Content aware video quality prediction model for HEVC encoded bitstream

Content aware video quality prediction model for HEVC encoded bitstream In this paper, a novel content based video quality prediction model for High Efficiency Video Coding (HEVC) encoded video stream is proposed, which takes into account the quantization parameter (QP) and the newly proposed content type classification (CTC) metric. The CTC metric is derived by combining different types of information extracted from the encoded video sequences: temporal and spatial complexity, the standard deviation of the bitrate and the value of quantized transform coefficients. This metric can establish a logarithmic relationship with the quality of the video sequence, which is evidenced by extensive experimental results. The experimental results demonstrate that the proposed prediction model can achieve better correlation between the actual PSNR and the predicted PSNR in the training and testing process, and outperforms the other existing prediction methods in terms of accuracy. Furthermore, subjective testing results also show a good consistency between the proposed prediction metric and the subjective rankings. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Multimedia Tools and Applications Springer Journals

Content aware video quality prediction model for HEVC encoded bitstream

Content aware video quality prediction model for HEVC encoded bitstream

Multimed Tools Appl (2017) 76:19191–19209 DOI 10.1007/s11042-017-4574-4 Content aware video quality prediction model for HEVC encoded bitstream 1,2 1 1 Yongfang Wang & Kanghua Zhu & Jian Wu & Yun Zhu Received: 12 July 2016 /Revised: 9 February 2017 /Accepted: 6 March 2017 / Published online: 27 March 2017 Springer Science+Business Media New York 2017 Abstract In this paper, a novel content based video quality prediction model for High Efficiency Video Coding (HEVC) encoded video stream is proposed, which takes into account the quantization parameter (QP) and the newly proposed content type classification (CTC) metric. The CTC metric is derived by combining different types of information extracted from the encoded video sequences: temporal and spatial complexity, the standard deviation of the bitrate and the value of quantized transform coefficients. This metric can establish a logarith- mic relationship with the quality of the video sequence, which is evidenced by extensive experimental results. The experimental results demonstrate that the proposed prediction model can achieve better correlation between the actual PSNR and the predicted PSNR in the training and testing process, and outperforms the other existing prediction methods in terms of accuracy. Furthermore, subjective testing results also show a good consistency between the proposed prediction metric and the subjective rankings. . . . Keywords Content type HEVC Video complexity Quality prediction 1 Introduction Video quality prediction is a significant area in video compression community, as it aims to improve quality of service (QoS) evaluation and codec performance assessment. And it has been shown that video quality is affected by encoding parameters, network quality of service, and content type [16]. * Kanghua Zhu zhukanghuashu@163.com Key Laboratory of Advance Display and System Application, Ministry of Education, Shanghai University, Shanghai, China School of Communication and...
Loading next page...
 
/lp/springer_journal/content-aware-video-quality-prediction-model-for-hevc-encoded-030UUJnupS
Publisher
Springer US
Copyright
Copyright © 2017 by Springer Science+Business Media New York
Subject
Computer Science; Multimedia Information Systems; Computer Communication Networks; Data Structures, Cryptology and Information Theory; Special Purpose and Application-Based Systems
ISSN
1380-7501
eISSN
1573-7721
D.O.I.
10.1007/s11042-017-4574-4
Publisher site
See Article on Publisher Site

Abstract

In this paper, a novel content based video quality prediction model for High Efficiency Video Coding (HEVC) encoded video stream is proposed, which takes into account the quantization parameter (QP) and the newly proposed content type classification (CTC) metric. The CTC metric is derived by combining different types of information extracted from the encoded video sequences: temporal and spatial complexity, the standard deviation of the bitrate and the value of quantized transform coefficients. This metric can establish a logarithmic relationship with the quality of the video sequence, which is evidenced by extensive experimental results. The experimental results demonstrate that the proposed prediction model can achieve better correlation between the actual PSNR and the predicted PSNR in the training and testing process, and outperforms the other existing prediction methods in terms of accuracy. Furthermore, subjective testing results also show a good consistency between the proposed prediction metric and the subjective rankings.

Journal

Multimedia Tools and ApplicationsSpringer Journals

Published: Mar 27, 2017

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off