A novel pavement transverse cracks detection model using WT-CNN and STFT-CNN for smartphone data analysis

Cheng Chen, Hyungjoon Seo*, Yang Zhao

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

34 Citations (Scopus)

Abstract

This paper proposes a novel pavement transverse crack detection model based on time–frequency analysis and convolutional neural networks. The accelerometer and smartphone installed in the vehicle collect the vibration response between the wheel and the road, such as pavement transverse cracks, manholes, and normal pavement. Since the original vibration signal can only contain a one-dimensional domain (time–acceleration). Time–frequency analysis, including Short-Time Fourier Transform and Wavelet Transform, can transfer the one-dimensional vibration signal into a two-dimensional time–frequency-energy spectrum matrix. The energy spectrum matrix obtained from STFT and WT can effectively obtain different signal features in terms of time and frequency features. If STFT and WT are further combined with CNN models, STFT-CNN and WT-CNN, respectively, pavement transverse cracks can be detected more accurately. In this study, the reliability of the developed pavement transverse cracks detection model was evaluated based on the data collected by conducting a road driving test. Analysis results of the developed model show that the accuracies of WT-CNN and STFT-CNN are 97.2% and 91.4%, respectively. The F1 scores to analyse the practicability and the adaptability of the crack detection model of WT-CNN and STFT-CNN are 96.35% and 89.56%, respectively.

Original languageEnglish
Pages (from-to)4372-4384
Number of pages13
JournalInternational Journal of Pavement Engineering
Volume23
Issue number12
DOIs
Publication statusPublished - 2022

Keywords

  • Novel pavement transverse cracks detection model
  • STFT
  • WT
  • deep convolutional neural network
  • vibration signal

Fingerprint

Dive into the research topics of 'A novel pavement transverse cracks detection model using WT-CNN and STFT-CNN for smartphone data analysis'. Together they form a unique fingerprint.

Cite this