MultiMedia Modeling: 22nd International Conference, MMM 2016, Miami, FL, USA, January 46, 2016, Proceedings, Part I

Media capture of live events such as concerts can be improved by including user generated content, adding more perspectives and possibly covering scenes outside the scope of professional coverage. In this paper we propose methods for visual quality analysis on mobile devices, in order to provide direct feedback to the contributing user about the quality of the captured content. Thus, wasting bandwidth and battery for uploading/streaming lowquality content can be avoided. We focus on realtime quality analysis that complements information that can be obtained from other sensors (e.g., stability). The proposed methods include realtime capable algorithms for sharpness, noise and over/ underexposure which are integrated in a capture app for Android. Objective evaluation results show that our algorithms are competitive to stateofthe art quality algorithms while enabling realtime quality feedback on mobile devices.