Academic Journal
Surface defect detection of hot rolled steel based on multi-scale feature fusion and attention mechanism residual block
| العنوان: | Surface defect detection of hot rolled steel based on multi-scale feature fusion and attention mechanism residual block |
|---|---|
| المؤلفون: | Zhang, Hongkai, Li, Suqiang, Miao, Qiqi, Fang, Ruidi, Xue, Song, Hu, Qianchuan, Hu, Jie, Chan, Sixian |
| المساهمون: | the Key Laboratory for Comprehensive Energy Saving of Cold Regions Architecture of the Ministry of Education of Jilin Jianzhu University, the National Natural Science Foundation of China |
| المصدر: | Scientific Reports ; volume 14, issue 1 ; ISSN 2045-2322 |
| بيانات النشر: | Springer Science and Business Media LLC |
| سنة النشر: | 2024 |
| الوصف: | To improve the precision of defect categorization and localization in images, this paper proposes an approach for detecting surface defects in hot-rolled steel strips. The approach uses an improved YOLOv5 network model to overcome the issues of inadequate feature extraction capacity and suboptimal feature integration when identifying surface defects on steel strips. The proposed method achieves higher detection accuracy and localization precision, making it more competitive and applicable in real production. Firstly, the multi-scale feature fusion (MSF) strategy is utilized to fuse shallow and deep features effectively and enrich detailed information relevant to target defects. Secondly, the CSPLayer Res2Attention block (CRA block) residual module is introduced to reduce the loss of defect information during hierarchical transmission, thereby enhancing the extraction of fine-grained features and improving the perception of details and global features. Finally, the experimental results indicate that the mAP on the NEU-DET and GC10-DET datasets approaches 78.5% and 67.3%, respectively, which is 4.9% and 2.1% higher than that of the baseline. Meanwhile, it has higher precision and more precise localization capabilities than other methods. Furthermore, it also achieves 59.2% mAP on the APDDD dataset, indicating its potential for growth in further domains. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| DOI: | 10.1038/s41598-024-57990-3 |
| الاتاحة: | http://dx.doi.org/10.1038/s41598-024-57990-3 https://www.nature.com/articles/s41598-024-57990-3.pdf https://www.nature.com/articles/s41598-024-57990-3 |
| Rights: | https://creativecommons.org/licenses/by/4.0 ; https://creativecommons.org/licenses/by/4.0 |
| رقم الانضمام: | edsbas.84DED66D |
| قاعدة البيانات: | BASE |
| DOI: | 10.1038/s41598-024-57990-3 |
|---|