A deterministic algorithm for optical flow estimation (Abstract/Poster in atti di convegno)

Type
Label
  • A deterministic algorithm for optical flow estimation (Abstract/Poster in atti di convegno) (literal)
Anno
  • 2010-01-01T00:00:00+01:00 (literal)
Alternative label
  • Gerace I.; Martinelli F. (2010)
    A deterministic algorithm for optical flow estimation
    in SIMAI 10th Congress, Cagliari
    (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
  • Gerace I.; Martinelli F. (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#note
  • In: SIMAI 10th Congress (Cagliari, 21-25 June 2010). Abstract, pp. 54 - 54. Società Italiana di Matematica Applicata, SEMA Spanish Society for Applied Mathematics - Spain. SIMAI, 2010. (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#descrizioneSinteticaDelProdotto
  • Motion computation is a fundamental and difficult problem of Computer Vision which regards either the computation of 3-D motion in the image space or the computation of 2-D motion in the image plane. In this paper, we deal with the latter problem, which is also called optical flow. We propose a new deterministic algorithm for determining optical flow through regular- ization techniques so that the solution of the problem is defined as the minimum of an appropriate energy function. We also assume that the displacements are piecewise continu- ous and that the discontinuities are variable to be estimated. More precisely, we introduce a hierarchical three-step optimization strategy to minimize the constructed energy function, which is not convex. In the first step we find a suitable initial guess of the displacements field by a gradient-based GNC algorithm. In the second step we define the local energy of a displacement field as the energy function obtained by fixing all the field with the exception of a row or of a column. Then, through an application of the shortest path technique we minimize iteratively each local energy function restricted to a row or to a column until we arrive at a fixed point. In the last step we use again a GNC algorithm to recover a sub-pixel accuracy. The experimental results confirm the goodness of this technique. (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
  • Università degli Studi di Perugia, CNR-ISTI, Pisa (literal)
Titolo
  • A deterministic algorithm for optical flow estimation (literal)
Prodotto di
Autore CNR
Insieme di parole chiave

Incoming links:


Prodotto
Autore CNR di
Insieme di parole chiave di
data.CNR.it