复数域最小二乘平差及其在POLInSAR植被高反演中的应用

传统的测量观测值都是实数,因此测量平差都是在实数空间中进行的。然而,随着科学技术的快速发展,现代测绘领域中出现了一些用复数表示的观测数据。与实数数据一样,这些复数数据同样面临着如何从带有误差的观测值中找出未知量的最佳估计值的问题。但目前涉及复数观测的数据处理时,主要还是依据观测过程,分步或直接解算,不能考虑观测误差、多余观测信息等。针对这一情况,本文介绍了复数域中数据处理的最小二乘方法,试图将测量平差从实数域推广到复数域,并定量研究了两种平差准则的优劣性。为了了解复数域最小二乘的有效性,本文以极化干涉SAR植被高反演为例,建立复数域平差函数模型和随机模型,构建复数域最小二乘法反演植被高。结果表明该算法反演的植被高结果可靠,其精度优于经典植被高反演算法,且计算简单,易于实现。     

基于力学模式的动态大地测量数据反演研究

本文在文献（１）的基础上，进一步研究了基于力学模式动态大地测量反演理论。首先提出了力学模式下动态大地测量反问题的六种形式，导出了第一，二类动态大地测量反问题的线性最小的二乘解，研究了动态大地测量反问题的妥；最后，结合数值例子，讨论了利用地壳垂直形变数据反演地壳断层错动的一种方法。     

On the gravimetric inverse problem in geodetic gravity field estimation

Gravity field estimation in geodesy, through linear(ized) least squares algorithms, operates under the assumption of Gaussian statistics for the estimable part of preselected models. The causal nature of the gravity field is implicitly involved in its geodetic estimation and introduces the need to include prior model information, as in geophysical inverse problems. Within the geodetic concept of stochastic estimation, the prior information can be in linear form only, meaning that only data linearly depending on the estimates can be used effectively. The consequences of the inverse gravimetric problem in geodetic gravity field estimation are discussed in the context of the various approaches (in model data spaces) which have the common goal to bring into agreement the statistics between these two spaces. With a simple numerical example of FAA prediction, it is shown that prior information affects the accuracy of estimates at least equally as the number of input data. Received: 25 April 1994; Accepted: 15 October 1996     

A solution to EIV model with inequality constraints and its geodetic applications

In the field of surveying, mapping and geodesy, there have been a number of works on the error-in-variable (EIV) model with constraints, where equality constraints are imposed on the parameter vector. However, in some cases, these constraints may be inequalities. The EIV model with inequality constraints has not been fully investigated. Therefore, this paper presents an inequality-constrained total least squares (ICTLS) solution for the EIV model with inequality constraints (denoted as ICEIV). Employing the proposed ICTLS method, the ICEIV problem is first converted into an equality-constrained problem by distinguishing the active constraints through exhaustive searching, and it is then resolved employing the method of equality-constrained total least squares (ECTLS). The applicability and feasibility of the proposed method is illustrated in two examples.     

基于变量投影的结构总体最小二乘算法

测绘领域诸多实际应用中系数矩阵和观测向量具有结构特征,即系数矩阵和观测向量中包含固定量(甚至固定列)和随机量,并且不同位置的随机量线性相关。针对这个问题,从变量误差(errors-in-variables,EIV)函数模型出发,首先,将系数矩阵和观测向量构成的增广矩阵表示为仿射函数形式,并采用变量投影法对函数模型进行重构;然后,利用拉格朗日法推导出了一种结构总体最小二乘(structured total least squares,STLS)估计算法。算例分析结果表明,该算法与已有能够解决系数矩阵和观测向量存在结构特征的加权或结构总体最小二乘算法估计结果一致,说明了该算法的有效性,同时阐明了该算法与已有相关算法的关系。     

