search

z-x-yang / CFBI

The official implementation of CFBI(+): Collaborative Video Object Segmentation by (Multi-scale) Foreground-Background Integration.
BSD 3-Clause "New" or "Revised" License
322 stars 43 forks source link

How FPS is calculated #21

Closed bo-miao closed 3 years ago

bo-miao commented 3 years ago

Hi,

May I know how to calculate FPS?

In dataset such as DAVIS2017, each frame might contain several objects to track, but the proposed method needs to track each object separately in each frame. In that case, how the FPS is calculated? If the object number is N and each object segmentation time cost is T in one frame, does it mean T*N s is needed in each frame?

Thanks!

z-x-yang commented 3 years ago

We calculated the multi-object FPS. For example, if a video contains 5 objects, we will calculate the inference time for completing all the object predictions.

CFBI tracks all the objects in a parallel way. The backbone feature of CFBI is shared for all the objects in a video. And only the ensembler processed each object separately but in parallel. Thus it will take only a little more computation to process multiple objects, compared to a single object.

bo-miao commented 3 years ago

Thanks for your answer.