A Decision-Tree-Based Perceptual Video Quality Prediction Model and Its Application in FEC for Wireless Multimedia Communications
Abstract: With the exponential growth of video traffic over wireless networked and embedded devices, mechanisms are needed to predict and control perceptual video quality to meet the quality of experience (QoE) requirements in an energyefficient way. This paper proposes an energy-efficient QoE support framework for wireless video communications. It consists of two components: 1) a perceptual video quality model that allows the prediction of video quality in real-time and with low complexity, and 2) an application layer energy-efficient and contentaware forward error correction (FEC) scheme for preventing quality degradation caused by network packet losses. The perceptual video quality model characterizes factors related to video content as well as distortion caused by compression and transmission. Prediction of perceptual quality is achieved through a decision tree using a set of observable features from the compressed bitstream and the network. The proposed model can achieve prediction accuracy of 88.9% and 90.5% on two distinct testing sets. Based on the proposed quality model, a novel FEC scheme is introduced to protect video packets from losses during transmission. Given a user-defined perceptual quality requirement, the FEC scheme adjusts the level of protection for different components in a video stream to minimize network overhead. Simulation results show that the proposed FEC scheme can enhance the perceptual quality of videos. Compared to
conventional FEC methods for video communications, the proposed FEC scheme can reduce network overhead by 41% on average.