GSCR: Tracking using global sparse collaborative representations


Benchmark:

Short name:

GSCR

Detector:

Public

Description:

n/a

Project page / code:

n/a

Reference:

L. Fagot-Bouquet, R. Audigier, Y. Dhome, F. Lerasle. Online multi-person tracking based on global sparse collaborative representations. In ICIP, 2015.

Processing:

Online

Last submitted:

March 08, 2016 (4 years ago)

Published:

March 15, 2016 at 02:58:15 CET

Submissions:

2

Open source:

No

Hardware:

2.7 GHZ, 8 Core

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201515.827.969.413.0440.07,59743,633514

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-1-1.125.768.52.012.03,1656,17965
ADL-Rundle-331.433.173.12.012.08616,02490
AVG-TownCentre16.532.667.86.0142.04375,48842
ETH-Crossing6.29.273.80.023.0109292
ETH-Jelmoli22.338.569.71.019.02961,65322
ETH-Linthescher5.612.868.01.0171.02518,16416
KITTI-1623.837.870.90.06.0961,18516
KITTI-1912.531.565.11.029.01,0243,59459
PETS09-S2L224.126.867.60.012.09466,214162
TUD-Crossing35.244.272.70.03.07062816
Venice-111.524.671.30.011.04413,57524

Raw data:


GSCR