Kernel based visual tracking with variant spatial resolution model

Kernel based tracking (KBT) has achieved considerable success in the visual tracking field owing to its simplicity and speediness. But the target's scale and rotation parameters cannot be estimated efficiently within its own framework. To complement the ability of KBT, both Cartesian and Log-polar co-ordinates are used as a joint tracking co-ordinate. By using the target's space-variant resolution model, the proposed algorithm can estimate the target's scale and rotation parameters.