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 high-speed 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 a good 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.