TY - CONF A1 - Paul, Felix A1 - Herder, Jens A2 - Herder, Jens A2 - Geiger, Christian A2 - Dörner, Ralf A2 - Grimm, Paul T1 - A model-based filtering approach for real-time human motion data T2 - Workshop Proceedings / Tagungsband: Virtuelle und Erweiterte Realität – 15. Workshop der GI-Fachgruppe VR/AR N2 - Acquiring human motion data from video images plays an important role in the field of computer vision. Ground truth tracking systems require markers to create high quality motion data. But in many applications it is desired to work without markers. In recent years affordable hardware for markerless tracking systems was made available at a consumer level. Efficient depth camera systems based on Time-of-Flight sensors and structured light systems have made it possible to record motion data in real time. However, the gap between the quality of marker-based and markerless systems is high. The error sources of a markerless motion tracking pipeline are discussed and a model-based filter is proposed, which adapts depending on spatial location. The proposed method is then proven to be more robust and accurate than the unfiltered data stream and can be used to visually enhance the presence of an actor within a virtual environment in live broadcast productions. KW - Virtual (TV) Studio Y1 - 2018 UR - https://opus4.kobv.de/opus4-hs-duesseldorf/frontdoor/index/index/docId/1586 UR - http://vsvr.medien.hs-duesseldorf.de/publications/gi-vrar2018-filter/ SN - 978-3-8440-6215-1 SP - 37 EP - 44 PB - Shaker Verlag CY - Herzogenrath ER -