Eingang zum Volltext in SciDok


Preprint (Vorabdruck) zugänglich unter
URN: urn:nbn:de:bsz:291-scidok-44179

Lucas/Kanade meets Horn/Schunck : combining local and global optic flow methods

Weickert, Joachim ; Bruhn, Andres ; Schnörr, Christoph

Dokument 1.pdf (827 KB)

Bookmark bei Connotea Bookmark bei
Freie Schlagwörter (Englisch): computer vision , differential techniques , confidence measures
Institut: Fachrichtung 6.1 - Mathematik
DDC-Sachgruppe: Mathematik
Dokumentart: Preprint (Vorabdruck)
Schriftenreihe: Preprint / Fachrichtung Mathematik, Universität des Saarlandes
Bandnummer: 82
Sprache: Englisch
Erstellungsjahr: 2003
Publikationsdatum: 06.12.2011
Kurzfassung auf Englisch: Differential methods belong to the most widely used techniques for optic flow computation in image sequences. They can be classified into local methods such as the Lucas-Kanade technique or Bigün's structure tensor method, and into global methods such as the Horn/Schunck approach and its extensions. Often local methods are more robust under noise, while global techniques yield dense flow fields. The goal of this paper is to contribute to a better understanding and the design of differential methods in four ways: (i) We juxtapose the role of smoothing/regularisation processes that are required in local and global differential methods for optic flow computation. (ii) This discussion motivates us to describe and evaluate a novel method that combines important advantages of local and global approaches: It yields dense flow fields that are robust against noise. (iii) Spatiotemproal and nonlinear extensions to this hybrid method are presented. (iv) We propose a simple confidence measure for optic flow methods that minimise energy functionals. It allows to sparsify a dense flow field gradually, depending on the reliability required for the resulting flow. Comparisons with experiments from the literature demonstrate the favourable performance of the proposed methods and the confidence measure.
Lizenz: Standard-Veröffentlichungsvertrag

Home | Impressum | Über SciDok | Policy | Kontakt | Datenschutzerklärung | English