Multiple Hypothesis Tracking with Discriminative Appearance Modeling

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

Short name:

MHT_DAM

Benchmark:

Description:

Hardware:

2 GHz, 4 Core

Detector:

Public

Processing:

Batch

Last submitted:

September 25, 2015 (2 years ago)

Published:

April 24, 2015 at 19:09:57 CET

Submissions:

3

Open source:

Yes

Project page / code:

Reference:

C. Kim, F. Li, A. Ciptadi, J. Rehg. Multiple Hypothesis Tracking Revisited. In ICCV, 2015.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
32.471.81.616.0 % 43.8 % 9,06432,0604358262 GHz, 4 CorePublic
IDF1ID PrecisionID Recall
45.358.936.8

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing75.080.374.70.01353.8 % 23.1 % 327036
PETS09-S2L250.840.070.42.14219.0 % 7.1 % 9333,667142201
ETH-Jelmoli37.463.074.11.24528.9 % 33.3 % 5181,0561436
ETH-Linthescher22.633.175.90.21978.6 % 70.6 % 2186,6731833
ETH-Crossing33.649.775.40.22615.4 % 50.0 % 4761635
AVG-TownCentre27.146.970.41.922617.3 % 44.2 % 8374,30074165
ADL-Rundle-118.445.772.46.53231.3 % 28.1 % 3,2324,3134572
ADL-Rundle-338.143.973.21.7449.1 % 25.0 % 1,0415,1876077
KITTI-1644.457.873.40.91711.8 % 17.6 % 1907362032
KITTI-1930.754.165.91.1629.7 % 22.6 % 1,2042,46337164
Venice-120.238.773.11.91729.4 % 35.3 % 8412,7791935

Raw data:


MHT_DAM