Presentation 1999/1/22
Metric Reconstruction with an Uncalibrated Camera
Tonko Martin, Keisuke Kinoshita,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper a monocular system for metric reconstruction of rigid three-dimensional textured objects from images of an uncalibrated camera is presented. Since the general way to obtain a metric reconstruction is already solved, the emphasis is on the improvement of metric reconstruction in the presense of noise as well as on the integration of metric reconstruction and point feature acquisition. For fully automatic point feature detection, the system processes gray-value images. High-curvature points on contours are used as point features. The estimation of the projective and further on Euclidian geometries, i.e.calibration and reconstruction, is based on trajectories of high-curvature points. Experiment results are given to assess the system performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Uncalibrated Vision / Projective and Metric Reconstruction / Feature Detection and Tracking
Paper # PRMU98-205
Date of Issue

Conference Information
Committee PRMU
Conference Date 1999/1/22(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) Metric Reconstruction with an Uncalibrated Camera
Sub Title (in English)
Keyword(1) Uncalibrated Vision
Keyword(2) Projective and Metric Reconstruction
Keyword(3) Feature Detection and Tracking
1st Author's Name Tonko Martin
1st Author's Affiliation ATR Human Information Processing Research Laboratories()
2nd Author's Name Keisuke Kinoshita
2nd Author's Affiliation ATR Human Information Processing Research Laboratories
Date 1999/1/22
Paper # PRMU98-205
Volume (vol) vol.98
Number (no) 528
Page pp.pp.-
#Pages 8
Date of Issue