We derive a probabilistic framework for robust, real-time, visual tracking of previously unseen objects from a moving camera. The tracking problem is handled using a bag-of-pixels ...
It has been shown that features can be selected adaptively for object tracking in changing environments [1]. We propose to use the variance of Mutual Information [2] for online fea...
Real-time human tracking is very important in surveillance and robot applications. We note that the performance of any human tracking system depends on its accuracy and its ability...
Fayez Idris, Mazen Abu-Zaher, Rashad J. Rasras, Ib...
We have developed a novel human face tracking system that operates in real time at the video frame rate without a need for any special hardware. Our approach is based on the use o...