DCD-YOLOv8n:一种高效的钢材表面缺陷检测算法  

DCD-YOLOv8n:Efficient Algorithm for Steel Surface Defect Detection

作　　者：梁礼明 陈康泉 钟奕 龙鹏威 冯耀 LIANG Liming;CHEN Kangquan;ZHONG Yi;LONG Pengwei;FENG Yao(School of Electrical Engineering and Automation,Jiangxi University of Science and Technology,Ganzhou,Jiangxi 341000,China)

机构地区：[1]江西理工大学电气工程与自动化学院,江西赣州341000

出　　处：《计算机工程与应用》2025年第7期117-127,共11页Computer Engineering and Applications

基　　金：国家自然科学基金(51365017,61463018);江西省自然科学基金(20192BAB205084);江西省教育厅科学技术研究青年项目(GJJ2200848)。

摘　　要：针对现有钢材表面缺陷检测算法资源消耗较大、检测精度和效率较低等问题,提出一种基于YOLOv8n的高效钢材缺陷检测算法(DCD-YOLOv8n)。该方法一是设计轻量化的多分支特征聚合网络,有效精简模型体积并提升检测速度;二是利用跨维度聚合模块,通过自适应机制建模多维度特征,以提升检测精度;三是采用可变形多头注意力机制,动态调整注意力的形状和范围,有效应对形态多样和结构复杂的缺陷特征,从而提升检测性能。在Severstal和NEU-DET钢材缺陷数据集上进行实验验证,相较于YOLOv8n算法,DCD-YOLOv8n算法的mAP分别提高2.4个百分点和1.9个百分点;参数量和复杂度分别降低0.5×10^(6)和1.9×10^(9);FPS分别提升22帧和7帧。实验结果表明,该算法在平衡计算开销、检测精度和效率方面表现优异,具有一定的实际部署应用价值。To address the issues of high resource consumption,and low detection accuracy and efficiency in existing steel surface defect detection algorithms,a high-efficiency steel defect detection algorithm based on YOLOv8n,named DCDYOLOv8n,is proposed.Firstly,a lightweight diverse branch block efficient layer aggregation network is designed to effectively reduce model size and enhance detection speed.Secondly,a cross-dimensional aggregation module is utilized to model multi-dimensional features via adaptive mechanisms,improving detection accuracy.Finally,a deformable multihead attention mechanism is introduced to dynamically adjust the shape and scope of attention,effectively handling defects with diverse shapes and complex structures,and thus enhancing detection performance.Experimental validation on the Severstal and NEU-DET steel defect datasets shows that,compared to the YOLOv8n algorithm,the DCD-YOLOv8n algorithm achieves improvements in mAP of 2.4%and 1.9%respectively,reduces in parameters and computations of 0.5×10^(6) and 1.9×10^(9) respectively,and increases in FPS of 22 and 7 frames respectively.The experimental results demonstrate that the algorithm excels in balancing computational cost,detection accuracy,and efficiency,offering significant practical deployment value.

关 键 词：缺陷检测 YOLOv8n 多分支特征聚合网络 跨维度聚合模块 可变形多头注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]