Improving the Performance of the Single Shot Multibox Detector for Steel Surface Defects with Context Fusion and Feature Refinement
Electronics · 27.05.2023 · 12 (11) · 2440
DOI: 10.3390/electronics12112440 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 27.05.2023. Verfasst von Yiming Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hefei University graduate innovation and entrepreneurship program, Natural Science Foundation of China, Talent Foundation of Hefei University.
Abstract (Originalsprache)
Strip surface defects have large intraclass and small interclass differences, resulting in the available detection techniques having either a low accuracy or very poor real-time performance. In order to improve the ability for capturing steel surface defects, the context fusion structure introduces the local information of the shallow layer and the semantic information of the deep layer into multiscale feature maps. In addition, for filtering the semantic conflicts and redundancies arising from context fusion, a feature refinement module is introduced in our method, which further improves the detection accuracy. Our experimental results show that this significantly improved the performance. In particular, our method achieved 79.5% mAP and 71 FPS on the public NEU-DET dataset. This means that our method had a higher detection accuracy compared to other techniques.
Förderung
- Hefei University graduate innovation and entrepreneurship program
- Natural Science Foundation of China
- Talent Foundation of Hefei University
- Visiting and Research Foundation for Outstanding Young Talents of Anhui Province
Zitieren
APA
Li, Y., He, L., Zhang, M., Cheng, Z., Liu, W., & Wu, Z. (2023). Improving the Performance of the Single Shot Multibox Detector for Steel Surface Defects with Context Fusion and Feature Refinement. Electronics, 12(11), 2440. https://doi.org/10.3390/electronics12112440
Vancouver
Li Y, He L, Zhang M, Cheng Z, Liu W, Wu Z. Improving the Performance of the Single Shot Multibox Detector for Steel Surface Defects with Context Fusion and Feature Refinement. Electronics. 2023;12(11):2440. doi:10.3390/electronics12112440
BibTeX
@article{Li2023,
author = {Li, Yiming and He, Lixin and Zhang, Min and Cheng, Zhi and Liu, Wangwei and Wu, Zijun},
title = {Improving the Performance of the Single Shot Multibox Detector for Steel Surface Defects with Context Fusion and Feature Refinement},
journal = {Electronics},
year = {2023},
volume = {12},
number = {11},
pages = {2440},
doi = {10.3390/electronics12112440}
}
EUVIMED