A study on using an unsupervised learning technique, called a self-organizing map (SOM) or Kohonen map, for the detection of road cracks from pavement images is described in this paper. The main focus is on highly textured road images that make the crack detection very difficult. Road images are split into smaller rectangular cells, and a representative data set is generated for each cell by analyzing image texture and color properties. Texture and color properties are combined with a Kohonen map to distinguish crack areas from the background. Using this technique, cracks are detected to a precision of 77%. The algorithm also resulted in a recall of 73% despite the background having very strong visual texture. The technique applied here shows a great deal of promise despite the images being captured in an uncontrolled environment devoid of state-of-the-art image-acquisition setups. The results are also benchmarked against an advanced algorithm reported in a recent research paper. The benchmarking shows that the proposed algorithm performs better in terms of reducing the false positives in crack detection.
|Journal||ASCE Journal of Infrastructure Systems|
|Early online date||3 Nov 2014|
|Publication status||Published - Sep 2015|
Mathavan, S., Rahman, M., & Kamal, K. (2015). Use of the Self-Organizing Map for Crack Detection in Highly Textured Pavement Images. ASCE Journal of Infrastructure Systems, 21(3). https://doi.org/10.1061/(ASCE)IS.1943-555X.0000237