Orthogonal Bases Approach for the Decomposition of Mixed Pixels in Hyperspectral Imagery

The N-FINDR algorithm has been widely used in hyperspectral image analysis for endmember extraction due to its simplicity and effectiveness. However, there are several disadvantages of implementing the N-FINDR. This letter proposes an algorithm for decomposition of mixed pixels. It improves the N-FINDR in several aspects. First, an iterative Gram-Schmidt orthogonalization is applied in the endmember searching process to replace the matrix determinant calculation used in N-FINDR, which makes this algorithm run very fast and can also guarantee the stability of its final results. Second, with the set of orthogonal bases obtained by the Gram-Schmidt orthogonalization, the algorithm can also help to estimate the proper number of endmembers and unmix the original images by itself. In addition, unlike the N-FINDR, a dimensionality reduction transform is not necessary in this algorithm. Experimental results of both simulated images and practical remote sensing images demonstrate that this algorithm is a fast and accurate algorithm for the decomposition of mixed pixels.     

采用PPI算法改进的一种数学形态学端元提取方法

自动形态学端元提取(automated morphological endmember extraction,AMEE)算法将结构元素内最纯像元与混合度最大的像元之间的光谱角距离定义为形态学离心率指数(morphological eccentricity index,MEI)来定量化地表示像元的纯净度。然而作为参考标准的混合度最大的像元在不同的结构元素内也是不同的,尤其是当结构元素内的纯净像元占大多数时,像元的均值光谱将更接近纯像元,此时像元的MEI越高,纯度反而越低。针对这一问题,本文提出一种像元纯度指数(pure pixel index,PPI)算法与AMEE算法相结合的端元提取算法PPI-AMEE。在结构元素内,利用PPI指数代替AMEE算法中的MEI指数来寻找最纯像元。变换结构元素时,只有最纯净的像元始终能够投影到随机生成的直线的两端,其PPI值会不断累计增大,而其他像元的PPI值则无法持续增大。累计记录每个像元的PPI值,直至满足迭代终止条件,最终形成一幅PPI图像,端元将在PPI值较大的像元中选取。PPI-AMEE算法只在相对较小的结构元素内运行PPI算法,然后再结合数学形态学中的膨胀操作对整幅图像进行处理,其同时兼顾了图像的光谱信息和空间信息。最后,采用模拟数据及美国内华达州Cuprite地区的机载可见光/红外成像光谱仪(airborne visible infrared imaging spectrometer,AVIRIS)高光谱数据对提出的PPI-AMEE算法进行试验验证。试验结果表明,PPI-AMEE算法的端元提取精度总体上优于AMEE算法和PPI算法。     

高光谱端元自动确定与提取的迭代算法

针对端元提取算法依赖人工确定端元数量的问题, 提出一种端元自动确定与提取的迭代算法。首先, 通过统计分析获得像元相似性阈值, 确定候选端元判据;其次, 对候选端元进行内、外部相关性判断, 对端元光谱集进行病态矩阵规避判断;最后, 以候选端元判据为迭代终止条件, 当图像空间不存在候选端元时, 获得端元集合并确定端元数。实验结果表明, 该方法正确有效, 可以避免顺序端元提取方法的错误风险, 提高端元提取自动化程度。     

高光谱端元自动提取的迭代分解方法

混合像元线性分解技术是进行高光谱影像处理的常用方法,应用这种方法的一个主要问题是难以有效、自动地确定影像的端元光谱。利用非监督的方法快速自动提取高光谱遥感图像的端元光谱是解决这个问题的主要技术手段。根据迭代误差分析思路,通过对线性混合像元模型分解的误差传播分析后,得到了端元选择的约束条件。结合端元存在的空间信息,自动提取出端元光谱并进行了混合像元分解。利用不同地区、不同传感器的高光谱数据实例测试了该文的方法,分析和讨论了选择迭代初始值与参数阈值的敏感性问题。研究结果表明此方法可以自动提取端元光谱,并且精度较高。     

利用卡方分布改进N-FINDR端元提取算法

针对N-FINDR算法计算速度慢、搜索范围较大的特点,提出改进的快速N-FINDR算法,通过提供一个像元个数较少的候选端元集合,为N-FINDR算法提供一个较小的搜索范围。在N-FINDR算法中,所有的端元被认为是处于所有像元构成的单形体的顶点位置,表示这些像元远离像元聚类中心。因此,利用卡方分布的分位点可以分离出这些像元,形成数量较少的候选端元集合。利用合成的和真实的高光谱数据对该算法的性能进行了验证。实验表明,在与N-FINDR算法有相同的端元提取精度的前提下,该算法计算速度更快。     

