This paper proposes a new approach to rectification, a process whereby a stereo pair of images is re-sampled so as to make imposing the two view geometric constraint simple. This is normally performed by applying a single linear transformation per image, a method which has the drawback that some camera motions produce rectified images which are heavily distorted or unbounded. More recent attempts have applied nonlinear transformations to each image to allow any camera motion, but as a consequence distort each image in a different non rigid way. This work provides a hybrid linear/nonlinear method that greatly reduces this problem, and simplifies the technique. The technique also provides further improvements by selecting the rectifying transformation so as to minimise perspective effects between the images.
Home Contents Author index Keyword index
This document produced for BMVC 2001