Automatic classification of ground-penetrating-radar signals for railway-ballast assessment

Wenbin Shao; Abdesselam Bouzerdoum; Son Lam Phung; Lijun Su; Buddhima Indraratna; Cholachat Rujikiatkamjorn

doi:10.1109/TGRS.2011.2128328

Automatic classification of ground-penetrating-radar signals for railway-ballast assessment

Wenbin Shao^*, Abdesselam Bouzerdoum, Son Lam Phung, Lijun Su, Buddhima Indraratna, Cholachat Rujikiatkamjorn

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

94 Citations (Scopus)

Abstract

The ground-penetrating radar (GPR) has been widely used in many applications. However, the processing and interpretation of the acquired signals remain challenging tasks since an experienced user is required to manage the entire operation. In this paper, we present an automatic classification system to assess railway-ballast conditions. It is based on the extraction of magnitude spectra at salient frequencies and their classification using support vector machines. The system is evaluated on real-world railway GPR data. The experimental results show that the proposed method efficiently represents the GPR signal using a small number of coefficients and achieves a high classification rate when distinguishing GPR signals reflected by ballasts of different conditions.

Original language	English
Article number	5756666
Pages (from-to)	3961-3972
Number of pages	12
Journal	IEEE Transactions on Geoscience and Remote Sensing
Volume	49
Issue number	10 PART 2
DOIs	https://doi.org/10.1109/TGRS.2011.2128328
Publication status	Published - Oct 2011
Externally published	Yes

Keywords

Ground-penetrating radar (GPR) processing
railway-ballast assessment
support vector machine (SVM)

Access to Document

10.1109/TGRS.2011.2128328

Cite this

@article{81ffe97257d74aa48ab8e1f7373a1b3b,

title = "Automatic classification of ground-penetrating-radar signals for railway-ballast assessment",

abstract = "The ground-penetrating radar (GPR) has been widely used in many applications. However, the processing and interpretation of the acquired signals remain challenging tasks since an experienced user is required to manage the entire operation. In this paper, we present an automatic classification system to assess railway-ballast conditions. It is based on the extraction of magnitude spectra at salient frequencies and their classification using support vector machines. The system is evaluated on real-world railway GPR data. The experimental results show that the proposed method efficiently represents the GPR signal using a small number of coefficients and achieves a high classification rate when distinguishing GPR signals reflected by ballasts of different conditions.",

keywords = "Ground-penetrating radar (GPR) processing, railway-ballast assessment, support vector machine (SVM)",

author = "Wenbin Shao and Abdesselam Bouzerdoum and Phung, {Son Lam} and Lijun Su and Buddhima Indraratna and Cholachat Rujikiatkamjorn",

year = "2011",

month = oct,

doi = "10.1109/TGRS.2011.2128328",

language = "English",

volume = "49",

pages = "3961--3972",

journal = "IEEE Transactions on Geoscience and Remote Sensing",

issn = "0196-2892",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10 PART 2",

}

TY - JOUR

T1 - Automatic classification of ground-penetrating-radar signals for railway-ballast assessment

AU - Shao, Wenbin

AU - Bouzerdoum, Abdesselam

AU - Phung, Son Lam

AU - Su, Lijun

AU - Indraratna, Buddhima

AU - Rujikiatkamjorn, Cholachat

PY - 2011/10

Y1 - 2011/10

N2 - The ground-penetrating radar (GPR) has been widely used in many applications. However, the processing and interpretation of the acquired signals remain challenging tasks since an experienced user is required to manage the entire operation. In this paper, we present an automatic classification system to assess railway-ballast conditions. It is based on the extraction of magnitude spectra at salient frequencies and their classification using support vector machines. The system is evaluated on real-world railway GPR data. The experimental results show that the proposed method efficiently represents the GPR signal using a small number of coefficients and achieves a high classification rate when distinguishing GPR signals reflected by ballasts of different conditions.

AB - The ground-penetrating radar (GPR) has been widely used in many applications. However, the processing and interpretation of the acquired signals remain challenging tasks since an experienced user is required to manage the entire operation. In this paper, we present an automatic classification system to assess railway-ballast conditions. It is based on the extraction of magnitude spectra at salient frequencies and their classification using support vector machines. The system is evaluated on real-world railway GPR data. The experimental results show that the proposed method efficiently represents the GPR signal using a small number of coefficients and achieves a high classification rate when distinguishing GPR signals reflected by ballasts of different conditions.

KW - Ground-penetrating radar (GPR) processing

KW - railway-ballast assessment

KW - support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=80053566490&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2011.2128328

DO - 10.1109/TGRS.2011.2128328

M3 - Article

AN - SCOPUS:80053566490

SN - 0196-2892

VL - 49

SP - 3961

EP - 3972

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

IS - 10 PART 2

M1 - 5756666

ER -

Automatic classification of ground-penetrating-radar signals for railway-ballast assessment

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this