The detection of outliers and change points from time series has become research focus in the area of time series data mining since it can be used for fraud detection, rare event discovery, event/trend change detectio...The detection of outliers and change points from time series has become research focus in the area of time series data mining since it can be used for fraud detection, rare event discovery, event/trend change detection, etc. In most previous works, outlier detection and change point detection have not been related explicitly and the change point detections did not consider the influence of outliers, in this work, a unified detection framework was presented to deal with both of them. The framework is based on ALARCON-AQUINO and BARRIA's change points detection method and adopts two-stage detection to divide the outliers and change points. The advantages of it lie in that: firstly, unified structure for change detection and outlier detection further reduces the computational complexity and make the detective procedure simple; Secondly, the detection strategy of outlier detection before change point detection avoids the influence of outliers to the change point detection, and thus improves the accuracy of the change point detection. The simulation experiments of the proposed method for both model data and actual application data have been made and gotten 100% detection accuracy. The comparisons between traditional detection method and the proposed method further demonstrate that the unified detection structure is more accurate when the time series are contaminated by outliers.展开更多
发现在二幅图象之间的可靠的相应的点是在计算机视觉的一个基本问题，特别与 L 视觉框架的发展。这篇论文介绍歧管的通讯并且建议一个新奇计划由听说向上的看法拒绝孤立点歧管。建议计划独立于在出版工作要估计并且克服可得到的方法的...发现在二幅图象之间的可靠的相应的点是在计算机视觉的一个基本问题，特别与 L 视觉框架的发展。这篇论文介绍歧管的通讯并且建议一个新奇计划由听说向上的看法拒绝孤立点歧管。建议计划独立于在出版工作要估计并且克服可得到的方法的下列限制的参量的模型：效率严厉地因孤立点百分比的增加和估计的模型参数的数字倒下；孤立点拒绝被结合模型选择和模型评价。真实图象对的实验显示出我们的建议计划的优秀性能。展开更多
Precise point positioning (PPP)-based deformation monitoring scheme is presented for the use in mining deformation monitoring. Within the solutions of daily observation, outliers are detected and removed to avoid any ...Precise point positioning (PPP)-based deformation monitoring scheme is presented for the use in mining deformation monitoring. Within the solutions of daily observation, outliers are detected and removed to avoid any potential misinterpretation of the results and then the deformation can be extracted by the coordinate differences between the two consecutive solutions. Meanwhile, because of the special location of a rover station in mining areas, the satellite geometry may be insufficient for a reasonable PPP solution, and the multipath impact an also be significant. Therefore, it is necessary to predict the satellite geometry before any daily observation. To evaluate the ability of extracting the deformation using the PPP-based method, various quality measures were introduced. The results of three datasets of the same station show that the precision of deformation monitored by PPP can reach up to cm level and even mm level.展开更多
针对传统多尺度模型对模型点云比较方法(Multiscale Model to Model Cloud Comparison,M3C2)计算法向量与形变量时易受离群点影响的缺点,提出一种基于离群点探测准则的改进算法。首先,在估计关键点法向量时,依据改进离群点探测准则迭代...针对传统多尺度模型对模型点云比较方法(Multiscale Model to Model Cloud Comparison,M3C2)计算法向量与形变量时易受离群点影响的缺点,提出一种基于离群点探测准则的改进算法。首先,在估计关键点法向量时,依据改进离群点探测准则迭代剔除离群点,提高法向量估计的准确性,然后,通过离群点探测剔除圆柱内离群点,最后,结合正态分布加权计算形变量。实验结果表明,相较于M3C2原始算法,改进算法将法向量均方差精度指标提升50%以上,在形变量较大区域可将形变量估值均方差精度指标提高200%以上。改进算法具有更好的适用性和可靠性。展开更多
基于特征的点云配准技术利用点云局部特征建立对应点,但受噪声和重复结构影响,对应点结果不可避免地包含了大量错误匹配,导致配准精度降低。为充分利用离散点间几何信息优化同平台点云配准精度,本文提出了基于空间一致性的同平台点云配...基于特征的点云配准技术利用点云局部特征建立对应点,但受噪声和重复结构影响,对应点结果不可避免地包含了大量错误匹配,导致配准精度降低。为充分利用离散点间几何信息优化同平台点云配准精度,本文提出了基于空间一致性的同平台点云配准方法,该方法通过增加候选匹配点构建同平台点云图模型,为获取图模型的最优匹配结果,提出了重加权随机游走匹配(reweight random walks matching,RRWM)的优化方法。基于假设验证方法构建了点云配准模型,并结合试验验证了本文方法的有效性。展开更多
基金Project(2011AA040603) supported by the National High Technology Ressarch & Development Program of ChinaProject(201202226) supported by the Natural Science Foundation of Liaoning Province, China
文摘The detection of outliers and change points from time series has become research focus in the area of time series data mining since it can be used for fraud detection, rare event discovery, event/trend change detection, etc. In most previous works, outlier detection and change point detection have not been related explicitly and the change point detections did not consider the influence of outliers, in this work, a unified detection framework was presented to deal with both of them. The framework is based on ALARCON-AQUINO and BARRIA's change points detection method and adopts two-stage detection to divide the outliers and change points. The advantages of it lie in that: firstly, unified structure for change detection and outlier detection further reduces the computational complexity and make the detective procedure simple; Secondly, the detection strategy of outlier detection before change point detection avoids the influence of outliers to the change point detection, and thus improves the accuracy of the change point detection. The simulation experiments of the proposed method for both model data and actual application data have been made and gotten 100% detection accuracy. The comparisons between traditional detection method and the proposed method further demonstrate that the unified detection structure is more accurate when the time series are contaminated by outliers.
