Paper Info
Title
Parametric Subpixel Matchpoint Recovery with Uncertainty Estimation: A Statistical Approach
Abstract
We present a novel matchpoint acquisition method capable of producing accurate correspondences at subpixel preci- sion. Given the known representation of the point to be matched, such as a projected fiducial in a structured light system, the method estimates the fiducial location and its expected uncertainty. Improved matchpoint precision has application in a number of calibration tasks, and uncer- tainty estimates can be used to significantly improve overall calibration results. A simple parametric model captures the relationship be- tween the known fiducial and its corresponding position, shape, and intensity on the image plane. For each match- point pair, these unknown model parameters are recovered using maximum likelihood estimation to determine a sub- pixel center for the fiducial. The uncertainty of the match- point center is estimated by performing forward error anal- ysis on the expected image noise. Uncertainty estimates used in conjunction with the accurate matchpoints can im- prove calibration accuracy for multi-view systems.
Year
DOI
Venue
2003
10.1109/CVPRW.2003.10091
CVPR Workshops
Field
DocType
Volume
Computer vision,Fiducial marker,Parametric model,Structured light,Pattern recognition,Computer science,Image plane,Image noise,Parametric statistics,Artificial intelligence,Subpixel rendering,Calibration
Conference
8
Issue
ISSN
Citations 
1
1063-6919
3
PageRank 
References 
Authors
0.46
14
2
Name
Order
Citations
PageRank
Matt Steele151.26
Christopher Jaynes224520.92