Pavement Distress Detection Based on Nonsubsampled Contourlet Transform

Abstract

Automatic recognition of road distresses has been a hot topic since it reduces economic loses before cracks and potholes become too severe. However, weak information of road distress and computing complexity make it difficult to detect road distress effectively. In this paper, we describe pavement distress detection based on nonsubsampled contourlet transform (NSCT). The NSCT is based on a nonsubsampled pyramid structure and nonsubsampled directional filter banks. The coefficients in different scales and different directions are obtained by image decomposition using the nonsubsampled contourlet transform. After the enhancement of weak information and repress noise through adjustment the coefficients in NSCT subbands with proposed algorithm in this paper then reconstruction of these coefficients, pavement distress detection is implemented. Compared with other algorithms, this approach can get better effect especial for weak information. Experimental results proved that the proposed detection was an effective method for the pavement distress image in the practical application, which could inspect the weak object accurately.