Tracking Through Clutter Using Graph Cuts

The standard graph cut technique is a robust method for globally optimal image segmentation. However, because of its global nature, it is prone to capture outlying areas similar to the object of interest. This paper proposes a novel method to constrain the standard graph cut technique for tracking objects in a region of interest. By introducing an additional penalty on pixels based upon their distance from a region of interest, segmentation is biased to remain in this area. We employ a filter which predicts the location of the object. The distance penalty is then centered at this location and adaptively scaled based on prediction confidence. This method tracks at real-time rates and easily generalizes to tracking multiple noninteracting objects.