Visual Trackingwith Robust Target Localization

In this paper, we present a tracking method with robust target localization for tracking of visual objects. We use an adaptive appearance model that incorporates structural information to avoid drifts and can be updated incrementally using partial models. The proposed method works especially well for aerial surveillance sequences where the objects of interest are small and detecting robust feature points in a repeatable manner is difficult due to scale, blur and changing viewpoints. We compare our method using standard sequences and show results on aerial video sequences including wide-area motion imagery (WAMI).