Data Association

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

Short name:

CF_MCMC

Benchmark:

Description:

Mainly use markov chain monte carlo algorithm to associate the detection data to get stable tracking trajectories. Human and shoulder detection is a helper algorithm.

Hardware:

2.26 GHz,2 Core

Detector:

Public

Processing:

Batch

Last submitted:

March 01, 2016 (1 year ago)

Published:

August 19, 2015 at 16:12:16 CET

Submissions:

19

Open source:

No

Project page / code:

n/a

Reference:

Anonymous submission

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
31.469.81.510.3 % 40.9 % 8,79832,5418141,7112.26 GHz,2 CorePublic
IDF1ID PrecisionID Recall
36.447.929.4

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing60.747.471.20.51353.8 % 0.0 % 1023032851
PETS09-S2L244.627.668.53.0427.1 % 7.1 % 1,2883,763288484
ETH-Jelmoli44.951.872.50.84517.8 % 31.1 % 3511,0281955
ETH-Linthescher25.034.972.30.31976.6 % 69.5 % 3496,3153784
ETH-Crossing30.441.273.90.4263.8 % 69.2 % 975911014
AVG-TownCentre35.150.869.02.022612.4 % 35.0 % 8803,69267247
ADL-Rundle-120.333.770.74.6329.4 % 25.0 % 2,2815,06569181
ADL-Rundle-331.831.271.62.3449.1 % 20.5 % 1,4255,365140132
KITTI-1634.851.666.41.9175.9 % 11.8 % 3916625695
KITTI-1921.742.664.91.2624.8 % 27.4 % 1,2572,86365278
Venice-127.525.870.20.81717.6 % 47.1 % 3772,8943590

Raw data:


CF_MCMC
TO