Accession Number:

ADA167783

Title:

Perspective Projection Invariants,

Descriptive Note:

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s):

Report Date:

1986-02-01

Pagination or Media Count:

17.0

Abstract:

An important part of stereo vision consists of finding and matching points in two images which correspond to the same physical element in the scene. This document shows that zeros of curvature of curves are perspective invariants and can therefore be used to find corresponding points. These can be used to help solve the registration problem and to obtain the correct depth when a curve enters the forbidden zone. These are also relevant to theories for representing image curves. The stability of these zeros of curvature are considered. Author

Subject Categories:

  • Theoretical Mathematics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE