LDCT: Learning to Divide and Conquer Tracker


Benchmark:

Short name:

LDCT

Detector:

Public

Description:

Test are performed on fixed camera video only:
- TUD-Crossing
- PETS09-S2L2
- AVG-TownCentre
- ADL-Rundle-3
- KITTI-16
- Venice-1

Results on other sequences are not meaningful.

Project page / code:

Reference:

F. Solera, S. Calderara, R. Cucchiara. Learning to Divide and Conquer for Online Multi-Target Tracking. In ICCV, 2015

Processing:

Online

Last submitted:

April 22, 2015 (4 years ago)

Published:

April 22, 2015 at 22:31:13 CET

Submissions:

1

Open source:

No

Hardware:

3 GHZ, 1 Core

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 20154.716.871.782.0234.014,06632,15612,348

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-1-68.00.370.89.04.06,3584,1415,133
ADL-Rundle-325.220.273.42.027.04537,039110
AVG-TownCentre31.742.072.236.024.01,8782,608395
ETH-Crossing-6.12.573.73.010.078706280
ETH-Jelmoli-23.71.672.88.011.06411,0971,399
ETH-Linthescher-1.72.073.54.0132.02686,7402,076
KITTI-1653.043.479.02.03.09166544
KITTI-19-48.01.266.63.014.02,6262,7922,490
PETS09-S2L247.426.970.86.03.09953,779297
TUD-Crossing67.752.582.99.01.010020551
Venice-133.524.768.40.05.05782,38473

Raw data:


LDCT