随着三维激光扫描技术的快速发展,点云数据在自动驾驶、三维建模、医学研究、逆向工程、乡村振兴等领域得到了广泛的应用。但是由于受到仪器性能、周围环境以及被扫描目标本身特性的影响,扫描获取的点云数据往往包含大量噪声,严重影响...随着三维激光扫描技术的快速发展,点云数据在自动驾驶、三维建模、医学研究、逆向工程、乡村振兴等领域得到了广泛的应用。但是由于受到仪器性能、周围环境以及被扫描目标本身特性的影响,扫描获取的点云数据往往包含大量噪声,严重影响后续点云处理的准确度,因此有必要对其进行去噪处理。针对传统滤波算法对参敏感性不强、计算复杂度高、几何特征保持性差等问题,提出一种几何特征保持的层次化点云去噪算法。首先,该算法在半径滤波算法中引入点云密度特征以改进初始参数选取,实现大尺度噪声去除;然后,利用KD树(K-Dimensional Tree)优化基于密度的噪声应用空间聚类(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)算法,并结合角点特征对DBSCAN算法的参数实现自适应选取,从而将点云数据分为有效簇、模糊簇和噪声簇,去除噪声簇;最后,利用距离共识评估算法对模糊簇进行判定,通过计算模糊点与点云拟合曲面之间的距离来判断是否为噪声点,以完成对点云小尺度噪声的去除。实验采用公共点云数据集和实地采集的乡村点云数据验证所提算法,结果表明,与DBSCAN算法、改进森林去噪法、几何特征保持去噪法、改进密度聚类去噪法和多特征网格去噪法相比,所提算法的尖锐几何特征保持性更佳,去噪精度分别提高了约43%,27%,29%,21%和9%。该算法可以在有效保持几何特征的同时提高去噪精度,是一种有效的点云去噪算法。展开更多
For space-borne gravitational wave detection missions based on the heterodyne interferometry principle,tilt-to-length(TTL)coupling noise is an important optical noise source,significantly influencing the accuracy of t...For space-borne gravitational wave detection missions based on the heterodyne interferometry principle,tilt-to-length(TTL)coupling noise is an important optical noise source,significantly influencing the accuracy of the measurement system.We present a method for analyzing TTL coupling noise under the joint influence of multiple factors.An equivalent simulated optical bench for the test mass interferometer was designed,and Gaussian beam tracing was adopted to simulate beam propagation.By simulating the interference signal,it can analyze the impact of various factors on the TTL coupling noise,including positional,beam parameters,detector parameters,and signal definition factors.On this basis,a random parameter space composed of multiple influential factors was constructed within a range satisfying the analysis requirement,and the corresponding simulation results from random sampling were evaluated via variance-based global sensitivity analysis.The calculated results of the main and total effect indexes show that the test mass rotation angle and the piston effect(lateral)significantly influence the TTL coupling noise in the test mass interferometer.The analysis provides a qualitative reference for designing and optimizing space-borne laser interferometry systems.展开更多
为实现对非平稳、非线性股票价格时间序列的高精度预测,提出经验模态分解下基于支持向量回归的股票价格集成预测方法EMD-SVRF(EMD and SVR based stock price integrated forecasting)。首先,运用经验模态分解方法获得股票对数收益率时...为实现对非平稳、非线性股票价格时间序列的高精度预测,提出经验模态分解下基于支持向量回归的股票价格集成预测方法EMD-SVRF(EMD and SVR based stock price integrated forecasting)。首先,运用经验模态分解方法获得股票对数收益率时间序列的本征模函数及趋势序列,然后,利用ε不敏感支持向量回归为各本征模函数及趋势序列分别建立预测模型,并计算各本征模函数及趋势项的预测值,最后,集成得到股票收益率序列预测值。实验表明,相对现有的EMD-Elman网络和ARMA-GARCH等主流股价预测方法,EMD-SVRF具有更小的拟合误差和预测误差,是一种高精度的股票价格预测方法。展开更多
文摘随着三维激光扫描技术的快速发展,点云数据在自动驾驶、三维建模、医学研究、逆向工程、乡村振兴等领域得到了广泛的应用。但是由于受到仪器性能、周围环境以及被扫描目标本身特性的影响,扫描获取的点云数据往往包含大量噪声,严重影响后续点云处理的准确度,因此有必要对其进行去噪处理。针对传统滤波算法对参敏感性不强、计算复杂度高、几何特征保持性差等问题,提出一种几何特征保持的层次化点云去噪算法。首先,该算法在半径滤波算法中引入点云密度特征以改进初始参数选取,实现大尺度噪声去除;然后,利用KD树(K-Dimensional Tree)优化基于密度的噪声应用空间聚类(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)算法,并结合角点特征对DBSCAN算法的参数实现自适应选取,从而将点云数据分为有效簇、模糊簇和噪声簇,去除噪声簇;最后,利用距离共识评估算法对模糊簇进行判定,通过计算模糊点与点云拟合曲面之间的距离来判断是否为噪声点,以完成对点云小尺度噪声的去除。实验采用公共点云数据集和实地采集的乡村点云数据验证所提算法,结果表明,与DBSCAN算法、改进森林去噪法、几何特征保持去噪法、改进密度聚类去噪法和多特征网格去噪法相比,所提算法的尖锐几何特征保持性更佳,去噪精度分别提高了约43%,27%,29%,21%和9%。该算法可以在有效保持几何特征的同时提高去噪精度,是一种有效的点云去噪算法。
文摘For space-borne gravitational wave detection missions based on the heterodyne interferometry principle,tilt-to-length(TTL)coupling noise is an important optical noise source,significantly influencing the accuracy of the measurement system.We present a method for analyzing TTL coupling noise under the joint influence of multiple factors.An equivalent simulated optical bench for the test mass interferometer was designed,and Gaussian beam tracing was adopted to simulate beam propagation.By simulating the interference signal,it can analyze the impact of various factors on the TTL coupling noise,including positional,beam parameters,detector parameters,and signal definition factors.On this basis,a random parameter space composed of multiple influential factors was constructed within a range satisfying the analysis requirement,and the corresponding simulation results from random sampling were evaluated via variance-based global sensitivity analysis.The calculated results of the main and total effect indexes show that the test mass rotation angle and the piston effect(lateral)significantly influence the TTL coupling noise in the test mass interferometer.The analysis provides a qualitative reference for designing and optimizing space-borne laser interferometry systems.
文摘为实现对非平稳、非线性股票价格时间序列的高精度预测,提出经验模态分解下基于支持向量回归的股票价格集成预测方法EMD-SVRF(EMD and SVR based stock price integrated forecasting)。首先,运用经验模态分解方法获得股票对数收益率时间序列的本征模函数及趋势序列,然后,利用ε不敏感支持向量回归为各本征模函数及趋势序列分别建立预测模型,并计算各本征模函数及趋势项的预测值,最后,集成得到股票收益率序列预测值。实验表明,相对现有的EMD-Elman网络和ARMA-GARCH等主流股价预测方法,EMD-SVRF具有更小的拟合误差和预测误差,是一种高精度的股票价格预测方法。
