Data association using deep network

TUD-Crossing PETS09-S2L2 ETH-Jelmoli ETH-Linthescher ETH-Crossing AVG-TownCentre ADL-Rundle-1 ADL-Rundle-3 KITTI-16 KITTI-19

Short name:

DEEPDA_MOT

Benchmark:

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

Hardware:

i7, 1080ti

Detector:

Public

Processing:

Online

Last submitted:

September 17, 2018 (7 months ago)

Published:

January 18, 2019 at 12:21:30 CET

Submissions:

4

Open source:

No

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.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
22.570.91.36.4 % 62.0 % 7,34639,0921,1591,538i7, 1080tiPublic
IDF1ID PrecisionID Recall
25.939.819.2

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing59.840.371.70.51346.2 % 7.7 % 973073932
PETS09-S2L235.822.868.74.14211.9 % 9.5 % 1,8063,900481606
ETH-Jelmoli31.043.272.31.54520.0 % 26.7 % 6671,0067789
ETH-Linthescher20.924.973.20.21974.6 % 70.1 % 2846,6899597
ETH-Crossing23.930.273.70.32611.5 % 53.8 % 616901216
AVG-TownCentre1.45.269.00.42260.4 % 92.9 % 1976,8044442
ADL-Rundle-111.325.272.63.73218.8 % 53.1 % 1,8366,33188138
ADL-Rundle-333.533.872.90.8446.8 % 31.8 % 4956,1947582
KITTI-1633.434.371.21.5170.0 % 11.8 % 31273883120
KITTI-1919.024.466.20.5623.2 % 45.2 % 5453,681100207
Venice-115.324.670.62.31711.8 % 41.2 % 1,0462,75265109

Raw data:

n/a


DEEPDA_MOT
eTC