基于激光点云和视觉技术的盾构隧道皮带机渣土体积测量方法研究

Research on the Measurement Method of Spoil Volume on Shield Tunnel Belt Conveyor Based on Laser Point Cloud and Visual Technology

为提高盾构隧道施工过程中渣土体积测量的精度和自动化水平,提出一种基于激光点云和视觉技术的盾构隧道皮带机渣土体积测量方法。该方法系统硬件包括2台单线激光雷达和1个4 K摄像头,其中2台激光雷达分别用于采集断面点云和纵向点云数据,摄像头用于获取设备周围视频信息;采用改进的光流法判断传送带的运动状态,通过结合三角形累加截面积法(TACA)和改进的AE-ICP算法实现对渣土断面面积的精确测量,并通过辛普森法进行数值积分获得渣土体积。试验结果表明,该方法在复杂隧道环境下具有较高的测量精度和鲁棒性,渣土体积测量的相对误差控制在5%以内,测速精度的平均误差在1%以内,具备良好的工程应用前景。

To improve the accuracy and automation level of volume measurement for excavated soil during tunnel construction,a method for measuring the volume of excavated soil in shield tunnels based on laser point cloud and vision technology is proposed.The system hardware includes two single-line laser radars and one 4 K camera.The two laser radars are used to collect cross-section point cloud and longitudinal point cloud data,while the camera captures video information around the equipment.An improved optical flow method is used to determine the motion status of the conveyor belt.By combining the Triangle Accumulated Cross-sectional Area method(TACA)with the improved Adaptive Edge Iterative Closest Point(AE-ICP)algorithm,accurate measurement of the cross-sectional area of the excavated soil is achieved,and the volume of excavated soil is obtained through numerical integration using the Simpson′s rule.Experimental results indicate that this method demonstrates high measurement accuracy and robustness in complex tunnel environments,with the relative error of volume measurement controlled within 5%and the average error of speed measurement within 1%,showing promising prospects for engineering applications.