总体最小二乘用于线阵卫星遥感影像光束法平差解算

顾及像点观测方程的系数矩阵中存在随机误差,提出了基于总体最小二乘的线阵卫星遥感影像光束法平差模型。在假定像点观测误差和系数矩阵误差均为独立、等精度分布的基础上,利用拉格朗日条件极值法推导了包含外方位元素虚拟观测方程和控制点误差方程的总体最小二乘光束法平差算法的具体公式和计算方法。该方法利用方差分量估计确定各类虚拟观测值的方差,可求解包含多类虚拟观测量的平差问题,并可用先验信息或岭迹法确定系数矩阵观测值的权比例系数,从而克服了现有总体最小二乘虚拟观测方法不能处理多类虚拟观测值的不足,确保了光束法平差可正确有效求解。分别利用模拟算例与两组真实影像进行了试验验证。结果表明,相比于常规最小二乘虚拟观测法以及现有总体最小二乘虚拟观测方法,本文方法具有更高的求解精度与适应性。相较于传统线阵卫星遥感影像光束法平差方法,本文方法可以获得更高的平差计算精度。     

方差分量估计的抗差总体最小二乘算法

应用等价权函数建立总体最小二乘抗差估计算法,算法的有效性受到随机模型的影响。为减小随机模型误差对抗差算法的影响,提出方差分量估计确定总体最小二乘随机模型的思想;利用等价权函数对观测元素进行迭代定权,分类确定等价权函数的域值,提高权函数抗差算法的有效性。最后,通过算例验证算法可行性,结果表明本文算法是有效的。     

Multi-level arc combination with stochastic parameters

 The method of square root information filtering and smoothing (SRIF/S) is reviewed and has been implemented in the combined square root information filter and smoother (CSRIFS) program. CSRIFS is a part of the GEOSAT space geodesy software developed at Forsvarets forskningsinstitutt (FFI, The Norwegian Defence Research Establishment). The state vectors and complete variance–covariance matrices from the analyses of a number of independent arcs of space geodesy data can be combined using CSRIFS. Four parameter levels are available and any parameter can, at each level, be represented as either a constant or a stochastic parameter (white noise, colored noise, or random walk). The batch length (i.e. the time interval between the addition of noise to the SRIF array) can be made time and parameter dependent. CSRIFS was applied in the combination of 623 very long baseline interferometry (VLBI) observing sessions. The purpose of this test was to validate the computer implementation of the SRIF/S method and to give an example of how this method can be used in the analysis of a large number of space geodetic observations. The results show that the implementation is very satisfactory. Received: 28 May 1999 / Accepted: 15 June 2000     

Partial EIV模型的非负最小二乘方差分量估计

Partial Errors-in-Variables(Partial EIV)模型是EIV模型的扩展形式,权阵构造简单,当系数矩阵中存在非随机元素和随机元素时,Partial EIV模型的适用性更强。针对Partial EIV模型中随机模型不准确的情况,将系数矩阵和观测向量分别作为一类数据,本文在该模型的基础上,使用最小二乘方差分量估计方法,推导相关计算公式及迭代算法,分别估计出相应的方差分量估值。并对出现的负方差使用非负最小二乘理论,增加约束条件,对随机模型进行修正,得到更加合理的参数估值。试实验结果表明,本文的方法与其他方差分量估计方法等价。     

多元总体最小二乘问题的牛顿解法

为提高多元总体最小二乘问题参数估值的解算效率,推导了基于牛顿法的多元加权总体最小二乘算法;分析比较了基于牛顿法的多元加权总体最小二乘解和基于拉格朗日乘数法多元加权总体最小二乘解之间的关系,根据协因数传播律给出了多元总体最小二乘平差的16种协因数阵的近似计算公式。新算法能够解决观测矩阵和系数矩阵元素具有相关性的问题,并且可以把观测矩阵和系数矩阵的随机元素和常数元素纳入到一个协因数阵中进行处理。算例结果表明,本文提出的多元总体最小二乘问题的牛顿解法可行且收敛速度更快。     

一种基于F-J线性-非线性模型解的迭代最小二乘方法

基于贝叶斯理论的线性与非线性模型反演方法（Fukuda-Johnson,F-J）已广泛应用于地球物理模型的线性-非线性参数反演。但F-J方法的反演结果可能受马尔可夫链蒙特卡洛采样（Markov chain Monte Carlo,MCMC）经验参数选择的影响,而反复调试合适的经验参数需耗费大量计算时间。对线性与非线性模型进行线性化后,也可以利用迭代最小二乘方法反演,但该方法难以选择合适的初始值。为提高参数反演计算效率和避免参数初值选择影响,提出了一种以F-J方法模型解为初始值的迭代最小二乘方法。该方法只需计算一次F-J方法模型解和有限次最小二乘迭代,既提高了F-J方法的反演效率,又能获得迭代最小二乘全局最优解。针对模拟数据实验和实际数据算例,分别采用F-J方法、随机生成初始值的迭代最小二乘方法和以F-J方法结果为初值的迭代最小二乘方法进行参数反演。结果表明,直接使用F-J方法时,MCMC采样参数会影响反演结果;直接进行迭代最小二乘反演时,初始值选取不当会导致迭代无法收敛到正确的结果;以F-J方法的结果作为迭代最小二乘方法的初始值进行反演,可以充分发挥F-J方法的全局最优性和迭代最小二乘方法计算量小、稳定性好的优势。     

On estimating gravity anomalies— A comparison of least squares collocation with conventional least squares techniques

The least squares collocation algorithm for estimating gravity anomalies from geodetic data is shown to be an application of the well known regression equations which provide the mean and covariance of a random vector (gravity anomalies) given a realization of a correlated random vector (geodetic data). It is also shown that the collocation solution for gravity anomalies is equivalent to the conventional least-squares-Stokes' function solution when the conventional solution utilizes properly weighted zero a priori estimates. The mathematical and physical assumptions underlying the least squares collocation estimator are described.     

稳健估计的一种改进迭代算法

当观测值不含粗差、观测误差服从零均值分布时,最小二乘算法是最优无偏估计。若观测值包含粗差,由于最小二乘不具备抗差性,往往采用以M估计为代表的稳健估计方法,选权迭代算法是应用最为广泛的稳健估计方法之一。目前,选权迭代算法的每一步都需要对模型的稳健正交矩阵求逆,其运算复杂度是矩阵维数的三次方,在未知参数或粗差个数较多的情况下,计算量大、计算时间长。本文基于矩阵逆的运算法则,对现有选权迭代算法进行了改进,改进的选权迭代算法在迭代计算过程中仅需计算更新权阵后的解的改正项,不需要对正交矩阵求逆,显著提高了算法的效率。     

Sign-constrained robust least squares, subjective breakdown point and the effect of weights of observations on robustness

The findings of this paper are summarized as follows: (1) We propose a sign-constrained robust estimation method, which can tolerate 50% of data contamination and meanwhile achieve high, least-squares-comparable efficiency. Since the objective function is identical with least squares, the method may also be called sign-constrained robust least squares. An iterative version of the method has been implemented and shown to be capable of resisting against more than 50% of contamination. As a by-product, a robust estimate of scale parameter can also be obtained. Unlike the least median of squares method and repeated medians, which use a least possible number of data to derive the solution, the sign-constrained robust least squares method attempts to employ a maximum possible number of good data to derive the robust solution, and thus will not be affected by partial near multi-collinearity among part of the data or if some of the data are clustered together; (2) although M-estimates have been reported to have a breakdown point of 1/(t+1), we have shown that the weights of observations can readily deteriorate such results and bring the breakdown point of M-estimates of Huber’s type to zero. The same zero breakdown point of the L ₁-norm method is also derived, again due to the weights of observations; (3) by assuming a prior distribution for the signs of outliers, we have developed the concept of subjective breakdown point, which may be thought of as an extension of stochastic breakdown by Donoho and Huber but can be important in explaining real-life problems in Earth Sciences and image reconstruction; and finally, (4) We have shown that the least median of squares method can still break down with a single outlier, even if no highly concentrated good data nor highly concentrated outliers exist. An erratum to this article is available at .     

误差限的病态总体最小二乘解算

大地测量和地球物理数据解算中时常会涉及病态问题的处理。基于客观的观测精度,利用设计矩阵与观测向量的误差限制,一方面降低了病态性对求解造成的波动;另一方面避免引入正常数,从而提高整个解算过程的客观性与可靠性。计算表明,本文提出的方法可以有效地处理病态总体最小二乘问题,并且具有较高的稳定性。     

