Title :
Postures of a human wearing a multiple-colored suit based on color information processing
Author :
Kang, Dong-Wan ; Ohya, Jun
Author_Institution :
Graduate Sch. of Global Inf. & Telecommun. Studies, Waseda Univ., Tokyo, Japan
Abstract :
This paper proposes a non-contact type method for estimating human body postures. One of the major problems on the posture estimation using the silhouette image analysis is the overlapping of the body parts´ silhouettes. In order to solve this problem, this paper proposes a method for estimating the posture of a human wearing a multiple-colored suit based on color information processing. By analyzing the contour of the human´s silhouette, the method judges whether feature points are occluded by another body parts. If the occlusions occurs, color region segmentation is performed in order to know which region is frontal. The feature point in the frontal region is located in the skeleton of the region. Experimental results show the effectiveness of the proposed method.
Keywords :
gesture recognition; image colour analysis; image segmentation; motion estimation; virtual reality; color information processing; color region segmentation; human body postures estimation; multiple-colored suit; occlusions; silhouette image analysis; Computer vision; Flowcharts; Humans; Image color analysis; Image motion analysis; Information processing; Layout; Robustness; Skeleton; Virtual environment;
Conference_Titel :
Multimedia and Expo, 2003. ICME '03. Proceedings. 2003 International Conference on
Print_ISBN :
0-7803-7965-9
DOI :
10.1109/ICME.2003.1220904