| アイテムタイプ |
学術雑誌論文 / Journal Article(1) |
| 公開日 |
2024-09-06 |
| タイトル |
|
|
タイトル |
Region-based fully convolutional networks with deformable convolution and attention fusion for steel surface defect detection in industrial Internet of Things |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
artificial intelligence |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
computer vision |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
image segmentation |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
object detection |
| 資源タイプ |
|
|
資源タイプ |
journal article |
| アクセス権 |
|
|
アクセス権 |
open access |
| 著者 |
Fu, Meixia
Wu, Jiansheng
Wang, Qu
Sun, Lei
Ma, Zhangchao
Zhang, Chaoyi
Guan, Wanqing
Li, Wei
Chen, Na
Wang, Danshi
Wang, Jianquan
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Next-generation 6G networks will fully drive the development of the industrial Internet of Things. Steel surface defect detection as an important application in industrial Internet of Things has recently received increasing attention from the military industry, the aviation industry and other fields, which is closely related to the quality of industrial production products. However, many typical convolutional neural networks-based methods are insensitive to the problem of unclear boundaries. In this article, the authors develop a region-based fully convolutional networks with deformable convolution and attention fusion to adaptively learn salient features for steel surface defect detection. Specifically, deformable convolution is applied into selectively replace the standard convolution in the backbone of the region-based fully convolutional networks, which performs significantly in scenarios with unclear defect boundaries. Moreover, convolutional block attention module is utilised in region proposal network to further enhance detection accuracy. The proposed architecture is demonstrated on two popular steel defect detection benchmarks, including NEU-DET and GC10-DET, which can effectively present the performance of steel surface defect detection by abundant experiments. The mean average precision on two datasets reaches 80.9% and 66.2%. The average precision of defect crazing, inclusion, patches, pitted-surface, rolled-in scale and scratches on NEU-DET is 58.2%, 82.3%, 95.7%, 85.6%, 75.9%, and 87.9% respectively. |
| 書誌情報 |
en : IET Signal Processing
巻 17,
号 5,
発行日 2023-05-02
|
| 出版者 |
|
|
出版者 |
Wiley |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
1751-9683 |
| 出版者版DOI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1049/sil2.12208 |
| 出版者版URI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://ietresearch.onlinelibrary.wiley.com/doi/full/10.1049/sil2.12208 |
| 権利 |
|
|
権利情報Resource |
http://creativecommons.org/licenses/by/4.0/ |
|
権利情報 |
$00A9 2023 The Authors. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work isproperly cited. |
| 著者版フラグ |
|
|
出版タイプ |
NA |
