the MWIS part will take a really long time when the number of branches reaches 35 or more. about openmht HOT 8 CLOSED

Can you please try lowering the gating area parameter in params.txt?

from openmht.

I will test that and get back to you.

from openmht.

Yeah, actually I set the gating area to 6, and my input is ground thruth(no false alarm), which means there is only one measurement can be included in the gating area.
I'm thinking maybe there is too many vertices and edges for the MWIS( when the number of tracks reach 70, it feels like to loop forever in the bron_kerbosch() function), so I am wondering how many detections a frame could it handle and what is the N-scan window size you set? Thanks a lot :>

from openmht.

Yes, I think I will try the NetworkX maximum-weighted matching implementation to see if there is an improvement in performance. For track pruning, I set an N-scan window of 1. I will also add a user-defined parameter for this, but you can modify it here in the code:

from openmht.

Any updates on this? I run into the same problem. The MWIS part is taking very long in the second frame with 14 detections.

from openmht.

Any update on this? Its super slow

from openmht.

I have added two missing pruning parameters from the paper: Bth for setting the maximum number of branches, and Nmiss for the maximum number of consecutive frames with missing observations for a track in commit 5627c53. Please try adjusting these parameters to improve performance.

from openmht.

from openmht.