Computer Science ›› 2020, Vol. 47 ›› Issue (3): 137-142.doi: 10.11896/jsjkx.190200261

• Computer Graphics & Multimedia • Previous Articles     Next Articles

Adaptive Levenberg-Marquardt Cloud Registration Method for 3D Reconstruction

ZENG Jun-fei,YANG Hai-qing,WU Hao   

  1. (College of Information Engineering, Zhejiang University of Technology, Hangzhou 310000, China)
  • Received:2019-02-02 Online:2020-03-15 Published:2020-03-30
  • About author:ZENG Jun-fei,born in 1993,postgra-duate.His main research interests include visual SLAM and three-dimensional reconstruction. YANG Hai-qing,born in 1971,asso-ciate professor,postgraduate supervisor.His main research interests include computer vision and so on.
  • Supported by:
    This work was supported by the Natural Science Foundation of Zhejiang pvovince, China (LY13F010008) and Science and Technology Plan Project of Zhejiang province, China (2015F50009).

Abstract: To address the problems that point cloud registration process in three-dimensional (3D) reconstruction is susceptible to environmental noise,point cloud exposure,illumination,object occlusion and other factors,as well as the traditional ICP registration algorithm with low accuracy and long time-consuming,this paper proposed a point cloud registration algorithm based on adaptive Levenberg-Marquart.Firstly,the initial point cloud data is pretreated by way of statistical filtering and voxel raster filtering,and then the filtered point cloud is stratified to eliminate the outlier data,so as to improve the accuracy of subsequent point cloud registration.Furthermore,aiming at the problem that traditional point cloud feature description method is computation-intensive,smoothness parameter is adopted to conduct extracting point cloud features and improve the efficiency of point cloud re-gistration.Finally,the point-to-line and point-to-surface constraints between frames are established on the basis of the point cloud features,and the modified Levenberg-Marquardt method is utilized to realize point cloud registration,so as to construct a satis-fying 3D reconstruction model.The experimental results show that the proposed point cloud registration method is suitable for 3D reconstruction of indoor and outdoor scenes,with outstanding environmental adaptability.Meanwhile,the accuracy and efficiency of point cloud registration are greatly improved compared with the traditional methods.

Key words: 3D reconstruction, Point cloud registration, Point cloud feature, Smoothness, Levenberg-Marquardt

CLC Number: 

