ZHONG Yu,BAI Fan,LIU Yong,et al.Study on point cloud splicing method of underground pipe gallery in power plants based on improved 3D-Harris operator[J].Thermal Power Generation,2023,52(01):89-97.[doi:10.19666/j.rlfd.202205073]
基于改进3D-Harris角点检测算法的电厂地下管廊点云拼接方法研究
- Title:
- Study on point cloud splicing method of underground pipe gallery in power plants based on improved 3D-Harris operator
- 摘要:
- 提出一种基于改进3D-Harris角点检测算法的电厂地下管廊点云拼接方法。以电厂地下管廊多组海量点云数据为分析对象，利用主成分分析法获取目标检测点在邻域点云微切平面上的法向信息，进而提取点云的边界点；构建基于目标检测点法向信息的协方差矩阵，计算并比较其角点响应强度函数，从中选出部分待筛选点作为真伪角点检测对象；利用基于高斯曲率极值点的伪角点检测方法，滤除伪角点并筛选出真角点；最后通过快速点特征直方图方法匹配各组点云间的相似角点，利用最近点搜索点云配准算法实现地下管廊多组点云间的拼接，并与传统3D-Harris角点检测算法的结果进行比较。对比表明，所提出算法计算耗时短且角点提取正确率高，可实现电厂地下管廊海量点云的精确拼接。
参考文献/References:
［1］ SIPIRAN I, BUSTOS B. Harris 3D: a robust extension of the Harris operator for interest point detection on 3D meshes[J]. Visual Computer, 2011, 27(11): 963.
［2］ HENDAOUI R, ABDELLAOUI M, DOUIK A. Synthesis of spatio-temporal interest point detectors: Harris 3D, MoSIFT and SURF-MHI[C]//2014 1st International Conference on Advanced Technologies for Signal and Image Processing (ATSIP). IEEE, 2014.
［3］ 王丞, 田暄, 郭瑞, 等. 自适应Harris角点提取的点云粗配准算法[J]. 西安交通大学学报, 2022, 56(3): 33-44.
WANG Cheng, TIAN Xuan, GUO Rui, et al. Coarse point cloud registration based on adaptive Harris corner extraction[J]. Journal of Xi’an Jiaotong University, 2022, 56(3): 33-44.
［4］ 李昌华, 史浩, 李智杰. 基于卷积神经网络结合改进Harris-SIFT的点云配准方法[J]. 激光与光电子学进展, 2020, 57(20): 230-239.
LI Changhua, SHI Hao, LI Zhijie. Point cloud registration method based on combination of convolutional neural network and improved Harris-SIFT[J]. Laser & Optoelectronics Progress, 2020, 57(20): 230-239.
［5］ 林增刚, 张艳宁, 郭哲. 基于变形分析的三维Susan 角点检测算法[J]. 计算机应用研究, 2011, 28(8): 3141-3144.
LIN Zenggang, ZHANG Yanning, GUO Zhe. 3D Susan corner detection algorithm based on deformation analyzing[J]. Application Research of Computers, 2011, 28(8): 3141-3144.
［6］ 范强, 刘鹏, 杨俊, 等. 基于3D-Harris与FPFH改进的3D-NDT配准算法[J]. 图学学报, 2020, 41(4): 567-575.
FAN Qiang, LIU Peng, YANG Jun, et al. Improved 3D-NDT point cloud registration algorithm based on 3D-Harris and FPFH[J]. Journal of Graphics, 2020, 41(4): 567-575.
［7］ XU H, YU L, HOU J, et al. Automatic reconstruction method for large scene based on multi-site point cloud stitching[J]. Measurement, 2018, 131: 590-596.
［8］ SUNGH O, BYU N, KEONH W A, et al. Registration of 3D scan data using image reprojection[J]. International Journal of Precision Engineering and Manufacturing, 2017, 18(9): 1221-1229.
［9］ CHU J, NIE C M. Multi-view point clouds registration and stitching based on SIFT feature[C]//2011 3rd IEEE International Conference on Computer Research and Development (ICCRD 2011). IEEE, 2011: 274-278.
［10］陈金广, 郭秋梦, 马丽丽, 等. 用于多视点云拼接的改进ICP算法[J]. 计算机系统应用, 2018, 27(1): 180-184.
CHEN Jinguang, GUO Qiumeng, MA Lili, et al. Improved ICP algorithm for multi-view point cloud splicing[J]. Computer Systems & Applications, 2018, 27(1): 180-184.
［11］马骊溟, 徐毅, 李泽湘. 基于高斯曲率极值点的散乱点云数据特征点提取[J]. 系统仿真学报, 2008, 20(9): 2341-2344.
MA Liming, XU Yi, LI Zexiang. Extracting feature points for scattered points based on gauss curvature extreme point[J]. Journal of System Simulation, 2008, 20(9): 2341-2344.
［12］陈义仁, 王一宾, 彭张节, 等. 一种改进的散乱点云边界特征点提取算法[J]. 计算机工程与应用, 2012, 48(23): 177-180
CHEN Yiren, WANG Yibin, PENG Zhangjie, et al. Improved algorithm for extraction of boundary characteristic point from scattered point cloud[J]. Computer Engineering and Applications, 2012, 48(23): 177-180.
［13］孙殿柱, 范志先, 李延瑞. 散乱数据点云边界特征自动提取算法[J]. 华中科技大学学报(自然科学版), 2008, 36(8): 82-84.
SUN Dianzhu, FAN Zhixian, LI Yanrui. Automatic extraction of boundary characteristic from scatter data[J]. Journal of Huazhong University of Science & Technology, 2008, 36(8): 82-84.
［14］ZHANG X, LI H, CHENG Z. Curvature estimation of 3D point cloud surfaces through the fitting of normal section curvatures[J]. Proceedings of Asia Graph, 2008, 13: 72-79.
［15］RUSU R B, BLODOW N, BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]//IEEE International Conference on Robotics & Automation. IEEE, 2009.
［16］BESL P J, MCKAY N D. A method for registration of 3D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256.
备注/Memo
仲宇（1991），男，工程师，主要研究方向为电力工程建设，509493525@qq.com。
