Convolutional Neural Networks for Video Quality Assessment

• Published in: arXiv.org 2018-09
• Main Authors: Giannopoulos, Michalis, Tsagkatakis, Grigorios, Blasi, Saverio, Toutounchi, Farzad, Mouchtaris, Athanasios, Tsakalides, Panagiotis, Mrak, Marta, Izquierdo, Ebroul
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Coding standards; Compression tests; Distortion; Feature extraction; Machine learning; Mathematical models; Neural networks; Quality; Quality assessment; User satisfaction; Video compression; Video transmission
• ISSN: 2331-8422

Video Quality Assessment (VQA) is a very challenging task due to its highly subjective nature. Moreover, many factors influence VQA. Compression of video content, while necessary for minimising transmission and storage requirements, introduces distortions which can have detrimental effects on the perceived quality. Especially when dealing with modern video coding standards, it is extremely difficult to model the effects of compression due to the unpredictability of encoding on different content types. Moreover, transmission also introduces delays and other distortion types which affect the perceived quality. Therefore, it would be highly beneficial to accurately predict the perceived quality of video to be distributed over modern content distribution platforms, so that specific actions could be undertaken to maximise the Quality of Experience (QoE) of the users. Traditional VQA techniques based on feature extraction and modelling may not be sufficiently accurate. In this paper, a novel Deep Learning (DL) framework is introduced for effectively predicting VQA of video content delivery mechanisms based on end-to-end feature learning. The proposed framework is based on Convolutional Neural Networks, taking into account compression distortion as well as transmission delays. Training and evaluation of the proposed framework are performed on a user annotated VQA dataset specifically created to undertake this work. The experiments show that the proposed methods can lead to high accuracy of the quality estimation, showcasing the potential of using DL in complex VQA scenarios.