A moving region whose location and extend change over time can imply topological changes such as region split and hole formation. To study this phenomenon is useful in many applic...
This article describes a method to insert virtual objects into a real video stream based on feature tracking and camera pose estimation from a set of single-camera video frames. To...
Computational models of visual attention result in considerable data compression by eliminating processing on regions likely to be devoid of meaningful content. While saliency map...
We present a Bayesian framework for learning higherorder transition models in video surveillance networks. Such higher-order models describe object movement between cameras in the...
The task of multi-camera surveillance is to reconstruct the paths taken by all moving objects that are temporarily visible from multiple non-overlapping cameras. We present a Baye...