Linear Programming 2D coordinates baseline

MOT16-01 MOT16-03 MOT16-06 MOT16-07 MOT16-08 MOT16-12 MOT16-14

Short name:

LP2D_16

Benchmark:

Description:

The tracker builds a graphical model where nodes are the 2D detections. The solution is then found by computing the minimum cost-flow problem.

Hardware:

3 GHz, 1 core

Detector:

Public

Processing:

Batch

Last submitted:

February 28, 2017 (1 year ago)

Published:

February 28, 2017 at 12:16:56 CET

Submissions:

1

Open source:

Yes

Project page / code:

Reference:

MOT baseline: Linear programming on 2D image coordinates.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
35.775.80.98.7 % 50.7 % 5,084111,1639151,2643 GHz, 1 corePublic
IDF1ID PrecisionID Recall
34.258.024.2

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0123.630.373.20.22313.0 % 56.5 % 884,7831739
MOT16-0341.334.875.91.814810.8 % 31.8 % 2,71958,275418546
MOT16-0641.446.473.90.422110.9 % 48.9 % 4316,202126165
MOT16-0731.032.274.21.1547.4 % 48.1 % 55810,61991184
MOT16-0826.529.379.80.9639.5 % 46.0 % 57511,6418089
MOT16-1237.949.577.30.38610.5 % 54.7 % 2994,8321829
MOT16-1416.720.974.90.61642.4 % 70.1 % 41414,811165212

Raw data:


LP2D_16
AM