Impact of video content and transmission impairments on quality of experience

SUMMARY360 videos have recently become a popular virtual reality content type. However, a good quality metric for 360 videos is still an open issue. In this work, our goal is to identify appropriate objective quality metrics for 360 video communications. Especially, fourteen objective quality measures at different processing phases are considered. Also, a subjective test is conducted in this study. The relationship between objective quality and subjective quality is investigated. It is found that most of the PSNR-related quality measures are well correlated with subjective quality. However, for evaluating video quality across different contents, a content-based quality metric is needed. key words: 360 video, objective quality, subjective quality, video processing

show abstract

“…Such content-related parameters can be obtained by computing content features (e.g. spatial information) [20].…”

Section: Remarks On Evaluation Resultsmentioning

confidence: 99%

A Study on Quality Metrics for 360 Video Communications

Tran

Pham

Ngoc

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…This video set allows for an extensive analysis of the effects that packet loss has on different video types. We focused on packet loss effects, due to its being the most impairing network condition [4], [19]. Our approach calculates the average quality over the entire video fragment.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…They are therefore inapplicable in situations where real-time analysis is needed. Examples of such situations include adaptive streaming systems and real-time quality of experience management [4], [5], [6]. Furthermore, as new video streaming systems, compression standards, and content types appear, the scalability of the assessment methods becomes crucial.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Quality Assessment in Live Video Streaming

Vega

Mocanu

Famaey

et al. 2017

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Abstract-Video content providers put stringent requirements on the quality assessment methods realized on their services. They need to be accurate, real-time, adaptable to new content, and scalable as the video set grows. In this letter, we introduce a novel automated and computationally efficient video assessment method. It enables accurate real-time (online) analysis of delivered quality in an adaptable and scalable manner. Offline deep unsupervised learning processes are employed at the server side and inexpensive no-reference measurements at the client side. This provides both real-time assessment, as well as performance comparable to the full reference counter-part, while maintaining its no-reference characteristics. We tested our approach on the LIMP Video Quality Database (an extensive packet loss impaired video-set) obtaining a correlation between 78% and 91% to the FR benchmark (the Video Quality Metric, VQM). Due to its unsupervised learning essence, our method is flexible, dynamically adaptable to new content and scalable with the number of videos.Index Terms-Deep learning, unsupervised learning, video quality assessment, multimedia video services.

show abstract

“…Moreover, the exponential increase of video streaming types, the appearance of new high quality compression standards, and the broad variety of video content demand the use of scalable and general methods. This situation is requiring service providers to perform video quality assessment not only in real-time [3,18,29] but also in an adaptable and scalable manner. However, it is not enough anymore to assess the quality just on the network level, i.e.…”

Section: Introductionmentioning

confidence: 99%

“…Packet losses, jitters or delays, while providing with a statistical representation of the network behavior, cannot accurately assess how the unpredictable network fluctuations may affect the perception of the final beneficiary of these services, i.e. the user's Quality of Experience (QoE) [1,29,30].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised deep learning for real-time assessment of video streaming services

Vega

Mocanu

Liotta

2017

Multimed Tools Appl

View full text Add to dashboard Cite

Evaluating quality of experience in video streaming services requires a quality metric that works in real time and for a broad range of video types and network conditions. This means that, subjective video quality assessment studies, or complex objective video quality assessment metrics, which would be best suited from the accuracy perspective, cannot be used for this tasks (due to their high requirements in terms of time and complexity, in addition to their lack of scalability). In this paper we propose a light-weight No Reference (NR) method that, by means of unsupervised machine learning techniques and measurements on the client side is able to assess quality in real-time, accurately and in an adaptable and scalable manner. Our method makes use of the excellent density estimation capabilities of the unsupervised deep learning techniques, the restricted Boltzmann machines, and light-weight video features computed just on the impaired video to provide a delta of quality degradation. We have tested our approach in two network impaired video sets, the LIMP and the ReTRiEVED video quality databases, benchmarking the results of our method against the well-known full reference metric VQM. We have obtained levels of accuracy of at least 85% in both datasets using all possible cases.

show abstract

Impact of video content and transmission impairments on quality of experience

Cited by 43 publications

References 27 publications

A Study on Quality Metrics for 360 Video Communications

A Study on Quality Metrics for 360 Video Communications

Deep Learning for Quality Assessment in Live Video Streaming

Unsupervised deep learning for real-time assessment of video streaming services

Contact Info

Product

Resources

About