Online Multi-Person Tracking using Integral Channel Features

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

Short name:

oICF

Benchmark:

Description:

n/a

Hardware:

2.30GHz, 2 Core

Detector:

Public

Processing:

Online

Last submitted:

March 27, 2016 (1 year ago)

Published:

April 15, 2016 at 18:24:36 CET

Submissions:

1

Open source:

No

Project page / code:

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.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
27.170.01.36.4 % 48.7 % 7,59436,7574541,6602.30GHz, 2 CorePublic
IDF1ID PrecisionID Recall
40.558.830.9

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing64.269.674.20.11338.5 % 15.4 % 20370426
PETS09-S2L241.539.468.12.2429.5 % 9.5 % 9544,508180477
ETH-Jelmoli43.658.971.30.54515.6 % 31.1 % 2021,2191051
ETH-Linthescher13.421.071.70.11973.0 % 83.2 % 1497,5681248
ETH-Crossing22.338.572.00.2263.8 % 61.5 % 38741010
AVG-TownCentre15.436.267.53.42264.9 % 42.9 % 1,5484,41782394
ADL-Rundle-127.746.571.23.13212.5 % 31.3 % 1,5265,17824141
ADL-Rundle-333.542.472.31.9449.1 % 27.3 % 1,2155,47863150
KITTI-1636.051.371.41.1170.0 % 17.6 % 2388321963
KITTI-1918.046.164.71.1624.8 % 32.3 % 1,1483,18252249
Venice-116.131.772.01.2175.9 % 52.9 % 5563,264851

Raw data:


oICF