HSED-YOLO:一种轻量化的带钢表面缺陷检测模型  

HSED-YOLO:A Lightweight Model for Detecting Surface Defects in Strip Steel

作　　者：戴林华 黎远松 石睿 何忠良 李雷 DAI Linhua;LI Yuansong;SHI Rui;HE Zhongliang;LI Lei(School of Computer Science and Engineering,Sichuan University of Science&Engineering,Yibin Sichuan 643002,China)

机构地区：[1]四川轻化工大学计算机科学与工程学院,四川宜宾643002

出　　处：《广西师范大学学报(自然科学版)》2025年第2期95-106,共12页Journal of Guangxi Normal University:Natural Science Edition

基　　金：国家自然科学基金(42074218)。

摘　　要：针对当前带钢表面缺陷检测算法计算复杂度高、检测精度较低、容易产生漏检和误检等问题,本文提出一种轻量化的带钢表面缺陷检测模型HSED-YOLO。首先,将原始YOLOv8n主干网络更换为改进后的HGNetV2,减少特征图计算冗余,从而降低模型的参数量。然后,为了进一步降低模型的复杂度,在模型颈部网络结构中引入Slim-Neck结构化设计;同时,在特征融合阶段引入EMA(efficient multi-scale attention module)注意力机制,提高模型的特征提取能力;为了进一步提高模型的检测精度,使用DIoU损失函数设计。最后,在带钢缺陷数据集上进行大量实验,得到改进后模型的参数量和计算量分别为2.1×106和6.1×109,仅为基准模型的70%和75.3%,并且平均精度相比于基准模型提升2个百分点,表明改进模型是有效的。In response to the high computational complexity,low detection accuracy,and the issues of missed detection and false alarms in the current strip steel surface defect detection algorithm,a lightweight strip steel surface defect detection model,HSED-YOLO,is proposed.Initially,the original YOLOv8n backbone network is replaced with the improved HGNetV2,reducing the redundancy in feature map computation and thereby decreasing the number of the model’s parameters.Subsequently,to further reduce the model’s complexity,a Slim-Neck structured design is introduced into the model’s bottleneck network structure.Concurrently,an EMA attention mechanism is introduced during the feature fusion stage to enhance the model’s feature extraction capability.To further improve the model’s detection accuracy,a DIoU loss function is designed.Extensive experiments are conducted on the strip steel defect dataset.The number of improved model’s parameters and computational load are 2.1×106 and 6.1×109 FLOPs,respectively,which are only 70%and 75.3%of those of the baseline model.Moreover,the average accuracy is improved by 2%compared with the baseline model.These results demonstrate the effectiveness of the improved network.

关 键 词：缺陷检测 带钢 YOLOv8 注意力机制 损失函数 图像识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]