Direct computation of qualitative 3D shape and motion invariants

Daphna Weinshall*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

The author shows that the sign of the normal curvature in a given direction at a given point in the image can be computed from a simple difference of slopes of line-segments in one image. Using this result, local surface patches can be classified as convex, concave, parabolic (cylindrical), hyperbolic (saddle point) or planar. At the same time the translational component of the optical flow is obtained, from which the focus of expansion can be computed. In addition, the axes of principal curvature and the axes of zero curvature are obtained.

Original languageEnglish
Title of host publicationProc 3 Int Conf Comput Vision
PublisherPubl by IEEE
Pages230-237
Number of pages8
ISBN (Print)0818620579
StatePublished - 1990
Externally publishedYes
EventProceedings 3rd International Conference on Computer Vision - Osaka, Jpn
Duration: 4 Dec 19907 Dec 1990

Publication series

NameProc 3 Int Conf Comput Vision

Conference

ConferenceProceedings 3rd International Conference on Computer Vision
CityOsaka, Jpn
Period4/12/907/12/90

Fingerprint

Dive into the research topics of 'Direct computation of qualitative 3D shape and motion invariants'. Together they form a unique fingerprint.

Cite this