Updating mixture of principal components for error concealment

ABSTRACT This paper is organized as follows. In Section 2, we formulate the proposed UMPC method for modeling nonstationary and multi-modal data. Both MPC and UPC are shown to be special cases of the proposed UMPC model. We apply UMPC to error concealment in Section 3. The experiment results in Section 4 show the performance of UMPC for error concealment over conventional methods. We then conclude in Section 5. In this paper, we present a new statistical modeling technique called “updating mixture of principal components” (UMPC). UMPC specifically captures the non-stationary as well as the multi-modal characteristics of the data. Real-world data such as video data typically have these two characteristics. The video content changes over time and has a multi-modal probability distribution. We apply UMPC to perform error concealment for video data transmitted over networks with losses, and show that UMPC outperforms conventional error concealment methods. 2. UPDATING MIXTURE OF PRINCIPAL COMPONENTS (UMPC)