Detail publikace

Estimating PSNR in High Definition H.264/AVC Video Sequences Using Artificial Neural Networks

Originální název

Estimating PSNR in High Definition H.264/AVC Video Sequences Using Artificial Neural Networks

Anglický název

Estimating PSNR in High Definition H.264/AVC Video Sequences Using Artificial Neural Networks

Jazyk

en

Originální abstrakt

The paper presents a video quality metric designed for the H.264/AVC codec. The metric operates directly on the encoded H.264/AVC bit stream, parses the encoding parameters and processes them using an artificial neural network. The network is designed to estimate peak signal-to-noise ratios of the video sequence frames, thus enabling computation of full reference objective quality metric values without having the undistorted video material prior to encoding for comparison. We present the metric framework and test its performance for LDTV (low definition television) as well as HDTV (high definition television) video material.

Anglický abstrakt

The paper presents a video quality metric designed for the H.264/AVC codec. The metric operates directly on the encoded H.264/AVC bit stream, parses the encoding parameters and processes them using an artificial neural network. The network is designed to estimate peak signal-to-noise ratios of the video sequence frames, thus enabling computation of full reference objective quality metric values without having the undistorted video material prior to encoding for comparison. We present the metric framework and test its performance for LDTV (low definition television) as well as HDTV (high definition television) video material.

BibTex


@article{BUT47911,
  author="Martin {Slanina} and Václav {Říčný}",
  title="Estimating PSNR in High Definition H.264/AVC Video Sequences Using Artificial Neural Networks",
  annote="The paper presents a video quality metric designed for the H.264/AVC codec. The metric operates directly on the encoded H.264/AVC bit stream, parses the encoding parameters and processes them using an artificial neural network. The network is designed to estimate peak signal-to-noise ratios of the video sequence frames, thus enabling computation of full reference objective quality metric values without having the undistorted video material prior to encoding for comparison. We present the metric framework and test its performance for LDTV (low definition television) as well as HDTV (high definition television) video material.",
  chapter="47911",
  journal="Radioengineering",
  number="3",
  volume="17",
  year="2008",
  month="september",
  pages="103--108",
  type="journal article - other"
}