Screen Content Video Quality Assessment: Subjective and Objective Study

Screen Content Video Quality Assessment: Subjective and Objective Study
复制标题

屏幕内容视频质量评估:主客观研究

DOI:
10.1109/tip.2020.3018256
复制
发表时间:
2020-08
影响因子:
10.6
通讯作者:
Kai-Kuang Ma
Kai-Kuang Ma
中科院分区:
计算机科学1区
文献类型:
--
作者:
Shan Cheng;Huanqiang Zeng;Jing Chen;Junhui Hou;Jianqing Zhu;Kai-Kuang Ma

文献摘要

参考文献

被引文献

相似文献

在本文中,我们首次尝试研究屏幕内容视频(SCV)的主观和客观质量评估。为此,我们专门针对 SCV 构建了第一个大规模视频质量评估 (VQA) 数据库,称为屏幕内容视频数据库 (SCVD)。该 SCVD 提供 16 个参考 SCV、800 个失真 SCV 及其相应的主观评分,并公开供研究使用。失真的 SCV 是根据每个参考 SCV 生成的,具有 10 种失真类型和每种失真类型的 5 个退化级别。每个扭曲的 SCV 由至少 32 名受试者在主观测试中进行评分。此外,我们提出了第一个针对 SCV 的全参考 VQA 模型,称为基于时空 Gabor 特征张量的模型(SGFTM),以客观地评估扭曲 SCV 的感知质量。这是因为观察到 3D-Gabor 滤波器可以很好地刺激人类视觉系统(HVS)在感知视频时的视觉功能,对 SCV 中经常遇到的边缘和运动信息更加敏感。具体来说,所提出的 SGFTM 利用 3D-Gabor 滤波器从参考和扭曲的 SCV 中单独提取时空 Gabor 特征张量,然后测量它们的相似性,然后通过开发的时空特征张量池化策略将它们组合在一起,以获得最终的 SGFTM 分数。 SCVD 的实验结果表明,所提出的 SGFTM 在 SCV 质量的主观感知上具有高度一致性,并且始终优于多个经典和最先进的图像/视频质量评估模型。
In this article, we make the first attempt to study the subjective and objective quality assessment for the screen content videos (SCVs). For that, we construct the first large-scale video quality assessment (VQA) database specifically for the SCVs, called the screen content video database (SCVD). This SCVD provides 16 reference SCVs, 800 distorted SCVs, and their corresponding subjective scores, and it is made publicly available for research usage. The distorted SCVs are generated from each reference SCV with 10 distortion types and 5 degradation levels for each distortion type. Each distorted SCV is rated by at least 32 subjects in the subjective test. Furthermore, we propose the first full-reference VQA model for the SCVs, called the spatiotemporal Gabor feature tensor-based model (SGFTM), to objectively evaluate the perceptual quality of the distorted SCVs. This is motivated by the observation that 3D-Gabor filter can well stimulate the visual functions of the human visual system (HVS) on perceiving videos, being more sensitive to the edge and motion information that are often-encountered in the SCVs. Specifically, the proposed SGFTM exploits 3D-Gabor filter to individually extract the spatiotemporal Gabor feature tensors from the reference and distorted SCVs, followed by measuring their similarities and later combining them together through the developed spatiotemporal feature tensor pooling strategy to obtain the final SGFTM score. Experimental results on SCVD have shown that the proposed SGFTM yields a high consistency on the subjective perception of SCV quality and consistently outperforms multiple classical and state-of-the-art image/video quality assessment models.
DOI: 10.1109/tip.2007.901812
发表时间: 2007-08
影响因子: 10.6
作者:
Mu Feng;T. Reed
通讯作者: Mu Feng;T. Reed
使用多尺度高斯差分的屏幕内容图像质量评估
DOI: 10.1109/tcsvt.2018.2854176
发表时间: 2018-07
影响因子: 8.4
作者:
Fu Ying;Zeng Huanqiang;Ma Lin;Ni Zhangkai;Zhu Jianqing;Ma Kai Kuang
通讯作者: Ma Kai Kuang
基于混合区域特征融合的屏幕内容图像无参考质量评估
DOI: 10.1109/tmm.2019.2894939
发表时间: 2019-01
影响因子: 7.3
作者:
Zheng Linru;Shen Liquan;Chen Jianan;An Ping;Luo Jun
通讯作者: Luo Jun
DOI: 10.1109/jetcas.2016.2598756
发表时间: 2016-12-01
影响因子: 4.6
作者:
Wang, Shiqi;Gu, Ke;Gao, Wen
通讯作者: Gao, Wen
DOI: 10.1016/s0065-2458(08)60261-2
发表时间: 1988-08
期刊: Science
影响因子: 56.9
作者:
Azriel Rosenfeld
通讯作者: Azriel Rosenfeld