| 沈冰星,黄洪琼.基于ESE-YOLO的钢带表面缺陷检测研究[J].电子测量与仪器学报,2025,39(8):126-135 |
| 基于ESE-YOLO的钢带表面缺陷检测研究 |
| Research on surface defect detection of steel strip based on ESE-YOLO |
| |
| DOI： |
| 中文关键词: 缺陷检测 YOLOv8n EIEStem shift-wise convolutio EMBSFPN |
| 英文关键词:defect detection YOLOv8n EIEStem shift-wise convolution EMBSFPN |
| 基金项目: |
|
|
|
|
| 摘要点击次数: 663 |
| 全文下载次数: 755 |
| 中文摘要: |
| 针对传统钢带表面缺陷检测方法特征提取能力不足、检测精度受限以及计算资源消耗大的问题，提出了一种基于YOLOv8的ESE YOLO模型，旨在有效检测钢带表面缺陷。首先，为增强模型对边缘特征的提取能力，引入EIEStem高效前端模块，该模块通过SobelConv分支提取图像的边缘信息，并结合池化分支捕获重要空间信息，从而提升模型对缺陷区域的感知能力。其次，在主干网络部分，将shift-wise convolution与C2f模块融合，构建C2f_SWC模块，通过位移操作扩展模型的视野，增强其对上下文信息的捕捉能力，进一步提高空间特征的提取精度。此外，为优化特征金字塔网络的结构，采用高效多分支与尺度特征金字塔网络（EMBSFPN）模块，根据不同尺度的特征层自适应选择多尺度卷积核，实现对多尺度感知信息的逐步获取，并通过加权融合不同尺度特征的重要性提升检测精度，同时显著降低模型的参数量和计算成本。实验结果表明，与原始YOLOv8n相比，ESE-YOLO在NEU-DET数据集上的平均精度均值（mAP）提高了4.1%，参数量下降26.8%，浮点运算量减少64%；在GC10-DET数据集上，mAP提高了9.9%。ESE-YOLO在显著提升检测精度的同时，大幅降低了计算资源需求，更好满足工业场景中资源受限设备的部署需求。 |
| 英文摘要: |
| To address the limitations of traditional steel strip surface defect detection methods, such as insufficient feature extraction capability, restricted detection accuracy, and high computational resource consumption, this study proposes ESE-YOLO, a model based on YOLOv8, designed to effectively detect surface defects on steel strips. Firstly, to enhance the model’s ability to extract edge features, an EIEStem efficient front-end module is introduced. This module utilizes a SobelConv branch to extract edge information from images, combined with a pooling branch to capture essential spatial information, thereby improving the model’s perception of defect regions. Secondly, within the backbone network, shift-wise convolution is integrated with the C2f module to construct the C2f_SWC module. This integration expands the model’s field of view through shift operations, enhancing its ability to capture contextual information and further improving the accuracy of spatial feature extraction. Additionally, to optimize the structure of the feature pyramid network, the EMBSFPN module is employed. This module adaptively selects multi-scale convolutional kernels based on different feature layers, enabling progressive acquisition of multi-scale perceptual information. By weighted fusion of the importance of features across different scales, the detection accuracy is enhanced while significantly reducing the model’s parameter count and computational cost. Experimental results indicate that, compared to the original YOLOv8n, ESE-YOLO achieves a 4.1% improvement in mAP on the NEU-DET dataset, with a 26.8% reduction in parameters and a 64% decrease in floating-point operations. On the GC10-DET dataset, ESE-YOLO demonstrates a 9.9% improvement in mAP. Thus, ESE-YOLO significantly enhances detection accuracy while drastically reducing computational resource requirements, better meeting the deployment needs of resource-constrained devices in industrial scenarios. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
