Academic Journals Database
Disseminating quality controlled scientific knowledge

Automatic Pavement Crack Detection Using Texture and Shape Descriptors

ADD TO MY LIST
 
Author(s): HU Yong | ZHAO Chun-xia | WANG Hong-nan

Journal: IETE Technical Review
ISSN 0256-4602

Volume: 27;
Issue: 5;
Start page: 398;
Date: 2010;
Original page

Keywords: Canny detector | Gray-Level co-occurrence matrix | Pavement crack detection | Shape descriptors | Support vector machine | Texture analysis

ABSTRACT
Pavement distress detection and analysis is the most important part of automated pavement -inspection -systems. Due to the circumstances such as complex texture, uneven illumination, and nonuniform -background, pavement distress detection is not a simply edge detection process. Over the past 30 years, lots of methods were proposed to detect pavement distresses, especially cracks. In this letter, a novel automatic pavement crack detection approach based on texture analysis and shape descriptors is proposed. Pavement surface is seen as a texture surface, and distresses are defined as inhomogeneities occurring in the texture surface. Six texture features and two translation-invariant shape descriptors were used here as discriminate features against irregular texture and uneven illumination. By using a SVM classifier, all sub-images are classified as crack or non-crack. Final results were obtained after post-processing, which includes segmentation, fake-crack eliminating, and crack-measuring methods. Compared with a traditional edge detector such as a Canny operator, experimental results demonstrated that all cracks are correctly detected by the proposed method, even in a strong texture background or in the surface with uneven illumination.
Why do you need a reservation system?      Affiliate Program