Wavelet-Based Pavement Distress Classification

Abstract

A two-step method–-wavelet transform followed by Radon transform–- is proposed for pavement distress classification. First, a pavement image is decomposed into different frequency subbands by wavelet transform. Distress is transformed into the high-amplitude wavelet coefficients, which are referred to as the details, in the high-frequency subbands. The wavelet modulus is calculated by combining the horizontal, vertical, and diagonal details. Since distress, especially crack, has dominant orientations in both the space domain and the wavelet domain, Radon transform is then applied to the wavelet modulus to transform cracks into peaks in the Radon domain. The patterns and parameters of the peaks are finally used for distress classification. Both simulated and experimental results demonstrate that the proposed two-step method is an effective method for pavement distress classification.