Time resolved skeleton representation

OS Oliver Sturman
LZ Lukas von Ziegler
CS Christa Schläppi
FA Furkan Akyol
MP Mattia Privitera
DS Daria Slominski
CG Christina Grimm
LT Laetitia Thieren
VZ Valerio Zerbi
BG Benjamin Grewe
JB Johannes Bohacek
ask Ask a question
Favorite

A position and orientation invariant skeletal representation was created from the DLC tracked coordinates at each frame. Based on distances, angles and areas, 22 variables were used as features for the supervised machine learning. For details of the feature description see Supplementary Materials and methods.

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

post Post a Question
0 Q&A