TFMOT: Joint Cost Minimization for Multi-Object Tracking

TUD-Crossing


Benchmark:

Short name:

TFMOT

Detector:

Public

Description:

n/a

Reference:

M. Abhijeet Boragule. Joint Cost Minimization for Multi-Object Tracking. In 2017 IEEE International Conference on Advanced Vide and Signale Based Surveillance, 2017.

Last submitted:

March 21, 2017 (3 years ago)

Published:

March 29, 2018 at 10:08:33 CET

Submissions:

3

Project page / code:

n/a

Open source:

No

Hardware:

3.3 GHz 1 core.

Runtime:

11.3 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201523.832.371.335 (4.9)447 (62.0)4,53341,87331.881.20.8404 (12.7)792 (24.9)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-117.335.372.96112,1945,44241.563.84.463106
ADL-Rundle-335.038.173.92125036,04940.589.10.85970
AVG-TownCentre18.028.370.3121521585,66320.890.40.437104
ETH-Crossing16.222.875.0019683017.296.60.055
ETH-Jelmoli29.241.372.94211251,65634.787.60.31632
ETH-Linthescher6.411.273.12180178,3306.797.20.0812
KITTI-1632.239.072.505561,08136.491.70.31730
KITTI-1922.840.464.53246323,46635.174.80.629154
PETS09-S2L238.432.469.03115295,26245.489.21.2145233
TUD-Crossing49.458.674.4334450853.993.10.2617
Venice-115.124.873.7092693,58621.478.40.61929

Raw data: