基于显著性峰值与特征对齐的点云配准模型  

Point Cloud Registration Model Based on Significance Peak and Feature Alignment

作　　者：张富凯 张露露 张海燕[3] 张艳梅[4] 袁冠[4] 赵珊[1] 王登科[2] 霍占强[1] 陈玮[1] ZHANG Fukai;ZHANG Lulu;ZHANG Haiyan;ZHANG Yanmei;YUAN Guan;ZHAO Shan;WANG Dengke;HUO Zhanqiang;CHEN Wei(School of Software,Henan Polytechnic University,Jiaozuo 454000,China;State Key Laboratory Cultivation Base for Gas Geology and Gas Control,Henan Polytechnic University,Jiaozuo 454000,China;School of Computer Science and Technology,Henan Polytechnic University,Jiaozuo 454000,China;School of Computer Science and Technology,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[1]河南理工大学软件学院,河南焦作454000 [2]河南理工大学河南省瓦斯地质与瓦斯治理重点实验室,河南焦作454000 [3]河南理工大学计算机科学与技术学院,河南焦作454000 [4]中国矿业大学计算机科学与技术学院,江苏徐州221116

出　　处：《湖南大学学报(自然科学版)》2025年第4期34-43,共10页Journal of Hunan University:Natural Sciences

基　　金：国家自然科学基金资助项目(71774159,52174174);河南省科技攻关项目(252102320210);河南省高等学校重点科研项目(24B520014);河南理工大学青年骨干教师资助计划(2023XQG-14)。

摘　　要：点云配准的核心是估算变换矩阵.两个点云对之间存在部分重叠、高噪声和密度差异,现有方法无法精确解决显著点云对应关系之间特征对齐问题.因此,提出显著性峰值与特征对齐网络(significance peak and feature alignment network,SPFANet),实现由粗到细的点云配准.SPFANet由多显著性峰值检测器、粗配准和细配准三部分组成.首先,多显著性峰值检测器引入一种基于描述符方差和重叠分数重加权峰值损失方法,去除非歧视与非重叠的关键点云;其次,粗配准阶段通过检测互补关键点集来计算粗步的配准方案;最后,细配准阶段引入带有前向后向变换的特征度量框架细化粗配准,完成高效点云配准.在同源3DMatch数据集和跨源3DCSR数据集上的实验验证了SPFANet的有效性.The core of point cloud registration is to estimate the transformation matrix.There is partial overlap,high noise,and density difference between two point cloud pairs.The existing methods cannot accurately solve the problem of feature alignment between significant point cloud correspondences.Therefore,a significance peak and feature alignment network(SPFANet)is proposed to achieve point cloud registration from coarse to fine one.SPFANet consists of three parts:multi-significance peak detector,coarse registration,and fine registration.Firstly,the multi-significance peak detector introduces a re-weighted peak loss method based on descriptor variance and overlap score to remove non discriminatory and non overlapping key point clouds.Secondly,the coarse registration stage detects the complementary key point sets to compute the coarse registration scheme.Finally,the fine registration stage introduces a feature metric framework with a forward-backward transform to refine the coarse registration scheme and achieve efficient point cloud registration.The effectiveness of SPFANet is validated through experiments on the same source 3DMatch dataset and cross-source 3DCSR dataset.

关 键 词：点云配准 跨源点云 多显著性峰值检测 特征度量 重加权峰值损失 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]