A novel objective no-reference metric for digital video quality assessment

Fuzheng Yang; Shuai Wan; Yilin Chang; Hong Ren Wu

doi:10.1109/LSP.2005.855553

A novel objective no-reference metric for digital video quality assessment

Fuzheng Yang
, Shuai Wan
, Yilin Chang
, Hong Ren Wu

State Key Laboratory of Integrated Services Networks
Royal Melbourne Institute of Technology University

科研成果: 期刊稿件 › 文章 › 同行评审

65 引用（Scopus）

摘要

A novel objective no-reference metric is proposed for video quality assessment of digitally coded videos containing natural scenes. Taking account of the temporal dependency between adjacent images of the videos and characteristics of the human visual system, the spatial distortion of an image is predicted using the differences between the corresponding translational regions of high spatial complexity in two adjacent images, which are weighted according to temporal activities of the video. The overall video quality is measured by pooling the spatial distortions of all images in the video. Experiments using reconstructed video sequences indicate that the objective scores obtained by the proposed metric agree well with the subjective assessment scores.

源语言	英语
页（从-至）	685-688
页数	4
期刊	IEEE Signal Processing Letters
卷	12
期	10
DOI	https://doi.org/10.1109/LSP.2005.855553
出版状态	已出版 - 10月 2005
已对外发布	是

访问文件

10.1109/LSP.2005.855553

其它文件与链接

链接到 Scopus 的出版物

引用此

@article{58688b88cc5445c5a39ed331847170cf,

title = "A novel objective no-reference metric for digital video quality assessment",

abstract = "A novel objective no-reference metric is proposed for video quality assessment of digitally coded videos containing natural scenes. Taking account of the temporal dependency between adjacent images of the videos and characteristics of the human visual system, the spatial distortion of an image is predicted using the differences between the corresponding translational regions of high spatial complexity in two adjacent images, which are weighted according to temporal activities of the video. The overall video quality is measured by pooling the spatial distortions of all images in the video. Experiments using reconstructed video sequences indicate that the objective scores obtained by the proposed metric agree well with the subjective assessment scores.",

keywords = "Digital video quality assessment (VQA), Human visual system (HVS), No-reference (NR) metrics",

author = "Fuzheng Yang and Shuai Wan and Yilin Chang and Wu, \{Hong Ren\}",

year = "2005",

month = oct,

doi = "10.1109/LSP.2005.855553",

language = "英语",

volume = "12",

pages = "685--688",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10",

}

TY - JOUR

T1 - A novel objective no-reference metric for digital video quality assessment

AU - Yang, Fuzheng

AU - Wan, Shuai

AU - Chang, Yilin

AU - Wu, Hong Ren

PY - 2005/10

Y1 - 2005/10

N2 - A novel objective no-reference metric is proposed for video quality assessment of digitally coded videos containing natural scenes. Taking account of the temporal dependency between adjacent images of the videos and characteristics of the human visual system, the spatial distortion of an image is predicted using the differences between the corresponding translational regions of high spatial complexity in two adjacent images, which are weighted according to temporal activities of the video. The overall video quality is measured by pooling the spatial distortions of all images in the video. Experiments using reconstructed video sequences indicate that the objective scores obtained by the proposed metric agree well with the subjective assessment scores.

AB - A novel objective no-reference metric is proposed for video quality assessment of digitally coded videos containing natural scenes. Taking account of the temporal dependency between adjacent images of the videos and characteristics of the human visual system, the spatial distortion of an image is predicted using the differences between the corresponding translational regions of high spatial complexity in two adjacent images, which are weighted according to temporal activities of the video. The overall video quality is measured by pooling the spatial distortions of all images in the video. Experiments using reconstructed video sequences indicate that the objective scores obtained by the proposed metric agree well with the subjective assessment scores.

KW - Digital video quality assessment (VQA)

KW - Human visual system (HVS)

KW - No-reference (NR) metrics

UR - https://www.scopus.com/pages/publications/26844533871

U2 - 10.1109/LSP.2005.855553

DO - 10.1109/LSP.2005.855553

M3 - 文章

AN - SCOPUS:26844533871

SN - 1070-9908

VL - 12

SP - 685

EP - 688

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 10

ER -

A novel objective no-reference metric for digital video quality assessment

摘要

访问文件

其它文件与链接

学术指纹

引用此