MHT_DAM: Multiple Hypothesis Tracking with Discriminative Appearance Modeling


Benchmark:

Short name:

MHT_DAM

Detector:

Public

Description:

Project page / code:

Reference:

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

Processing:

Batch

Last submitted:

September 25, 2015 (4 years ago)

Published:

April 24, 2015 at 19:09:57 CET

Submissions:

3

Open source:

Yes

Hardware:

2 GHz, 4 Core

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201532.445.371.8115.0316.09,06432,060435

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-118.445.772.410.09.03,2324,31345
ADL-Rundle-338.143.973.24.011.01,0415,18760
AVG-TownCentre27.146.970.439.0100.08374,30074
ETH-Crossing33.649.775.44.013.0476163
ETH-Jelmoli37.463.074.113.015.05181,05614
ETH-Linthescher22.633.175.917.0139.02186,67318
KITTI-1644.457.873.42.03.019073620
KITTI-1930.754.165.96.014.01,2042,46337
PETS09-S2L250.840.070.48.03.09333,667142
TUD-Crossing75.080.374.77.03.032703
Venice-120.238.773.15.06.08412,77919

Raw data:


MHT_DAM