Detail publikace

Estimating Peak SNR Without Reference for Real H.264/AVC Sequence Intra Frames

Originální název

Estimating Peak SNR Without Reference for Real H.264/AVC Sequence Intra Frames

Anglický název

Estimating Peak SNR Without Reference for Real H.264/AVC Sequence Intra Frames

Jazyk

en

Originální abstrakt

The paper describes a novel metric for video quality measurement. The metric is capable of estimating peak signal-to-noise ratio (PSNR) values of pictures in compressed bit streams conforming to the H.264/AVC standard. It is designed and has been tested for intra predicted pictures with varying encoder settings. The metric uses an artificial neural network to estimate PSNR examining the compressed bit stream only. In other words, we do not need to decode the actual pixels within the pictures being evaluated. We present a concept of the metric and its performance results in this paper.

Anglický abstrakt

The paper describes a novel metric for video quality measurement. The metric is capable of estimating peak signal-to-noise ratio (PSNR) values of pictures in compressed bit streams conforming to the H.264/AVC standard. It is designed and has been tested for intra predicted pictures with varying encoder settings. The metric uses an artificial neural network to estimate PSNR examining the compressed bit stream only. In other words, we do not need to decode the actual pixels within the pictures being evaluated. We present a concept of the metric and its performance results in this paper.

Dokumenty

BibTex


@inproceedings{BUT25749,
  author="Martin {Slanina} and Václav {Říčný}",
  title="Estimating Peak SNR Without Reference for Real H.264/AVC Sequence Intra Frames",
  annote="The paper describes a novel metric for video quality measurement. The metric is capable of estimating peak signal-to-noise ratio (PSNR) values of pictures in compressed bit streams conforming to the H.264/AVC standard. It is designed and has been tested for intra predicted pictures with varying encoder settings. The metric uses an artificial neural network to estimate PSNR examining the compressed bit stream only. In other words, we do not need to decode the actual pixels within the pictures being evaluated. We present a concept of the metric and its performance results in this paper.",
  address="Czechoslovakia Section IEEE",
  booktitle="Proceedings of the 18th International Conference Radioelektronika 2008",
  chapter="25749",
  howpublished="print",
  institution="Czechoslovakia Section IEEE",
  year="2008",
  month="april",
  pages="55--58",
  publisher="Czechoslovakia Section IEEE",
  type="conference paper"
}