A method of visual metrology from uncalibrated images

  • Authors:

  • Zezhi Chen;Nick Pears;Bojian Liang

  • Affiliations:

  • Department of Computer Science, University of York, York YO10 5DD, UK;Department of Computer Science, University of York, York YO10 5DD, UK;Department of Computer Science, University of York, York YO10 5DD, UK

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2006

Quantified Score

Hi-index 0.10

Visualization

Abstract

A method of measuring the height of any feature above a reference plane from a pair of uncalibrated images, separated by a (near) pure translation is presented. The output of the algorithm is a feature height, expressed as a fraction of the height of the camera above the reference plane. There are three contributions. Firstly a robust method of computing the dual epipole or focus of expansion (FOE) under pure translation is presented. Secondly, a novel reciprocal-polar (RP) image rectification scheme is presented, which allows planar image motion, expressed as a planar homography, to be accurately detected and recovered by 1D correlation. The technique can work even when there are no corner features on the reference plane and even over large image distortions caused by large camera motion, which would cause correlation techniques in the original image space to fail. Thirdly, we present a projective construct to enable measurement of the relative (or affine) feature height. Results show that our algorithm performs very well against outliers and noise. The mean of absolute error is 1.8mm, and the mean of relative error is only 0.13% with two outliers removed.