A regression-based framework for estimating the objective quality of HEVC coding units and video frames

作者：

Highlights：

• A no-reference objective quality estimation framework is proposed. The framework is suitable for any block-based video codec.

• In the proposed solution, features are extracted from coding units and summarized to form features at frame levels. Stepwise regression is used to select the important feature variables and reduce the dimensionality of feature vectors.

• Thereafter, a polynomial regression-based approach is used to model the nonlinear relationship between the feature vectors and the true objective quality values. Such values are estimated for coding units and video frames.

• The proposed framework is implemented using MPEG-2 and HEVC. The objective quality estimation results are compared against an existing state-of-the-art solution and quantified using the Pearson correlation factor and the root mean square error measure.

摘要

•A no-reference objective quality estimation framework is proposed. The framework is suitable for any block-based video codec.•In the proposed solution, features are extracted from coding units and summarized to form features at frame levels. Stepwise regression is used to select the important feature variables and reduce the dimensionality of feature vectors.•Thereafter, a polynomial regression-based approach is used to model the nonlinear relationship between the feature vectors and the true objective quality values. Such values are estimated for coding units and video frames.•The proposed framework is implemented using MPEG-2 and HEVC. The objective quality estimation results are compared against an existing state-of-the-art solution and quantified using the Pearson correlation factor and the root mean square error measure.

论文关键词：PSNR estimation,SSIM estimation,Machine learning,Regression analysis,Video codecs,Video compression

论文评审过程：Received 21 August 2014, Revised 12 December 2014, Accepted 26 February 2015, Available online 17 March 2015.

论文官网地址：https://doi.org/10.1016/j.image.2015.02.008