Thesis: Developing a Framework for Motion Data Synthesis
From a classical marker-based motion capture system (MoCap) you obtain the coordinates of placed markers, which are used to establish a biomechanical model. However, information of the subject’s circumferences (silhouette) and surface effects is not provided, which is crucial in case of surface attached sensor synthesis. New digital modelling techniques can help to approximate subject’s silhouette based on the marker coordinates and allow a more realistic synthesis performance.
Extend the existing framework from real Motion Capture data to surface shape models while walking and running, developed at the chair. Use 3D modeling techniques (blender), automatic human body rigging and personalized shape models to synthesise different sensor signals in order to evaluate sensor placement effects.
|Project type||BA/MA Thesis|
|Period||Summer term 2021|
|Presense time||Virtual, working from remote, depending on the needs|
|Useful knowledge||3D modeling, programming, biomechanics|
|Work distribution||70% programming and algorithm development, 30% simulation|
|Med. Eng. designation||Advanced Context Recognition (ACR)|
|StudOn link||Please join|
|First meeting||online-introduction-vorbesprechung-of-summer-term-2021-seminars, on 12th April 2021 at 16:15|
|Registration||E-Mail to email@example.com|
Literature recommendations are provided during the meetings. The candidate is further encouraged to research relevant publications on this topic.
Final presentation and final report/thesis