Automatic Pavement Crack Detection by Multi-Scale Image Fusion

Pavement crack detection from images is a challenging problem due to intensity inhomogeneity, topology complexity, low contrast, and noisy texture background. Traditional learning-based approaches have difficulties in obtaining representative training samples. The authors propose a new unsupervised multi-scale fusion crack detection (MFCD) algorithm that does not require training data. First, they develop a windowed minimal intensity path-based method to extract the candidate cracks in the image at each scale. Second, they find the crack correspondences across different scales. Finally, they develop a crack evaluation model based on a multivariate statistical hypothesis test. Their approach successfully combines strengths from both the large-scale detection (robust but poor in localization) and the small-scale detection (detail-preserving but sensitive to clutter). The authors analyze and experimentally test the computational complexity of their MFCD algorithm. They have implemented the algorithm and have it extensively tested on three public data sets, including two public pavement data sets and an airport runway data set. Compared with six existing methods, experimental results show that their method outperforms all counterparts. Specifically, it increases the precision, recall, and F1-measure over the state-of-the-art by 22%, 12%, and 19%, respectively, on one public data set.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01709803
  • Record Type: Publication
  • Files: TLIB, TRIS
  • Created Date: Jun 13 2019 2:53PM