LP2D_16: Linear Programming 2D coordinates baseline

MOT16-01


Benchmark:

MOT16 |

Short name:

LP2D_16

Detector:

Public

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.

Project page / code:

Reference:

MOT baseline: Linear programming on 2D image coordinates.

Processing:

Batch

Last submitted:

February 28, 2017 (3 years ago)

Published:

February 28, 2017 at 12:16:56 CET

Submissions:

1

Open source:

Yes

Hardware:

3 GHz, 1 core

Runtime:

49.3 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1635.734.275.866 (8.7)385 (50.7)5,084111,16339.093.30.9915 (23.4)1,264 (32.4)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-011.930.372.22396765,58412.754.51.51266
MOT16-037.134.874.9257927,41269,49233.556.118.3263707
MOT16-0638.946.473.9211323186,65942.393.90.373143
MOT16-0723.032.273.65331,80610,69534.575.73.667242
MOT16-087.029.378.86512,37413,11321.760.43.882143
MOT16-1217.549.577.19681,0215,71931.171.61.110065
MOT16-144.120.974.622701,68515,99413.559.62.243119

Raw data: