TSDA_OAL: Online Multi-Person Tracking with Two-Stage Data Association and Online Appearance Model Learning


Benchmark:

Short name:

TSDA_OAL

Detector:

Public

Description:

n/a

Project page / code:

n/a

Reference:

Processing:

Online

Last submitted:

January 17, 2016 (4 years ago)

Published:

January 08, 2016 at 09:32:23 CET

Submissions:

4

Open source:

No

Hardware:

3.4GHz, 4 Core

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201518.636.169.768.0305.016,35032,853806

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-1-6.133.770.67.07.05,4624,312104
ADL-Rundle-327.734.272.04.08.02,0455,200100
AVG-TownCentre18.845.767.425.082.01,7723,930105
ETH-Crossing15.434.872.60.015.01347132
ETH-Jelmoli26.047.769.69.014.07701,06641
ETH-Linthescher12.927.171.35.0148.07696,97730
KITTI-1630.547.169.60.02.028087824
KITTI-196.336.864.82.019.01,8233,10777
PETS09-S2L238.632.768.57.03.01,8783,762275
TUD-Crossing63.864.474.06.02.07231017
Venice-112.933.470.63.05.01,3452,59831

Raw data:


TSDA_OAL