大视角变化下点云配准方法研究  

Research on point cloud registration algorithm under large viewing changes

作　　者：马晓敏 杨烨 朱磊[1] 姚新阳 赵子仪 Ma Xiaomin;Yang Ye;Zhu Lei;Yao Xinyang;Zhao Ziyi(School of Electronics and Information,Xi'an Polytechnic University,Xi'an 71o048,China)

机构地区：[1]西安工程大学电子信息学院,西安710048

出　　处：《电子测量技术》2022年第21期54-60,共7页Electronic Measurement Technology

基　　金：陕西省科技厅一般青年项目(2022JQ-711);西安市科技计划项目(21XJZZ0022);西安工程大学大学生创新训练计划项目(2021013)资助。

摘　　要：为了提高大视角变化下点云配准的精度和效率,本文提出了一种基于仿射不变特征点云提纯与改进随机梯度下降法的点云配准方法。该方法首先获取具有抗视角变化能力的二维特征匹配点,并借助特征点云的空间拓扑关系设计点云提纯方法来估计点云初始位姿变换;然后,在随机梯度下降法的基础上,设计聚类近邻快速搜索策略以提高点云对应点的查找效率,概率地动态调整随机梯度下降法的学习率以提高配准的全局收敛性。实验结果表明,本文方法对大视角改变时的点云配准具有很好的适应性,能够有效提高配准的精确度和配准效率。In order to improve the accuracy and efficiency of point cloud registration when there are large view changes, a point cloud registration method based on affine-invariant feature cloud purification and improved stochastic gradient descent is proposed in this paper. Firstly, the 2 D feature matches with the ability to resist the change of view changes are obtained, and the point cloud purification method is designed to estimate the initial pose transformation of the point cloud based on the spatial topological relationship of the feature cloud. Then, on the basis of stochastic gradient descent method, a fast clustering nearest neighbor search strategy is designed to enhance the efficiency of searching for the corresponding points. The learning rate of the stochastic gradient descent is dynamically adjusted in probability to improve the global convergence. The experimental results show that the proposed point cloud registration method has a good adaptability to large viewing changes, and can effectively improve the accuracy and efficiency of registration.

关 键 词：点云配准 仿射不变特征 点云提纯 随机梯度下降 学习率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]