oICF: Online Multi-Person Tracking using Integral Channel Features

ETH-Jelmoli


Benchmark:

Short name:

oICF

Detector:

Public

Description:

n/a

Reference:

H. Kieritz, S. Becker, W. Hübner, M. Arens. Online Multi-Person Tracking using Integral Channel Features. In IEEE Advanced Video and Signal-based Surveillance (AVSS) 2016, 2016.

Last submitted:

March 27, 2016 (4 years ago)

Published:

April 15, 2016 at 18:24:36 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

2.30GHz, 2 Core

Runtime:

1.4 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201527.140.570.046 (6.4)351 (48.7)7,59436,75740.276.51.3454 (11.3)1,660 (41.3)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-127.746.571.24101,5265,17844.473.03.124141
ADL-Rundle-333.542.472.34121,2155,47846.179.41.963150
AVG-TownCentre15.436.267.511971,5484,41738.263.83.482394
ETH-Crossing22.338.572.01163874126.187.30.2010
ETH-Jelmoli43.658.971.37142021,21952.086.70.51051
ETH-Linthescher13.421.071.761641497,56815.390.10.11248
KITTI-1636.051.371.40323883251.178.51.11963
KITTI-1918.046.164.73201,1483,18240.465.31.152249
PETS09-S2L241.539.468.1449544,50853.284.32.2180477
TUD-Crossing64.269.674.2522037066.497.30.1426
Venice-116.131.772.0195563,26428.570.01.2851

Raw data: