DFFNet: a lightweight approach for efficient feature-optimized fusion in steel strip surface defect detection
Complex & Intelligent Systems · 2024-10 · 10 (5) · 6705-6723
DOI: 10.1007/s40747-024-01512-1 ↗Kurz gefasst
Fachartikel in der Zeitschrift Complex & Intelligent Systems, online erschienen am 20.06.2024. Verfasst von Xianming Hu und 1 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Steel surface defect detection is crucial in manufacturing, but achieving high accuracy and real-time performance with limited computing resources is challenging. To address this issue, this paper proposes DFFNet, a lightweight fusion network, for fast and accurate steel surface defect detection. Firstly, a lightweight backbone network called LDD is introduced, utilizing partial convolution to reduce computational complexity and extract spatial features efficiently. Then, PANet is enhanced using the Efficient Feature-Optimized Converged Network and a Feature Enhancement Aggregation Module (FEAM) to improve feature fusion. FEAM combines the Efficient Layer Aggregation Network and reparameterization techniques to extend the receptive field for defect perception, and reduce information loss for small defects. Finally, a WIOU loss function with a dynamic non-monotonic mechanism is designed to improve defect localization in complex scenes. Evaluation results on the NEU-DET dataset demonstrate that the proposed DFFNet achieves competitive accuracy with lower computational complexity, with a detection speed of 101 FPS, meeting real-time performance requirements in industrial settings. Furthermore, experimental results on the PASCAL VOC and MS COCO datasets demonstrate the strong generalization capability of DFFNet for object detection in diverse scenarios.
Zitieren
APA
Hu, X., & Lin, S. (2024). DFFNet: a lightweight approach for efficient feature-optimized fusion in steel strip surface defect detection. Complex & Intelligent Systems, 10(5), 6705-6723. https://doi.org/10.1007/s40747-024-01512-1
Vancouver
Hu X, Lin S. DFFNet: a lightweight approach for efficient feature-optimized fusion in steel strip surface defect detection. Complex & Intelligent Systems. 2024;10(5):6705-6723. doi:10.1007/s40747-024-01512-1
BibTeX
@article{Hu2024,
author = {Hu, Xianming and Lin, Shouying},
title = {DFFNet: a lightweight approach for efficient feature-optimized fusion in steel strip surface defect detection},
journal = {Complex & Intelligent Systems},
year = {2024},
volume = {10},
number = {5},
pages = {6705--6723},
doi = {10.1007/s40747-024-01512-1}
}
EUVIMED