v64
ML model
Select shoe
Camera input
Enable ML
OF enable
OF image size
OF window size
OF Thread
OF enable GPU (test)
Distortion
Vertical sync
Low quality
Resize shoes by reproj error
Enable smooth
Keep shoe visible for short time
Preffer points close to last pos
Disable confidence for legit points
Compute jitter points
Compute missing points
Ignore points out of cluster
Ignore points at wrong foot
Ignore points by reprojection
Ignore output by reprojection
Ignore output by size
Hide one shoe if overlapping
Show points
Show point labels
Show ML frame
Enable cropping
Compute mode
Async mode
Buffer length
1
Shoes visibility
Confidence
0.15
FPS cap
30
TF backend