基于时间序列及邻域分析的管道点云障碍物检测  

Obstacle Detection for a Pipeline Point Cloud Based on Time Series and Neighborhood Analysis

作　　者：林时雨 闫雪娇 谢哲 付宏文 蒋松 姜宏志[1,3] 李旭东 赵慧洁[1,3] Lin Shiyu;Yan Xuejiao;Xie Zhe;Fu Hongwen;Jiang Song;Jiang Hongzhi;Li Xudong;Zhao Huijie(Key Laboratory of Precision OptoMechatronics Technology,Ministry of Education,School of Instrumentation and Optoelectronic Engineering,Beihang University,Beijing 100191,China;Shanghai Aerospace System Research Institute,Shanghai 201108,China;Qingdao Research Institute of Beihang University,Qingdao 266100,Shandong,China)

机构地区：[1]北京航空航天大学仪器科学与光电工程学院精密光机电一体化技术教育部重点实验室,北京100191 [2]上海宇航系统研究所,上海201108 [3]北京航空航天大学青岛研究院,山东青岛266100

出　　处：《激光与光电子学进展》2022年第22期131-137,共7页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61735003)。

摘　　要：采用管道机器人定期检测输送管线的状态对于确保管道安全可靠运行意义重大。受限于机器人的结构尺寸和功耗,常用精度较低的微小型三维测量传感器为机器人提供环境及导航信息。针对低精度三维传感器得到的点云数据质量不佳、难以可靠分辨障碍物的问题,提出了一种基于时间序列及邻域分析的点云处理方法。利用障碍物点云与噪声点云在时间序列分布和空间分布方面的特性有效去除噪声,并通过拟合管道内壁实现管道内障碍物检测。测试结果表明,所提方法的检测精度提升了约30个百分点,检测时间小于1 s,满足管道机器人的应用需求。Employing a robot to inspect the inner surface of the pipeline periodically is crucial to guarantee that the pipeline runs safely and reliably.Limited by the robot size and power,small three-dimensional measurement sensors with lower accuracy are frequently used with the robot to obtain environmental and navigation information.However,the quality of the pipeline point cloud acquired using such a sensor is substandard,making it challenging to reliably detect obstacles.Therefore,a point cloud processing approach according to time series and neighborhood analysis is proposed,which employs time and spatial distribution characteristics of obstacle point clouds and noise point clouds to remove noise and finally detects the obstacles by fitting the pipeline inner wall point clouds.The experiments reveal that the detection accuracy improves by30 percentage points and the processing time is less than 1 s,meeting the requirements of the pipeline inspection robot.

关 键 词：图像处理 管道检测 三维点云 障碍物检测 时间序列 邻域分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]