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
To do that, I recommend creating an artificial time-lapse and setting the max_noise parameter to create some variation between frames -- ultrack over-segments when frames are identical and without noise.
video=np.stack([image] *5) # creating 5 frames videosconfig.segmentation_config.max_noise=0.01
... # set other configurations as usual and compute foreground and contour maps# run ultrack on foreground and video contour maps
Hello,
I wonder if Ultrack could be used for segmentation of non-timelapse datasets and if that is possible how that could be done?
Thanks!
The text was updated successfully, but these errors were encountered: