Analog-VLSI, array-processor-based, Bayesian, multi-scale optical flow estimation

L. Török, A. Zarándy

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Optical flow (OF) estimation aims at derive a motion-vector field that characterizes motions on a video sequence of images. In this paper, we propose a new multi-scale (or scale-space) algorithm that generates OF on cellular neural/non-linear network universal machine, a general purpose analog-VLSI hardware, at resolution of 128 × 128 with fair accuracy and working over a speed of 100 frames/s. The performance of the hardware implementation of the proposed algorithm is measured on a standard image sequence. As far as we are concerned, this is the first time when an OF estimator hardware is tested on a practical-size standard image sequence.

Original languageEnglish
Pages (from-to)49-75
Number of pages27
JournalInternational Journal of Circuit Theory and Applications
Volume34
Issue number1
DOIs
Publication statusPublished - Jan 2006

Fingerprint

Optical flows
Optical Flow
Parallel processing systems
Image Sequence
Analogue
Hardware
Nonlinear networks
Motion Vector
Scale Space
Hardware Implementation
Vector Field
Estimator
Motion
Standards

Keywords

  • Analog VLSI implementation
  • Cellular neural/non-linear network
  • Multi-scale
  • Optical flow algorithm

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Analog-VLSI, array-processor-based, Bayesian, multi-scale optical flow estimation. / Török, L.; Zarándy, A.

In: International Journal of Circuit Theory and Applications, Vol. 34, No. 1, 01.2006, p. 49-75.

Research output: Contribution to journalArticle

@article{44eecacac81745cba9ea257a1c82a56f,
title = "Analog-VLSI, array-processor-based, Bayesian, multi-scale optical flow estimation",
abstract = "Optical flow (OF) estimation aims at derive a motion-vector field that characterizes motions on a video sequence of images. In this paper, we propose a new multi-scale (or scale-space) algorithm that generates OF on cellular neural/non-linear network universal machine, a general purpose analog-VLSI hardware, at resolution of 128 × 128 with fair accuracy and working over a speed of 100 frames/s. The performance of the hardware implementation of the proposed algorithm is measured on a standard image sequence. As far as we are concerned, this is the first time when an OF estimator hardware is tested on a practical-size standard image sequence.",
keywords = "Analog VLSI implementation, Cellular neural/non-linear network, Multi-scale, Optical flow algorithm",
author = "L. T{\"o}r{\"o}k and A. Zar{\'a}ndy",
year = "2006",
month = "1",
doi = "10.1002/cta.342",
language = "English",
volume = "34",
pages = "49--75",
journal = "International Journal of Circuit Theory and Applications",
issn = "0098-9886",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - Analog-VLSI, array-processor-based, Bayesian, multi-scale optical flow estimation

AU - Török, L.

AU - Zarándy, A.

PY - 2006/1

Y1 - 2006/1

N2 - Optical flow (OF) estimation aims at derive a motion-vector field that characterizes motions on a video sequence of images. In this paper, we propose a new multi-scale (or scale-space) algorithm that generates OF on cellular neural/non-linear network universal machine, a general purpose analog-VLSI hardware, at resolution of 128 × 128 with fair accuracy and working over a speed of 100 frames/s. The performance of the hardware implementation of the proposed algorithm is measured on a standard image sequence. As far as we are concerned, this is the first time when an OF estimator hardware is tested on a practical-size standard image sequence.

AB - Optical flow (OF) estimation aims at derive a motion-vector field that characterizes motions on a video sequence of images. In this paper, we propose a new multi-scale (or scale-space) algorithm that generates OF on cellular neural/non-linear network universal machine, a general purpose analog-VLSI hardware, at resolution of 128 × 128 with fair accuracy and working over a speed of 100 frames/s. The performance of the hardware implementation of the proposed algorithm is measured on a standard image sequence. As far as we are concerned, this is the first time when an OF estimator hardware is tested on a practical-size standard image sequence.

KW - Analog VLSI implementation

KW - Cellular neural/non-linear network

KW - Multi-scale

KW - Optical flow algorithm

UR - http://www.scopus.com/inward/record.url?scp=32344431666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=32344431666&partnerID=8YFLogxK

U2 - 10.1002/cta.342

DO - 10.1002/cta.342

M3 - Article

AN - SCOPUS:32344431666

VL - 34

SP - 49

EP - 75

JO - International Journal of Circuit Theory and Applications

JF - International Journal of Circuit Theory and Applications

SN - 0098-9886

IS - 1

ER -