Improved Method of Point Cloud Registration Based on FPFH Feature

doi:10.3969/j.issn.1006-2475.2017.11.009

Abstract

Abstract: ICP algorithm is the most commonly used algorithm in point cloud registration, and the FPFH feature can provide initial matching information to register point cloud. An improved method based on FPFH feature registration of point cloud is proposed. Firstly, the Bhattacharyya distance between the FPFH features of two point clouds is calculated. The k-d tree is used to retrieve the corresponding points with the smallest Bhattacharyya distance. Then, the initial transformation matrix is calculated, the ICP algorithm gets the final transformation matrix. Experiment shows that the method has higher accuracy under the same iterations.

Key words: Bhattacharyya distance, FPFH, point cloud feature, point cloud registration

CLC Number:

TP391.41

MA Da-he, LIU Guo-zhu. Improved Method of Point Cloud Registration Based on FPFH Feature[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2017.11.009.

References

[1] 胡晓彤,王建东. 基于子空间特征向量的三维点云相似性分析[J]. 红外与激光工程, 2014,43(4):1316-1321.

[2] 孙晓鹏,王冠,王璐,等. 3D点云形状特征的二维主流形描述[J]. 软件学报, 2015,26(3):699-709.

[3] Tatsuma A, Aono M. Multi-Fourier spectra descriptor and augmentation with spectral clustering for 3D shape retrieval[J]. The Visual Computer, 2009,25(8):785-804.

[4] De Oliveira W A A, Barcelos C A Z, Giraldi G, et al. HSD: A 3D shape descriptor based on the Hilbert curve and a reduction dimensionality approach[C]// Proceedings of the 2012 IEEE International Conference on Systems, Man, and Cybernetics. 2012:156-161.

[5] Johnson A E. Spin-Images: A Representation for 3-D Surface Matching[D]. Pittsburgh: The Robotics Institute, Carnegie Mellon University, 1997.

[6] Frome A, Huber D, Kolluri R, et al. Recognizing objects in range data using regional point descriptors[C]// Proceedings of the 2004 European Conference on Computer Vision. 2004:224-237.

[7] Mian A S, Bennamoun M, Owens R A. A novel representation and feature matching algorithm for automatic pairwise registration of range images[J]. International Journal of Computer Vision, 2006,66(1):19-40.

[8] Rusu R B, Blodow N, Beetz M. Fast point feature histograms (FPFH) for 3D registration[C]// Proceedings of the 2009 IEEE International Conference on Robotics and Automation. 2009:3212-3217.

[9] Rusu R B, Marton Z C, Blodow N, et al. Persistent point feature histograms for 3D point clouds[C]// Proceedings of the 10th International Conference on Autonomous Systems. 2008:119-128.

[10] 艾达,王苗,倪国斌. 基于FPFH特征的三维场景重建[J]. 计算机测量与控制, 2016,24(7):232-236.

[11] 郭裕兰,鲁敏,谭志国,等. 距离图像局部特征提取方法综述[J]. 模式识别与人工智能, 2012,25(5):783-791.

[12] Rusu R B, Holzbach A, Blodow N, et al. Fast geometric point labeling using conditional random fields[C]// Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2009:7-12.

[13] 朱延娟,周来水,张丽艳. 散乱点云数据配准算法[J]. 计算机辅助设计与图形学学报, 2006,18(4):475-481.

[14] Besl P J, McKay N D. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992,14(2):239-256.

[15] 朱新宇,万剑华,刘善伟,等. 改进的ICP点云配准算法[J]. 海洋测绘, 2015,35(2):77-79.

[16] Choi E, Lee C. Feature extraction based on the Bhattacharyya distance[J]. Pattern Recognition, 2003,36(8):1703-1709.

[17] 焦良葆,陈瑞,张健. 一个新的线索KD树并行算法[J]. 工程图学学报, 2011,32(5):46-50.