Video tracking is widely used for surveillance, security, and defense purposes. In cases where the camera is not fixed due to pans and tilts, or due to being fixed on a moving platform, tracking can become more difficult. Camera motion must be taken into account, and objects that come and go from the field of view should be continuously and uniquely tracked. We propose a tracking system that can meet these needs by using a frame registration technique to estimate camera motion. This estimate is then used as the input control signal to a Kalman filter which estimates the target's motion model based on measurements from a mean-shift localization scheme. Thus we decouple the camera and object motion and recast the problem in terms of a principled control theory solution. Our experiments show that using a controller built on these principles we are able to track videos with multiple objects in sequences with moving cameras. Furthermore, the techniques are computationally efficient and allow us to accomplish these results in real-time. Of specific importance is that when objects are lost off-frame they
can still be uniquely identified and reacquired when they return to the field of view.
In this paper we present a gradient descent flow based on a novel energy functional that is capable of producing
robust and accurate segmentations of medical images. This flow is a hybridization of local geodesic active
contours and more global region-based active contours. The combination of these two methods allows curves
deforming under this energy to find only significant local minima and delineate object borders despite noise,
poor edge information, and heterogeneous intensity profiles. To accomplish this, we construct a cost function
that is evaluated along the evolving curve. In this cost, the value at each point on the curve is based on the
analysis of interior and exterior means in a local neighborhood around that point. We also demonstrate a novel
mathematical derivation used to implement this and other similar flows. Results for this algorithm are compared
to standard techniques using medical and synthetic images to demonstrate the proposed method's robustness
and accuracy as compared to both edge-based and region-based alone.