基于图像智能识别的钢轨伸缩调节器位移监测技术

Displacement Monitoring Technology of Rail Expansion Joint Based on Image Intelligent Recognition

针对传统大桥钢轨伸缩调节器位移检测方法检测成本高、设备维护复杂等问题,提出了一种基于二维码的位移检测方法。采用先粗检测后精检测的策略,粗检测环节使用Viola-Jones快速目标检测框架确定待检测图像中二维码的候选区域,精检测环节基于二维码的定位标志确定各候选区域中二维码的三个顶点。在检测定位二维码的基础上利用模板匹配算法,计算出钢轨伸缩调节器的位移,从而对桥梁健康状况进行检测。试验结果表明,利用二维码技术进行桥梁结构位移检测具有较高的精度,检测精度可以达到毫米级。

Aiming at the problems of high detection cost and complex equipment maintenance in the traditional displacement detection method of rail expansion joint,a displacement detection method based on QR(Quick Response)code was proposed in this paper.The strategy of coarse detection followed by fine detection was adopted.The coarse detection stage uses the Viola-Jones fast object detection framework to determine the candidate regions of the QR code in the image to be detected.In the fine detection phase,three vertices of the QR code in each candidate region were determined based on the location markers of the QR code.On the basis of detecting and locating the QR code,a template matching algorithm was used to calculate the displacement of the rail expansion joint,thereby detecting the health status of the bridge.The experimental results show that the displacement detection of bridge structure using QR code technology has high accuracy,and the detection accuracy can reach millimeter level.