Dataset-driven new set of video quality evaluations towards reference-free video quality evaluations

The popularity of network video service, which leads to the specification of the network video service quality is becoming more and more urgent, and human is the ultimate watch users of network video, Evaluation of human observers on the video’s perception of the situation is becoming more important, depending on the source video network video know nothing, you will need to refer to the participation of video quality evaluation algorithm. However, when the quality evaluation is done by human rating, it is time-consuming and laborious, so the computer is required to make an objective evaluation of the video. In the objective evaluation, the excellent performance of convolutional neural network based on deep learning in feature extraction contributes to the rapid development of the research field of video quality evaluation. However, the development of deep learning algorithms requires appropriate data sets for training and testing. The existing data sets are relatively small in scale and not comprehensive in terms of video content types and distortion types. Therefore, it is necessary to provide a new data set to evaluate the quality of video without reference, expand the scale of the data set, expand the content and distortion type of the video. At the same time, considering the new development of network video services, the video resolution is positioned as high definition, and the original video sampling ratio is 4:2:2. The dataset is freely available to relevant researchers for scientific research.