A robust mean-transform based visual tracker

We present a robust particle filter based visual tracker based on an earlier approach called mean-transform which can track a window with orientation and scale changes. This work is the first work combining sparse coding, mean transform and particle filtering in visual tracking. We show that particle filter is effective in enhancing the mean-transform tracker. From the result, we see that such architecture can provide comparable accuracy to the state-of-art trackers with increased robustness. The current approach may provide a framework for investigating a state approach that incorporates velocity and acceleration of objects in the tracker.