QualityCrowd – Crowdsourcing für subjektive Videoqualitätstests
Abstract Despite continuing research on the development of better quality metrics, subjective tests are still indispensable for the assessment of video quality. These tests are both time-consuming and expensive and require installing a suitable laboratory that fulfills the corresponding ITU recommendations. In this thesis the use of crowdsourcing in conjunction with the internet-based performing of such tests shall be examined comparing the results of such a test and the results of conventional laboratory tests. ...
Temporal Video Quality Prediction Using Multi-Way Data Analysis
Abstract Currently the most reliable method of determining the visual quality of video sequences is subjective testing with human observers. Since this is both time-consuming and expensive, there is ongoing research on objective video quality metrics that allow to measure the visual quality without carrying out subjective tests. A very promising approach in the field of no-reference video quality metrics are metrics based on data analysis rather than on modeling the human visual system. It has been shown that the results improve when taking the temporal structure of the video sequence into account using multi-way data analysis methods. ...