From Wikibooks, open books for an open world
< SwisTrack‎ | Components
Jump to navigation Jump to search


Uses CamShiftTracking. I always ran it on the post-background-subtracted video. That worked well, but it tended to lose the person when they moved too quickly. I track only using R. I recently added multidimensional histograms so it can use more than one channel but it doesn't work so well. I use motion templates for my tracking now.

On the other hand, I think it should be possible to get this working... cam shift is *supposed* to be good.



The number of histogram dimensions; the number of channels to use in tracking.


Threshold for "almost black."


Threshold for "almost grey."

These parameters screen out noise. Read "Seeing with OpenCV" from Servo magazine for details. Swistrack uses the library described in that article. (Google for camshift-Servo-OpenCV-part3.pdf.)


The length in pixels of the side of a square to make an initial window size. It will always use the same size. Really it should set this automatically from the particle...


The number of frames to keep the track around before killing it, if it hasn't been updated.


The minimum distance a new track must be from existing tracks.


If two tracks get less than this distance to each other, the shorter one will be destroyed.


The maximum number of simultaneous trackers.