rafaelpadilla/review_object_detection_metrics

Equation (9) and (11) in publication

karl-gardner opened this issue · 3 comments

Hello Rafael,

I will be using an example like the one you have in the publication for my proposal defense, and I am trying to understand how you have derived equation (11) in the paper. I have gone through the math and do understand the following statement you make:

"Actually the N-point interpolation as defined by Equation (11) computes an AP value
which is equal to the value computed by the Riemann integral in Equation (9) multiplied
by (N−1)/N"

However, I don't understand why the AP value from the Riemann integral isn't used directly. Thus, I am wondering why the following value wouldn't be used:

image

Is this just from what people have used from in the previous implementations or maybe equation (8) in the paper?

Thanks,

Karl Gardner

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

Hello @rafaelpadilla,

Any thoughts?

Thanks,

Karl

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.