MPNTrack: Learning a Neural Solver for Multiple Object Tracking

TUD-Crossing


Benchmark:

Short name:

MPNTrack

Detector:

Public

Description:

Project page / code:

n/a

Reference:

G. Brasó, L. Leal-Taixé. Learning a Neural Solver for Multiple Object Tracking. In CVPR, 2020.

Processing:

Batch

Last submitted:

April 16, 2020 (1 month ago)

Published:

April 17, 2020 at 10:41:55 CET

Submissions:

1

Open source:

Yes

Hardware:

NVIDIA Quadro P5000

Runtime:

6.5 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201551.558.676.0225 (31.2)187 (25.9)7,62021,78064.683.91.3375 (5.8)872 (13.5)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-133.353.974.01533,0253,14366.267.16.142111
ADL-Rundle-355.961.881.61981,0013,45466.087.01.63235
AVG-TownCentre60.462.571.586374392,33567.391.61.058222
ETH-Crossing52.162.582.67106141658.590.60.336
ETH-Jelmoli60.472.680.3181337262675.383.70.8730
ETH-Linthescher49.158.580.144966923,82657.288.10.62473
KITTI-1655.569.570.92110763662.690.90.51433
KITTI-1949.162.771.314145992,08860.984.50.634102
PETS09-S2L255.243.774.8625833,59362.791.21.3147238
TUD-Crossing80.762.773.7704515785.895.50.21113
Venice-151.767.674.3736961,50667.081.51.539

Raw data: