摘要
针对传统热轧钢表面缺陷检测存在的检测精度较低、检测速度较慢,传统机器学习检测存在检测速度慢、鲁棒性差等问题,提出一种基于改进轻量级SE-Yolov4热轧钢表面缺陷检测方法.Yolov4主干特征提取网络CSPDarknet53的每一层残差网络中嵌入SENet结构,构成SE-Yolov4网络,有选择地聚集有效信息;同时在主干特征网络输出不同特征信息后和空间池化金字塔前后增加卷积层数,网络结构复杂化;SE-Yolov4算法中嵌入轻量化MobileNet v3结构,减少模型参数量,提高检测速度.实验结果表明:该改进算法在测试集中的mAP值达到93.02%,较Yolov4算法检测精度提升7.2%,检测速度提升近3倍.
Aiming at the problems of low detection accuracy and slow detection speed of traditional hot rolled steel surface defect detection,and the problems of slow detection speed and poor robustness of traditional machine learning detection,a surface defect detection method based on improved lightweight SE-Yolov4 hot rolled steel is proposed.The SE-Yolov4 network is composed of SE-Yolov4 network,which is embedded in the residual network of each layer of the Yolov4 backbone feature extraction network CSPDarknet53 to selectively gather effective information.At the same time,after the backbone feature network outputs different feature information before and after the Spatial Pooling Pyramid,the number of convolution layers is increased,and the network structure is complex;SE-Yolov4 algorithm embeds lightweight mobileNet v3 structure to reduce the amount of model parameters and improve the detection speed.The experimental results show that the mAP value of the improved algorithm in the testset reaches 93.02%,which improves the detection accuracy by 7.2%and the detection speed by nearly three times compared with Yolov4 algorithm.
作者
黄晓红
李静
董诗琪
王云阁
HUANG Xiaohong;LI Jing;DONG Shiqi;WANG Yunge(School of Artificial Intelligence,North China University of Technology,Tangshan 063210,China;Tangshan Iron and Steel Co.,Ltd.,Tangshan 063016,China;Hebei Key Laboratory of Industrial Intelligent Perception,North China University of technology,Tangshan 063210,China)
出处
《湖南科技大学学报(自然科学版)》
CAS
北大核心
2024年第1期80-86,共7页
Journal of Hunan University of Science And Technology:Natural Science Edition
基金
河北省高等学校科学技术研究项目资助(ZD2020152)
华北理工大学技术转移基金资助平台及推广项目资助(TG2018004)
科技基础研究项目资助(JQN2019006)。