On Novel System for Detection Video Impairments Using Unsupervised Machine Learning Anomaly Detection Technique
Recently, the necessity of video testing at the point of reception has become a challenge for video distributors. This paper presents a new system framework for managing the quality of video degradation detection. The system is based on objective video quality assessment metrics and unsupervised machine learning techniques that use the dimensionality reduction of time series. It was demonstrated that it is possible to detect anomalies in the video during video streaming in soft real time. In addition, the model discovers degradations based on the visible correlation between adjacent images in the video sequence regardless the quick or slow change of a scene in the sequence. With additional hardware manipulations on the equipment on the user side, the proposed solution can be used in practical implementations where the need for monitoring possible degradations during video streaming exists.