Skip to main content Skip to main navigation


One Sensor is not Enough: Adapting and Fusing Sensors for the Quality Assessment of User Generated Video

Stefan Wilk; Manisha Luthra; Wolfgang Effelsberg
In: Proceedings of the 24th ACM International Conference on Multimedia. ACM International Conference on Multimedia (ACM MM-2016), Amsterdam, Netherlands, Pages 626-630, MM '16, ISBN 9781450336031, Association for Computing Machinery, 2016.


In comparison to professional productions, UGV often suffers from quality degradations such as camera shakes or harmful occlusions. Quick and reliable algorithms are needed to detect and assess the impact of these quality degradations. Recently, researchers leverage data from auxiliary sensors such as gyroscope readings or accelerometer values for quality assessment. In comparison to video-based approaches, auxiliary sensor-based ones achieve results more quickly but often lack precision.This work proposes a framework for the combined analysis of UGV which leverages the strength of video-based and auxiliary sensor-based algorithms. In addition, we propose a hybrid algorithm for camera shake detection, which dynamically adapts which sensor readings to use for the assessment. A hybrid algorithm achieves an improved precision and a reduced runtime in comparison to the usage of a single sensor.