首页|基于改进YOLOv7的钢材缺陷检测

基于改进YOLOv7的钢材缺陷检测

扫码查看
钢材表面缺陷检测在实际生产中非常重要.为了准确检测缺陷,设计了一种基于改进的YOLOv7的钢材表面缺陷检测模型.首先在骨干网络结构中引入Ghost模块,增强模型提取特征和识别小特征的能力,同时降低模型参数量;其次在池化模块中嵌入注意力机制;最后通过引入EIOU改善损失函数,从而更好地优化YOLOv7网络模型,且可以更好地处理样本的不平衡,从而达到更好的优化相似度.实验结果表明,与原模型相比,所提模型mAP达到76.9%,提高了4.2%.该模型可以满足钢表面缺陷的准确检测和识别需求.
Steel Defect Detection Based on Improved YOLOv7
Steel surface defect detection is very important in actual production.In order to accurately detect defects,this paper de-signs a steel surface defect detection model based on improved YOLOv7.Firstly,the Ghost module is introduced into the back-bone network structure to enhance the ability of the model to extract features and identify small features while reducing the num-ber of model parameters.Secondly,the attention mechanism is embedded in the pooling module.Finally,the loss function is im-proved by introducing EIOU,so as to better optimize the YOLOv7 network model,which can better deal with the imbalance of samples,so as to achieve better optimization similarity.Experimental results show that,compared with the original model,the mAP of the proposed model increases by 4.2%to 76.9%.The model can meet the needs of accurate detection and identification of steel surface defects.

YOLOv7Defect detectionDeep learningAttention module

黄海新、吴迪

展开 >

沈阳理工大学自动化与电气工程学院 沈阳 110159

yolov7 缺陷检测 深度学习 注意力模块

国家自然科学基金

61672359

2024

计算机科学
重庆西南信息有限公司(原科技部西南信息中心)

计算机科学

CSTPCD北大核心
影响因子:0.944
ISSN:1002-137X
年,卷(期):2024.51(z1)
  • 14