基于改进YOLOv7的钢材表面缺陷检测

付帅; 凌铭; 楚东港

基于改进YOLOv7的钢材表面缺陷检测

引用本文：付帅，凌铭，楚东港.基于改进YOLOv7的钢材表面缺陷检测[J].计算技术与自动化,2024,(2):10-16

摘要点击次数: 561

全文下载次数: 0

作者	单位
付帅，凌铭，楚东港	（上海工程技术大学电子与电气工程学院，上海 201620）

中文摘要:钢材表面缺陷对于钢材行业来说是一个巨大的挑战。针对传统的钢材缺陷检测方法存在着效率低、检测精度不高等问题，基于YOLOv7设计了一种AFSD-YOLOv7模型进行实时的钢材表面缺陷检测。首先，在YOLOv7模型中使用一种轻量化卷积结构替换标准卷积结构，，以加速模型的推理过程；然后采用快速空间金字塔池化结构替换原始空间金字塔池化结构，以加速网络的特征提取过程；最后添加改进的ECA-Net注意力机制，以提升模型检测精度。实验结果表明，AFSD-YOLOv7能够对钢材缺陷进行有效识别，相比YOLOv7模型，计算量减少了54.8%，mAP提高了3.2%，对于钢材表面缺陷检测具有实际应用价值。

中文关键词:钢材缺陷检测 YOLOv7 神经网络深度学习注意力机制标准卷积

Steel Surface Defect Detection Based on Improved YOLOv7

Abstract:Surface defects on steel are a significant challenge for the steel industry. Traditional steel defect detection methods suffer from low efficiency and accuracy. To address these issues, an AFSD-YOLOv7 model has been designed for real-time steel surface defect detection. First, a lightweight convolutional structure was used to replace the standard convolutional structure in the YOLOv7 model, speeding up the inference process. Next, a fast spatial pyramid pooling structure was used to replace the original spatial pyramid pooling structure to accelerate the network’s feature extraction process. Finally, an improved ECA-Net attention mechanism was added to enhance the model′s detection accuracy. Experimental results show that AFSD-YOLOv7 can effectively identify steel defects. Compared to the YOLOv7 model, AFSD-YOLOv7 reduces computation by 54.8% and improves mAP by 3.2%, indicating significant practical value for steel surface defect detection.

keywords:steel defect detection YOLOv7 neural networks deep learning attention mechanism standard convolution

查看全文 查看/发表评论 下载pdf阅读器