Novel Approach to Pavement Cracking Detection Based on Fuzzy Set Theory

Abstract

Conventional visual and manual pavement cracking analysis approaches are very costly, time-consuming, dangerous, labor-intensive, and subjective. They possess various drawbacks such as having a high degree of variability, being unable to provide meaningful quantitative information, and almost always leading to inconsistencies in cracking details over space and across evaluations. In this paper, a novel pavement cracking detection algorithm based on fuzzy logic is proposed. The main idea of the proposed method is based on the fact that the crack pixels in pavement images are “darker than their surroundings and continuous.” First, the proposed method determines how much darker the pixels are than the surroundings by deciding the brightness membership function for gray levels in the difference image. Second, we map the fuzzified image into the crack domain by finding the crack membership values of the pixels. Third, we check the connectivity of the darker pixels to eliminate the pixels lacking in connectivity. Finally, an image projection algorithm is employed to classify cracks. The experimental results have demonstrated that the cracks are correctly and effectively detected by the proposed method. The main advantages of the proposed method are: (1) it can correctly discover thin cracks, even from very noisy pavement images; (2) the necessary parameters can be determined automatically; (3) the efficiency and accuracy of the proposed algorithm are superior; and (4) its application-dependent nature can simplify the design of the entire system.