A no-reference network video quality assessment method based on video content characteristics

doi:10.1145/3349341.3349493

	A no-reference network video quality assessment method based on video content characteristics
	Zhao, Hong 1; Chang, Zhaobin 1; Cao, Chang 1; Zeng, Xiangyan 2
	2019-07-12
会议日期	July 12, 2019 - July 13, 2019
会议地点	Wuhan, China
关键词	Artificial intelligence Video recording Assessment models Coding distortion Frame loss Payload information Transmission distortion Video contents Video quality Video quality assessment
DOI	10.1145/3349341.3349493
页码	698-704
英文摘要	A novel model of no-reference network video quality assessment is proposed in this study. First, a new definition of video content complexity is represented by the type of frame, the type of macro block, and the motion vector that consists of payload information. The proposed assessment model consists of a coding distortion module and a transmission distortion module. The coding distortion module adds the proposed complexity to a standard G.1070 model. The transmission distortion module describes the impact of frame loss rate, concentrative degree of frame loss and video content complexity on video quality. Several experiment results are presented to show that video content characteristics have a considerable influence on perceived quality. Thus, the proposed model provides a promising metric for video quality assessment. © 2019 Association for Computing Machinery.
会议录	ACM International Conference Proceeding Series
会议录出版者	Association for Computing Machinery
语种	英语
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/118032]
专题	计算机与通信学院
作者单位	1.School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China; 2.Department of Mathematics and Computer Science, Fort Valley State University, GA, United States
推荐引用方式 GB/T 7714	Zhao, Hong,Chang, Zhaobin,Cao, Chang,et al. A no-reference network video quality assessment method based on video content characteristics[C]. 见:. Wuhan, China. July 12, 2019 - July 13, 2019.