|
二维码（扫一下试试看！） |
| Study on an Efficient Detection Method Based on Lightweight YOLOv8 with Reparameterized Attention |
| Received:February 02, 2026 Revised:February 22, 2026 |
| DOI：10.11980/j.issn.0254-508X.2026.06.025 |
| Key Words:paper defect detection online quality control YOLOv8 model re-parameterized convolution lightweight neural network |
| Fund Project:中国索引学会人工智能研究项目基金（CSI25C01）；中国成人教育协会人工智能一般项目（AI-Y2025028S）；中国机械工业教育协会（ZJJX25SY001）；全国高等学校计算机教育研究会（CERACU2026RO7）。 |
| Author Name | Affiliation | Postcode | | HUANG Qibao* | 1School of Digital Technology Application Industry, Shangrao Normal College, Shangrao, Jiangxi Province, 340001 | 340001 | | ZHOU Zaifeng* | 2China National Pulp and Paper Research Institute Co., Ltd., Beijing, 100102 | 100102 | | LI Zhiguo | 3School of Artificial Intelligence, Neijiang Normal University, Neijiang, Sichuan Province, 641100 | 641100 | | HU Zhiyong | 4Tengzhou Huawen Paper Co., Ltd., Tengzhou, Shandong Province, 277518 | 277518 |
|
| Hits: 578 |
| Download times: 43 |
| Abstract:The synergistic optimization of accuracy and real-time performance in online paper defect detection represents a core bottleneck for quality control in high-speed papermaking production lines. Taking YOLOv8n as the baseline model， the study proposed a lightweight framework that integrated re-parameterized convolution with position-sensitive multi-query attention (C2PMQA). Through the collaborative optimization of three core modules： partial depthwise separable convolution (PDSConv)， re-parameterized ConvNeXt-enhanced C2f (RCNXC2f)， and C2PMQA， the proposed framework achieved parameter reduction， multi-scale feature extraction， and global-local feature fusion. Furthermore， a non-maximum suppression (NMS-Free) strategy incorporating a lightweight detection head (LWHead) was adopted to enable end-to-end inference， resulting in a re-parameterized attention lightweight YOLOv8 model. Validation on a dataset comprising four typical defect types (dark spots， holes， wrinkles， and scratches) demonstrated that the proposed model achieved improved feature extraction capability， parameter efficiency， and inference speed. Specifically， it attained a mean average precision (mAP₅₀) of 99.2%， with only 1.35 MB of parameter size and 3.07 GFLOPs of computational volume. On the RTX 4060 GPU， the inference frame rate reached 175 FPS， satisfying the requirements of a 600 m/min high-speed paper machine. |
| View Full Text HTML View/Add Comment Download reader |
|
|
|