RMOT: Bayesian Multi-Object Tracking Using Motion Context from Multiple Objects


Benchmark:

Short name:

RMOT

Detector:

Public

Description:

Project page / code:

n/a

Reference:

J. Yoon, H. Yang, J. Lim, K. Yoon. Bayesian Multi-Object Tracking Using Motion Context from Multiple Objects. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2015.

Processing:

Online

Last submitted:

December 09, 2014 (5 years ago)

Published:

December 09, 2014 at 03:08:21 CET

Submissions:

2

Open source:

No

Hardware:

3.5 GHz, 1 Core

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201518.632.669.638.0384.012,47336,835684

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-1-1.333.269.77.07.04,7904,54196
ADL-Rundle-320.630.971.64.010.02,5745,388112
AVG-TownCentre5.526.666.92.0135.01,2605,42474
ETH-Crossing16.820.373.61.020.01181310
ETH-Jelmoli40.449.671.38.015.02631,21929
ETH-Linthescher13.119.371.93.0160.01427,58926
KITTI-1637.652.970.80.03.018285821
KITTI-1917.837.865.53.020.01,1983,11779
PETS09-S2L237.232.367.74.06.01,1264,743190
TUD-Crossing62.864.673.04.02.03436214
Venice-118.832.871.22.06.08932,78133

Raw data:


RMOT