Presentation 1996/10/17
A Method of Pose Estimation Using 3D Models from an Image Sequence
Takashi Mori, Masao Izumi, Kunio Fukunaga,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we proposed a new method of position and pose estimation using 3D information extracted by the motion analysis of input image sequences. At first, this method roughly estimates the position and the pose of an object using repulsive force and gravity force. In this next, our method corrects the position and the pose of an object using 2D information comparing the input edge images and the synthesized images from estimated 3D position and pose in the previous stage. Experiment results using both synthetic and real images are also described.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) object recognition / motion analysis / global pose estimation / local pose estimation / model-based / 3D reconstruction
Paper # PRMU96-60
Date of Issue

Conference Information
Committee PRMU
Conference Date 1996/10/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Method of Pose Estimation Using 3D Models from an Image Sequence
Sub Title (in English)
Keyword(1) object recognition
Keyword(2) motion analysis
Keyword(3) global pose estimation
Keyword(4) local pose estimation
Keyword(5) model-based
Keyword(6) 3D reconstruction
1st Author's Name Takashi Mori
1st Author's Affiliation College of Engineering, Osaka Prefecture University()
2nd Author's Name Masao Izumi
2nd Author's Affiliation College of Engineering, Osaka Prefecture University
3rd Author's Name Kunio Fukunaga
3rd Author's Affiliation College of Engineering, Osaka Prefecture University
Date 1996/10/17
Paper # PRMU96-60
Volume (vol) vol.96
Number (no) 307
Page pp.pp.-
#Pages 8
Date of Issue