CS_MOT: A Cost Matrix Optimization Method Based on Spatial Constraints under Hungarian Algorithm

MOT16-01


Benchmark:

MOT16 | MOT17 |

Short name:

CS_MOT

Detector:

Public

Description:

Reference:

A Cost Matrix Optimization Method Based on Spatial Constraints under Hungarian Algorithm

Last submitted:

July 13, 2020 (3 months ago)

Published:

July 18, 2020 at 08:26:19 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

Tesla P100

Runtime:

1.2 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1646.751.574.076 (10.0)332 (43.7)5,94190,56650.393.91.0619 (12.3)2,981 (59.2)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0130.127.772.02111504,28433.093.40.336145
MOT16-0356.759.274.234262,68942,45459.495.81.81571,485
MOT16-0636.242.072.4101183816,90940.192.40.377271
MOT16-0741.441.271.66189268,50947.989.41.9133407
MOT16-0837.744.777.111225239,82641.393.00.886268
MOT16-1239.753.877.49404254,54545.289.80.52990
MOT16-1418.928.570.449784714,03924.084.01.1101315

Raw data: