Automatic Pavement Crack Detection and Classification Using Multiscale Feature Attention Network

Pavement crack detection and characterization is a fundamental part of road intelligent maintenance systems. Due to the high non-uniformity of cracks, topological complexity, and similar noise from crack texture, the challenge arises in this domain with automated crack detection and classi?cation in a complex environment. In this work, an overarching framework for a universal and robust automatic method that simultaneously characterizes the type of crack and its severity level was developed. For crack detection, we propose a novel and ef?cient crack detection network that captures the crack context information by establishing a multi scale dilated convolution module. On this foundation, an attention mechanism is introduced to further re?ne the high-level features. Moreover, the rich features at different levels are fused in an up sampling module to generate more detailed crack detection results. For crack classi?cation, a novel characterization algorithm is developed to classify the type of crack after detection. The crack segment branches are then merged and classi?ed into four types: transversal, longitudinal, block, and alligator; the severity levels of cracks are assessed by calculating the average width and distance between the crack branches.

KEYWORDS: Pavement crack detection, crack classi?cation, convolutional neural network.