基于主动式全景视觉的管道形变检测及重构技术的研究  

In-pipe deformation detection and reconstruction based on active stereo omni-directional vision sensor

作　　者：鲁少辉[1] 吴挺[1] 汤一平[1] 郭伟青[1] 

机构地区：[1]浙江工业大学信息工程学院,浙江杭州310023

出　　处：《光电子．激光》2015年第7期1301-1308,共8页Journal of Optoelectronics·Laser

基　　金：国家自然科学基金(61070134)资助项目

摘　　要：研究了一种采用主动式全景视觉传感器(ASODVS)的管道内表面全方位检测方法。基于主动式全景视觉检测原理,提出了一种能够快速、全方位获取管道内壁三维点云信息,实现视觉检测管道形变的全景激光视觉系统;利用携带有ASODVS的爬行机器人进入管道内部,采集激光横断扫描全景图像;然后根据提取的管道内壁三维点云数据计算最小直径、横断面面积等几何特征判断变形率;最后根据三维点云圆周分布的特征,采用三角格网模型进行三维重构。实验结果表明:基于主动式全景视觉的管道内壁全方位检测系统能够实时完成对管道凹凸形变的检测和识别,并恢复管道内壁的三维形貌,具有较高的检测精度。Underground pipe inner surface defect detection is constrained by space accessibility.In this work we propose an in-pipe defect detection method based on active stereo omni-directional vision.An omni-directional laser visual system is designed to detect the geometric information of the pipe.The system can obtain the three-dimensional point cloud data in real time.In our system,a crawling robot equipped with the active stereo omni-directional vision sensor（ASODVS）traverses along the pipeline and takes panoramic image sequences using laser streaks on the inner surface of the pipe.Afterwards,the 3D point cloud data are extracted and the 3Dcoordinates are calculated.The 3Dpoint cloud data are used to calculate the geometrical features,such as minimum diameter,cross sectional area.Based on the geometrical information,the deformation rate of the pipe can be estimated.Since 3Dpoint cloud data are circularly distributed,a triangular grid model is used for 3Dreconstruction.Experimental results show that our deformation detection and the 3Dtopography recovery technique are accurate.

关 键 词：主动式全景视觉传感器(ASODVS) 管道缺陷 三维视觉检测 全景激光视觉 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]