Automatic Crack Detection by Multi-Seeding Fusion on 1mm Resolution 3D Pavement Images

2D image-based crack detection has been studied for many years. But researchers are still short of a robust method, which can generate satisfied results on general cases. 3D pavement images have obvious advantages over 2D images in dealing with disturbances caused by lane markings, sun-light shadows, oil marks and debris. Taking advantage of the state-of-the-art 3D image acquisition technology, this paper proposes a novel crack detection algorithm. It has four steps: 1) First, generate two partly overlapped images with 8×8 pixel grid cells; 2) Second, extract 10 images of crack seeds through symmetry check and grayscale verification; 3) Third, connect scattered seeds by an optimal path searching process considering grayscale values, cell direction and proximity; and 4) Finally, combine and de-noise 10 detection results from two grid cell images to obtain final results. Experiments based on 166 test images show that the proposed method can achieve better performance measured by F-measure, which takes both precision and recall rates into consideration.

Language

  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; References;
  • Pagination: pp 543-552
  • Monograph Title: T&DI Congress 2014: Planes, Trains, and Automobiles

Subject/Index Terms

Filing Info

  • Accession Number: 01528817
  • Record Type: Publication
  • ISBN: 9780784413586
  • Files: TRIS, ASCE
  • Created Date: Jun 26 2014 9:19AM