Online Deep Tracking Metric learning

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

Short name:

AMIR15

Benchmark:

Description:

n/a

Hardware:

TITAN X 3GHZ 1 Core

Detector:

Public

Processing:

Online

Last submitted:

March 14, 2017 (7 months ago)

Published:

November 21, 2016 at 23:48:33 CET

Submissions:

3

Open source:

No

Project page / code:

Reference:

A. Sadeghian, A. Alahi, S. Savarese. Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies. In arXiv preprint arXiv:1701.01909, 2017.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
37.671.71.415.8 % 26.8 % 7,93329,3971,0262,024TITAN X 3GHZ 1 CorePublic
IDF1ID PrecisionID Recall
46.058.438.0

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing73.757.474.80.11353.8 % 0.0 % 182561636
PETS09-S2L247.036.370.51.44211.9 % 9.5 % 6164,236254397
ETH-Jelmoli45.158.273.70.64517.8 % 37.8 % 2611,1141861
ETH-Linthescher34.544.675.20.31977.6 % 46.7 % 3305,370145332
ETH-Crossing32.946.876.30.2267.7 % 38.5 % 336192147
AVG-TownCentre36.252.569.53.222626.1 % 17.7 % 1,4482,882234389
ADL-Rundle-124.944.371.96.13212.5 % 3.1 % 3,0413,838107254
ADL-Rundle-340.645.072.90.9449.1 % 25.0 % 5525,387101130
KITTI-1650.463.573.30.51711.8 % 11.8 % 1117141835
KITTI-1936.751.766.00.7628.1 % 19.4 % 7262,60255220
Venice-129.140.472.51.81717.6 % 23.5 % 7972,37957123

Raw data:


LMP
AMIR15