search

cheind / py-motmetrics

:bar_chart: Benchmark multiple object trackers (MOT) in Python
MIT License
1.37k stars 259 forks source link

MOTP is computed incorrectly #112

Closed ningdez closed 4 years ago

ningdez commented 4 years ago

The MOTP is incorrect when IoU is not set to be 0.5. For example, when we set Iou to 0.3, the correct MOTP is (1-motp), where motp is the ouput result.

cheind commented 4 years ago

Hey! The Readme states

Metric MOTP seems to be off. To convert compute (1 - MOTP) * 100. MOTChallenge benchmarks compute MOTP as percentage, while py-motmetrics sticks to the original definition of average distance over number of assigned objects [1].

Does this resolve your issue?

ningdez commented 4 years ago

Hey! The Readme states

Metric MOTP seems to be off. To convert compute (1 - MOTP) * 100. MOTChallenge benchmarks compute MOTP as percentage, while py-motmetrics sticks to the original definition of average distance over number of assigned objects [1].

Does this resolve your issue?

Ok, I got it. Thanks.