Gap Reconstruction in Optical Motion Capture Sequences Using Neural Networks

Optical motion capture is a mature contemporary technique for the acquisition of motion data; alas, it is non-error-free. Due to technical limitations and occlusions of markers, gaps might occur in such recordings. The article reviews various neural network architectures applied to the gap-filling p...

Full description

Saved in:
Bibliographic Details
Published inSensors (Basel, Switzerland) Vol. 21; no. 18; p. 6115
Main Authors Skurowski, Przemysław, Pawlyta, Magdalena
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 12.09.2021
MDPI
Subjects
Actors
Computer architecture
Dictionaries
FFNN
gap filling
Interpolation
Kinematics
LSTM
Motion capture
Neural networks
Optical communication
reconstruction
Time series
Online AccessGet full text

Cover

More Information
Summary:Optical motion capture is a mature contemporary technique for the acquisition of motion data; alas, it is non-error-free. Due to technical limitations and occlusions of markers, gaps might occur in such recordings. The article reviews various neural network architectures applied to the gap-filling problem in motion capture sequences within the FBM framework providing a representation of body kinematic structure. The results are compared with interpolation and matrix completion methods. We found out that, for longer sequences, simple linear feedforward neural networks can outperform the other, sophisticated architectures, but these outcomes might be affected by the small amount of data availabe for training. We were also able to identify that the acceleration and monotonicity of input sequence are the parameters that have a notable impact on the obtained results.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-3
content type line 23
ObjectType-Review-1
ISSN:1424-8220
1424-8220
DOI:10.3390/s21186115