Real-Time Steel Surface Defect Detection with Improved Multi-Scale YOLO-v5
Processes · 28.04.2023 · 11 (5) · 1357
DOI: 10.3390/pr11051357 ↗Kurz gefasst
Fachartikel in der Zeitschrift Processes, online erschienen am 28.04.2023. Verfasst von Ling Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 105-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cooperation Innovation Plan of Yingkou for Enterprise and Doctor, Liaoning Science and Technology Joint Fund, Foundation of Liaoning Key Laboratory of Chemical Additive Synthesis and Separation.
Abstract (Originalsprache)
Steel surface defect detection is an important issue when producing high-quality steel materials. Traditional defect detection methods are time-consuming and uneconomical and require manually designed prior information or extra supervisors. Surface defects have different representations and features at different scales, which make it challenging to automatically detect the locations and defect types. This paper proposes a real-time steel surface defect detection technology based on the YOLO-v5 detection network. In order to effectively explore the multi-scale information of the surface defect, a multi-scale explore block is especially developed in the detection network to improve the detection performance. Furthermore, the spatial attention mechanism is also developed to focus more on the defect information. Experimental results show that the proposed network can accurately detect steel surface defects with approximately 72% mAP and satisfies the real-time speed requirement.
Förderung
- Cooperation Innovation Plan of Yingkou for Enterprise and Doctor
- Liaoning Science and Technology Joint Fund
- Foundation of Liaoning Key Laboratory of Chemical Additive Synthesis and Separation
- Program for Excellent Talents of Science and Technology in Yingkou Institute of Technology
- Liaoning Province’s Science and Technology Plan (Major) Project of “Jiebangguashuai”
Zitieren
APA
Wang, L., Liu, X., Ma, J., Su, W., & Li, H. (2023). Real-Time Steel Surface Defect Detection with Improved Multi-Scale YOLO-v5. Processes, 11(5), 1357. https://doi.org/10.3390/pr11051357
Vancouver
Wang L, Liu X, Ma J, Su W, Li H. Real-Time Steel Surface Defect Detection with Improved Multi-Scale YOLO-v5. Processes. 2023;11(5):1357. doi:10.3390/pr11051357
BibTeX
@article{Wang2023,
author = {Wang, Ling and Liu, Xinbo and Ma, Juntao and Su, Wenzhi and Li, Han},
title = {Real-Time Steel Surface Defect Detection with Improved Multi-Scale YOLO-v5},
journal = {Processes},
year = {2023},
volume = {11},
number = {5},
pages = {1357},
doi = {10.3390/pr11051357}
}
EUVIMED