Paper Info
Title
Spatiotemporal No-Reference Video Quality Assessment model on distortions based on encoding.
Abstract
With increasing demand on video applications, the video quality estimation became an important issue of today's technological world. There are different researchers and institutions working on video quality estimation. Most of the objective Video Quality Assessment (VQA) algorithms are Full-Reference (FR) metrics, and they require the original video. Metrics which require some features extracted from reference video are called as Reduced-Reference (RR). Additionally, No-Reference (NR) metrics do not require any information about the original video. Therefore, NR metrics are much suitable for online applications such as video streaming. A novel, objective, NR video quality assessment metric is proposed in this study. The proposed algorithm is based on utilization of spatial extent of video, temporal extent of video using motion vectors and bit rate. Test results obtained using the bit streams which have distortions based on encoding from LIVE video quality database. Results indicate the proposed metric is an accurate and robust algorithm.
Year
DOI
Venue
2013
10.1109/SIU.2013.6531235
Signal Processing and Communications Applications Conference
Keywords
Field
DocType
Video quality assessment (VQA),spatiotemporal information,no-reference metric,quality of experience (QoE)
Computer vision,Video processing,Computer science,Multiview Video Coding,Subjective video quality,PEVQ,Video tracking,Artificial intelligence,Video denoising,Video quality,Video compression picture types
Conference
ISSN
Citations 
PageRank 
2165-0608
2
0.42
References 
Authors
7
4
Name
Order
Citations
PageRank
Emin Zerman1146.22
Gozde Bozdagi Akar212920.15
Baris Konuk392.35
Gokce Nur4394.77