基于尺度不变特征变换的无砟轨道板钢筋检测  

Rebar detection of ballastless track plate based on scale invariant feature transform

在线阅读下载全文

作  者:吴应永 高晓蓉 杨阳 尹紫红[4] WU Yingyong;GAO Xiaorong;YANG Yang;YIN Zihong(Communication Technology Consultancy Institute,Zhejiang Post and Telecommunications College,Hangzhou 310000,China;Photoelectric Engineering Institute,School of Physical Science and Technology,Southwest Jiaotong University,Chengdu 610031,China;Hangzhou Branch,China Mobile Communications Group Zhejiang Co.,Ltd.,Hangzhou 310000,China;Department of Road and Railway Engineering,School of Civil Engineering,Southwest Jiaotong University,Chengdu 610031,China)

机构地区:[1]浙江邮电职业技术学院通信技术咨询院,杭州310000 [2]西南交通大学物理科学与技术学院光电工程研究所,成都610031 [3]中国移动通信集团浙江有限公司杭州分公司,杭州310000 [4]西南交通大学土木工程学院道路与铁道工程系,成都610031

出  处:《无损检测》2020年第3期72-76,共5页Nondestructive Testing

摘  要:为实现高速铁路无砟轨道板的钢筋自动检测识别和计数功能,通过系统地对比分析高速铁路无砟轨道板的结构和主要病害类型及其原因,以及对应无损检测方法的优缺点,采用探地雷达法无疑是一种很好的方法。基于探地雷达图像,进行了无砟轨道板的钢筋检测和计数研究,采用尺度不变特征变换(SITF)算法提取和建立了特征点,并优化去除了重复和错误匹配特征点,同时结合模板匹配的方法实现了钢筋自动检测和数目计数判断功能,为后续的进一步缺陷自动检测识别工作奠定了良好的基础。In order to realize the automatic detection,identification and counting of the steel bar of the highspeed railway ballastless track plate,this paper systematically compares and analyzes the structure of the high-speed railway ballastless track plate and the main types of diseases and their causes and the advantages and disadvantages of the corresponding non-destructive testing methods.Ground Penetrating Radar is undoubtedly agood method to employ,so this paper studies the defect detection technology of the ballastless track plate based on GPR and the algorithm of Scale Invariant Feature Transform(SIFT)is employed to extract and establish feature points with the repeated and mismatched feature points being removed at the same time.In addition,the method of template matching is also used to count the number of steel bars,which lays a good foundation for further exploratory.

关 键 词:无砟轨道板 探地雷达 钢筋计数 SIFT优化 模板匹配 

分 类 号:TG115.28[金属学及工艺—物理冶金]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象