Automatic Generation of Statistical Shape Models in Motion

Conference paper (2019)

Authors

Femke Danckaers Universiteit Antwerpen
Sofia Scataglini Royal Military Academy, Military Hospital Queen Astrid
Robby Haelterman Royal Military Academy
Damien Van Tiggelen Military Hospital Queen Astrid
T. Huysmans Universiteit Antwerpen, Applied Ergonomics and Design - IDE
Jan Sijbers Universiteit Antwerpen
Research Group
Applied Ergonomics and Design (IDE) (TU Delft)
Statistical body shape model Motion capturing Shape prediction
More Info
expand_more

Published Date

2019

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Industrial Design Engineering

Department

Human-Centered Design

Research Group

Applied Ergonomics and Design

Abstract

Statistical body shape modeling (SBSM) is a well-known technique to map out the variability of body shapes and is commonly used in 3D anthropometric analyses. In this paper, a new approach to integrate movement acquired by a motion capture system with a body shape is proposed. This was done by selecting landmarks on a body shape model, and predicting a body shape based on features. Then, a virtual skeleton was generated relative to those landmarks. This skeleton was parented to a body shape, allowing to modify its pose and to add pre-recorded motion to different body shapes in a realistic way.