Beamlet Transform Based Pavement Image Crack Detection

Abstract

The complex nature of road images and weak signal make the detection of pavement cracks particularly difficult. An algorithm for pavement cracks detection based on Beamlet Transform is proposed. Beamlet transform is a new tool for high dimensional singularity analysis. First, the pavement surface image was segmented into unit image and transformed to binary image. Then beamlet transform was performed. Experimental results show the proposed method is effective in detecting line features with any orientation, location and length in pavement images. Compared with traditional edge detectors, the proposed method has the ability of anti-noise and linear connection.