A regression-based framework for estimating the objective quality of HEVC coding units and video frames

IEEE Signal Process. Lett.

Famaey

et al. 2017

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.

Section: Introductionmentioning

confidence: 99%

Deep Learning for Quality Assessment in Live Video Streaming

IEEE Signal Process. Lett.

Famaey

et al. 2017

“…Nowadays, Video Quality Assessment (VQA) methods and metrics are drawn 30 from knowledge in human QoE and perception [15]. At its essence, VQA is a subjective matter, best judged by human subjects, as in subjective studies and subjective analyses [16].…”

Section: Introductionmentioning

confidence: 99%

“…This direction is currently being explored in the development of NR algorithms. Promising examples are the Adaboost approach for assessing artifacts levels in videos, by Vink et al [27]; the bitstream based ar-75 tificial neural network, by Shahid et al [28]; the artificial neural network for jerkiness evaluation, by Xue et al [29]; and the regression framework for estimating the objective quality index (SSIM or PSNR), by Shanableh [30].…”

Section: Introductionmentioning

confidence: 99%

Predictive no-reference assessment of video quality

Signal Processing: Image Communication

Stavrou

et al. 2017

Among the various means to evaluate the quality of video streams, light-weight No-Reference (NR) methods have low computation and may be executed on thin clients. Thus, these methods would be perfect candidates in cases of real-time quality assessment, automated quality control and in adaptive mobile streaming. Yet, existing real-time, NR approaches are not typically designed to tackle network distorted streams, thus performing poorly when compared to Full-Reference (FR) algorithms. In this work, we present a generic NR method whereby machine learning (ML) may be used to construct a quality metric trained on simplistic NR metrics. Testing our method on nine, representative ML algorithms allows us to show the generality of our approach, whilst finding the best-performing algorithms. We use an extensive video dataset (960 video samples), generated under a variety of lossy network conditions, thus verifying that our NR metric remains accurate under realistic streaming scenarios. In this way, we achieve a quality index that is comparably as computationally efficient as typical NR metrics and as accurate as the FR algorithm Video Quality Metric (97% correlation).

“…Promising examples of cognitive approaches are the Adaboost approach for assessing artifacts levels in videos, by Vink and de Haan [43]; the bitstream based artificial neural network, by Shahid et al [35]; the artificial neural network for jerkiness evaluation, by Xue et al [46]; and the regression framework for estimating the objective quality index (SSIM or PSNR), by Shanableh [36]. However, these approaches are usually based on supervised learning techniques, thus requiring labelled data to perform the offline training.…”

Section: Introductionmentioning

confidence: 99%

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

Liotta

2017

Multimed Tools Appl

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.