师 乐,罗 钧,何小妹.基于高斯过程模型的多源点云数据融合方法[J].电子测量与仪器学报,2023,37(2):65-75 |
基于高斯过程模型的多源点云数据融合方法 |
Multi-source point cloud data fusion method based on Gaussian process model |
|
DOI: |
中文关键词: 多传感器测量 数据融合 自适应距离 点云配准 高斯过程 |
英文关键词:multi-sensor measurement data fusion adaptive distance point cloud registration Gaussian process |
基金项目:国家科技重大专项(J2019-VIII-0015-0176)项目资助 |
|
|
摘要点击次数: 686 |
全文下载次数: 972 |
中文摘要: |
多传感器测量技术被认为是表面计量学中一个很有效的解决方案。 针对多源数据的融合问题,本文提出了一种基于高
斯过程模型的多源点云数据融合框架。 首先,提出一种自适应距离的鲁棒点云配准方法统一不同测量数据集的坐标系;然后,
通过引入平差理论,对来自不同传感器的多个独立数据集之间的残差进行近似,构建基于 Matern 核函数的高斯过程模型;最
后,通过仿真模拟和实际应用,与现有方法进行了一系列对比实验,验证了该方法的有效性。 实验结果表明,该方法能以更高的
融合精度和更快的计算效率融合多传感器数据集。 |
英文摘要: |
Multi-sensor measurement technology is considered to be a very effective solution in surface metrology. Aiming at the problem
of modeling and fusion of multi-scale complex data sets, this paper proposes a multi-source point cloud data fusion framework based on
Gaussian process. Firstly, a robust point cloud registration method with adaptive distance is proposed to unify coordinate systems of
different measurement datasets. Then, by introducing adjustment theory, the residuals between multiple independent data sets from
different sensors are approximated, and a Gaussian process model based on Matern kernel function is constructed. Finally, the method is
verified by simulation verification and practical application, and a series of comparative experiments with existing methods are carried out
to verify the effectiveness of the method. The results show that the method can fuse multi-sensor datasets with higher fusion accuracy and
faster computational efficiency. |
查看全文 查看/发表评论 下载PDF阅读器 |