摘要
为实现高铁轨道CPⅢ基准点的自动高效检测,研发基于双目视觉的CPⅢ基准点动态非接触自动检测系统。首先对双相机拍摄的图像进行自适应分割处理,对分割后的图像利用改进模板匹配算法计算获得CPⅢ标识物在图像中的位置;然后对提取的标识物目标图像进行自适应阈值分割提取边缘轮廓,计算标识物中心坐标;最后利用基准点计算方法和双相机标定的参数计算CPⅢ基准点坐标。试验结果表明,检测系统在水平方向上的最大误差为0.95 mm,垂直方向最大误差0.25 mm,最大变异系数为0.211%,该方法可为CPⅢ基准点高精度自动化检测的应用提供参考。
In order to realize the automatic and efficient detection of CPdatum points of high-speed railway track,a dynamic non-contact automatic detection system for CPⅢdatum points based on binocular vision is developed.Firstly,the image captured by binocular camera is adaptively segmented,and for the segmented image,the position of CPⅢmarker in the image is obtained by calculation using the improved template matching algorithm.Then,adaptive threshold segmentation is performed on the extracted marker target image to extract the edge contour and calculate the marker center coordinates.Finally,the coordinates of CPⅢdatum point are calculated using the datum point calculation method and the parameters calibrated by binocular camera.The test results show that the maximum error of the detection system is 0.95 mm in the horizontal direction,0.25 mm in the vertical direction,and the maximum variation coefficient is 0.211%.This method can provide a reference for the application of high-precision automatic detection of CPⅢdatum points.
作者
王建锋
吴学勤
WANG Jianfeng;WU Xueqin(Road Traffic Intelligent Detection Laboratory,Chang’an University,Xi’an Shaanxi 710064,China;Shaanxi Road Traffic Intelligent Detection and Equipment Engineering Technology Research Center,Xi’an Shaanxi 710064,China)
出处
《中国铁路》
2022年第8期135-142,共8页
China Railway
基金
陕西省重点产业链项目(2020ZDLGY16-05)。
关键词
CPⅢ基准点
自动检测
高铁轨道
双目相机
图像分割
CPdatum point
automatic detection
HSR track
binocular camera
image segmentation
