Loading...
Please wait, while we are loading the content...
Similar Documents
Estimation of Channel-Induced Distortion in H . 264 / AVC video from decoded pixels only
| Content Provider | Semantic Scholar |
|---|---|
| Author | Valenzise, Giuseppe Magni, Stefano Tagliasacchi, Marco Tubaro, Stefano |
| Copyright Year | 2010 |
| Abstract | Video transmitted over an error-prone network may be received at the decoder with some degradations due to packet losses. No-reference (NR) quality monitoring algorithms are the most practical way to measure the quality of the received video, since they do not impose any change in network architecture. Conventionally, these methods assume the availability of the corrupted bitstream. In some situations this is not possible, e.g. because the bitstream is encrypted or processed by third party decoders, and only the decoded pixel values can be used. It turns out that the major limitation in this scenario is the lack of knowledge about which slices have been actually lost. In this paper we propose a NR-P (pixel) technique to estimate these bitstream parameters directly from the decoded video. We use this information as input to a no-reference quality monitoring system which produces accurate estimates of the MSE distortion. The results produced by the proposed method are well correlated (linear correlation coefficient larger than 0.9 over a wide range of packet loss rates) with the distortion computed in fullreference mode. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://stday2010.uniud.it/stday2010/papers_files/stday2010_submission_12.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
