Adaptive template matching algorithm based on swad for robust target tracking

The sum of absolute differences (SAD) is widely used in video coding and disparity computation for its simplicity. However, SAD is not very common in tracking applications owing to issues like partial occlusion and target changes, which can dramatically affect its performance. Presented is a novel adaptive template matching algorithm for target tracking, based on a sum of weighted absolute differences (SWAD). The target template is updated using an infinite impulse response filter, while a weighting kernel is adopted to reduce the effects of partial occlusion. Simulation results demonstrate that the proposed tracker outperforms conventional SAD in terms of efficiency and accuracy, and its performance is comparable with more complex trackers, such as the mean shift algorithm.