Presentation 2005/3/10
Self-Location Estimation of a Camera by Observing Known Background Images
Toshiyuki ADACHI, Katsuya KONDO, Syoji KOBASHI, Yutaka HATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Such applications as visual navigation of mobile robot with image sensor and mixed, augmented reality have been investigated actively. Many of these techniques require the localization of human or robot. In this report, we propose a camera position and pose estimation method using extracted feature points in time-series of images. The technique can be applied to indoor environment with known background images. In our approach, the camera position and pose in the next frame are predicted from an estimated trajectory of moving camera to extract feature points. The correction based on the prediction and current measurement, and update prediction are performed for efficient estimation of 3D position and camera parameters representing pan and tilt.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Camera Position / Feature Point / Monocular Vision / Moving Camera / Prediction and Correction
Paper # SIS2004-57
Date of Issue

Conference Information
Committee SIS
Conference Date 2005/3/10(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 Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Self-Location Estimation of a Camera by Observing Known Background Images
Sub Title (in English)
Keyword(1) Camera Position
Keyword(2) Feature Point
Keyword(3) Monocular Vision
Keyword(4) Moving Camera
Keyword(5) Prediction and Correction
1st Author's Name Toshiyuki ADACHI
1st Author's Affiliation Graduate School of Engineering, University of Hyogo()
2nd Author's Name Katsuya KONDO
2nd Author's Affiliation Graduate School of Engineering, University of Hyogo
3rd Author's Name Syoji KOBASHI
3rd Author's Affiliation Graduate School of Engineering, University of Hyogo
4th Author's Name Yutaka HATA
4th Author's Affiliation Graduate School of Engineering, University of Hyogo
Date 2005/3/10
Paper # SIS2004-57
Volume (vol) vol.104
Number (no) 735
Page pp.pp.-
#Pages 6
Date of Issue