DocumentCode
3366774
Title
Human upper body identification from images
Author
Jacques, J. C S, Jr. ; Dihl, L. ; Jung, C.R. ; Thielo, M.R. ; Keshet, R. ; Musse, S.R.
Author_Institution
Pontificia Univ. Catolica do Rio Grande do Sul, Rio Grande, Brazil
fYear
2010
fDate
26-29 Sept. 2010
Firstpage
1717
Lastpage
1720
Abstract
Estimating human pose in static images is challenging due to the high dimensional state space, presence of image clutter and ambiguities of image observations. In this paper we propose a method to automatically segment human subjects in images, based on dominant colors, and given the face captured by a face detector. The posture is estimated using a 2D model combined with anthropometric data. Experimental results showed that the proposed technique performs well in non trivial images.
Keywords
clutter; face recognition; image colour analysis; image segmentation; object detection; pose estimation; 2D model; face detector; human pose estimation; human upper body identification; image clutter; image color; image observation; image segmentation; posture estimation; static image; Elbow; Face; Humans; Image color analysis; Image segmentation; Pixel; Skin; human upper body parts estimation; segmentation;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location
Hong Kong
ISSN
1522-4880
Print_ISBN
978-1-4244-7992-4
Electronic_ISBN
1522-4880
Type
conf
DOI
10.1109/ICIP.2010.5653552
Filename
5653552
Link To Document