Temporal shape error concealment for video objects

A novel temporal shape error concealment technique is proposed, which can be used in the context of object-based video coding schemes. In order to reduce the effect of the shape variations of a video object, the curvature scale space (CSS) technique is adopted to extract features, and then these features are used for boundary matching between the current frame and the previous frame. Because the temporal, spatial and statistical video contour information are all considered, the proposed method can find the optimal matching, which is used to replace the damaged contours. The simulation results show that the proposed algorithm achieves better subjective, objective qualities and higher efficiency than those previously developed methods.