Parallel implementation of endmember extraction algorithms from hyperspectral data

Automated extraction of spectral endmembers is a crucial task in hyperspectral data analysis. In most cases, the computational complexity of endmember extraction algorithms is very high, in particular, for very high-dimensional datasets. However, the intrinsic properties of available techniques are amenable to the design of parallel implementations. In this letter, we evaluate several parallel algorithms that represent three representative approaches to the problem of extracting endmembers. Two parallel algorithms have been selected to represent a first class of algorithms based on convex geometry concepts. In particular, we develop parallel implementations of approximate versions of the N-FINDR and pixel purity index algorithms, along with a parallel hybrid of both techniques. A second class is given by algorithms based on constrained error minimization and represented by a parallel version of the iterative error analysis algorithm. Finally, a parallel version of the automated morphological endmember extraction algorithm is also presented and discussed. This algorithm integrates the spatial and spectral information as opposed to the other discussed algorithms, a feature that introduces additional considerations for its parallelization. The proposed algorithms are quantitatively compared and assessed in terms of both endmember extraction accuracy and parallel efficiency, using standard AVIRIS hyperspectral datasets. Performance data are measured on Thunderhead, a parallel supercomputer at NASA's Goddard Space Flight Center.     

Energy integral method for gravity field determination from satellite orbit coordinates

A fast iterative method for gravity field determination from low Earth satellite orbit coordinates has been developed and implemented successfully. The method is based on energy conservation and avoids problems related to orbit dynamics and initial state. In addition, the particular geometry of a repeat orbit is exploited by using a very efficient iterative estimation scheme, in which a set of normal equations is approximated by a sparse block-diagonal equivalent. Recovery experiments for spherical harmonic gravity field models up to degree and order 80 and 120 were conducted based on a 29-day simulated data set of orbit coordinates. The method was found to be very flexible and could be easily adapted to include observations of non-conservative accelerations, such as (to be) provided by satellites like CHAMP, GRACE, and GOCE. A serious drawback of the method is its large sensitivity to satellite velocity errors. Existing orbit determination strategies need to be altered or augmented to include algorithms that focus on optimizing the accuracy of estimated velocities.     

平面点集凸包Graham算法的改进

本文提出了一种计算平面点集最小凸包的快速算法。该算法首先对平面点集进行扫描,查找到最左、最右、最上、最下4个方向上的极值点,以此构造出一个初始凸包,并删除初始凸包内部的所有点;然后把剩余点集分组,每组运用格雷厄姆(Graham)算法生成一个新的凸包;最后将所有子集凸包的顶点看作一个新的点集,再次运用Graham算法生成最终凸包。测试结果表明,改进后的算法可较大幅度地提高执行效率。     

采用目标端元修正的高光谱混合像元盲分解

针对非负矩阵盲信号分离(NMF)用于混合像元分解易陷入局部极小值的不足,将非监督端元提取与盲分解方法相结合,构建了一种基于目标端元修正的混合像元盲分解模型(ATGP-NMF)。ATGP-NMF模型利用非监督正交子空间投影算法(ATGP)和非负最小二乘法(NNLS)获取NMF盲分离的初始值,然后将获得初始目标端元光谱与丰度输入NMF模型,通过迭代运算不断逼近优化目标而得到最终的端元光谱和端元丰度。为了检验模型对于各类数据的有效性和适用性,将ATGP-NMF与传统NMF分别应用于模拟仿真数据、室内控制数据和真实遥感影像3类实验数据进行分析验证。结果表明,ATGP-NMF模型具有较好的适用性,在没有先验信息、先验信息很少,以及纯像元假设不存在情况下都能较好地分解混合像元,且能够更好克服局部极小问题,提高混合像元分解的精度。     

以凸面单体边界为搜索空间的端元快速提取算法

提出了以凸面单体边界为搜索空间的端元快速提取算法, 其核心包括凸面单体边界的确定和以凸面单体边界为基础的端元搜索两部分。实验表明: 该算法不仅能够准确地寻找到端元, 而且端元提取速度明显快于现有的端元提取算法。     

