Research Article
Video Quality Assessment by Decoupling Distortions on Primary Visual Information
@INPROCEEDINGS{10.1007/978-3-319-72998-5_32, author={Yang Li and Xu Wang and Feng Li and Qingrui Guo and Qiang Fan and Qiwei Peng and Wang Luo and Min Feng and Yuan Xia and Shaowei Liu}, title={Video Quality Assessment by Decoupling Distortions on Primary Visual Information}, proceedings={Wireless Internet. 9th International Conference, WICON 2016, Haikou, China, December 19-20, 2016, Proceedings}, proceedings_a={WICON}, year={2018}, month={1}, keywords={Video quality assessment Human visual system Transmission distortion Decoupling distortion}, doi={10.1007/978-3-319-72998-5_32} }- Yang Li
Xu Wang
Feng Li
Qingrui Guo
Qiang Fan
Qiwei Peng
Wang Luo
Min Feng
Yuan Xia
Shaowei Liu
Year: 2018
Video Quality Assessment by Decoupling Distortions on Primary Visual Information
WICON
Springer
DOI: 10.1007/978-3-319-72998-5_32
Abstract
Video quality assessment (VQA) aims to evaluate the video quality consistently with the human perception. In most of existing VQA metrics, additive noises and losses of primary visual information (PVI) are decoupled and evaluated separately for quality assessment. However, PVI losses always include different types of distortions such that PVI distortions are not evaluated well enough. In this paper, a novel full-reference video quality metric is developed by decoupling PVI distortions into two classes: compression distortions and transmission distortions. First, video denoising method is adopted to decompose an input video into two portions, the portion of additive noises and the PVI portion. Then, maximal distortion regions searching (MDRS) algorithm is designed to decompose PVI losses into transmission distortions and compression distortions. Finally, the three distortions are evaluated separately and combined to compute the overall quality score. Experimental results on LIVE database show the effectiveness of the proposed VQA metric.