一种动态特征匹配的部分重叠点云配准方法

doi:10.11959/j.issn.1000-0801.2021010

电信科学 ›› 2021, Vol. 37 ›› Issue (4): 97-107.doi: 10.11959/j.issn.1000-0801.2021010

一种动态特征匹配的部分重叠点云配准方法

杜辉¹, 郑长亮¹, 苗春雨², 张小孟²

¹ 北京电子科技职业学院电信工程学院，北京 100176
² 杭州安恒信息技术股份有限公司，浙江杭州 310051

修回日期:2020-12-27 出版日期:2021-04-20 发布日期:2021-04-01
作者简介:杜辉（1978- ），男，北京电子科技职业学院副教授、高级工程师，主要研究方向为三维重建、网络安全等
郑长亮（1981- ），男，北京电子科技职业学院讲师，主要研究方向为三维重建
苗春雨（1978- ），男，副教授，现就职于杭州安恒信息技术股份有限公司，主要研究方向为无线传感器网络、网络安全、深度学习、三维重建等
张小孟（1983- ），男，现就职于杭州安恒信息技术股份有限公司，主要研究方向为网络安全、深度学习、三维重建等
基金资助:
浙江省基础公益研究计划项目(LGG18F020008);北京电子科技职业学院院内科技类重点课题(2017Z001-003-KXZ)

A partial overlapping point cloud registration method based on dynamic feature matching

Hui DU¹, Changliang ZHENG¹, Chunyu MIAO², Xiaomeng ZHANG²

¹ College of Telecommunication Engineering, Beijing Polytechnic, Beijing 100176, China
² DBAPP Security Co., Ltd., Hangzhou 310051, China

Revised:2020-12-27 Online:2021-04-20 Published:2021-04-01
Supported by:
Zhejiang Basic Public Welfare Research Project(LGG18F020008);The key project of science and technology in Beijing Electronic Technology Vocational College: Design of a network attack and defense system centered on multi-stage drones(2017Z001-003-KXZ)

摘要/Abstract

摘要：

点云配准方法能够有效地完成对不同重叠率、不同规模点云间的配准，可确保三维重建模型的精度。针对该问题，提出一种动态特征匹配的部分重叠点云配准方法，首先基于欧氏距离分割法将点云分割为子点云；然后提取子点云特征，考虑到不同点云的规模不同，提取的特征规模也是不同的，提出利用动态时间规整算法（DTW）完成子点云间的映射；最后利用迭代配准算法求取拼接点云间的平移、旋转矩阵，利用该矩阵完成点云间的配准和拼接。实验结果表明，提出的方法能够有效地解决部分重叠点云和不同规模点云的配准问题。

关键词: 激光雷达, 重叠点云, 点云分割, 点云映射, 点云配准

Abstract:

The point cloud registration method can effectively complete the registration of point clouds with different overlap rates and various sizes, and ensure the accuracy of the 3D reconstruction model.To address the above issues, a partial overlapping point cloud registration method based on dynamic feature matching named PPCR was proposed.Firstly, the point cloud was divided into sub-point clouds based on the Euclidean distance segmentation method.Secondly, the features of sub-point clouds were extracted.Since the sizes of different point clouds are varied, the scales of the extracted features are also different.Thus, a dynamic time warping (DTW) algorithm was proposed to map the sub-point clouds.Finally, the registration algorithm was iterated to obtain the translation and rotation matrix between point clouds.This matrix was used to complete the registration and stitching between point clouds.Experimental results show that the proposed method can effectively solve the registration problems of partially overlapping point clouds and point clouds with different scales.

Key words: lidar, overlapping point cloud, point cloud segmentation, point cloud mapping, point cloud registration

中图分类号:

P237

杜辉, 郑长亮, 苗春雨, 张小孟. 一种动态特征匹配的部分重叠点云配准方法[J]. 电信科学, 2021, 37(4): 97-107.

Hui DU, Changliang ZHENG, Chunyu MIAO, Xiaomeng ZHANG. A partial overlapping point cloud registration method based on dynamic feature matching[J]. Telecommunications Science, 2021, 37(4): 97-107.

