Aug 2026· Engineering Research Express· Vol 8· 0 citations· 33 references
Physics
TL;DR
The proposed SDM-YOLO framework enhances feature representation by replacing the original C2PSA module with C2PSA_SEAM in the backbone, introduces DySample-based dynamic upsampling in the neck for content-aware multi-scale feature alignment, and incorporates a multi-scale convolutional attention mechanism before the detection head to improve sensitivity to subtle, low-contrast, and morphologically varied defects.
Abstract
Surface defects generated during steel manufacturing significantly affect product quality, structural reliability, and operational safety, creating a strong demand for accurate and real-time inspection systems in industrial environments. However, existing detection approaches often struggle with subtle defect textures, complex surface backgrounds, weak visual contrast, and the trade-off between detection accuracy and computational efficiency. To address these challenges, this paper proposes SDM-YOLO, a lightweight framework for steel surface defect detection based on YOLO11n. Rather than introducing an entirely new detection architecture, the main contribution of this work lies in the coordinated integration and task-specific adaptation of complementary modules within a unified lightweight detection framework. Specifically, the proposed method enhances feature representation by replacing the original C2PSA module with C2PSA_SEAM in the backbone, introduces DySample-based dynamic upsampling in the neck for content-aware multi-scale feature alignment, and incorporates a multi-scale convolutional attention mechanism before the detection head to improve sensitivity to subtle, low-contrast, and morphologically varied defects. In addition, a normalized Wasserstein distance loss is employed to improve localization stability for small and overlapping defects without increasing inference-time parameters or computational cost. Extensive experiments on the NEU-DET and GC10-DET datasets demonstrate that SDM-YOLO achieves mAP50 scores of 81.0% and 72.3%, respectively, while attaining mAP50:95 values of 46.7% and 38.0%. The proposed framework maintains real-time performance with only 2.68 M parameters, 6.6 GFLOPs, and an inference speed of 94.5 FPS. These results demonstrate that SDM-YOLO achieves an effective balance between detection accuracy, localization precision, and computational efficiency, making it suitable for practical steel surface defect inspection applications.
The YOLOv5s-CBAM model introduces the Convolutional Block Attention Module (CBAM), effectively suppressing background noise and significantly enhancing the feature response of weak defects, and the improved lightweight model uses the Ghost module to reconstruct the backbone.
Bing-Zhang Li, Wei-Sen Song, Yu-Zhong Kang et al.· International Conference on...· 0 citations
Steel surface defect detection is a critical component of intelligent manufacturing and industrial visual quality control. However, due to large variations in defect scale, elongated morphologies, strong directional continuity, and high inter-class visual similarity, existing detection methods struggle to achieve a des...
Steel surface defect detection is essential for ensuring product quality. Industrial defect detection is challenged by redundant spatial computation, loss of deep feature information, and limited local receptive fields. To address these limitations, we propose PDGA-YOLO, a steel surface defect detection network based o...
Guan-Lin Wu, Xu-Ming Lu, Wei-Hao Wu et al.· 2026 2nd International Confe...· 0 citations
Industrial surface defect detection is simultaneously constrained by weak-contrast small targets, strong textural backgrounds, and directional structures. Although existing real-time YOLO methods offer high speed, neck enhancements often lack scale-specific functional partitioning, edge information is easily entangled...
Tian-Ping Luo· 2026 7th International Confe...· 0 citations
A lightweight detection method integrating adaptive image enhancement, generative sample synthesis, and an optimized detection model is proposed, which delivers a highly efficient and robust solution for attaining real-time industrial quality control.
Lu-Ya Yang, Min Zhang, Ya-Xian Gao· PLoS ONE· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.