摘要
针对目前传统图像处理算法对踏面缺陷检测存在效率不高、对环境鲁棒性不足等问题,本文提出基于改进Faster RCNN的踏面缺陷检测方法。改进的网络首先使用Resnet50作为特征提取网络,并在特征金字塔层(FPN)特征融合输出部分加入自注意力机制,加强了检测网络对小缺陷的检测能力,最后使用K-means++聚类算法对踏面缺陷数据集锚框进行聚类,并通过聚类结果定制出更适合轮对踏面缺陷的锚框。实验结果表明,改进后的Faster RCNN网络对轮对踏面缺陷检测的平均检测速度为68 ms,平均精度(mAP)达到了97.3%,对小目标缺陷的检测精度(mAP^(small))达到了39.3%。
To address the problems of inefficiency and lack of robustness to the environment in the current traditional image processing algorithms for tread surface defect detection,this paper proposes an improved tread surface defect detection method based on the Faster RCNN.The improved network first uses Resnet50 as the feature extraction network,and adds a self-attention mechanism to the feature fusion output part of the Feature Pyramid Network to enhance the detection ability of the detection network for small defects,and finally uses the K-means++ clustering algorithm to cluster the anchor frames of the tread defect dataset,and uses the clustering results to customize anchor frames that are more suitable for wheel-to-tread defects.The experimental results show that the improved Faster RCNN network has an average detection speed of 68 ms,an average accuracy(mAP) of 97.3% and an accuracy of 39.3% for the detection of small target defects.
作者
刘应桃
郭世伟
付孟新
张青松
Liu Yingtao;Guo Shiwei;Fu Mengxin;Zhang Qingsong(School of Mechanical Engineering,Southwest Jiaotong University,,Chengdu 610031,China;State Key Laboratory of Traction Power,Southwest Jiaotong University,,Chengdu 610031,China)
出处
《电子测量技术》
北大核心
2023年第12期34-41,共8页
Electronic Measurement Technology
基金
博士后科学基金(2020M682506)
成都科技局重点研发项目(2019-YF05-01823-SN)资助。
