We frame the problem of object recognition from edge cues in terms of determining whether individual edge pixels belong to the target object or to clutter, based on the configurat...
When constructing a Bayesian network, it can be advantageous to employ structural learning algorithms to combine knowledge captured in databases with prior information provided by...
Many state-of-the-art object recognition systems rely on identifying the location of objects in images, in order to better learn its visual attributes. In this paper, we propose fo...
We present a method for object tracking over time sequence imagery. The image plane is represented with a 4-connected planar graph where vertices are associated with pixels. On ea...
Mehmet Emre Sargin, Pratim Ghosh, B. S. Manjunath,...
Background subtraction is commonly used to detect foreground objects in video surveillance. Traditional background subtraction methods are usually based on the assumption that the...