Multi-class structural damage segmentation using fully convolutional networks

doi:10.1016/j.compind.2019.08.002

Multi-class structural damage segmentation using fully convolutional networks

2019-11-01

72

PRE

AI

J

Juan José Álvarez Rubio

DOI：10.1016/j.compind.2019.08.002

Original

Original request for help

Save

Abstract

En 中文

Structural Health Monitoring (SHM) has benefited from computer vision and more recently, Deep Learning approaches, to accurately estimate the state of deterioration of infrastructure. In our work, we test Fully Convolutional Networks (FCNs) with a dataset of deck areas of bridges for damage segmentation. We create a dataset for delamination and rebar exposure that has been collected from inspection records of bridges in Niigata Prefecture, Japan. The dataset consists of 734 images with three labels per image, which makes it the largest dataset of images of bridge deck damage. This data allows us to estimate the performance of our method based on regions of agreement, which emulates the uncertainty of in-field inspections. We demonstrate the practicality of FCNs to perform automated semantic segmentation of surface damages. Our model achieves a mean accuracy of 89.7% for delamination and 78.4% for rebar exposure, and a weighted F1 score of 81.9%. (C) 2019 Published by Elsevier B.V.

Keywords:

Bridge damage detection

Deep learning

Semantic segmentation

Multi-class structural damage segmentation using fully convolutional networks

Abstract

AI Summary

Journal

Organization