search

got-10k / toolkit

Official Python toolkit for generic object tracking benchmark GOT-10k and beyond
http://got-10k.aitestunion.com/
MIT License
554 stars 94 forks source link

ExperimentVOT robustness metric #49

Open bqm1111 opened 3 years ago

bqm1111 commented 3 years ago

When I evaluate my tracker on VOT, it gives the result of robustness of 50.53 which is confusing to me because robustness in VOT result should be < 1. Is there any difference of how robustness metric is calculated in GOT10k toolkit

giorgiocruciata commented 3 years ago

Did you find a solution? my robustness result is 45.64 on VOT 2016

bqm1111 commented 3 years ago

GOT10k implemented the unnormalized robustness. You can see its source code to understand how they implemented it. About the solution, I used python version of the official VOT challenge toolkit