Please use this identifier to cite or link to this item:
Title: Dual attention deep learning network for automatic steel surface defect segmentation
Authors: Pan, Yue
Zhang, Limao
Keywords: Engineering::Civil engineering
Issue Date: 2022
Source: Pan, Y. & Zhang, L. (2022). Dual attention deep learning network for automatic steel surface defect segmentation. Computer-Aided Civil and Infrastructure Engineering, 37(11), 1468-1487.
Project: 04MNP000279C120
Journal: Computer-Aided Civil and Infrastructure Engineering
Abstract: A dual attention deep learning network is developed to classify three types of steel defects, locate their positions, and depict their shapes on the steel surface in an automatic and accurate manner. The novel pixel-level detection algorithm called DAN-DeepLabv3+ integrates a dual attention module into the DeepLabv3+ framework in pursue of more precise segmentation results. For one thing, the dual parallel attention module helps to explicitly model rich contextual dependencies over local feature representations in the spatial and channel dimensions. For another, the popular DeepLabv3+ in an encoder-decoder architecture is useful in capturing multi-scale contextual information and sharp object boundaries. The DAN-DeepLabv3+ is applied to an available dataset containing 6666 images, where three types of steel defects are taken by high-frequency cameras and have been annotated manually. Experimental results show that, compared with other deep learning models, DAN-DeepLabv3+ based on the Xception backbone exhibits the best segmentation performance under the mean intersection over union (IoU) of 89.95% and the frequency-weighted IoU of 97.34%. Besides, the F1-score for the three kinds of defects can reach 86.90%, 99.20%, and 92.81%. From the comparative study, it has been found that the adoption of the dual attention module and DeepLabv3+ contributes to boosting the segmentation performance. The significance of the proposed hybrid model lies in the enhancement in accurately detecting single or multiple steel defects, which has proven to outperform other classical methods.
ISSN: 1093-9687
DOI: 10.1111/mice.12792
Rights: © 2021 Computer-Aided Civil and Infrastructure Engineering. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:CEE Journal Articles

Citations 50

Updated on Nov 25, 2022

Web of ScienceTM
Citations 20

Updated on Nov 19, 2022

Page view(s)

Updated on Nov 26, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.