Rotation invariant detection of moving and standing objects using analogic cellular neural network algorithms based on ring-codes

Csaba Rekeczky, Akio Ushida, T. Roska

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Cellular Neural Networks (CNNs) are nonlinear dynamic array processors with mainly local interconnections. In most of the applications, the local interconnection pattern, called cloning template, is translation invariant. In this paper, an optimal ring-coding method for rotation invariant description of given set of objects, is introduced. The design methodology of the templates based on the ring-codes and the synthesis of CNN analogic algorithms to detect standing and moving objects in a rotationally invariant way, is discussed in detail. It is shown that the algorithms can be implemented using the CNN Universal Machine, the recently invented analogic visual microprocessor. The estimated time performance and the parallel detecting capability is emphasized, the limitations are also thoroughly investigated.

Original languageEnglish
Pages (from-to)1316-1330
Number of pages15
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE78-A
Issue number10
Publication statusPublished - Oct 1995

Fingerprint

Cellular neural networks
Rotation Invariant
Network Algorithms
Cellular Networks
Neural Networks
Ring
Interconnection
Template
Invariant
Cloning
Microprocessor
Parallel processing systems
Moving Objects
Nonlinear Dynamics
Design Methodology
Microprocessor chips
Coding
Synthesis
Object

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Electrical and Electronic Engineering

Cite this

@article{165b017129cf40d0ae34ef385029d637,
title = "Rotation invariant detection of moving and standing objects using analogic cellular neural network algorithms based on ring-codes",
abstract = "Cellular Neural Networks (CNNs) are nonlinear dynamic array processors with mainly local interconnections. In most of the applications, the local interconnection pattern, called cloning template, is translation invariant. In this paper, an optimal ring-coding method for rotation invariant description of given set of objects, is introduced. The design methodology of the templates based on the ring-codes and the synthesis of CNN analogic algorithms to detect standing and moving objects in a rotationally invariant way, is discussed in detail. It is shown that the algorithms can be implemented using the CNN Universal Machine, the recently invented analogic visual microprocessor. The estimated time performance and the parallel detecting capability is emphasized, the limitations are also thoroughly investigated.",
author = "Csaba Rekeczky and Akio Ushida and T. Roska",
year = "1995",
month = "10",
language = "English",
volume = "E78-A",
pages = "1316--1330",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "10",

}

TY - JOUR

T1 - Rotation invariant detection of moving and standing objects using analogic cellular neural network algorithms based on ring-codes

AU - Rekeczky, Csaba

AU - Ushida, Akio

AU - Roska, T.

PY - 1995/10

Y1 - 1995/10

N2 - Cellular Neural Networks (CNNs) are nonlinear dynamic array processors with mainly local interconnections. In most of the applications, the local interconnection pattern, called cloning template, is translation invariant. In this paper, an optimal ring-coding method for rotation invariant description of given set of objects, is introduced. The design methodology of the templates based on the ring-codes and the synthesis of CNN analogic algorithms to detect standing and moving objects in a rotationally invariant way, is discussed in detail. It is shown that the algorithms can be implemented using the CNN Universal Machine, the recently invented analogic visual microprocessor. The estimated time performance and the parallel detecting capability is emphasized, the limitations are also thoroughly investigated.

AB - Cellular Neural Networks (CNNs) are nonlinear dynamic array processors with mainly local interconnections. In most of the applications, the local interconnection pattern, called cloning template, is translation invariant. In this paper, an optimal ring-coding method for rotation invariant description of given set of objects, is introduced. The design methodology of the templates based on the ring-codes and the synthesis of CNN analogic algorithms to detect standing and moving objects in a rotationally invariant way, is discussed in detail. It is shown that the algorithms can be implemented using the CNN Universal Machine, the recently invented analogic visual microprocessor. The estimated time performance and the parallel detecting capability is emphasized, the limitations are also thoroughly investigated.

UR - http://www.scopus.com/inward/record.url?scp=0029390283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029390283&partnerID=8YFLogxK

M3 - Article

VL - E78-A

SP - 1316

EP - 1330

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 10

ER -