A Fast Weighted Registration Method of 3D Point Cloud Based on Curvature Feature

被引：6
|
作者：
Liu, Bing
Gao, Xuehai
Liu, Houde [1 ]
Wang, Xueqian
Liang, Bin
机构：
[1] Tsinghua Univ, Ctr Intelligent Control & Telesci, Shenzhen, Peoples R China
来源：
PROCEEDINGS OF 2018 THE 3RD INTERNATIONAL CONFERENCE ON MULTIMEDIA AND IMAGE PROCESSING (ICMIP 2018) | 2018年
基金：
中国国家自然科学基金;
关键词：
3D point cloud; curvature feature; distance-weighted ICP; ROBUST REGISTRATION;
D O I：
10.1145/3195588.3195595
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
In order to realize the fast and accurate registration of 3D point cloud data, a new fast weighted registration method is proposed in this paper. Firstly, using curvature feature, the method samples the original 3D point cloud data to quickly find matching points and remove wrong point pairs. Secondly, by introducing the iterative re-weighted least squares (IRLS) algorithm, the method carries out coarse alignment of the scattered point cloud. Finally, the method presents an improved distance-weighted Iterative Closest Point (ICP) algorithm to achieve fine matching. The experimental results show that the method has good convergence, robustness and accuracy.
引用
收藏
页码：83 / 87
页数：5
相关论文
共 50 条
  • [1] An automatic 3D point cloud registration method based on regional curvature maps
    Sun, Junhua
    Zhang, Jie
    Zhang, Guangjun
    [J]. IMAGE AND VISION COMPUTING, 2016, 56 : 49 - 58
  • [2] Point Cloud Registration Based on Fast Point Feature Histogram Descriptors for 3D Reconstruction of Trees
    Peng, Yeping
    Lin, Shengdong
    Wu, Hongkun
    Cao, Guangzhong
    [J]. REMOTE SENSING, 2023, 15 (15)
  • [3] Rigid 3D Point Cloud Registration Based on Point Feature Histograms
    Wang, Xi
    Zhang, Xutang
    [J]. PROCEEDINGS OF THE 2017 2ND INTERNATIONAL CONFERENCE ON MACHINERY, ELECTRONICS AND CONTROL SIMULATION (MECS 2017), 2017, 138 : 543 - 550
  • [4] A 3D Point Cloud Registration Algorithm based on Feature Points
    Ren, Yi
    Zhou, Fucai
    [J]. PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON INFORMATION SCIENCES, MACHINERY, MATERIALS AND ENERGY (ICISMME 2015), 2015, 126 : 803 - 807
  • [5] 3D Point Cloud Registration Algorithm Based on Feature Matching
    Liu Jian
    Bai Di
    [J]. ACTA OPTICA SINICA, 2018, 38 (12)
  • [6] A Fast Coherent Point Drift Method for Rigid 3D Point Cloud Registration
    Liu, Zhengmao
    Yu, Chengpu
    Qiu, Fanshuo
    Liu, Yixuan
    [J]. Chinese Control Conference, CCC, 2023, 2023-July : 7776 - 7781
  • [7] Improved Feature Point Algorithm for 3D Point Cloud Registration
    Kamencay, Patrik
    Sinko, Martin
    Hudec, Robert
    Benco, Miroslav
    Radil, Roman
    [J]. 2019 42ND INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP), 2019, : 517 - 520
  • [8] Fast Point Feature Histograms (FPFH) for 3D Registration
    Rusu, Radu Bogdan
    Blodow, Nico
    Beetz, Michael
    [J]. ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7, 2009, : 1848 - 1853
  • [9] Point cloud registration algorithm based on curvature feature similarity
    Yao, Zongwei
    Zhao, Quanxiao
    Li, Xuefei
    Bi, Qiushi
    [J]. MEASUREMENT, 2021, 177
  • [10] Feature Based Sampling: A Fast and Robust Sampling Method for Tasks Using 3D Point Cloud
    Han, Jung-Woo
    Synn, Dong-Joo
    Kim, Tae-Hyeong
    Chung, Hae-Chun
    Kim, Jong-Kook
    [J]. IEEE ACCESS, 2022, 10 : 58062 - 58070
12345