| 赵佰亭,张敏,贾晓芬.YOLOv8n-CSG：轻量化钢材表面缺陷检测算法[J].电子测量与仪器学报,2025,39(8):115-125 |
| YOLOv8n-CSG：轻量化钢材表面缺陷检测算法 |
| YOLOv8n-CSG: Lightweight steel surface defect detection algorithm |
| |
| DOI： |
| 中文关键词: 缺陷检测 轻量化YOLOv8n C2f_CG C2f_Star GSE_Detect |
| 英文关键词:defect detection lightweight YOLOv8n C2f_CG C2f_Star GSE_Detect |
| 基金项目:国家自然科学基金面上项目(52174141)、安徽省自然科学基金面上项目(2108085ME158)资助 |
|
|
| Author | Institution |
| Zhao Baiting | 1.State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining，Anhui University of Science and Technology,
Huainan 232001,China;2.China Institute of Electrical and Information Engineering, Anhui University of Science and
Technology, Huainan 232001,China |
| Zhang Min | China Institute of Electrical and Information Engineering, Anhui University of Science and
Technology, Huainan 232001,China |
| Jia Xiaofen | State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining，Anhui University of Science and Technology,
Huainan 232001,China |
|
| 摘要点击次数: 737 |
| 全文下载次数: 678 |
| 中文摘要: |
| 为解决钢材表面缺陷检测中因缺陷类型繁多、尺寸差异显著造成检测精度低,以及现有模型复杂度高等问题,提出了一种改进YOLOv8n的轻量化检测算法YOLOv8n-CSG。首先,引入上下文引导模块(context guided block,CG block)设计C2f_CG模块增强对周围特征的捕捉能力,增强信息关联性;其次,加入星型网络模块(Star Block)设计出C2f_Star模块,将输入数据映射到高维的非线性特征空间,生成丰富的特征表示,使得模型在处理细微缺陷时更加有效；最后,设计了集成分组混洗卷积（grouped and shuffled convolution,GSConv）和高效多尺度注意力机制（efficient multi-Scale attention,EMA）的轻量化检测头GSE_Detect,保持了原检测头的高效的同时降低复杂度。在NEU-DET数据集上进行多组实验,结果表明,改进后的YOLOv8n-CSG网络模型平均精度均值（mAP）mAP@0.5达到了76.8%,相较于YOLOv8n,mAP@0.5提升了6.9%、精度提升了11.3%、计算量降低了37%、参数量降低了35.2%,展现出对钢材表面缺陷更佳的检测能力,且平衡了模型的性能和复杂度。 |
| 英文摘要: |
| In order to solve the problems of low detection accuracy and high complexity of existing models due to the variety of defect types, significant size differences, and high complexity of existing models in the detection of steel surface defects, a lightweight detection algorithm YOLOv8n-CSG with improved YOLOv8n was proposed. Firstly, the design of the CG Block module was introduced C2f_CG which enhanced the ability to capture the surrounding features and enhance the information relevance. Secondly, a C2f_Star module is designed by adding the Star Block module, which maps the input data to the high-dimensional nonlinear feature space and generates rich feature representations, which makes the model more effective in dealing with subtle defects. Finally, a lightweight detector GSE_Detect integrating GSConv and EMA attention mechanisms was designed to maintain the high efficiency of the original detector and reduce the complexity. Multiple sets of experiments on the NEU-DET dataset show that the improved YOLOv8n-CSG network model mAP@0.5 reaches 76.8%, compared with YOLOv8n, mAP@0.5 is improved by 6.9%, the accuracy is increased by 11.3%, the calculation cost is reduced by 37%, and the parameter quantity is reduced by 35.2%, showing a better detection ability for steel surface defects, and balancing the performance and complexity of the model. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
