You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
LOBSTER outperforms most of the other algorithms in my testing, however:
If I feed in a single image for 1000 times, there should be NO motion and every pixel should be classified into background instead of foreground, right? But, in my case, after 1000 frames, both the background and foreground keep roughly the same as for the 1st frame.
I didn't quite understand why is it so for LOBSTER, but this algorithm should have taken this into consideration, isn't it?
At least, for ViBe, if no motion, every pixel will be correctly classified as background...
Cheers
The text was updated successfully, but these errors were encountered:
Hi @jiapei100 , sorry for my delayed feedback to you.
You're right, I will check this.
For info, I just released a new version of the BGSLibrary, now v3.1.0.
I tested it on Windows, Mac and Linux, both compiling the C++ library on OpenCV 3.4.7, 3.4.16 and 4.6.0.
I also tested its respective Python wrapper and GT user interface.
Please feel free to get back to me if you have any issues,
Andrews
Is it a potential bug for LOBSTER?
LOBSTER outperforms most of the other algorithms in my testing, however:
I didn't quite understand why is it so for LOBSTER, but this algorithm should have taken this into consideration, isn't it?
Cheers
The text was updated successfully, but these errors were encountered: