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

TUD-Crossing PETS09-S2L2 ETH-Jelmoli ETH-Linthescher ETH-Crossing AVG-TownCentre ADL-Rundle-1 ADL-Rundle-3 KITTI-16 KITTI-19

Short name:

EDA_GNN

Benchmark:

Description:

n/a

Hardware:

NVIDIA TITAN XP

Detector:

Public

Processing:

Online

Last submitted:

November 15, 2018 (1 month ago)

Published:

November 15, 2018 at 17:07:05 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

Paper ID 2713

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
21.870.52.19.0 % 40.2 % 11,97034,5871,4881,851NVIDIA TITAN XPPublic
IDF1ID PrecisionID Recall
27.835.822.6

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing59.236.872.40.51338.5 % 15.4 % 1052984735
PETS09-S2L236.523.869.12.9424.8 % 4.8 % 1,2544,577289406
ETH-Jelmoli35.642.872.41.04524.4 % 31.1 % 4231,1446662
ETH-Linthescher20.325.873.10.31974.1 % 69.5 % 3306,7008796
ETH-Crossing20.431.773.70.42611.5 % 53.8 % 946931115
AVG-TownCentre13.832.768.64.02269.7 % 32.7 % 1,8064,008347419
ADL-Rundle-111.929.271.95.33218.8 % 34.4 % 2,6465,442115156
ADL-Rundle-324.725.771.63.6446.8 % 20.5 % 2,2435,246166133
KITTI-1628.526.671.41.4170.0 % 11.8 % 285819113117
KITTI-1911.127.466.31.5624.8 % 30.6 % 1,6282,948175293
Venice-113.721.870.82.61711.8 % 35.3 % 1,1562,71272119

Raw data:

n/a


AEb
EDA_GNN