RAR15pub: Recurrent Autoregressive Networks for Online Multi-Object Tracking


Benchmark:

Short name:

RAR15pub

Detector:

Public

Description:

Recurrent autoregressive networks tracking framework with public detections

Project page / code:

Reference:

K. Fang, Y. Xiang, X. Li, S. Savarese. Recurrent Autoregressive Networks for Online Multi-Object Tracking. In The IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.

Processing:

Online

Last submitted:

March 27, 2017 (3 years ago)

Published:

July 23, 2018 at 09:34:33 CET

Submissions:

2

Open source:

No

Hardware:

Titan X, 1.5GHZ, 1Core

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201535.145.470.994.0305.06,77132,717381

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-126.347.471.58.011.02,1354,69031
ADL-Rundle-339.643.172.24.010.07295,34464
AVG-TownCentre30.351.369.442.096.09174,03825
ETH-Crossing37.655.174.85.014.076190
ETH-Jelmoli40.658.372.79.013.04861,00418
ETH-Linthescher26.938.273.712.0132.01996,30723
KITTI-1641.257.772.50.03.017480918
KITTI-1931.350.166.13.014.08192,80941
PETS09-S2L249.636.469.64.03.07983,923135
TUD-Crossing70.177.872.76.01.04627311
Venice-126.039.071.81.08.04612,90115

Raw data:


RAR15pub