Automatic Pavement Crack Detection using Multi-Scale Image & Neighborhoods Information

Abstract

Pavement cracks are dangerous because they can cause accidents such as tire punctures, slips, and collapses. Therefore, it is necessary to repair them properly. In recent years, various crack detection methods using pavement images have been proposed. However, in many cases, there are problems with accuracy and processing time. In this paper, we propose a new crack detection method using multi-scale image and neighborhood information. Experimental results show that the proposed method is superior to the most advanced crack detection methods in both accuracy and processing time.