Airport pavement inspection through multi-static GPR surveys using deep neural networks

Lilong Zou (Contributor), Ying Li (Contributor), Kevin Munisami (Contributor), Amir M. Alani (Contributor), Motoyuki Sato (Contributor)

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Downloads (Pure)

Abstract

A novel method for airport pavement inspection was proposed, combining multi-static Ground Penetrating Radar (GPR) data with deep learning techniques. The study utilized the Markov Transition Field (MTF) to transform GPR time-series data into two-dimensional images suitable for analysis by Convolutional Neural Networks (CNNs). This framework enabled the automatic detection and classification of interlayer debonding in pavements. Experimental validation was conducted using real-world data from Haneda International Airport, demonstrating the capability of the proposed method to accurately identify debonding regions. The results highlighted the framework's efficiency and reliability in monitoring airport pavements, making it a promising tool for infrastructure maintenance and management.
Original languageEnglish
Title of host publication2025 13th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)
Place of PublicationPiscataway, U.S.
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Number of pages6
ISBN (Electronic)9798331523350
ISBN (Print)9798331523367
DOIs
Publication statusPublished - 14 Aug 2025
Event13th International Workshop on Advanced Ground Penetrating Radar (IWAGPR2025) - Thessaloniki, Greece
Duration: 2 Jul 20254 Jul 2025

Publication series

NameInternational Workshop on Advanced Ground Penetrating Radar (IWAGPR)
PublisherInstitute of Electrical and Electronics Engineers, Inc.
ISSN (Print)2687-7880
ISSN (Electronic)2687-7899

Conference

Conference13th International Workshop on Advanced Ground Penetrating Radar (IWAGPR2025)
Period2/07/254/07/25

Keywords

  • Civil engineering

Fingerprint

Dive into the research topics of 'Airport pavement inspection through multi-static GPR surveys using deep neural networks'. Together they form a unique fingerprint.

Cite this