The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)
Online ISSN : 2424-3124
2009
Session ID : 1A1-C20
Conference information
1A1-C20 Finding arid 3D Posture Estimation Method using SIFT with 3D Textured Mo(Iel arid its GPU acceleration
Takahiro NAKADA, Michel Philipp, Joel Chestnutt, Yasuhide FUKUSHIMA, Yoshitaka YAMAUCHI, Koichi NISHIWAKI, Satoshi KAGAMI, Takeo KANADE, Hiroshi MIZOGUCHI
Author information
Keywords: Image Processing, Vision, GPGPU
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Download PDF (1112K)
Download citation RIS

(compatible with EndNote, Reference Manager, ProCite, RefWorks)

BIB TEX

(compatible with BibDesk, LaTeX)

Text
How to download citation
Contact us
Abstract
This paper describes a pose estimation method using a 3D textured model of object that a robot has targeted for handling. The proposed method estimates the pose of this object using the POSIT algorithm and matching SIFT features generated from both the camera image and projected images of the model from a range of postures. Also, we achieved fast computation of this method using Graphics Processing Unit.
Content from these authors
© 2009 The Japan Society of Mechanical Engineers
Previous article Next article
Favorites & Alerts

Recently viewed articles
Announcements from publisher
Share this page
feedback
 Top