When does lower bitrate give higher quality in modern video services?

Giordano

2015 Seventh International Workshop on Quality of Multimedia Experience (QoMEX)

et al. 2015

Self Cite

Abstract-The evaluation of mobile streaming services, particularly in terms of delivered Quality of Experience (QoE), entails the use of automated methods (which excludes subjective QoE) that can be executed in real-time (i.e. without delaying the streaming process). This calls for lightweight algorithms that provide accurate results under considerable constraints. Starting from a low complexity no-reference objective algorithm for still images, in this work we contribute a new version that not only works for videos but, is general enough to adjust to a diverse range of video types while not significantly increasing the computational complexity. To achieve the necessary level of flexibility and computational efficiency, our method relies merely on information available at the client side and is equipped with a lightweight Artificial Neural Network which makes the algorithm independent from type of network or video. Its resource efficiency and generality make our method fit to be used in mobile streaming services. To prove the viability of our approach, we show a high level of correlation with the well-known full-reference method SSIM.

Section: Experiments and Resultsmentioning

confidence: 69%

Cognitive no-reference video quality assessment for mobile streaming services

Giordano

2015 Seventh International Workshop on Quality of Multimedia Experience (QoMEX)

et al. 2015

Self Cite

“…First, the bitstream bitrate influences the quality in a direct and substantial manner. Higher bitrates result in higher quality indices [35]. Second, the received number of frames gives an idea of the duration of the video.…”

Section: Real-time Cognitive Video Quality Assessment Methodsmentioning

confidence: 99%

Deep Learning for Quality Assessment in Live Video Streaming

IEEE Signal Process. Lett.

Famaey

et al. 2017

Self 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.

“…The selection of the encoding bitrates has been done in a way as to obtain the most diverse variety of video qualities. These 80 (10 videos at 8 bitrates) videos were then streamed in a controlled real network environment (given by a network emulator) and subjected to 12 levels of packet loss (0, 0.5%, 1%, 1.5%, 2%, 2.5%, 3%, 3.5%, 4%, 4.5%, 5%, and 10%), which is the most impairing condition in networks [23]. This makes a total of 960 different videos that we use to benchmark our quality metric.…”

Section: Evaluation Methodology Video Dataset and Learning Conditionsmentioning

confidence: 99%

A Regression Method for real-time video quality evaluation

Proceedings of the 14th International Conference on Advances in Mobile Computing and Multi Media

Liotta

2016

Self Cite

No-Reference (NR) metrics provide a mechanism to assess video quality in an ever-growing wireless network. Their low computational complexity and functional characteristics make them the primary choice when it comes to realtime content management and mobile streaming control. Unfortunately, common NR metrics suffer from poor accuracy, particularly in network-impaired video streams. In this work, we introduce a regression-based video quality metric that is simple enough for real-time computation on thin clients, and comparably as accurate as state-of-the-art FullReference (FR) metrics, which are functionally and computationally inviable in real-time streaming. We benchmark our metric against the FR metric VQM (Video Quality Metric), finding a very strong correlation factor.