2012 年 E95.A 巻 5 号 p. 961-968
This paper proposes a video-quality estimation method based on a reduced-reference model for realtime quality monitoring in video streaming services. The proposed method chooses representative-luminance values for individual original-video frames at a server side and transmits those values, along with the pixel-position information of the representative-luminance values in each frame. On the basis of this information, peak signal-to-noise ratio (PSNR) values at client sides can be estimated. This enables realtime monitoring of video-quality degradation by transmission errors. Experimental results show that accurate PSNR estimation can be achieved with additional information at a low bit rate. For SDTV video sequences which are encoded at 1 to 5Mbps, accurate PSNR estimation (correlation coefficient of 0.92 to 0.95) is achieved with small amount of additional information of 10 to 50kbps. This enables accurate realtime quality monitoring in video streaming services without average video-quality degradation.
