Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Smoothing techniques for 3D animated human pose estimation data

Lundgren, Oliver LU and Bergöö, August (2024) In Master's Theses in Mathematical Sciences FMAM05 20241
Mathematics (Faculty of Engineering)
Abstract
Virtual 3D reconstructions of live sport events are on the horizon and to produce
a high quality experience for viewers it is important that the movements of the 3D
models look natural. Today, state of the art pose estimators produce data that con-tains noise, resulting in jittery animations with pose errors. The goals for this thesis were to evaluate the performance of a Long Short-Term Memory (LSTM) Neural Network and classical filters in their ability to reduce such noise, and if they can be used to improve the viewer experience. This was done by comparing the Mean Per Joint Positional Error (MPJPE) and Absolute Acceleration Error (AAE) for
artificially added noise to motion capture data and comparing the results. A qual-
itative... (More)
Virtual 3D reconstructions of live sport events are on the horizon and to produce
a high quality experience for viewers it is important that the movements of the 3D
models look natural. Today, state of the art pose estimators produce data that con-tains noise, resulting in jittery animations with pose errors. The goals for this thesis were to evaluate the performance of a Long Short-Term Memory (LSTM) Neural Network and classical filters in their ability to reduce such noise, and if they can be used to improve the viewer experience. This was done by comparing the Mean Per Joint Positional Error (MPJPE) and Absolute Acceleration Error (AAE) for
artificially added noise to motion capture data and comparing the results. A qual-
itative survey was also constructed to evaluate how the different methods affected
the human perception of the animations when focusing on different aspects. We
concluded that our methods were (to varying degrees) able to reduce the amount
of noise introduced to the motion data. The qualitative study also indicated that the Savitzky-Golay smoothing algorithm improved the participants perception of the
animations. (Less)
Please use this url to cite or link to this publication:
author
Lundgren, Oliver LU and Bergöö, August
supervisor
organization
course
FMAM05 20241
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Pose Estimation, 3D, Animations, Data Smoothing and Filtering, Sports, Machine Learning, Neural Networs, Spiideo
publication/series
Master's Theses in Mathematical Sciences
report number
LUTFMA-3547-2024
ISSN
1404-6342
other publication id
2024:E48
language
English
id
9173997
date added to LUP
2024-09-30 14:25:32
date last changed
2024-09-30 14:25:32
@misc{9173997,
  abstract     = {{Virtual 3D reconstructions of live sport events are on the horizon and to produce
a high quality experience for viewers it is important that the movements of the 3D
models look natural. Today, state of the art pose estimators produce data that con-tains noise, resulting in jittery animations with pose errors. The goals for this thesis were to evaluate the performance of a Long Short-Term Memory (LSTM) Neural Network and classical filters in their ability to reduce such noise, and if they can be used to improve the viewer experience. This was done by comparing the Mean Per Joint Positional Error (MPJPE) and Absolute Acceleration Error (AAE) for
artificially added noise to motion capture data and comparing the results. A qual-
itative survey was also constructed to evaluate how the different methods affected
the human perception of the animations when focusing on different aspects. We
concluded that our methods were (to varying degrees) able to reduce the amount
of noise introduced to the motion data. The qualitative study also indicated that the Savitzky-Golay smoothing algorithm improved the participants perception of the
animations.}},
  author       = {{Lundgren, Oliver and Bergöö, August}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master's Theses in Mathematical Sciences}},
  title        = {{Smoothing techniques for 3D animated human pose estimation data}},
  year         = {{2024}},
}