Fractals and Independent Component Analysis for Defect Detection in Bridge Decks

Fractals and Independent Component Analysis for Defect Detection in Bridge Decks

We present in this paper a framework for the automatic detection and localization of defects inside bridge decks. Using Ground-Penetrating Radar (GPR) raw scans, this framework is composed of a feature extraction algorithm using fractals to detect defective regions and a deconvolution algorithm usin...

Full description

Bibliographic Details
Main Authors: Ikhlas Abdel-Qader, Fadi Abu-Amara, Osama Abudayyeh
Format: Article
Language:English
Published: Hindawi Limited 2011-01-01
Series:Advances in Civil Engineering
Online Access:http://dx.doi.org/10.1155/2011/506464
id doaj-a4160de64cb848878b362669a67b5334
record_format Article
spelling doaj-a4160de64cb848878b362669a67b53342020-11-24T22:35:00ZengHindawi LimitedAdvances in Civil Engineering1687-80861687-80942011-01-01201110.1155/2011/506464506464Fractals and Independent Component Analysis for Defect Detection in Bridge DecksIkhlas Abdel-Qader0Fadi Abu-Amara1Osama Abudayyeh2Department of Electrical and Computer Engineering, Western Michigan University, Kalamazoo, MI 49008, USADepartment of Computer Engineering, Al-Hussein Bin Talal University, Ma'an 71111, JordanDepartment of Civil and Construction Engineering, Western Michigan University, Kalamazoo, MI 49008, USAWe present in this paper a framework for the automatic detection and localization of defects inside bridge decks. Using Ground-Penetrating Radar (GPR) raw scans, this framework is composed of a feature extraction algorithm using fractals to detect defective regions and a deconvolution algorithm using banded-independent component analysis (ICA) to reduce overlapping between reflections and to estimate the radar waves travel time and depth of defects. Results indicate that the defects' estimated horizontal location and depth falling within 2 cm (76.92% accuracy) and 1 cm (84.62% accuracy) from their actual values.http://dx.doi.org/10.1155/2011/506464
collection DOAJ
language English
format Article
sources DOAJ
author Ikhlas Abdel-Qader
Fadi Abu-Amara
Osama Abudayyeh
spellingShingle Ikhlas Abdel-Qader
Fadi Abu-Amara
Osama Abudayyeh
Fractals and Independent Component Analysis for Defect Detection in Bridge Decks
Advances in Civil Engineering
author_facet Ikhlas Abdel-Qader
Fadi Abu-Amara
Osama Abudayyeh
author_sort Ikhlas Abdel-Qader
title Fractals and Independent Component Analysis for Defect Detection in Bridge Decks
title_short Fractals and Independent Component Analysis for Defect Detection in Bridge Decks
title_full Fractals and Independent Component Analysis for Defect Detection in Bridge Decks
title_fullStr Fractals and Independent Component Analysis for Defect Detection in Bridge Decks
title_full_unstemmed Fractals and Independent Component Analysis for Defect Detection in Bridge Decks
title_sort fractals and independent component analysis for defect detection in bridge decks
publisher Hindawi Limited
series Advances in Civil Engineering
issn 1687-8086
1687-8094
publishDate 2011-01-01
description We present in this paper a framework for the automatic detection and localization of defects inside bridge decks. Using Ground-Penetrating Radar (GPR) raw scans, this framework is composed of a feature extraction algorithm using fractals to detect defective regions and a deconvolution algorithm using banded-independent component analysis (ICA) to reduce overlapping between reflections and to estimate the radar waves travel time and depth of defects. Results indicate that the defects' estimated horizontal location and depth falling within 2 cm (76.92% accuracy) and 1 cm (84.62% accuracy) from their actual values.
url http://dx.doi.org/10.1155/2011/506464
work_keys_str_mv AT ikhlasabdelqader fractalsandindependentcomponentanalysisfordefectdetectioninbridgedecks
AT fadiabuamara fractalsandindependentcomponentanalysisfordefectdetectioninbridgedecks
AT osamaabudayyeh fractalsandindependentcomponentanalysisfordefectdetectioninbridgedecks
_version_ 1725725177522683904

Similar Items