Predict and Associate Online Tracker

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

Short name:

CppSORT

Benchmark:

Description:

n/a

Hardware:

1,8 GHz i5

Detector:

Public

Processing:

Online

Last submitted:

April 03, 2017 (8 months ago)

Published:

June 23, 2017 at 07:47:38 CET

Submissions:

1

Open source:

Yes

Project page / code:

Reference:

S. Murray. Real-Time Multiple Object Tracking - A Study on the Importance of Speed. In arXiv preprint arXiv:1709.03572, 2017.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
21.771.21.53.7 % 49.1 % 8,42238,4541,2312,0051,8 GHz i5Public
IDF1ID PrecisionID Recall
26.839.720.3

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing50.648.174.00.1137.7 % 15.4 % 224893357
PETS09-S2L236.823.869.31.2420.0 % 16.7 % 5115,251331480
ETH-Jelmoli36.346.473.50.54511.1 % 33.3 % 2061,3585288
ETH-Linthescher13.719.174.20.11971.5 % 79.2 % 627,58165119
ETH-Crossing17.925.675.30.0260.0 % 61.5 % 9806818
AVG-TownCentre20.333.269.51.02263.1 % 47.3 % 4695,100131259
ADL-Rundle-19.022.771.67.03218.8 % 25.0 % 3,5234,757189292
ADL-Rundle-323.326.872.93.2446.8 % 25.0 % 2,0005,630172218
KITTI-1630.136.373.00.5170.0 % 17.6 % 1111,0334587
KITTI-1919.131.166.10.8623.2 % 35.5 % 8493,346126263
Venice-115.821.772.41.5170.0 % 41.2 % 6603,10379124

Raw data:

n/a


CppSORT
MTT