MTS tracker

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

Short name:

MTSTracker

Benchmark:

Description:

n/a

Hardware:

CPU 16GHZ, 8 core

Detector:

Public

Processing:

Online

Last submitted:

July 07, 2017 (5 months ago)

Published:

July 07, 2017 at 15:21:09 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

F. Nguyen Thi Lan Anh, F. Bremond. Multi-Object Tracking using Multi-Channel Part Appearance Representation. In International conference on Advanced video and Signal Based Surveillance, 2017.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
20.670.32.69.0 % 36.9 % 15,16132,2121,3872,357CPU 16GHZ, 8 corePublic
IDF1ID PrecisionID Recall
31.938.027.5

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing72.168.873.00.31361.5 % 7.7 % 552302243
PETS09-S2L237.128.368.74.34211.9 % 7.1 % 1,8813,744435599
ETH-Jelmoli28.948.472.71.54520.0 % 33.3 % 6481,1104566
ETH-Linthescher22.029.873.10.41974.1 % 66.0 % 4246,46380176
ETH-Crossing24.843.873.40.4263.8 % 46.2 % 86662612
AVG-TownCentre21.839.468.83.82268.8 % 27.9 % 1,7173,671203396
ADL-Rundle-12.425.671.18.43218.8 % 25.0 % 4,2004,749138241
ADL-Rundle-324.729.971.63.8449.1 % 20.5 % 2,4005,062197219
KITTI-1628.439.871.61.3170.0 % 23.5 % 27288858103
KITTI-196.632.265.81.8626.5 % 27.4 % 1,8562,986147379
Venice-15.225.770.83.6170.0 % 23.5 % 1,6222,64756123

Raw data:


IOU
MTSTracker