Generalized Convexity in Multiple View Geometry

Research output: Contribution to journalArticle

Abstract

Recent work on geometric vision problems has exploited convexity properties in order to obtain globally optimal solutions. In this paper we give an overview of these developments and show the tight connections between different types of convexity and optimality conditions for a large class of multiview geometry problems. We also show how the convexity properties are closely linked to different types of optimization algorithms for computing the solutions. Moreover, it is also demonstrated how convexity can be used for detection and removal of outliers. The theoretical findings are accompanied with illustrative examples and experimental results on real data.

Details

Authors
Organisations
Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • Mathematics

Keywords

  • Generalized convexity, Multiple view geometry, Computer vision
Original languageEnglish
Pages (from-to)35-51
JournalJournal of Mathematical Imaging and Vision
Volume38
Issue number1
StatePublished - 2010
Publication categoryResearch
Peer-reviewedYes