Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection

TLDR

Automatic crack detection in pavement images benefits from considering both photometric and geometric characteristics. This paper proposes a new algorithm for automatic crack detection from 2D pavement images. The algorithm localizes minimal paths—sequences of neighboring pixels weighted by intensity—selects a set of such paths, applies two post‑processing steps, and is validated on synthetic and real images from five acquisition systems against five existing methods. It achieves robust, precise, fully unsupervised results that surpass the current state of the art across diverse scenarios.

Abstract

This paper proposes a new algorithm for automatic crack detection from 2D pavement images. It strongly relies on the localization of minimal paths within each image, a path being a series of neighboring pixels and its score being the sum of their intensities. The originality of the approach stems from the proposed way to select a set of minimal paths and the two postprocessing steps introduced to improve the quality of the detection. Such an approach is a natural way to take account of both the photometric and geometric characteristics of pavement images. An intensive validation is performed on both synthetic and real images (from five different acquisition systems), with comparisons to five existing methods. The proposed algorithm provides very robust and precise results in a wide range of situations, in a fully unsupervised manner, which is beyond the current state of the art.