图/表 16

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

图11

表2

图12

表3

表4

参考文献 19

[1]	吴淑芳, 刘勃洋, 雷琪 ,等. 基于三维重建技术的坡面细沟侵蚀演变过程研究[J]. 农业工程学报, 2019,35(9): 114-120.
	WU S F , LIU B Y , LEI Q ,et al. Research on the evolution process of slope rill erosion based on 3D reconstruction technology[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019,35(9): 114-120.
[2]	PORPIGLIA F , CHECCUCCI E , AMPARORE D ,et al. Augmented-reality robot-assisted radical prostatectomy using hyper-accuracy three-dimensional reconstruction (HA3D?) technology:a radiological and pathological study[J]. BJU International, 2019,123(5): 834-845.
[3]	ZHOU Y , ZHANG L , XING C ,et al. Target three-dimensional reconstruction from the multi-view radar image sequence[J]. IEEE Access, 2019(7): 36722-36735.
[4]	ZHOU Y Q , LIU L , WANG L ,et al. Service aware 6G:an intelligent and open network based on convergence of communication,computing and caching[J]. Digital Communications and Networks, 2020,6(3): 253-260.
[5]	ZHOU Y Q , TIAN L , LIU L ,et al. Fog computing enabled future mobile communication networks:a convergence of communication and computing[J]. IEEE Communications Magazine, 2019,57(5): 20-27.
[6]	KARG M , PROKOFYEVA O . Method for three- dimensional graphic reconstruction of a vehicle:LUS20200026905,744[P]. 2020.
[7]	陈佳舟, 彭鹤年, 吴宁 ,等. 文物三维重建误差点的自动剔除方法[J]. 小型微型计算机系统, 2019,40(9): 71-77.
	CHEN J Z , PENG H N , WU N ,et al. Automatic removal of error points in the 3D reconstruction of cultural relics[J]. Small Microcomputer System, 2019,40(9): 71-77.
[8]	RAO Y B , FAN B J , WANG Q F ,et al. Extreme feature regions detection and accurate quality assessment for point-cloud 3D reconstruction[J]. IEEE Access, 2019(7): 37757-37769.
[9]	LAN Z Q , YEW Z J , LEE G H . Robust point cloud based reconstruction of large-scale outdoor scenes[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piacataway:IEEE Press, 2019: 9690-9698.
[10]	徐斌, 行鸿彦, 解建华 ,等. 基于三维重建的大腿假肢接受腔定制研究[J]. 电子测量与仪器学报, 2018(9): 23-28.
	XU B , XING H Y , XIE J H ,et al. Customization of the thigh prosthetic cavity based on 3D reconstruction[J]. Journal of Electronic Measurement and Instrument, 2018(9): 23-28.
[11]	张一, 姜挺, 江刚武 ,等. 特征法视觉 SLAM 逆深度滤波的三维重建[J]. 测绘学报, 2019,48(6): 54-61.
	ZHANG Y , JIANG T , JIANG G W ,et al. Three-dimensional reconstruction of feature-based visual SLAM inverse depth filtering[J]. Journal of Surveying and Mapping, 2019,48(6): 54-61.
[12]	丁忠军, 赵子毅, 张春堂 ,等. 载人潜水器的深海地貌线结构光三维重建[J]. 红外与激光工程, 2019,48(5): 77-84.
	DING Z J , ZHAO Z Y , ZHANG C T ,et al. Structured light three-dimensional reconstruction of deep sea landforms for manned submersibles[J]. Infrared and Laser Engineering, 2019,48(5): 77-84.
[13]	SEDAGHAT N , ZOLFAGHARI M , AMIR E ,et al. Orientation-boosted voxel nets for 3D object recognition[J].arXiv preprint:1604.03351,2016. arXiv preprint:1604.03351, 2016.
[14]	李斌, 张建平, 刘学军 . 基于Hadoop的不确定异常时间序列检测[J]. 传感技术学报, 2015(7): 124-130.
	LI B , ZHANG J P , LIU X J . Uncertain anomalous time series detection based on Hadoop[J]. Journal of Sensor Technology, 2015(7): 124-130.
[15]	李翔宇, 许力, 李瑞兴 . 基于CM-DTW算法的智能手机动态手势身份认证[J]. 计算机系统应用, 2019(8): 87-96.
	LI X Y , XU L , LI R X . Smart phone dynamic gesture identity authentication based on CM-DTW algorithm[J]. Computer Systems ＆ Applications, 2019(8): 87-96.
[16]	DING Q , HE J . The detection of non-cooperative targets in space by using 3D point cloud[C]// Proceedings of 2019 5th International Conference on Control,Automation and Robotics (ICCAR). Piacataway:IEEE Press, 2019: 545-549.
[17]	CHEN X W , ZHU Y L , WU T ,et al. The point cloud registration technology based on SAC-IA and improved ICP[J]. Journal of Xi'an Polytechnic University, 2017,31(3): 395-401.
[18]	LIU T , WANG N , FU Q ,et al. Research on 3D reconstruction method based on laser rotation scanning[C]// Proceedings of 2019 IEEE International Conference on Mechatronics and Automation (ICMA). Piacataway:IEEE Press, 2019: 1600-1604.
[19]	SUN M H , YANG S W , LIU H Z . Scale-aware camera localization in 3D LiDAR maps with a monocular visual odometry[J]. Computer Animation and Virtual Worlds, 2019,30(3-4): e1879.

算法	35%	30%	25%	20%	15%	10%	5%
PPCR算法	113	102	95	81	74	69	66
ICP算法	206	184	167	146	123	119	108

滤波阈值	S/5	S/4	S/3	S/2
E_R	0.351	0.286	0.241	0.179
E_t	0.092	0.075	0.058	0.042
E_R+t	0.443	0.361	0.299	0.211
拼接效果	1	1	1	1

下采样矩阵大小	3×3	5×5	7×7	9×9
E_R	0.273	0.415	0.689	0.840
E_t	0.051	0.089	0.095	0.139
E_R+t	0.324	0.504	0.784	0.979
配准效果	1	1	0	0

g(unit)	2	3	4	5	6	7	8	9	10
E_R+t	0.71	0.47	0.39	0.36	0.37	0.34	0.38	0.33	0.35

一种动态特征匹配的部分重叠点云配准方法

A partial overlapping point cloud registration method based on dynamic feature matching

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 19

相关文章 0

Metrics

推荐阅读 0