基金Supported by National Natural Science Foundation of China （60675020, 60773132）, Natural Science Foundation of Shandong Province （Q2007G02）, and Opening Task-fund for National Laboratory of Pattern Recognition
文摘发现在二幅图象之间的可靠的相应的点是在计算机视觉的一个基本问题，特别与 L 视觉框架的发展。这篇论文介绍歧管的通讯并且建议一个新奇计划由听说向上的看法拒绝孤立点歧管。建议计划独立于在出版工作要估计并且克服可得到的方法的下列限制的参量的模型：效率严厉地因孤立点百分比的增加和估计的模型参数的数字倒下；孤立点拒绝被结合模型选择和模型评价。真实图象对的实验显示出我们的建议计划的优秀性能。
基金Projects(40904004,41074010)supported by the National Natural Science Foundation of ChinaProject(BK2009099)supported by the Natural Science Fund of Jiangsu Province,China+2 种基金Project supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions,ChinaProjects(200802901516,200802900501)supported by the Ph.D.Programs Foundation of Ministry of Education of ChinaProject supported by the Qing Lan Project of Jiangsu Province,China
文摘Precise point positioning (PPP)-based deformation monitoring scheme is presented for the use in mining deformation monitoring. Within the solutions of daily observation, outliers are detected and removed to avoid any potential misinterpretation of the results and then the deformation can be extracted by the coordinate differences between the two consecutive solutions. Meanwhile, because of the special location of a rover station in mining areas, the satellite geometry may be insufficient for a reasonable PPP solution, and the multipath impact an also be significant. Therefore, it is necessary to predict the satellite geometry before any daily observation. To evaluate the ability of extracting the deformation using the PPP-based method, various quality measures were introduced. The results of three datasets of the same station show that the precision of deformation monitored by PPP can reach up to cm level and even mm level.
文摘针对传统多尺度模型对模型点云比较方法(Multiscale Model to Model Cloud Comparison,M3C2)计算法向量与形变量时易受离群点影响的缺点,提出一种基于离群点探测准则的改进算法。首先,在估计关键点法向量时,依据改进离群点探测准则迭代剔除离群点,提高法向量估计的准确性,然后,通过离群点探测剔除圆柱内离群点,最后,结合正态分布加权计算形变量。实验结果表明,相较于M3C2原始算法,改进算法将法向量均方差精度指标提升50%以上,在形变量较大区域可将形变量估值均方差精度指标提高200%以上。改进算法具有更好的适用性和可靠性。
文摘基于特征的点云配准技术利用点云局部特征建立对应点,但受噪声和重复结构影响,对应点结果不可避免地包含了大量错误匹配,导致配准精度降低。为充分利用离散点间几何信息优化同平台点云配准精度,本文提出了基于空间一致性的同平台点云配准方法,该方法通过增加候选匹配点构建同平台点云图模型,为获取图模型的最优匹配结果,提出了重加权随机游走匹配(reweight random walks matching,RRWM)的优化方法。基于假设验证方法构建了点云配准模型,并结合试验验证了本文方法的有效性。
基金supported by the Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)[grant number SML2020SP007]the National Natural Science Foundation of China[grant number 41906167]the Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology[grant number 2018r077].
