The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.
|Author:||Stefan Wilk, Manisha Luthra, Wolfgang Effelsberg|
|Kind:||In proceedings - use for conference & workshop papers|
|Address:||New York, NY, USA|
|Book title:||Proceedings of the 2016 ACM on Multimedia Conference|
|Abstract:||In comparison to professional productions, User Generated Video (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 lever- age 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 analy- sis 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 dynami- cally 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.|
|Full paper (pdf)|