Video quality is a key factor in modern video streaming systems. Video compression artifacts affect it but also delay, jitter and packet loss may compromise it. Objective metrics have been proposed to emulate the human visual system: several experimental works have evaluated their adherence to opinions expressed by real users. Instead of dealing with subjective tests, we focused on the effects of network packet losses on objective metrics: since quality metrics are generally computationally intensive, a convenient approach could consist in inferring information about transmission quality from network impairment statistics. We did experimental tests on two computer-animated videos, whose high color contrasts allow a fair comparison between content dependent and content independent metrics. We studied the encoding parameters that minimize/maximize the values of some metrics (PSNR, BI-PSNR, SSIM, 3SSIM, MSSSIM, VQM) for several packet loss percentages. We analyzed also the Empirical Cumulative Density Function of the degradations of quality metrics
Packet losses and objective video quality metrics in H.264 video streaming
F. Tommasi;V. De Luca;C. Melle
2015-01-01
Abstract
Video quality is a key factor in modern video streaming systems. Video compression artifacts affect it but also delay, jitter and packet loss may compromise it. Objective metrics have been proposed to emulate the human visual system: several experimental works have evaluated their adherence to opinions expressed by real users. Instead of dealing with subjective tests, we focused on the effects of network packet losses on objective metrics: since quality metrics are generally computationally intensive, a convenient approach could consist in inferring information about transmission quality from network impairment statistics. We did experimental tests on two computer-animated videos, whose high color contrasts allow a fair comparison between content dependent and content independent metrics. We studied the encoding parameters that minimize/maximize the values of some metrics (PSNR, BI-PSNR, SSIM, 3SSIM, MSSSIM, VQM) for several packet loss percentages. We analyzed also the Empirical Cumulative Density Function of the degradations of quality metricsI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.