摘要
Error-resilient video communication over lossy packet networks is often designed and operated based on models for the effect of losses on the reconstructed video quality. This paper analyzes the channel distortion for video over lossy packet networks and proposes a new model that, compared to previous models, more accurately estimates the expected mean-squared error distortion for different packet loss patterns by accounting for inter-frame error propagation and the correlation between error frames. The accuracy of the proposed model is validated with JVT/H.264 encoded standard test sequences and previous frame concealment, where the proposed model provides an obvious accuracy gain over previous models.
Error-resilient video communication over lossy packet networks is often designed and operated based on models for the effect of losses on the reconstructed video quality. This paper analyzes the channel distortion for video over lossy packet networks and proposes a new model that, compared to previous models, more accurately estimates the expected mean-squared error distortion for different packet loss patterns by accounting for inter-frame error propagation and the correlation between error frames. The accuracy of the proposed model is validated with JVT/H.264 encoded standard test sequences and previous frame concealment, where the proposed model provides an obvious accuracy gain over previous models.
基金
Project (No. Y2001005) supported by the Natural Science Foundation of Shandong Province, China
