search

iago-suarez / efficient-descriptors

:rocket::rocket: Revisiting Binary Local Image Description for Resource Limited Devices
https://iago-suarez.com/efficient-descriptors
164 stars 26 forks source link

Descriptors Matching Computational Cost #5

Open JajamesVid opened 1 year ago

JajamesVid commented 1 year ago

Hello, I'm trying to reproduce the results of the paper in terms of computational cost using my own computer (intel i7), at the moment I'm able to obtain the same description time in ms using opencv 4.5.5 and oxford dataset.

The issue comes when I arrive to reproduce the matching results, the paper says that detecting 2000 ORB keypoints, descripting them with BAD-256 and matching them using BF Matcher in 100 runs the mean average computational cost is 4.65 ms but I'm obtaining 210 ms.

For the moment I'm using the code that is provided on the repo, called "stereo_demo.cpp", is there something that I'm doing wrong?

Thanks in advance

iago-suarez commented 1 year ago

Hi @JajamesVid thanks for your interest and sorry for the late reply. Are you using binaries compiled in release mode? 210 ms is certainly too much for OpenCV in i7. I used Ubuntu 18in my experiments without other important processes running in parallel.

Can you also try homography_demo,cpp?