Mobile digital image stabilisation using SIMD data path

S. W. Ha, H. C. Park, T. D. Han

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Digital image stabilisation for mobile devices based on real-time phase correlation with support for the SIMD data path is presented. By using sub-image projection, the phase correlation process can be fitted within the real-time criteria. The proposed method acquires a global motion vector from a sub-image at the centre of the viewport, which is projected onto the x- and y-axes on which the phase correlation is performed. The projection stage and the FFT calculations are accelerated using the Neon SIMD engine that is facilitated in the ARM CPU. With this acceleration, the global motion vector for each image frame can be calculated in<20 ms on the Samsung Galaxy S smartphone running at 1.0GHz.

Original languageEnglish
Pages (from-to)922-924
Number of pages3
JournalElectronics Letters
Volume48
Issue number15
DOIs
Publication statusPublished - 2012 Jul 17

Fingerprint

Stabilization
Neon
Galaxies
Smartphones
Mobile devices
Fast Fourier transforms
Program processors
Engines

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Ha, S. W. ; Park, H. C. ; Han, T. D. / Mobile digital image stabilisation using SIMD data path. In: Electronics Letters. 2012 ; Vol. 48, No. 15. pp. 922-924.
@article{d0fb49a03eee4cbe8b89e3bb47dfe30a,
title = "Mobile digital image stabilisation using SIMD data path",
abstract = "Digital image stabilisation for mobile devices based on real-time phase correlation with support for the SIMD data path is presented. By using sub-image projection, the phase correlation process can be fitted within the real-time criteria. The proposed method acquires a global motion vector from a sub-image at the centre of the viewport, which is projected onto the x- and y-axes on which the phase correlation is performed. The projection stage and the FFT calculations are accelerated using the Neon SIMD engine that is facilitated in the ARM CPU. With this acceleration, the global motion vector for each image frame can be calculated in<20 ms on the Samsung Galaxy S smartphone running at 1.0GHz.",
author = "Ha, {S. W.} and Park, {H. C.} and Han, {T. D.}",
year = "2012",
month = "7",
day = "17",
doi = "10.1049/el.2012.0784",
language = "English",
volume = "48",
pages = "922--924",
journal = "Electronics Letters",
issn = "0013-5194",
publisher = "Institution of Engineering and Technology",
number = "15",

}

Mobile digital image stabilisation using SIMD data path. / Ha, S. W.; Park, H. C.; Han, T. D.

In: Electronics Letters, Vol. 48, No. 15, 17.07.2012, p. 922-924.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Mobile digital image stabilisation using SIMD data path

AU - Ha, S. W.

AU - Park, H. C.

AU - Han, T. D.

PY - 2012/7/17

Y1 - 2012/7/17

N2 - Digital image stabilisation for mobile devices based on real-time phase correlation with support for the SIMD data path is presented. By using sub-image projection, the phase correlation process can be fitted within the real-time criteria. The proposed method acquires a global motion vector from a sub-image at the centre of the viewport, which is projected onto the x- and y-axes on which the phase correlation is performed. The projection stage and the FFT calculations are accelerated using the Neon SIMD engine that is facilitated in the ARM CPU. With this acceleration, the global motion vector for each image frame can be calculated in<20 ms on the Samsung Galaxy S smartphone running at 1.0GHz.

AB - Digital image stabilisation for mobile devices based on real-time phase correlation with support for the SIMD data path is presented. By using sub-image projection, the phase correlation process can be fitted within the real-time criteria. The proposed method acquires a global motion vector from a sub-image at the centre of the viewport, which is projected onto the x- and y-axes on which the phase correlation is performed. The projection stage and the FFT calculations are accelerated using the Neon SIMD engine that is facilitated in the ARM CPU. With this acceleration, the global motion vector for each image frame can be calculated in<20 ms on the Samsung Galaxy S smartphone running at 1.0GHz.

UR - http://www.scopus.com/inward/record.url?scp=84866854574&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866854574&partnerID=8YFLogxK

U2 - 10.1049/el.2012.0784

DO - 10.1049/el.2012.0784

M3 - Article

AN - SCOPUS:84866854574

VL - 48

SP - 922

EP - 924

JO - Electronics Letters

JF - Electronics Letters

SN - 0013-5194

IS - 15

ER -