LDCT: Learning to Divide and Conquer Tracker

ETH-Crossing


Benchmark:

MOT15 |

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.

Reference:

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

Last submitted:

April 22, 2015 (6 years ago)

Published:

April 22, 2015 at 22:31:13 CET

Submissions:

1

Project page / code:

Open source:

No

Hardware:

3 GHZ, 1 Core

Runtime:

20.7 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT154.716.819.082 (11.4)234 (32.5)14,06632,15647.767.612.430.814.572.637.553.175.32.412,348 (259.1)2,918 (61.2)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
ADL-Rundle-1-68.00.32.8946,3584,14155.544.80.326.70.3100.044.135.674.212.75,133570
ADL-Rundle-325.220.216.82274537,03930.887.312.922.513.566.323.767.276.70.7110101
AVG-TownCentre31.742.033.836241,8782,60863.570.727.641.934.949.051.457.275.24.2395509
ETH-Crossing-6.12.56.73107870629.679.22.321.52.3100.023.262.176.60.428044
ETH-Jelmoli-23.71.66.78116411,09756.869.21.435.71.494.744.654.376.31.51,399182
ETH-Linthescher-1.72.05.241322686,74024.589.11.818.11.8100.018.868.477.00.22,076435
KITTI-1653.043.435.4239166560.991.926.946.631.356.650.576.282.40.44457
KITTI-19-48.01.24.93142,6262,79247.749.31.427.41.4100.038.639.870.72.52,490561
PETS09-S2L247.426.922.7639953,77960.885.512.841.413.859.945.864.474.82.3297300
TUD-Crossing67.752.545.19110020581.490.033.262.038.756.269.977.384.80.55130
Venice-133.524.722.0055782,38447.879.014.634.415.561.537.361.872.61.373129

Raw data: