光学技术, 2018, 44 (5): 562, 网络出版: 2018-10-08   

基于保局PCA的三维点云配准算法

3D point cloud registration algorithm based on locality preserving PCA
作者单位
北京联合大学 信息学院, 北京 100101
摘要
三维点云配准是三维重建过程中的重要环节, PCA算法应用于点云配准时无法保留点云局部特征, 影响了配准效果, 故提出一种基于保局PCA的三维点云配准算法。为了保留点云局部特征, 采用保局投影LPP的思想, 通过K近邻准则构造点云的邻接图及其补图; 对邻近点和非邻近点采取不同的处理方式进行特征提取, 通过特征矩阵求得转换参数, 进行坐标归一化完成配准; 为了减少光照噪声影响, 对特征向量矩阵前三个主分量加权后求转换参数。实验结果表明, 改进算法在对局部特征结构明显的点云进行配准时有较好的效果, 改善了对光照噪声的鲁棒性。
Abstract
Three-dimensional point cloud registration is an important step to reconstruct three dimension model. The local feature of point cloud can not be retained and the registration effect is influenced when the PCA algorithm is applied to point cloud registration. A 3D point cloud registration algorithm based on locality preserving PCA is proposed. LPP projection is used to preserve the local characteristics of point cloud. LPP constructs the adjacency graph and its complement of point cloud through K-Nearest Neighbor Criterion.The feature extraction is carried out by using different processing methods for adjacent and non-nearest neighbors. The conversion parameters are obtained by the feature matrix, and the coordinates are normalized to complete point cloud registration. The purpose of finding the conversion parameters after weighting the first three principal components of the eigenvector matrix is to reduce the influence of illumination noise. The experimental results show that the improved algorithm has better effect in registration of the point cloud with obvious local feature structure, and the robustness to lighting noise is improved.
参考文献

[1] 陈兆学, 姚春荣. 基于OTSU多阈值分割算法的激光线扫点云数据表达及精简方法研究[J]. 光学技术,2016,42(5):435-440.

    Chen Zhaoxue, Yao Chunrong. Research on an expression & reduction method of laser point cloud data based on OTSU multi-threshold segmention algorithm [J]. Optical Technique,2016,42(5):435-440.

[2] 王勇, 唐靖, 饶勤菲, 等. 采用点云重心距离进行边界检测的点云数据配准[J]. 小型微型计算机系统,2015,36(9):2096-2101.

    Wang Yong, Tang Jing, Rao Qinfei, et al. Point clud data registration based on boundary detection by the center of mass distance feature [J]. Journal of Chinese Computer Systems,2015,36(9):2096-2101.

[3] 苏本跃, 马金宇, 彭玉升, 等. 面向RGBD深度数据的快速点云配准方法[J]. 中国图象图形学报,2017,22(5):643-655.

    Su Benyue, Ma Jinyu, Peng Yusheng, et al. Fast point cloud registration based on RGB-D data [J]. Journal of Image and Graphics,2017,22(5):643-655.

[4] Geng N, Ma F, Yang H, et al. Neighboring constraint-based pairwise point cloud registration algorithm [J]. Multimedia Tools & Applications,2016,75(24):16763-16780.

[5] 刘江, 张旭, 朱继文. 一种基于K-D树优化的ICP三维点云配准方法[J]. 测绘工程,2016,25(6):15-18.

    Liu Jiang, Zhang Xu, Zhu Jiwen. ICP three-dimenional point cloud registration based on K-D tree optimization [J]. Engineering of Surveying and Mapping,2016,25(6):15-18.

[6] Li W, Song P. A modified ICP algorithm based on dynamic adjustment factor for registration of point cloud and CAD model [J]. Pattern Recognition Letters,2015,65:88-94.

[7] Chung D H, Yun I D, Sang U L. Registration of multiple-range views using the reverse-calibration technique [J]. Pattern Recognition,1998,31(4):457-464.

[8] 薛耀红. 点云数据配准及曲面细分技术研究[D]. 长春:吉林大学,2010.

    Xue Yaohong. Research on technology of point clouds resgistation anf subdivision surface [D]. Changchun:Jilin University,2010.

[9] Lin B, Tamaki T, Zhao F, et al. Scale alignment of 3D point clouds with different scales [J]. Machine Vision & Applications, 2014,25(8):1989-2002.

[10] He X, Niyogi P. Locality preserving projections [J]. Advances in Neural Information Processing Systems,2003,16(1):186-197.

[11] 赵鑫, 汪维家, 曾雅云, 等. 改进的模块PCA人脸识别新算法[J]. 计算机工程与应用,2015,51(2):161-164.

    Zhao Xin, Wang Weijia, Zeng Yang, et al. Improved modular PCA face recognition algorithm [J]. Computer Engineer and Application,2015,51(2):161-164.

[12] 舒程珣, 何云涛, 孙庆科. 基于卷积神经网络的点云配准方法[J]. 激光与光电子学进展,2017(3):123-131.

    Shu Chengxun, He Yuntao, Sun Qingke. Point cloud registration base on convalutional neural network [J]. Computer Engineering and Applications,2017(3):123-131.

[13] 梁胜杰, 张志华, 崔立林, 等. 基于主成分分析与核独立成分分析的降维方法[J]. 系统工程与电子技术,2011,33(9): 2144-2148.

    Liang Shengjie, Zhang Zhihua, Cui Lilin, et al. Dimensionality reduction method based on PCA and KICA [J]. Systems Engineering and Electronics,2011,33(9):2144-2148.

[14] 辜小花, 龚卫国, 杨利平. 有监督图优化保局投影[J]. 光学精密工程,2011,19(3):672-680.

    Gu Xiaohua, Gong Weiguo, Yang Liping. Supercised graph-optimized locality presering projections [J]. Optics and Precision Engineering,2011,19(3):672-680.

[15] 黄璞, 唐振民. 无参数局部保持投影及人脸识别[J]. 模式识别与人工智能,2013,26(9):865-871.

    Huang Pu, Tang Zhenmin. Parameter-free locality preserving projections and face recognition [J]. Pattern Recognition and Artificial Intelligence,2013,26(9):865-871.

[16] 屠良平, 魏会明, 王志衡, 等. 基于局部均值的K-近质心近邻光谱分类[J]. 光谱学与光谱分析,2015,35(4):1103-1106.

    Tu Liangping, Wei Huiming, Wang Zhiheng, et al. Spectra classification based on lacal mean-based K-nearest centroid nerghbor method [J]. Spectroscopy and Spectral Analysis, 2015,35(4):1103-1106.

[17] 张顺岚, 莫建文, 邹路路. 基于K近邻和法向精度的点云精简算法[J]. 武汉理工大学学报,2014,38(3):572-574.

    Zhang Shunlan, Mo Jianwen, Zhou Lulu. Point cloud simplification algorithm based on K neighbor and normal accuracy [J]. Journal of Wuhan University of Technology, 2014,38(3):572-574.

[18] 王可, 唐忠辉, 孙兴伟. 基于拉格朗日乘数法对曲线点云数据的光顺处理[J]. 沈阳工业大学学报,2013(3): 309-313.

    Wang Ke, Tang Zhonghui, Sun Xingwei. Fairing processing of curve point cloud data based on lagrange multiplier method [J]. Journal of Shenyang University of Technology, 2013(3): 309-313.

王育坚, 吴明明, 高倩. 基于保局PCA的三维点云配准算法[J]. 光学技术, 2018, 44(5): 562. WANG Yujian, WU Mingming, GAO Qian. 3D point cloud registration algorithm based on locality preserving PCA[J]. Optical Technique, 2018, 44(5): 562.

该篇论文已被引用 1
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!