Laser curve extraction of train wheelset based on U-Net
![](/skin/Gold/line_sep1.gif)
摘 要
研究列车轮对条纹图像快速准确提取的方法,采用经典的U-Net网络模型,实现了激光条纹的精确分割,以构建模板的方式对分割后的图像采用灰度重心法达到亚像素的提取。首先利用U-Net网络模型对激光条纹进行分割,然后用模板法初步找到光条中心,最后再使用灰度重心法实现快速、准确的激光曲线提取。结果表明,该方法可以有效地克服动态环境下背景噪声以及亮斑对激光条纹提取带来的影响。
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
![](flash/relate.gif)
Abstract
The method for rapid and accurate extraction of fringe images of wheel pairs is studied. The classic U-Net network model is used to achieve precise segmentation of laser stripes, and the gray center of gravity method is used to achieve sub-pixel extraction of the segmented image in the form of a template. Firstly, the U-net network model is used to do laser stripe segmentation, then the template method is used to find the center of the light bar, and finally the gray center of gravity method is used to achieve fast and accurate laser curve extraction. Experimental results show that this method can effectively overcome the effects of background noise and bright spots on laser stripe extraction under dynamic environment.
中图分类号 TG115.28 DOI 10.11973/wsjc202101006
所属栏目 试验研究
基金项目
收稿日期 2020/5/29
修改稿日期
网络出版日期
![](/skin/blank.gif)
作者单位点击查看
![](skin/blank.gif)
![](/skin/blank.gif)
备注杨凯(1980-),男,博士,主要研究方向为无损检测、数字图像和信号处理算法在铁路安全检测方向的应用
引用该论文: YANG Kai,LUO Shuai,WANG Yong,GAO Xiaorong,PENG Jianping,JIANG Tianci. Laser curve extraction of train wheelset based on U-Net[J]. Nondestructive Testing, 2021, 43(1): 19~23
杨凯,罗帅,王勇,高晓蓉,彭建平,蒋天赐. 基于U-Net的列车轮对激光曲线提取[J]. 无损检测, 2021, 43(1): 19~23
共有人对该论文发表了看法,其中:
人认为该论文很差
人认为该论文较差
人认为该论文一般
人认为该论文较好
人认为该论文很好
![请选择您对本文的评价](/skin/Gold/evaluation/ev_01.gif)
![您认为本文一无是处!](/skin/Gold/evaluation/ev_02.gif)
![您认为本文较差,没啥用!](/skin/Gold/evaluation/ev_03.gif)
![您认为本文一般,没太大参考价值](/skin/Gold/evaluation/ev_04.gif)
![您认为本文尚可,值得参考](/skin/Gold/evaluation/ev_05.gif)
![您认为本文很好,值得推荐](/skin/Gold/evaluation/ev_06.gif)
参考文献
【1】席剑辉, 包辉.基于改进质心法的激光条纹中心提取算法[J]. 火力与指挥控制, 2019,44(5):149-153.
【2】WANG G, LI W, AERTSEN M, et al. Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks[J]. Neurocomputing, 2019, 338(4):34-45.
【2】WANG G, LI W, AERTSEN M, et al. Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks[J]. Neurocomputing, 2019, 338(4):34-45.
相关信息