Online Multi-Person Tracking with Two-Stage Data Association and Online Appearance Model 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:

TSDA_OAL

Benchmark:

Description:

n/a

Hardware:

3.4GHz, 4 Core

Detector:

Public

Processing:

Online

Last submitted:

January 17, 2016 (1 year ago)

Published:

January 08, 2016 at 09:32:23 CET

Submissions:

4

Open source:

No

Project page / code:

n/a

Reference:

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
18.669.72.89.4 % 42.3 % 16,35032,8538061,5443.4GHz, 4 CorePublic
IDF1ID PrecisionID Recall
36.142.731.2

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing63.864.474.00.41346.2 % 15.4 % 723101722
PETS09-S2L238.632.768.54.34216.7 % 7.1 % 1,8783,762275410
ETH-Jelmoli26.047.769.61.84520.0 % 31.1 % 7701,0664186
ETH-Linthescher12.927.171.30.61972.5 % 75.1 % 7696,9773071
ETH-Crossing15.434.872.60.6260.0 % 57.7 % 13471325
AVG-TownCentre18.845.767.43.922611.1 % 36.3 % 1,7723,930105270
ADL-Rundle-1-6.133.770.610.93221.9 % 21.9 % 5,4624,312104216
ADL-Rundle-327.734.272.03.3449.1 % 18.2 % 2,0455,200100105
KITTI-1630.547.169.61.3170.0 % 11.8 % 2808782462
KITTI-196.336.864.81.7623.2 % 30.6 % 1,8233,10777227
Venice-112.933.470.63.01717.6 % 29.4 % 1,3452,5983170

Raw data:


TSDA_OAL