31.4591 (8.0)1,731 (23.3)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-141.356.574.11132,2713,13166.473.14.557221
ADL-Rundle-353.756.480.01831,1523,48365.785.31.871172
AVG-TownCentre58.973.070.6110221,1631,68076.582.52.698312
ETH-Crossing76.776.081.81023119780.496.30.1623
ETH-Jelmoli68.777.581.434145632587.282.91.01259
ETH-Linthescher70.771.881.174395251,98677.893.00.4109196
KITTI-1654.768.474.27131443274.680.21.52556
KITTI-1955.970.272.43121,0621,23876.879.41.058202
PETS09-S2L277.158.075.42715001,58283.694.21.1121392
TUD-Crossing88.882.576.9130506494.295.40.2921
Venice-155.764.078.7853301,66763.589.80.72577

Raw data: