Automatic Analysis of 3D Scans of Professional Athletes - 15.092
A. Giachetti et al., "Automatic Analysis of 3D Scans of Professional Athletes", in Proc. of 6th Int. Conf. on 3D Body Scanning Technologies, Lugano, Switzerland, 2015, pp. 92-97, https://doi.org/10.15221/15.092.
Title:
Automatic Analysis of 3D Scans of Professional Athletes
Authors:
Andrea GIACHETTI 1, Francesco PISCITELLI 2, Valentina CAVEDON 2, Chiara MILANESE 2, Carlo ZANCANARO 2
1 Dpt. of Computer Science, University of Verona, Verona, Italy;
2 Lab. of Anthropometry & Body Composition, Dpt. of Neurological and Movement Sciences, Verona, Italy
Abstract:
In this paper we present an analysis of body features of professional athletes performed using 3D body scanning with automatic processing and measurement of acquired 3D meshes and body composition data from dual-energy X-ray absorptiometry (DXA) acquisition. The aim of the work was to investigate whether professional male athletes practicing different sports show sport-specific features in terms of specific body dimensions and body composition. To perform the study, we collected 3D body scans and DXA scans of 211 players practicing basketball, soccer, golf, handball, rugb, volleyball as well as a control group of 38 physically active young adults.
A set of geometrical parameters were extracted automatically from the models exploiting a custom software tool based on body segmentation based curve skeleton analysis and symmetry based heuristics and previously applied with success to the analysis of body fat.
By measuring these body features from the scans, we could perform statistical analysis of their correlation with body composition parameters and also analyze differences among sports, in order to understand which features are more characterizing individual sports.
Furthermore, we checked if combinations of the selected feature measurements could possibly be characteristics of the disciplines and/or distinguish between professional athletes and physically active subjects, by visually analyzing the multidimensional feature space and testing automatic "athlete" or "discipline" labeling in a leave one out classification framework using different feature combinations and different classification methods. This allowed us to extract the most relevant features related to each different group.
Details:
Full paper: 15.092.pdf
Proceedings: 3DBST 2015, 27-28 Oct. 2015, Lugano, Switzerland
Pages: 92-97
DOI: 10.15221/15.092
License/Copyright notice:
Proceedings: © Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, hometrica.ch.
Authors retain all rights to individual papers, which are licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The papers appearing in the proceedings reflect the author's opinions. Their inclusion in the proceedings does not necessary constitute endorsement by the editor or by the publisher.
Note: click the + on the top left of the page to open/close the menu.