一种非监督快速端元提取方法

正交子空间投影(OSP)方法广泛用于目标与背景的分离之中,对于高光谱影像,OSP可用于目标提取和混合像元分解,但缺点是需要端元的先验知识。针对这一问题,本文基于OSP的原理提出了一种非监督快速端元提取方法。实验使用模拟高光谱数据和由OM ISⅠ获取的真实高光谱数据,结果精度令人满意,证明了本文算法进行端元自动提取的可行性。     

基于权重光谱解混方法的高光谱矿物填图

提出了一种基于Fisher权重分析的迭代光谱解混方法(WLSMA),该方法首先对高光谱图像进行区域分割,在分割后的各子块中自动提取端元;再次对提取的端元进行聚类,从光谱的整体特征上将不同类别的端元区分开,针对聚类结果中的每一类别各选取几个具有代表性的端元光谱,并对最优光谱进行窗口卷积处理,结合In_CoB指标构建端元光谱样本库;最后对图像进行迭代光谱解混处理,在丰度反演过程中引入基于Fisher准则的补偿权值矩阵以提高反演精度。AVIRIS高光谱数据实验证明,WLSMA不需要大量先验信息,利用Fisher准则和迭代光谱分析理论增强了相似性矿物的可分性,为加强对矿区地表岩性的认识和模拟提供了更大的灵活性和可能性,对高光谱矿物填图有一定的借鉴意义。     

端元快速提取的光谱梯度特征搜索法

由于数据量大,目前大多数端元提取算法均需较长的计算时间,限制了这些算法的有效应用。本文提出了以光谱梯度特征为搜索条件的快速端元提取方法,其核心包括基于光谱梯度特征的候选端元快速筛选和基于光谱解混误差的端元识别两部分。由于能够从影像中快速筛选出少量的像元光谱作为候选端元,故具有较好的计算性能;同时由于避免了非端元光谱参与端元识别,使得识别的结果具有更高的精度。试验表明,相比经典的IEA算法和ECHO算法,该算法不仅能大幅度提高端元提取速度,而且具有更准确的端元识别能力。同时,基于该算法原理,也可对现有各种算法进行改进,提升现有的各种端元提取算法的运算速度。     

A building extraction approach for Airborne Laser Scanner data utilizing the Object Based Image Analysis paradigm

In the past two decades Object-Based Image Analysis (OBIA) established itself as an efficient approach for the classification and extraction of information from remote sensing imagery and, increasingly, from non-image based sources such as Airborne Laser Scanner (ALS) point clouds. ALS data is represented in the form of a point cloud with recorded multiple returns and intensities. In our work, we combined OBIA with ALS point cloud data in order to identify and extract buildings as 2D polygons representing roof outlines in a top down mapping approach. We performed rasterization of the ALS data into a height raster for the purpose of the generation of a Digital Surface Model (DSM) and a derived Digital Elevation Model (DEM). Further objects were generated in conjunction with point statistics from the linked point cloud. With the use of class modelling methods, we generated the final target class of objects representing buildings. The approach was developed for a test area in Biberach an der Riß (Germany). In order to point out the possibilities of the adaptation-free transferability to another data set, the algorithm has been applied “as is” to the ISPRS Benchmarking data set of Toronto (Canada). The obtained results show high accuracies for the initial study area (thematic accuracies of around 98%, geometric accuracy of above 80%). The very high performance within the ISPRS Benchmark without any modification of the algorithm and without any adaptation of parameters is particularly noteworthy.     

FAN模型的双种群差分进化光谱解混算法

双线性混合模型是近年来非线性光谱解混的研究重点之一,其克服了线性混合模型无法描述地物多重散射作用的缺陷,能够更精确地还原真实的地物光谱混合过程。然而,限于模型的复杂性,目前在缺乏准确的端元先验知识的条件下进行双线性光谱解混仍是一项具有挑战性的任务。差分进化算法(DE)是一种具有良好全局搜索能力的群智能优化算法,其优化求解过程无需进行复杂的数学推导,为双线性光谱解混问题提供了一种有效的解决途径。为此,本文以FAN双线性混合模型为例,提出了一种双种群机制的差分进化算法(记为DEFAN),实现非监督双线性光谱解混。DE-FAN算法通过建立端元与丰度两个种群的交替进化机制寻找最优解,同时在迭代中引入自适应重构策略增强种群多样性,降低算法陷入局部最优解的风险,最终实现端元与丰度的同时估计。通过模拟图像及真实图像的解混实验进行算法检验,证明DE-FAN算法较之传统非线性解混算法具有更高的解混精度及解混效率。     

