Infrastructure Crack Segmentation: Boundary Guidance Method and Benchmark Dataset

TL;DR

This paper introduces a boundary guidance method for high-precision steel crack segmentation and provides a new benchmark dataset, addressing the lack of standardized datasets for steel infrastructure crack detection.

Contribution

It proposes a novel boundary guidance crack segmentation model (BGCrack) and establishes a standardized steel crack dataset for benchmarking.

Findings

Boundary information improves segmentation accuracy.

The BGCrack model outperforms existing methods.

The steel crack dataset enables fair comparison of algorithms.

Abstract

Cracks provide an essential indicator of infrastructure performance degradation, and achieving high-precision pixel-level crack segmentation is an issue of concern. Unlike the common research paradigms that adopt novel artificial intelligence (AI) methods directly, this paper examines the inherent characteristics of cracks so as to introduce boundary features into crack identification and then builds a boundary guidance crack segmentation model (BGCrack) with targeted structures and modules, including a high frequency module, global information modeling module, joint optimization module, etc. Extensive experimental results verify the feasibility of the proposed designs and the effectiveness of the edge information in improving segmentation results. In addition, considering that notable open-source datasets mainly consist of asphalt pavement cracks because of ease of access, there is no standard and widely recognized dataset yet for steel structures, one of the primary structural forms in civil infrastructure. This paper provides a steel crack dataset that establishes a unified and fair benchmark for the identification of steel cracks.