Please use this identifier to cite or link to this item: doi:10.22028/D291-26234
Title: Lucas/Kanade meets Horn/Schunck : combining local and global optic flow methods
Author(s): Weickert, Joachim
Bruhn, Andres
Schnörr, Christoph
Language: English
Year of Publication: 2003
Free key words: computer vision
differential techniques
confidence measures
DDC notations: 510 Mathematics
Publikation type: Other
Abstract: 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 to this record: urn:nbn:de:bsz:291-scidok-44179
Series name: Preprint / Fachrichtung Mathematik, Universität des Saarlandes
Series volume: 82
Date of registration: 6-Dec-2011
Faculty: MI - Fakultät für Mathematik und Informatik
Department: MI - Mathematik
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
File Description SizeFormat 
preprint_82_03.pdf826,81 kBAdobe PDFView/Open

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.