  • TP391
[1]TAMAS V,RALPH R M,JORDAN C.Reverse engineering of geometric models-an introduction [J].Computer-Aided Design,1997,29(4):255-268.
[2]ZENG L I,ZHANG W,YANG Y.Multiple density leaf reconstruction based on limited details [J].Computer Science,2016,43(8):292-296.
[3]TONG J,ZHOU J,LIU L G,et al.Scanning 3D full human bodies using Kinects [J].IEEE Transactions on Visualization and Computer Graphics,2012,18(4):643-650.
[4]MARANI R,RENO V,NITTI M,et al.A modified iterative closest point algorithm for 3D point cloud registration [J].Computer-Aided Civil Infrastructure Engineering,2016,31(7):515-534.
[5]GUO Y L,BENNAMOUN M,SOHEL F,et al.A comprehensive performance evaluation of 3D local feature descriptors [J].International Journal of Computer Vision,2016,116(1):66-89.
[6]CHENG L,TONG L H,LI M C,et al.Semi-automatic registration of airborne and terrestrial laser scanning data using building corner matching with boundaries as reliability check[J].Remote Sensing,2013,5(12):6260-6283.
[7]DANIELS I J,OCHOTTA T,HA L K,et al.Spline-based feature curves from point-sampled geometry [J].The Visual Computer,2008,24(6):449-462.
[8]RUSU R B,BLODOW N,BEETZ M.Fast point feature histograms (FPFH) for 3D registration[C]∥Proceedings of IEEE International Conference on Robotics and Automation.New York:IEEE Press,2009:1848-1853.
[9]BIGAND A,BOUWMANS T,DUBUS J P.A new stereo matching algorithm based on linear features and the fuzzy integral [J].Pattern Recognition Letters,2001,22(2):133-146.
[10]DAI J,YANG J.A novel two-stage algorithm for accurate registration of 3-D point clouds[C]∥Proceedings of the International Conference on Multimedia Technology.New York:IEEE Press,2011:6187-6191.
[11]SUN J,ZHANG J,ZHANG G.An automatic 3D point cloud registration method based on regional curvature maps[J].Ima-ge and Vision Computing,2016,56:49-58.
[12]CHOI S,ZHOU Q Y,KOLTUN V.Robust reconstruction of indoor scenes[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2015:5556-5565.
[13]BESL P J,MCKAY N D.A method for registration of 3-D shapes [J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1992,14(2):239-256.
[14]MAVRIDIS P,ANDREADIS A,PAPAIOANNOU G.Efficient Sparse ICP [J].Computer Aided Geometric Design,2015,35(C):16-26.
[15]FAN J F,YANG J,AI D,et al.Convex hull indexed Gaussian mixture model (CH-GMM) for 3D point set registration [J].Pattern Recognition,2016,59:126-141.
[16]DU S,LIU J,ZHANG C J.Probability iterative closest point algorithm for m-D point set registration with noise [J].Neurocomputing,2015,157:187-198.
[17]XU S Y,ZHU J H,LI Y C,et al.Effective scaling registration approach by imposing emphasis on scale factor [J].Electronics Letters,2018,54(7):422-424.
[18]SUN Z L.Research on filtering method of 3D laser scanning point cloud data [D].Hunan:Central South University,2011.
[19]GENG N,MA F F,YANG H J,et al.Neighboring Constraint-based pairwise point cloud registration algorithm [J].Multimedia Tools and Applications,2016,75(24):16763-16780.
[20]ZHOU R R,ZHANG L Y,SU X,et a1.Algorithmic research on surface reconstruction from dense scattered points [J].Journal of Software,2001,12(2):249-255.
[21]DEBAYLE J,PRESLES B.Rigid image registration by General Adaptive Neighborhood matching [J].Pattern Recognition,2016,55:45-57.
[22]BENTLEY J L.Multidimensional binary search trees used for associative searching [J].Communications of the ACM,1975,18(9):509-517.
[1] LI Jian, YANG Xiang-ru, HE Bin. Geometric Features Matching with Deep Learning [J]. Computer Science, 2019, 46(7): 274-279.
[2] MIAO Hui-cui, WANG Ji-hua, ZHANG Quan-ying. Concave-convex Manufacturing Features Recognition Based on 3D Reconstruction of Single View [J]. Computer Science, 2019, 46(7): 280-285.
[3] MENG Wen-quan, WU Li-sheng. Triangulation Reconstruction of Plantar Surface Based on Depth Feature [J]. Computer Science, 2019, 46(6A): 205-207.
[4] LIU Zhen-yu, GUAN Tong. Head Posture Detection Based on RGB-D Image [J]. Computer Science, 2019, 46(11A): 334-340.
[5] ZHOU Sheng-pu, GENG Guo-hua, LI Kang, WANG Piao. Multi-view Geometric 3D Reconstruction Method Based on AKAZE Algorithm [J]. Computer Science, 2018, 45(11A): 180-184,207.
[6] WANG Lin, HE Kun-jin and CHEN Zheng-ming. Template-based Method for Auto-measuring Bone Parameters [J]. Computer Science, 2017, 44(6): 270-273.
[7] GUO Wei-qing, TANG Yi-ping, LU Shao-hui and CHEN Qi. Review of 3D Stereo Vision Measure and Reconstruction Based on Mirror Image [J]. Computer Science, 2016, 43(9): 1-10, 22.
[8] ZHENG Jin-xin,TANG Zhi and WANG Yong-tao. Survey on 3D Reconstruction from Single Line Drawings [J]. Computer Science, 2014, 41(1): 43-47,79.
[9] WU Xiao-liang and TIAN Huai-wen. Method of 3D Reconstruction Based on Given Axonometric Sketching [J]. Computer Science, 2013, 40(9): 275-278,316.
[10] ZHANG Yi-peng,CHENG Liang and HAO Huan. LM Based Training Algorithm for Quantum Neural Networks [J]. Computer Science, 2013, 40(9): 221-224.
[11] . Improved Method of Global Optical Flow Estimation [J]. Computer Science, 2012, 39(Z6): 510-512.
[12] HU Yan,GENG Guo-hua,ZHOU Ming-quan,WANG Xiao-feng`. Stereo Matching Algorithm Based on Uncalibrated Color Images for 3D Reconstruction [J]. Computer Science, 2011, 38(7): 277-279,293.
[13] LI Lin-yao,ZHANG Zhao-xiang,WANG Yun-hong,WANG Chao. Motion-based 3D Reconstruction and Applications to Virtual Reality [J]. Computer Science, 2011, 38(7): 273-276.
[14] WU Xiao-rong,WU Xiao-ming. Feature Extraction from Cryo-EM Image Based on DoG [J]. Computer Science, 2010, 37(9): 276-278.
[15] WANG Hong-xia. Analysis of Facet-braiding Based on 3D Reconstruction of Integral Imaging [J]. Computer Science, 2010, 37(10): 248-250.
Full text



