Pavement Cracks Detection Based on FDWT

Abstract

Automatic detection of road cracks has been a hot topic since it reduces economic loses. It is not easy to get efficient detection algorithms because of complexity, diversity of pavement images and pavement distress's weak information. In this paper, a new approach of pavement cracks detection based on FDWT (fractional differential and wavelet transform) is proposed. Fractional differential can effectively enhance high-frequency, medium-frequency signals and non-linearly preserve low-frequency signals. After fractional differential covering module is constructed and applied to road images, pavement crack reinforcement is implemented even if the crack is weak signal in smooth area. Then in order to filter noise, wavelet transform is carried out. This approach can reinforce availably pavement images and get better effect especial for weak crack information in smooth area. Experimental results proved that the proposed detection was a valid method for the different road crack image even if there is any noise exists.