Hierarchical decision based on higher order statistical on foreground detection in video sequence

An inter-frame segmentation strategy to assist region-based statistical test is presented. It is based on luminance and chromatic morphological algorithm, followed by a higher order statistical test (HOS). The HOS algorithm is suited for very small moving because of the characterization that suppress the statistic of Gaussian-distributed and enlarge the statistic of non-Gaussian-distributed. Due to the experiment result, we design a hierarchical decision to cancel the tracking computation had when one sequence lacking the motion information.