庄恩泽;吴献;

• 1:福建师范大学软件学院

摘要(Abstract)：

针对三维重建中点云特征点检测问题,提出了一种基于点云的最小核值相似区(SUSAN)特征点检测算法,并将其应用于三维重建的初始配准.首先,对待测点云进行遍历,利用kd-tree数据结构获取三维r-邻域核值相似区,计算得到点云的候选特征点;其次,使用快速点特征直方图对候选点进行特征描述并实现两幅点云特征点间的匹配;最后,利用奇异值矩阵分解法计算变换矩阵,完成两幅点云的初始配准.实验结果表明该特征点检测算法计算效率较高,产生的特征点匹配准确,可为精确配准提供较好的初始位置.

关键词(KeyWords)： 三维重建;SUSAN算子;特征描述;快速点特征直方图;迭代最近点算法

Abstract:

Keywords:

基金项目(Foundation): 福建省教育厅资助项目(JA12079);; 福建师范大学教学改革研究项目(I201503039)

作者(Authors): 庄恩泽;吴献;

参考文献(References)：

• [1]IZADI S,NEWCOMBE RA,KIM D,et al.Kinect Fusion:real-time dynamic 3D surface reconstruction and interaction[C]∥ACM SIGGRAPH,2011:1175-1184.
• [2]TONG J,ZHOU J,LIU L,et al.Scanning 3D full human bodies using kinects[J].IEEE Transactions on Visualization&Computer Graphics,2012,18(4):643-650.
• [3]PANG X,LAU R,SONG Z,et al.A tool-free calibration method for turntable-based 3D scanning systems.[J].IEEE Computer Graphics&Applications,2014,36(1):52-61.
• [4]程效军,贾东峰,程小龙.海量点云数据处理理论与技术[M].上海:同济大学出社,2014:43-44.
• [5]YANG R,ALLEN P K.Registering,integrating,and building CAD models from range data[C]∥IEEE International Conference on Robotics&Automation,1998:3115-3120.
• [6]HIGUCHI K,HEBERT M,IKEUCHI K.Building 3-D models from unregistered range images[C]∥IEEE International Conference on Robotics&Automation,2001:41-75.
• [7]梅峰,刘京,李淳芃,等.基于RGB-D深度相机的室内场景重建[J].中国图象图形学报,2015,20(10):1366-1373.
• [8]BESL P J,MCKAY H D.A method for registration of 3-D shapes[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1992,14(2):239-256.
• [9]RADU B S,RUSU B,KONOLIGE K,et al.NARF:3D range image features for object recognition[C]∥IROSW,2010.
• [10]杨荣,冯有前,袁修久.利用现有模型修复不完整三维模型[J].计算机辅助设计与图形学学报,2015,27(1):98-105.
• [11]CASTELLANI U,CRISTANI M,FANTONI S,et al.Sparse points matching by combining 3D mesh saliency with statistical descriptors[J].Computer Graphics Forum,2008,27(2):643-652.
• [12]杨红娟,陈继文,张运楚,等.基于SIFT特征的低区分度点云数据匹配[J].计算机辅助设计与图形学学报,2016,28(3):498-504.
• [13]ZHANG L,DING Z,LI H,et al.3D face recognition based on multiple keypoint descriptors and sparse representation.[J].Plos One,2014,9(6):e100120.
• [14]SIPIRAN I,BUSTOS B.A robust 3D interest points detector based on harris operator[C]∥Eurographics Workshop on3D Object Retrieval,Norrkping,2010:87-88.
• [15]Díez Y,Roure F,LladóX,et al.A qualitative review on 3D coarse registration methods[J].Acm Computing Surveys,2015,47(3):1-36.
• [16]PAULA I C,MEDEIROS F N S,BEZERRA F N,et al.Multiscale corner detection in planar shapes[J].Journal of Mathematical Imaging and Vision,2013,45(3):251-263.
• [17]刘力维.基于TOF深度摄像机的深度超分辨率恢复和深度融合研究[D].杭州:浙江大学,2014.
• [18]RUSU R B,BLODOW N,BEETZ M.Fast point feature histograms(FPFH)for 3D registration[C]∥IEEE International Conference on Robotics and Automation,2009:3212-3217.