Multiple Description Coding has recently proved to be an effective solution for the robust transmission of 3D video sequences over unreliable channels. The paper presents a novel Cognitive Source Coding scheme that improves the performance of traditional MDC schemes by combining adaptively traditional predictive and Wyner-Ziv codings according to the characteristics of the video sequence and to the channel conditions. The approach is applied to video+depth 3D transmission and permits improving the average PSNR value up to 2.5 dB with respect to traditional MDC schemes.
展开▼
