A 3D Registration Method based on Optimal Segmentation and Local Character Tensors

Jingjing Wang; Hajime Nobuhara; Yutaka Hatakeyama; Fangyan Dong; Kaoru Hirota

doi:10.14864/softscis.2006.0.151.0

SCIS & ISIS 2006

セッションID: TH-G2-3

DOI https://doi.org/10.14864/softscis.2006.0.151.0

会議情報

主催: Japan SOciety for Fuzzy Theory and intelligent informatics

共催: The Korea Fuzzy Logic and Intelligent Systems Society, IEEE Computational Intelligence Society, The International Fuzzy Systems Association, 21th Century COE Program "Creation of Agent-Based Social Systems Sciences"

TH-G2 Video/3D Image Processing

A 3D Registration Method based on Optimal Segmentation and Local Character Tensors

*Jingjing Wang, Hajime Nobuhara, Yutaka Hatakeyama, Fangyan Dong, Kaoru Hirota

著者情報

キーワード: spin image, Gaussian Curvature operator, local character tensor

会議録・要旨集フリー

詳細

抄録

An automatic 3D pair-wise registration method based on an optimal segmentation and a local character tensor is proposed. It consists of two characters, i.e., the optimal segmentation to realize the automatic processing and the local character tensor to improve the matching probability. Non-structured 3D datasets of a rabbit doll are tested on a PC with Intel Pentium M 1.60GHz and 512MB memory. Experiment results show the proposed method increases the matching probability average for 18.5% and decreases the computational time average for 21.6 second compared to those of the conventional spin image method.

責任著者(Corresponding author)

J-STAGEへの登録はこちら（無料）