Bitte benutzen Sie diese Referenz, um auf diese Ressource zu verweisen: doi:10.22028/D291-26234
Titel: Lucas/Kanade meets Horn/Schunck : combining local and global optic flow methods
Verfasser: Weickert, Joachim
Bruhn, Andres
Schnörr, Christoph
Sprache: Englisch
Erscheinungsjahr: 2003
Freie Schlagwörter: computer vision
differential techniques
confidence measures
DDC-Sachgruppe: 510 Mathematik
Dokumentart : Preprint (Vorabdruck)
Kurzfassung: 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.
Link zu diesem Datensatz: urn:nbn:de:bsz:291-scidok-44179
hdl:20.500.11880/26290
http://dx.doi.org/10.22028/D291-26234
Schriftenreihe: Preprint / Fachrichtung Mathematik, Universität des Saarlandes
Band: 82
SciDok-Publikation: 6-Dez-2011
Fakultät: Fakultät 6 - Naturwissenschaftlich-Technische Fakultät I
Fachrichtung: MI - Mathematik
Fakultät / Institution:MI - Fakultät für Mathematik und Informatik

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
preprint_82_03.pdf826,81 kBAdobe PDFÖffnen/Anzeigen


Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt.