Potential Position Based Multiple Object Tracking


Short name:

PoMOT

Benchmark:

Description:

n/a

Hardware:

1.8 GHZ

Detector:

Public

Processing:

Online

Last submitted:

July 16, 2019 (1 month ago)

Published:

July 16, 2019 at 21:10:01 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

Anonymous submission

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
16.770.51.85.0 % 50.3 % 10,18540,0259681,7481.8 GHZPublic
IDF1ID PrecisionID Recall
28.842.421.8

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing48.947.872.50.81330.8 % 15.4 % 1683682747
PETS09-S2L228.426.668.82.9424.8 % 21.4 % 1,2725,382249443
ETH-Jelmoli22.940.571.61.64517.8 % 26.7 % 6861,20069109
ETH-Linthescher12.425.171.60.91973.0 % 67.0 % 1,1216,62777161
ETH-Crossing12.733.872.00.9263.8 % 53.8 % 1986661221
AVG-TownCentre-3.418.367.73.42260.9 % 58.4 % 1,5285,669197328
ADL-Rundle-15.724.271.95.13218.8 % 46.9 % 2,5416,123111169
ADL-Rundle-330.137.272.31.6449.1 % 29.5 % 1,0116,00985109
KITTI-1630.241.672.00.9175.9 % 23.5 % 1969583358
KITTI-1914.433.265.91.1623.2 % 32.3 % 1,1183,36885257
Venice-111.821.272.10.8170.0 % 58.8 % 3463,6552346

Raw data:

n/a


PoMOT