基于三维图像的带肋钢筋表面检测系统研究

Research on the surface detection system of ribbed bars based on 3D images

带肋钢筋表面质量是反应产品质量的重要指标。针对目前二维带肋钢筋表面缺陷检测缺乏对深度方向维度的考量,从而导致缺陷检测不准确以及对严重程度不明确等问题,设计了基于三维图像的带肋钢筋表面检测系统。该系统主要包括带肋钢筋的轮廓检测、表面缺陷检测、长度检测以及温度测量。首先通过面阵相机和激光搭建激光三角获取点云数据,采用罗德里格矩阵模型将不同相机采集到的单幅点云数据配准到同一坐标系下进行组合拼接,从而得到带肋钢筋的三维轮廓图像,利用异常三维点云判断带肋钢筋表面缺陷。实验结果表明:本系统能够实时采集带肋钢筋三维图像,缺陷检测准确率大于95%。目前该系统已经应用于国内某棒材产线,能够对带肋钢筋表面进行全方位检测,有助于现场生成质量管理。

The surface quality of ribbed bars is an important indicator reflecting product quality.In response to the current lack of consideration for depth dimension in two-dimensional ribbed bars surface defect detection,which leads to inaccurate defects detection and unclear severity,a three-dimensional image-based ribbed bars surface detection system has been designed.The system mainly includes contour detection,surface defects detection,length detection and temperature measurement of ribbed bars.Firstly,point cloud data is obtained by constructing laser triangulation using a 3D camera and a laser.The Rodrigues matrix model is used to register the single point cloud data collected by different cameras into the same coordinate system for combination and stitching,thereby obtaining a 3D contour image of the ribbed bar.Then,the abnormal 3D point cloud is used to determine the surface defects of the ribbed bars.The experimental results show that this system can collect real-time three-dimensional images of ribbed bars,and the accuracy of defects detection is greater than 95%.At present,the system has been applied to a bar production site in China,which can conduct comprehensive inspection of the surface of ribbed bars,helping to generate quality management on site.