A CNN implementation of the Horn & Schunck motion estimation method

A. Gacsádi, C. Grava, V. Tiponuţ, P. Szolgay

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper the parallel implementation of the Horn and Schunck motion estimation method in image sequences is presented, by using Cellular Neural Networks (CNN). One of the drawbacks of the classical motion estimation algorithms is the computational time. The goal of the CNN implementation of the Horn & Schunck method is to increase the efficiency of the wellknown classical implementation of this method, which is one of the most used algorithms among the motion estimation techniques. The aim is to obtain a smaller computation time and to include such an algorithm in motion compensation algorithms implemented using CNN, in order to obtain homogeneous algorithms for real-time applications in artificial vision or medical imaging.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
DOIs
Publication statusPublished - 2006
Event2006 10th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2006 - Istanbul, Turkey
Duration: Aug 28 2006Aug 30 2006

Other

Other2006 10th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2006
CountryTurkey
CityIstanbul
Period8/28/068/30/06

Fingerprint

Cellular neural networks
Motion estimation
Motion compensation
Medical imaging
Computer vision

Keywords

  • Cellular neural networks
  • Image processing
  • Motion estimation
  • Optical flow
  • Real-time applications

ASJC Scopus subject areas

  • Software

Cite this

Gacsádi, A., Grava, C., Tiponuţ, V., & Szolgay, P. (2006). A CNN implementation of the Horn & Schunck motion estimation method. In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications [4145855] https://doi.org/10.1109/CNNA.2006.341615

A CNN implementation of the Horn & Schunck motion estimation method. / Gacsádi, A.; Grava, C.; Tiponuţ, V.; Szolgay, P.

Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. 2006. 4145855.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gacsádi, A, Grava, C, Tiponuţ, V & Szolgay, P 2006, A CNN implementation of the Horn & Schunck motion estimation method. in Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications., 4145855, 2006 10th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2006, Istanbul, Turkey, 8/28/06. https://doi.org/10.1109/CNNA.2006.341615
Gacsádi A, Grava C, Tiponuţ V, Szolgay P. A CNN implementation of the Horn & Schunck motion estimation method. In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. 2006. 4145855 https://doi.org/10.1109/CNNA.2006.341615
Gacsádi, A. ; Grava, C. ; Tiponuţ, V. ; Szolgay, P. / A CNN implementation of the Horn & Schunck motion estimation method. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. 2006.
@inproceedings{6c51309786974ada8778b14af925009b,
title = "A CNN implementation of the Horn & Schunck motion estimation method",
abstract = "In this paper the parallel implementation of the Horn and Schunck motion estimation method in image sequences is presented, by using Cellular Neural Networks (CNN). One of the drawbacks of the classical motion estimation algorithms is the computational time. The goal of the CNN implementation of the Horn & Schunck method is to increase the efficiency of the wellknown classical implementation of this method, which is one of the most used algorithms among the motion estimation techniques. The aim is to obtain a smaller computation time and to include such an algorithm in motion compensation algorithms implemented using CNN, in order to obtain homogeneous algorithms for real-time applications in artificial vision or medical imaging.",
keywords = "Cellular neural networks, Image processing, Motion estimation, Optical flow, Real-time applications",
author = "A. Gacs{\'a}di and C. Grava and V. Tiponuţ and P. Szolgay",
year = "2006",
doi = "10.1109/CNNA.2006.341615",
language = "English",
isbn = "1424406404",
booktitle = "Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications",

}

TY - GEN

T1 - A CNN implementation of the Horn & Schunck motion estimation method

AU - Gacsádi, A.

AU - Grava, C.

AU - Tiponuţ, V.

AU - Szolgay, P.

PY - 2006

Y1 - 2006

N2 - In this paper the parallel implementation of the Horn and Schunck motion estimation method in image sequences is presented, by using Cellular Neural Networks (CNN). One of the drawbacks of the classical motion estimation algorithms is the computational time. The goal of the CNN implementation of the Horn & Schunck method is to increase the efficiency of the wellknown classical implementation of this method, which is one of the most used algorithms among the motion estimation techniques. The aim is to obtain a smaller computation time and to include such an algorithm in motion compensation algorithms implemented using CNN, in order to obtain homogeneous algorithms for real-time applications in artificial vision or medical imaging.

AB - In this paper the parallel implementation of the Horn and Schunck motion estimation method in image sequences is presented, by using Cellular Neural Networks (CNN). One of the drawbacks of the classical motion estimation algorithms is the computational time. The goal of the CNN implementation of the Horn & Schunck method is to increase the efficiency of the wellknown classical implementation of this method, which is one of the most used algorithms among the motion estimation techniques. The aim is to obtain a smaller computation time and to include such an algorithm in motion compensation algorithms implemented using CNN, in order to obtain homogeneous algorithms for real-time applications in artificial vision or medical imaging.

KW - Cellular neural networks

KW - Image processing

KW - Motion estimation

KW - Optical flow

KW - Real-time applications

UR - http://www.scopus.com/inward/record.url?scp=47549114468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47549114468&partnerID=8YFLogxK

U2 - 10.1109/CNNA.2006.341615

DO - 10.1109/CNNA.2006.341615

M3 - Conference contribution

AN - SCOPUS:47549114468

SN - 1424406404

SN - 9781424406401

BT - Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

ER -