A novel quality model for HTTP adaptive streaming
Huyen T. T. Tran, Thang Vu, Nam Pham Ngoc, Truong Cong Thang · 2016
HTTP Adaptive Streaming (HAS) has become a popular trend for multimedia delivery nowadays. Because of throughput variations, video quality strongly fluctuates during a session. Therefore, a main challenge in HAS is how to evaluate the overall video quality of a session. In this paper, we explore the impact of quality variations on the perceptual quality of a video in HAS. We propose to use the histogram of segment quality values and the histogram of quality gradients in a session to model the overall video quality. Subjective test results show that the proposed model can capture the segment quality variations and accurately predict the overall quality of a session.