# A Convolutional Cost-Sensitive Crack Localization Algorithm for Automated and Reliable RC Bridge Inspection

Source: [A Convolutional Cost-Sensitive Crack Localization Algorithm for Automated and Reliable RC Bridge Inspection](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c425>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:34:37.515Z

Authors: Seyed Omid Sajedi, Xiao Liang

Published: 2019-05-23T15:22:16.000Z

## Abstract

Bridges are an essential part of the transportation infrastructure and need to be monitored periodically. Visual inspections by dedicated teams have been one of the primary tools in structural health monitoring (SHM) of bridge structures. However, such conventional methods have certain shortcomings. Manual inspections may be challenging in harsh environments and are commonly biased in nature. In the last decade, camera-equipped unmanned aerial vehicles (UAVs) have been widely used for visual inspections; however, the task of automatically extracting useful information from raw images is still challenging. In this paper, a deep learning semantic segmentation framework is proposed to automatically localize surface cracks. Due to the high imbalance of crack and background classes in images, different strategies are investigated to improve performance and reliability. The trained models are tested on real-world crack images showing impressive robustness in terms of the metrics defined by the concepts of precision and recall. These techniques can be used in SHM of bridges to extract useful information from the unprocessed images taken from UAVs.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1905.09716>)

[PDF](<https://arxiv.org/pdf/1905.09716.pdf>)
