Euclidean constraints for uncalibrated reconstruction
- 11 May 1993
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 466-470
- https://doi.org/10.1109/iccv.1993.378179
Abstract
International audienceIt is possible to recover the three-dimensional structure of a scene using images taken with uncalibrated cameras and pixel correspondences betweeen these images. But such reconstruction can only be performed up to a projective transformation of the 3-D space. Therefore, constraints have to be put on the reconstructed data to get the reconstruction in the Euclidean space. Such constraints arise from knowledge of the scene, such as the location of points, geometrical constraints on lines, etc. The kind of constraints that have to be added are discussed, and it is shown how they can be fed in a general framework. Experimental results on real data prove the feasibility, and experiments on simulated data address the accuracy of the resultsKeywords
This publication has 4 references indexed in Scilit:
- Stereo from uncalibrated camerasPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Factoring image sequences into shape and motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Finding point correspondence and determining motion of a rigid object from two weak perspective viewsComputer Vision, Graphics, and Image Processing, 1990
- Determining perspective structures using hierarchical Hough transformPattern Recognition Letters, 1989