EDA_GNN: End-to-end Data Association with Graph Neural Network for Online Multiple-Object Tracking


Benchmark:

Short name:

EDA_GNN

Detector:

Public

Description:

n/a

Project page / code:

n/a

Reference:

Paper ID 2713

Processing:

Online

Last submitted:

November 15, 2018 (1 year ago)

Published:

November 15, 2018 at 17:07:05 CET

Submissions:

1

Open source:

No

Hardware:

NVIDIA TITAN XP

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201521.827.870.565.0290.011,97034,5871,488

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-111.929.271.96.011.02,6465,442115
ADL-Rundle-324.725.771.63.09.02,2435,246166
AVG-TownCentre13.832.768.622.074.01,8064,008347
ETH-Crossing20.431.773.73.014.09469311
ETH-Jelmoli35.642.872.411.014.04231,14466
ETH-Linthescher20.325.873.18.0137.03306,70087
KITTI-1628.526.671.40.02.0285819113
KITTI-1911.127.466.33.019.01,6282,948175
PETS09-S2L236.523.869.12.02.01,2544,577289
TUD-Crossing59.236.872.45.02.010529847
Venice-113.721.870.82.06.01,1562,71272

Raw data:


EDA_GNN