融合Res2Net和部分卷积的带钢表面缺陷检测算法  

Strip Surface Defect Detection Algorithm Integrating Res2Net and PConv

作　　者：胡凯涛 马向华 孙向宇 刘闯 HU Kaitao;MAXianghua;SUN Xiangyu;LIU Chuang(School of Electrical and Electronic Engineering,Shanghai Institute of Technology,Shanghai 201418,China;Electronic Assembly Technology Center,Shanghai Institute of Aerospace Control Technology,Shanghai 201109,China)

机构地区：[1]上海应用技术大学电气与电子工程学院,上海201418 [2]上海航天控制技术研究所电子装联技术中心,上海201109

出　　处：《计算机工程与应用》2025年第5期334-343,共10页Computer Engineering and Applications

基　　金：上海应用技术大学协同创新基金(XTCX2022-22)。

摘　　要：为提升带钢表面缺陷的层次性特征提取能力和检测效率,提出基于多尺度表征和部分卷积(PConv)的快速检测网络(multi-scale and partially convolutional network,MSPC-Net)。将限制对比度自适应直方图均衡技术(contrast limited adaptive histogram equalization,CLAHE)引入到该模型以突出带钢表面的缺陷特征;在YOLOv5s的基础上新增检测层,提高对不同尺寸缺陷目标的检测率;设计了融合Res2Net的多尺度特征提取块并引入ECA注意力机制(BRE-block),既可以获取细粒度层面的特征,同时也增加了模型感受野;通过结合PConv减少了模型计算量(FLOPs),且增强了部分特征信息的聚合。在NEU-DET数据集上的实验结果表明,平均精度均值(mAP@IoU=0.5)达到了80.2%,较原基线网络提高了5.9个百分点;同时改进后网络的FPS达到157,远高于近期应用广泛的目标检测算法,有效提高了带钢表面缺陷的检测效率。In order to improve the hierarchical feature extraction capability and detection efficiency of strip surface defects,a rapid detection network(MSPC-Net)based on multi-scale representation and partial convolution(PConv)is proposed.Contrast limited adaptive histogram equalization(CLAHE)technology is introduced into the model to highlight the defect characteristics of the strip surface;a new detection layer is added based on YOLOv5s to improve the detection rate of defect targets of different sizes.A multi-scale feature extraction block that integrates Res2Net is designed,and the ECA attention mechanism(BRE-block)is introduced.This block can not only obtain fine-grained features but also increase the model receptive field.By combining with PConv(FLOPs),the amount of model calculation is reduced,and the aggregation of partial feature information is enhanced.Experimental results on the NEU-DET data set show that the average accuracy(mAP@IoU=0.5)reaches 80.2%,which is 5.9 percentage points higher than the original baseline network.At the same time,the FPS of the improved network reaches 157,which is much higher than that of the recently widely used target detection algorithm,effectively improving the detection efficiency of strip surface defects.

关 键 词：对比度增强 多尺度特征提取 改进Res2Net 融合PConv 信息聚合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]