| 杨本臣,潘子睿,王春艳,金海波,李世熙.融合共享参数的YOLOv10n钢材表面缺陷检测算法[J].电子测量与仪器学报,2025,39(8):168-177 |
| 融合共享参数的YOLOv10n钢材表面缺陷检测算法 |
| Fusion of YOLOv10n steel surface defect detectionalgorithm with shared parameters |
| |
| DOI： |
| 中文关键词: 钢材缺陷检测 YOLOv10n 轻量级检测头 PConv-C2f FasterNet 注意力机制 |
| 英文关键词:steel defect detection YOLOv10n lightweight detection head PConv-C2f FasterNet attention mechanism |
| 基金项目:国家自然科学基金（62173171）、国家自然科学基金（41801368）、辽宁省教育厅基本科研项目（LJKQZ2021154）资助 |
|
|
| Author | Institution |
| Yang Benchen | School of Software, Liaoning Technical University, Huludao 125105, China |
| Pan Zirui | School of Software, Liaoning Technical University, Huludao 125105, China |
| Wang Chunyan | School of Software, Liaoning Technical University, Huludao 125105, China |
| Jin Haibo | School of Software, Liaoning Technical University, Huludao 125105, China |
| Li Shixi | School of Software, Liaoning Technical University, Huludao 125105, China |
|
| 摘要点击次数: 681 |
| 全文下载次数: 617 |
| 中文摘要: |
| 针对钢材表面缺陷检测中的精度低、易受背景干扰的问题，提出一种融合共享参数的YOLOv10n目标检测算法。首先，骨干网络引入改进的FasterNet轻量网络和通道优先卷积注意力机制，以提升骨干网络对多维信息的表征能力；其次，针对C2f模块感受野差的问题，基于部分卷积（PConv）设计了PConv-C2f模块；再次，采用小波池化，解决原算法中因上下采样机制引起的图像高频信息混叠和易受背景干扰问题；最后，通过共享参数与动态分布技术融合，提出一种轻量级检测头，以减少模型的计算复杂度并提高边界框预测的准确性。改进算法在NEU-DET数据集上的平均精度均值（mAP）mAP@0.5达到86.3%，较原算法提升8.1%，精确率（precision）达到86.8%，较原算法提高了18.7%。通过消融、对比实验表明改进算法在钢材和金属材料表面缺陷检测中均具有较好的性能表现，不仅满足了实际应用中对钢材表面缺陷进行高效、准确检测的需求，还显著提升了检测的可靠性和实用性。 |
| 英文摘要: |
| With an aim to address the issues of low precision and susceptibility to background interference in steel surface defect detection, a YOLOv10n target detection algorithm based on fusion and shared parameters is proposed. Firstly, the backbone network incorporates the enhanced FasterNet lightweight network and the channel-first convolutional attention mechanism to enhance the capacity of the backbone network in representing multidimensional information. Secondly, the PCONV-C2F module is designed based on partial convolution (PConv) to tackle the problem of the disparity in the sensitivity field of the C2f module. Thirdly, wavelet pooling is utilized to address the problem of aliasing and background interference resulting from the up and down sampling mechanism in the original algorithm. Finally, a lightweight detection head is put forward to reduce the computational complexity of the model and enhance the accuracy of bounding box prediction by integrating shared parameters with dynamic distribution techniques. The mean average precision (mAP) mAP@0.5 of the improved algorithm on the NEU-DET dataset attains 86.3%, which is 8.1% higher than that of the original algorithm, and the precision reaches 86.8%, which is 18.7% higher than that of the original algorithm. The ablation and comparison experiments demonstrate that the improved algorithm exhibits excellent performance in the surface defect detection of steel and metal materials, which not only meets the requirement for efficient and accurate detection of steel surface defects in practical applications, but also significantly enhances the reliability and practicability of the detection. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
