Displacement vector estimation with cellular neural networks

Publikation: Beitrag zu KonferenzenPaperBeigetragenBegutachtung

Beitragende

  • Dirk Feiden - , Universitätsklinikum Frankfurt (Autor:in)
  • Ronald Tetzlaff - , Universitätsklinikum Frankfurt (Autor:in)

Abstract

Displacement vector estimation is one of the open key problems in Computer Vision and Video Coding. For example in Computer Vision the displacement vector estimation is usually the base of some kind of motion estimation. Unfortunately, the displacement vector estimation using statistical methods is always computationally complex what might be a restriction in real-time processing. In this contribution we show that displacement vector estimation can efficiently be performed by using Cellular Neural Networks (CNN). In order to find CNN-templates therefore, we have used the new optimization method of Iterative Annealing.

Details

OriginalspracheEnglisch
Seiten2049-2052
Seitenumfang4
PublikationsstatusVeröffentlicht - 2002
Peer-Review-StatusJa
Extern publiziertJa

Konferenz

Titel2002 International Joint Conference on Neural Networks (IJCNN'02)
Dauer12 - 17 Mai 2002
StadtHonolulu, HI
LandUSA/Vereinigte Staaten

Externe IDs

ORCID /0000-0001-7436-0103/work/142240265

Schlagworte

ASJC Scopus Sachgebiete