PEIV模型参数估计新算法

PEIV(Partial Errors-In-Variables)模型是EIV模型的扩展,它能解决系数矩阵含有非随机元素或存在结构特性的问题。针对常规PEIV模型算法的复杂性,提出了一种PEIV模型参数估计的新算法。该算法将系数矩阵含误差的元素看成是一类观测值,与平差模型原观测值构成两类观测值,将PEIV平差模型表示为类似于传统的最小二乘间接平差模型,再通过非线性最小二乘平差理论,推导出了算法的迭代公式和精度评定公式。算法迭代格式与间接平差类似,通过算例验证了算法的可行性和正确性。     

Geodetic numerical and statistical analysis of data

The paper presents a more generalized concept of the Helmert’s method of subjecting a least squares adjustment to rigorously enforced boundary conditions through the use of weighting functions applied to both the observed data as well as their functional but unobservable parameters. The generalized concept provides: (1) the algorithm necessary for statistically correct treatment of data from hybrid measuring systems; (2) a means of obtaining optimum design of experiments and achieving unique solutions from even nearly unstable normal equations. Various numerical and statistical measures for investigating nonlinearity effects, instability and convergency conditions, and establishment of statistical confidence in the derived parameters and observed data are given. The entire concept has been successfully applied to terrestrial and celestial geodesy, and is applicable to any experimental data that can be expressed as functions of other parameters that may or may not be directly measurable.     

基于非线性高斯-赫尔默特模型的结构总体最小二乘法

变量误差（error-in-variables,EIV）模型的系数矩阵存在结构特征的情况,并且这种结构特征可以扩展到观测向量中。首先采用变量投影法将系数矩阵的增广矩阵展开成仿射矩阵形式,提取系数矩阵和观测向量中的随机量,并将EIV模型表示为非线性高斯-赫尔默特模型,然后利用非线性最小二乘原理推导了一种结构总体最小二乘法。该算法统一了普通的结构总体最小二乘法、结构数据最小二乘法以及最小二乘法。将该算法应用到真实算例和模拟算例中,两个算例结果表明,该算法与已有能够解决EIV模型结构特征的结构或加权总体最小二乘法估计结果一致,验证了该算法的有效性。同时,该算法对结构特征的提取方式简单、规律性强且易于编程实现;且在算法设计中,把结构总体最小二乘问题转换为附有参数的条件平差问题,即将其纳入到最小二乘平差理论体系,便于其扩展应用。同时对平面拟合问题的误差估计特性进行了定性分析,由分析可知参数的相对大小对估计误差的一致性有直接影响,这说明EIV模型下系数矩阵和观测向量中随机量的估计误差与真误差的一致性关系相对复杂。     

Huber’s M-estimation in relative GPS positioning: computational aspects

When GPS signal measurements have outliers, using least squares (LS) estimation is likely to give poor position estimates. One of the typical approaches to handle this problem is to use robust estimation techniques. We study the computational issues of Huber’s M-estimation applied to relative GPS positioning. First for code-based relative positioning, we use simulation results to show that Newton’s method usually converges faster than the iteratively reweighted least squares (IRLS) method, which is often used in geodesy for computing robust estimates of parameters. Then for code- and carrier-phase-based relative positioning, we present a recursive modified Newton method to compute Huber’s M-estimates of the positions. The structures of the model are exploited to make the method efficient, and orthogonal transformations are used to ensure numerical reliability of the method. Economical use of computer memory is also taken into account in designing the method. Simulation results show that the method is effective.     

“数字化科学工程”构建中的广义非线性数据处理的一种新算法

在当今各国正大力倡导的“数字国家”、“数字城市”、“数字矿山”等科学工程构建中的数据处理是基础和核心 ,其数据又具有多源、多维、多类型、多时态、多精度并具有非线性特征等特点 ,其数据处理的参数估计模型大都是复杂的非线性函数模型 ,模型中的参数有非随机参数 ,也有随机参数 ,这些系广义非线性数据处理 ,应采用广义非线性动态最小二乘数据处理的理论、方法来完成。本文提出了一种新的解算模型和解算方法 ,将问题分离 ,转换成单变量的一般非线性最小二乘问题求解。先按非线性拟合模型线性逼近法求得靠近真值的最优初值 ,再按非线性最小二乘解算方法求解参数估值。本方法使原来的高维方程得以简化 ,还不用计算二阶导数 ,大大简化了计算难度 ,并大大减少了迭代次数和计算工作量。