Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
An automatic modeling of human bodies from sizing parameters
I3D '03 Proceedings of the 2003 symposium on Interactive 3D graphics
Estimation of the Location of Joint Points of Human Body from Successive Volume Data
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
The space of human body shapes: reconstruction and parameterization from range scans
ACM SIGGRAPH 2003 Papers
| Hi-index | 0.00 |
We present a novel method for extracting the 23 feature points on 3D human scans to make clothes not using landmark. In order to extract the feature points, we distribute the feature points into two types which are curvature feature points and structure feature points. The curvature feature points are determined from curvature distribution of a neighboring area from the feature points which have common chracteristics between individual body shapes. The structure feature points can not be determined from curvature distribution alone because of the great differences between individual body shapes. Therefore, in this paper, we propose the two methods for extracting the curvature feature points based on the shape of a standard model and the structure feature points by using a contour tree algorithm (which is a graph consisting of the structural relationships between the features extracted from the shape of an objective model). Finally, we evaluate our algorithm on 11 human body models with different shapes and the results in the experiment shows that our proposal method was effective.