DEEPDA_MOT: Data association using deep network


Benchmark:

Short name:

DEEPDA_MOT

Detector:

Public

Description:

Yoon, Kwangjin; Kim, Du Y.; Yoon, Young-Chul; Jeon, Moongu. 2019. "Data Association for Multi-Object Tracking via Deep Neural Networks." Sensors 19, no. 3: 559

Project page / code:

Reference:

K. Yoon, D. Kim, Y. Yoon, M. Jeon. Data Association for Multi-Object Tracking via Deep Neural Networks. In Sensors, 2019.

Processing:

Online

Last submitted:

September 17, 2018 (1 year ago)

Published:

January 18, 2019 at 12:21:30 CET

Submissions:

4

Open source:

No

Hardware:

i7, 1080ti

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201522.525.970.946.0447.07,34639,0921,159

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-111.325.272.66.017.01,8366,33188
ADL-Rundle-333.533.872.93.014.04956,19475
AVG-TownCentre1.45.269.01.0210.01976,80444
ETH-Crossing23.930.273.73.014.06169012
ETH-Jelmoli31.043.272.39.012.06671,00677
ETH-Linthescher20.924.973.29.0138.02846,68995
KITTI-1633.434.371.20.02.031273883
KITTI-1919.024.466.22.028.05453,681100
PETS09-S2L235.822.868.75.04.01,8063,900481
TUD-Crossing59.840.371.76.01.09730739
Venice-115.324.670.62.07.01,0462,75265

Raw data:


DEEPDA_MOT