Robust ISAR Range Alignment via Minimizing the Entropy of the Average Range Profile

In this letter, a novel global approach to range alignment for inverse synthetic aperture radar (ISAR) image formation is presented. The algorithm is based on the minimization of the entropy of the average range profile (ARP), and the processing chain is capable of exploiting the efficiency of the fast Fourier transform. With respect to the existing global methods, the new one requires no exhaustive search operation and eliminates the necessity of the parametric model for the relative offset among the range profiles. The derivation of the algorithm indicates that the presented methodology is essentially an iterative solution to a set of simultaneous equations, and its robustness is also ensured by the iterative structure. Some alternative criteria, such as the maximum contrast of the ARP, can be introduced into the algorithm with a minor change in the entropy-based method. The convergence and robustness of the presented algorithm have been validated by experimental ISAR data.     

端元可变非线性混合像元分解模型

遥感影像中混合像元普遍存在。端元固定的情况下对混合像元进行分解,很难高精度地识别影像地物。本文基于支持向量机,提出了端元可变的非线性混合像元分解模型。首先,通过构建多个支持向量机获取每个像元的优化端元集,在优化端元集的基础上运用支持向量机与两两配对方法相结合的算法获取像元组分。试验结果表明,本文提出的方法效果优于传统的多端元光谱分解法。     

基于AVHRR/2 10 d合成数据的青藏高原亚像元雪填图

为了满足水文和气象模型对长时段积雪面积数据的需求,基于第二代甚高分辨率辐射计（second series of advanced very high resolution radiometer,AVHRR/2）的10 d合成数据提出了一种青藏高原地区AVHRR/2数据亚像元雪填图算法,将中分辨率遥感数据亚像元级积雪面积数据集延伸至30 a时间跨度。本文算法以多端元线性光谱混合分析模型为基础,以归一化植被指数、第一波段、第二波段等作为选取端元的指标,直接从AVHRR/2图像中自动选取所需雪端元与非雪端元。基于TM数据对该算法的AVHRR/2数据亚像元雪填图结果进行验证,其均方根误差接近0.1,在青藏高原山区具有较高的精度。     

Independent Base Vector Representation to Address Endmember Variability in Hyperspectral Unmixing

The normal compositional model (NCM) is a well-known and powerful model in hyperspectral unmixing which represents endmembers as independent Gaussian vectors to capture endmember variability. However, the assumption of independent endmembers diminishes the model accuracy because the high degree of correlation between endmembers of a scene and identical sources of variability demonstrate that the endmembers are dependent. This paper proposes a new hyperspectral unmixing algorithm which represents endmembers using dependent Gaussian vectors to estimate abundance fractions. To overcome the higher complexity caused by dependence assumption, this algorithm introduces new independent Gaussian vectors named Base Vectors to represent different endmembers by a weighted linear combination. Also, the proposed unmixing algorithm uses maximum likelihood method to estimate weight coefficients of Base Vectors which are used to represent mixed pixel. Finally, abundance estimation can be done using the new representation for endmembers and mixed pixel. The proposed algorithm is evaluated and compared with other state-of-the-art unmixing algorithms using simulated and real hyperspectral images. Experimental results demonstrate that the proposed unmixing algorithm can unmix pixels composed of correlated endmembers in hyperspectral images in the presence of spectral variability more accurately than previous methods.     

稀疏差异先验信息支持的高光谱图像稀疏解混算法

基于光谱库的高光谱稀疏解混技术近年来得到了人们的关注,该技术利用光谱库中光谱样本作为端元,将解混问题转化为稀疏表示问题。然而,由于测量环境的差异,待解混图像的实际端元往往与光谱库中相应光谱信号存在差异。本文提出了一种光谱差异稀疏约束的联合稀疏回归解混算法。首先,假设光谱差异具有稀疏特性,建立了光谱库校正模型,使得在解混过程中可对光谱库进行自适应地调整;然后,将光谱库校正模型与联合稀疏回归解混模型结合,建立了考虑光谱差异的稀疏解混模型;最后,基于交替方向乘子法得到了迭代优化解决方案。分别利用仿真和真实高光谱数据进行了试验验证,结果表明,在光谱库不匹配的情形下,本文方法能够有效提高稀疏解混算法的解混性能。