一种基于球邻域空间体素切分的特征描述方法  

A feature description method based on voxel partitionin spherical neighborhood space

作　　者：张健[1] 杨炯 ZHANG Jian;YANG Jiong(School of Mechanical and Power Engineering,Zhengzhou University,Zhengzhou 450001,China)

机构地区：[1]郑州大学机械与动力工程学院,郑州450001

出　　处：《重庆理工大学学报（自然科学）》2023年第4期182-191,共10页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金青年基金项目(51705469);郑州大学青年人才企业合作创新团队支持计划项目(2021);工信部高技术船舶科研项目(〔2019〕360)。

摘　　要：针对复杂干扰场景中3D特征描述子描述性和稳定性低的问题,提出了一种基于球邻域空间体素切分的特征描述方法。此方法由一种稳定的局部参考坐标系LRF(local reference frame)和一种基于体素表达的特征描述子组成。对于LRF,以加权的协方差矩阵计算Z轴,以加权的点云投影向量之和作为X轴,Y轴由二轴的叉乘得到。对于特征描述子,对球邻域进行空间切分,通过判断每个空间体素内是否含有点来确定体素标签值,最后按照体素索引编码得到该关键点的特征信息。实验证明:该方法相比于其他描述子,对噪声、点云表面分布不均、散乱遮挡等干扰具有优异的性能,并且具有良好的泛化性,配准实验进一步验证了该描述子的有效性。Aiming at low description and stability of 3D feature descriptors in complex interference scenes,this paper proposes a feature description method based on voxel partition in spherical neighborhood space.This method consists of a stable local reference frame(LRF)and a feature descriptor based on voxel expression.For LRF,the Z-axis is calculated through the weighted covariance matrix,the sum of the weighted point cloud projection vectors is taken as the X-axis,and the Y-axis is obtained by the cross multiplication of the two axes.For feature descriptors,the spherical neighborhood is spatially divided,and the voxel label value is determined by judging whether there are points in each spatial voxel.Finally,the feature information of the key points is encoded according to the voxel index.The experiments show that,compared with other descriptors,this method has excellent performance against noise,uneven distribution of point cloud surface,scattered occlusion and other interference,and has good generalization.The registration experiments further verify the effectiveness of this descriptor.

关 键 词：LRF 体素切分 特征提取 特征描述 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]