Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection

Kasthurirangan Gopalakrishnan*, Siddhartha K. Khaitan, Alok Choudhary, Ankit Agrawal

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

187 Scopus citations

Abstract

Automated pavement distress detection and classification has remained one of the high-priority research areas for transportation agencies. In this paper, we employed a Deep Convolutional Neural Network (DCNN) trained on the ‘big data’ ImageNet database, which contains millions of images, and transfer that learning to automatically detect cracks in Hot-Mix Asphalt (HMA) and Portland Cement Concrete (PCC) surfaced pavement images that also include a variety of non-crack anomalies and defects. Apart from the common sources of false positives encountered in vision based automated pavement crack detection, a significantly higher order of complexity was introduced in this study by trying to train a classifier on combined HMA-surfaced and PCC-surfaced images that have different surface characteristics. A single-layer neural network classifier (with ‘adam’ optimizer) trained on ImageNet pre-trained VGG-16 DCNN features yielded the best performance.

Original languageEnglish (US)
Pages (from-to)322-330
Number of pages9
JournalConstruction and Building Materials
Volume157
DOIs
StatePublished - Dec 30 2017

Keywords

  • Convolutional Neural Networks
  • Deep learning
  • Digital Image
  • Pavement cracking
  • Random Forest
  • Transfer learning

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Materials Science(all)

Fingerprint Dive into the research topics of 'Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection'. Together they form a unique fingerprint.

Cite this