Content Based Video Quality Assessment Platform

This paper presents a novel system of a real-time non-reference video quality monitoring on a commercially available multi-core processor platform in a networked environment. System design stage incorporates; firstly, automate statistically based selection of appropriate objective measures from a large predefined set of measures for artifacts characterization. Secondly, this reduces set of objective measures that are used in conjunction with subjective assessments for derivation of a non-linear model which can be used for automated objective video quality assessment. The non-linear video quality assessment model is derived and based on different sets of the relevant objective measures and test video sequences with different content. The developed system captures live video, extracts video quality indicators in real-time and renders them on the remote workstation.