Methods for Interpreting Perspective Images,
Abstract
A fundamental probelm in computer vision is how, given an image, to determine the orientation of curves and surfaces in space. The problem is difficult because metric properties, such as orientation and length, are not invariant under projection. Under perspective projection (the correct model for most real images) the transform is nonlinear, and therefore hard to invert. Two methods are presented: one finds the orientation of parallel lines and planes by locating vanishing points and vanishing liners; the other determines the orientation of planes by backprojection of angles. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1982
- Accession Number
- ADP000125
Entities
People
- Stephen T. Barnard
Organizations
- SRI International