Ghent University Academic Bibliography

Advanced

Curvature-based human body parts segmentation in physiotherapy

Francis Deboeverie, Roeland De Geest, Tinne Tuytelaars, Peter Veelaert UGent and Wilfried Philips UGent (2015) 10th International Conference on Computer Vision Theory and Applications, Proceedings. 1. p.630-637
abstract
Analysing human sports activity in computer vision requires reliable segmentation of the human body into meaningful parts, such as arms, torso and legs. Therefore, we present a novel strategy for human body segmentation. Firstly, greyscale images of human bodies are divided into smooth intensity patches with an adaptive region growing algorithm based on low-degree polynomial fitting. Then, the key idea in this paper is that human body parts are approximated by nearly cylindrical surfaces, of which the axes of minimum curvature accurately reconstruct the human body skeleton. Next, human body segmentation is qualitatively evaluated with a line segment distance between reconstructed human body skeletons and ground truth skeletons. When compared with human body parts segmentations based on mean shift, normalized cuts and watersheds, the proposed method achieves more accurate segmentations and better reconstructions of human body skeletons.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
Human Body Parts Segmentation, Human Body Skeleton Reconstruction, Image Segmentation
in
10th International Conference on Computer Vision Theory and Applications, Proceedings
editor
José Braz, Sebastiano Battiato and Francisco Imai
volume
1
pages
630 - 637
publisher
SCITEPRESS – Science and Technology Publications
conference name
10th International Conference on Computer Vision Theory and Applications
conference location
Berlin, Germany
conference start
2015-03-11
conference end
2015-03-14
ISBN
9789897580895
language
English
UGent publication?
yes
classification
C1
copyright statement
I have transferred the copyright for this publication to the publisher
id
5902749
handle
http://hdl.handle.net/1854/LU-5902749
date created
2015-03-17 13:39:33
date last changed
2016-12-19 15:37:15
@inproceedings{5902749,
  abstract     = {Analysing human sports activity in computer vision requires reliable segmentation of the human body into meaningful parts, such as arms, torso and legs. Therefore, we present a novel strategy for human body segmentation. Firstly, greyscale images of human bodies are divided into smooth intensity patches with an adaptive region growing algorithm based on low-degree polynomial fitting. Then, the key idea in this paper is that human body parts are approximated by nearly cylindrical surfaces, of which the axes of minimum curvature accurately reconstruct the human body skeleton. Next, human body segmentation is qualitatively evaluated with a line segment distance between reconstructed human body skeletons and ground truth skeletons. When compared with human body parts segmentations based on mean shift, normalized cuts and watersheds, the proposed method achieves more accurate segmentations and better reconstructions of human body skeletons.},
  author       = {Deboeverie, Francis and De Geest, Roeland and Tuytelaars, Tinne and Veelaert, Peter and Philips, Wilfried},
  booktitle    = {10th International Conference on Computer Vision Theory and Applications, Proceedings},
  editor       = {Braz, Jos{\'e} and Battiato, Sebastiano and Imai, Francisco},
  isbn         = {9789897580895},
  keyword      = {Human Body Parts Segmentation,Human Body Skeleton Reconstruction,Image Segmentation},
  language     = {eng},
  location     = {Berlin, Germany},
  pages        = {630--637},
  publisher    = {SCITEPRESS -- Science and Technology Publications},
  title        = {Curvature-based human body parts segmentation in physiotherapy},
  volume       = {1},
  year         = {2015},
}

Chicago
Deboeverie, Francis, Roeland De Geest, Tinne Tuytelaars, Peter Veelaert, and Wilfried Philips. 2015. “Curvature-based Human Body Parts Segmentation in Physiotherapy.” In 10th International Conference on Computer Vision Theory and Applications, Proceedings, ed. José Braz, Sebastiano Battiato, and Francisco Imai, 1:630–637. SCITEPRESS – Science and Technology Publications.
APA
Deboeverie, F., De Geest, R., Tuytelaars, T., Veelaert, P., & Philips, W. (2015). Curvature-based human body parts segmentation in physiotherapy. In J. Braz, S. Battiato, & F. Imai (Eds.), 10th International Conference on Computer Vision Theory and Applications, Proceedings (Vol. 1, pp. 630–637). Presented at the 10th International Conference on Computer Vision Theory and Applications, SCITEPRESS – Science and Technology Publications.
Vancouver
1.
Deboeverie F, De Geest R, Tuytelaars T, Veelaert P, Philips W. Curvature-based human body parts segmentation in physiotherapy. In: Braz J, Battiato S, Imai F, editors. 10th International Conference on Computer Vision Theory and Applications, Proceedings. SCITEPRESS – Science and Technology Publications; 2015. p. 630–7.
MLA
Deboeverie, Francis, Roeland De Geest, Tinne Tuytelaars, et al. “Curvature-based Human Body Parts Segmentation in Physiotherapy.” 10th International Conference on Computer Vision Theory and Applications, Proceedings. Ed. José Braz, Sebastiano Battiato, & Francisco Imai. Vol. 1. SCITEPRESS – Science and Technology Publications, 2015. 630–637. Print.