Rectifying transformations that minimize resampling effects
- 25 August 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 111-117
- https://doi.org/10.1109/cvpr.2001.990463
Abstract
Image rectification is the process of warping a pair of stereo images in order to align the epipolar lines with the scan-lines of the images. Once a pair of images is rectified, stereo matching can be implemented in an efficient manner. Given the epipolar geometry, it is straightforward to define a rectifying transformation, however, many transformations will lead to unwanted image distortions. In this paper, we present a novel method for stereo rectification that deter- mines the transformation that minimizes the effects of resam- pling that can impede stereo matching. The effects we seek to minimize are the loss of pixels due to under-sampling and the creation of new pixels due to over-sampling. To min- imize these effects we parameterize the family of rectifica- tion transformations and solve for the one that minimizes the change in local area integrated over the area of the images.Keywords
This publication has 7 references indexed in Scilit:
- Rectification of images for binocular and trinocular stereovisionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Cylindrical rectification to minimize epipolar distortionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Theory and Practice of Projective RectificationInternational Journal of Computer Vision, 1999
- A simple and efficient rectification method for general motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Epipolar line estimation and rectification for stereo image pairsIEEE Transactions on Image Processing, 1996
- A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometryArtificial Intelligence, 1995
- Mathematical Methods of Classical MechanicsPublished by Springer Nature ,1989