[1] SUN Zhao-ying,LIU Gong-shen. Research on Neural Network Clustering Algorithm for Short Text[J]. Computer Science, 2018, 45(6A): 392 -395 .
[2] YANG Xiao-hua, GAO Hai-yun. Improved Bayesian Algorithm Based Automatic Classification Method for Bibliography[J]. Computer Science, 2018, 45(8): 203 -207 .
[3] QIN Meng-na, CHEN Jun-jie, GUO Hao. Multi-feature Fusion Classification Method Based on High-order Minimum Spanning Tree Brain Network[J]. Computer Science, 2018, 45(7): 293 -298, 314 .
[4] SHEN Xia-jiong, ZHANG Jun-tao, HAN Dao-jun. Short-term Traffic Flow Prediction Model Based on Gradient Boosting Regression Tree[J]. Computer Science, 2018, 45(6): 222 -227,264 .
[5] LI Xiao-xin, WU Ke-song, QI Pan-pan, ZHOU Xuan and LIU Zhi-yong. Local Sphere Normalization Embedding:An Improved Scheme for PCANet[J]. Computer Science, 2018, 45(5): 238 -242, 249 .
[6] YU Wei, ZHENG Ji-ping, WANG Hai-xiang, WANG Yong-ge, CHEN Jia-liang and JIANG Shun-qing. Spatial Skyline Queries:Applications,Research and Challenges[J]. Computer Science, 2017, 44(2): 1 -16 .
[7] XIONG Li-rong, YOU Ri-jing, JIN Xin. Sensor-based Adaptive Rate Control Method for Mobile Streaming[J]. Computer Science, 2018, 45(10): 124 -129 .
[8] ZHANG Nan, XU Xin, TONG Xiang-rong, GAO Xue-yi and JIANG Li-li. Distribution Reduction in Inconsistent Interval-valued Decision Systems[J]. Computer Science, 2017, 44(9): 78 -82, 104 .
[9] NIE Kai, ZHOU Qing-lei, ZHU Wei-jun and ZHANG Chao-yang. Modeling for Three Kinds of Network Attacks Based on Temporal Logic[J]. Computer Science, 2018, 45(2): 209 -214 .
[10] YANG Pei-an, WU Yang, SU Li-ya, LIU Bao-xu. Overview of Threat Intelligence Sharing Technologies in Cyberspace[J]. Computer Science, 2018, 45(6): 9 -18,26 .