TY  - JOUR
AU  - Juanjo Rubio
AU  - Takahiro Kashiwa
AU  - Teera Laiteerapong
AU  - Wenlong Deng
AU  - Kohei Nagai
AU  - Sergio Escalera
AU  - Kotaro Nakayama
AU  - Yutaka Matsuo
AU  - Helmut Prendinger
PY  - 2019//
TI  - Multi-class structural damage segmentation using fully convolutional networks
T2  - COMPUTIND
JO  - Computers in Industry
SP  - 103121
VL  - 112
KW  - Bridge damage detection
KW  - Deep learning
KW  - Semantic segmentation
N2  - 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%.
UR  - https://doi.org/10.1016/j.compind.2019.08.002
UR  - http://dx.doi.org/10.1016/j.compind.2019.08.002
N1  - HuPBA; no proj
ID  - Juanjo Rubio2019
ER  -