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
Well, I guess it's possible to modify headtrackr to do this, but in practice I think it would take a lot of work to get it to work properly. First of all, headtrackr is based on the "camshift" algorithm, which tracks faces purely by color. This algorithm is very quick, but also pretty imprecise, so it's likely that if two faces (of similar color) were somewhat close to each other, the camshift algorithm would get confused and mix up the faces. Second, if the tracker lost track of one of the faces, it would need to be able to detect the "correct" face when re-initializing tracking. This is a bit tricky and I can't think of an immediate solution to it.
Is it possible to modify the library to support simultaneously tracking multiple faces?
The text was updated successfully, but these errors were encountered: