Small target extraction based on independent component analysis for hyperspectral imagery

A small target detection approach based on independent component analysis for hyperspectral data is put forward. In this algorithm, firstly the fast independent component analysis(FICA) is used to collect target information hided in high-dimensional data and projects them into low-dimensional space. Secondly, the feature images are selected with kurtosis. At last, small targets are extracted with histogram image segmentation which has been labeled by skewness.     

基于独立分量分析的高光谱影像小目标提取研究

借助快速独立分量分析(FICA)将高维数据中隐藏的目标信息集中投影到低维特征影像中,然后以峰度为特征度量指标选择特征影像,最后用以偏斜为指标的直方图分割方法提取小目标。实验证明,此算法精度较高,适用于对高光谱影像中的小目标进行提取。     

独立成分分析的高光谱异常变化检测

遥感探测到的小目标信号一般是弱信号,利用传统的高光谱异常变化检测方法直接抑制背景来突出异常变化目标,往往导致小目标弱信号同时被抑制,造成目标探测率低、虚警率高。基于独立成分分析方法,研究了弱信号小目标的高光谱变化检测模型,该模型首先通过投影寻踪将异常变化影像投影到独立成分,突出异常变化目标,然后再抑制背景,从而达到异常变化目标和背景的有效分离。该模型可以有效降低虚警率,提高探测率。利用模拟数据和真实数据进行了精度验证,结果表明,利用模拟数据得到的探测精度为99%,利用真实数据得到的检测精度为86%,与传统异常变化检测算法相比,精度最高提高了9%。本文研究方法适用于弱信号小目标的高光谱异常变化检测。     

基于主成分抑制的高光谱图像异常目标检测方法

高光谱图像异常目标检测主要用于检测图像中的区别于背景环境的异常目标,为图像目标的判读提供一个初步的判断,是高光谱图像应用的一个重要内容。本文在研究现有异常目标检测算法的基础上,采用基于主成分抑制和顶点成分分析相结合的方法,对实验图像中的异常目标进行了检测,取得了较好的效果。     

Automated Target Detection and Discrimination Using Constrained Kurtosis Maximization

Exploiting hyperspectral imagery without prior information is a challenge. Under this circumstance, unsupervised target detection becomes an anomaly detection problem. We propose an effective algorithm for target detection and discrimination based on the normalized fourth central moment named kurtosis, which can measure the flatness of a distribution. Small targets in hyperspectral imagery contribute to the tail of a distribution, thus making it heavier. The Gaussian distribution is completely determined by the first two order statistics and has zero kurtosis. Consequently, kurtosis measures the deviation of a distribution from the background and is suitable for anomaly/target detection. When imposing appropriate inequality constraints on the kurtosis to be maximized, the resulting constrained kurtosis maximization (CKM) algorithm will be able to quickly detect small targets with several projections. Compared to the widely used unconstrained kurtosis maximization algorithm, i.e., fast independent component analysis, the CKM algorithm may detect small targets with fewer projections and yield a slightly higher detection rate.     

基于ETM+影像的绿地信息提取方法研究

文中以ETM+影像为数据源实现对贵阳市某城区的绿地信息提取。对获取的影像进行预处理,分别通过不同的方法:原始波段组合法、主成分分析法(PCA)、独立分量分析法(ICA)、归一化植被指数法(NDVI)及基于第一独立分量的实验室波段组合法,获取研究区的假彩色合成影像。将以上方法得到的影像数据进行对比分析,表明植被景观目视效果最好的是原始波段组合法。将得到的影像数据进行监督分类,通过目视解译的方法进行精度评价,结果表明,基于第一独立分量的实验室波段组合法绿地信息提取精度最高,是一种有效的绿地信息提取方法。     

An assessment of independent component analysis for detection of military targets from hyperspectral images

Hyperspectral data acquired over hundreds of narrow contiguous wavelength bands are extremely suitable for target detection due to their high spectral resolution. Though spectral response of every material is expected to be unique, but in practice, it exhibits variations, which is known as spectral variability. Most target detection algorithms depend on spectral modelling using a priori available target spectra In practice, target spectra is, however, seldom available a priori. Independent component analysis (ICA) is a new evolving technique that aims at finding out components which are statistically independent or as independent as possible. The technique therefore has the potential of being used for target detection applications. A assessment of target detection from hyperspectral images using ICA and other algorithms based on spectral modelling may be of immense interest, since ICA does not require a priori target information. The aim of this paper is, thus, to assess the potential of ICA based algorithm vis a vis other prevailing algorithms for military target detection. Four spectral matching algorithms namely Orthogonal Subspace Projection (OSP), Constrained Energy Minimisation (CEM), Spectral Angle Mapper (SAM) and Spectral Correlation Mapper (SCM), and four anomaly detection algorithms namely OSP anomaly detector (OSPAD), Reed–Xiaoli anomaly detector (RXD), Uniform Target Detector (UTD) and a combination of Reed–Xiaoli anomaly detector and Uniform Target Detector (RXD–UTD) were considered. The experiments were conducted using a set of synthetic and AVIRIS hyperspectral images containing aircrafts as military targets. A comparison of true positive and false positive rates of target detections obtained from ICA and other algorithms plotted on a receiver operating curves (ROC) space indicates the superior performance of the ICA over other algorithms.     

稻城地区遥感蚀变信息提取研究

根据围岩蚀变在多波段遥感图像（TM）上具有的光谱特征,利用比值分析、主成分分析及比值增强后主成分分析等方法,对 四川省稻城地区围岩蚀变信息进行提取和分析,通过多层次的筛选和评估提取矿区异常区,制作遥感异常图。     

基于静态模型的多视角SAR图像目标识别方法

传统的多视角SAR图像集合对于目标姿态角具有高度敏感性,因此在用于目标识别时存在一些不足之处。针对该问题提出一种多视角SAR图像的静态建模方法,它将来自一个目标多个视角下的图像信息集成到一个综合的数据结构中,并且该数据结构与目标散射中心有关而与角度无关。然后利用静态模型对不完全姿态角的目标数据进行静态建模,利用模板匹配法对输入多视角图像进行目标识别。理论分析和仿真结果表明,本方法在每个目标只有少量姿态角模板数据可用的情形下比传统模型具有优势。     

基于像元坐标的独立成分分析技术的端元提取方法

将基于像元坐标的空间信息与基于独立成分分析技术结合的方法用于混合像元的分解,是实现端元提取的一种方法。这种方法在空间信息充分利用的基础上得到提高。将该方法运用Cuprite地区的AVIRIS数据,并与传统的PPI方法进行对比,结果表明,利用本文提取端元的方法具有很高的可信度。     

基于核独立成分分析的极化SAR图像相干斑抑制

为提高极化合成孔径雷达图像相干斑抑制的效果,提出基于核独立成分分析(kernel independent component analysis,KICA)的极化SAR图像相干斑抑制方法.该方法将三个通道的极化信息作为输入数据,经过KICA变换得到三个独立分量,取相干斑指数最小的分量作为滤波后的信息图像.由于将核函数引入...     

一种改进的火星车多光谱影像深度新颖目标探测方法

火星车（即巡视探测器）是对火星表面探测和科学研究的重要手段。针对火星车采集到的日益增长的遥感数据,亟需一种能够智能化地从海量影像中探测出有科学价值的新颖目标的方法。传统的新颖探测多采用基于距离测度和基于影像重建的方法,其中基于距离测度的方法逐像素计算新颖分数,未考虑空间上下文信息;基于影像重建的方法侧重对典型地貌背景进行重建,新颖性表现为影像重建误差,对小型新颖目标如钻孔、除尘点等提取效果不佳。提出一种改进的火星车多光谱影像深度新颖目标探测方法(convolution auto-encoder combined Mahalanobis distance method, CAE-M),利用全卷积自编码神经网络提取深层特征进行典型地貌重建,并联合马氏距离将新颖目标与典型地貌背景分离,充分挖掘空间维与光谱维特征,提高火星车新颖目标探测结果的准确性。实验采用好奇号火星车多光谱影像数据集,在盖尔撞击坑地表采用Reed-Xiaoli探测器、主成分分析、卷积自编码神经网络、生成对抗网络与CAE-M进行对比实验,结果表明,CAE-M在探测精度和可视化解释上均优于对比方法,在不同类别的新颖目标探测上都有着均衡稳定的表现。     

点、多边形拓扑关系与多边形顺、逆判断优化算法

点与多边形拓扑关系判断是空间拓扑分析的重要内容之一,基于以往算法不可靠和过于复杂的缺点,本文提出了面积判断法,很好地解决了上述问题,且对于含有孤岛的多边形仍然有效。矢量多边形坐标存储顺、逆时针的判断是数据验证、数据转换必不可少的一项,但对于此种算法少有提及,为此本文提出了外围判断法,可以较为简单地完成此项任务,填补了此类算法的空白。     

Map algebra based analysis for directed flow networks

Based on the concept of map algebra, this research developed a network neighborhood analysis framework for directed flow networks. The analysis framework has two components: the first component defines how neighborhoods are delineated on networks and the second component calculates various statistics within the neighborhoods. The power and value of the analysis framework lie in its capability to delineate versatile network neighborhoods and its flexibility in calculating various statistics within the neighborhoods. It extends the raster map algebra to networks and provides a consistent analysis framework for the raster, vector, and network data models. Using a small section of the National Hydrography Dataset (NHD) networks, a prototype Web application is implemented to experiment and demonstrate the concept and uses of the analysis framework.     

卫星多故障探测和识别的独立分量分析法

鉴于独立分量对异常值具有较强的敏感性,提出了基于独立分量分析(ICA)的伪距多变量时间序列异常值探测算法,并且利用契比雪夫不等式给出了异常值探测的阈值,引入时间序列干预模型估计了潜在故障扰动的大小,根据3σ准则确定出故障星的位置。根据RAIM的实时性要求,采用滑动窗口的思想对上述批处理探测算法进行改造,本文提出了一种卫星多故障在线探测和识别的新算法,并给出了新RAIM算法的实施流程。利用5个iGMAS北斗监测站的民用观测数据对新算法进行验证,试验分析结果表明,新算法对于卫星多故障的实时处理具有较好的效果,且其故障正确探测率优于以往的RANCO方法。     

Feature Identification via a Combined ICA–Wavelet Method for Image Information Mining

Image transformation is required for color–texture image segmentation. Various techniques are available for the transformation along the spatial and spectral axes. For instance, the HSV–wavelet technique is shown to be very effective for image information mining in remote-sensing applications. However, the HSV transformation approach uses only three spectral bands at a time. In this letter, a new feature set, obtained by combining independent component analysis and wavelet transformation for image information mining in geospatial data, is presented. Experimental results show the effectiveness of the presented method for image information mining in Earth observation data archives.      

利用TPCA分析北京平原区地面沉降的时空演化特征

时间主成分分析（temporal principal component analysis,TPCA）可用于地学领域中提取时空数据的时序特征和空间分布特征,北京平原区的地面沉降具有典型的时序和空间特征。在利用永久散射体干涉测量技术获取的北京平原区2003—2010年地面沉降数据的基础上,采用TPCA方法分析了北京平原区地面沉降时空演化特征。经分析发现:（1）TPCA分析得到的第一主成分反映了地面沉降在该长时序阶段的空间分布特征。（2）第二主成分得分为正的空间点与可压缩层厚度在130 m以上的区域在空间分布上有一致性和相关性。（3）在空间上,第一主成分为负值与第二主成分为正值的永久散射体点分布在年均沉降速率30 mm/a以上的严重沉降区域。严重沉降区具有明显的南北沉降分类现象和季节性差异,具体表现为:北部沉降区在春夏季节的沉降量大于秋冬季节;南部沉降区则与之相反。总之,基于时间主成分分析方法可分析得到研究区的地面沉降时空演化规律,为城市安全监测提供数据支撑。     

高分五号高光谱影像的关联对齐域适应与分类

高分五号(GF-5)搭载的高光谱传感器兼顾宽覆盖和高分辨率的特性,但在实际应用中宽覆盖范围内各种地物类别的标注十分困难。当标记样本很少甚至没有标记样本时,遥感图像分类异常困难。此时,可以采用域适应方法,借助已标记的历史数据(源域)实现对未标记数据(目标域)的分类。本文提出了一种基于稀疏矩阵变换的关联对齐域适应分类算法。首先,利用稀疏矩阵变换估计源域和目标域的协方差矩阵;然后,运用协方差关联对齐方法估计源域到目标域的变换矩阵;接着,运用估计得到的变换矩阵将源域数据进行变换,使得其与目标域对齐;最后,在变换后的源域数据上建立分类器,实现对目标域数据的分类。本文的算法在两个真实的GF-5高光谱数据集上进行了验证。实验结果表明,本文算法要优于常用的子空间对齐算法和关联对齐算法。特别地,在黄河口GF-5数据上,本文算法比原始关联对齐方法的最近邻分类准确率提升了3.5%,支持向量机分类准确率提升了2.3%。     

Segmented Principal Component Analysis for Parallel Compression of Hyperspectral Imagery

Principal component analysis (PCA) is widely used for spectral decorrelation in the JPEG2000 compression of hyperspectral imagery. However, due to the data-dependent nature of principal components, the principal component transform matrix is stored in the JPEG2000 bitstream, constituting an overhead that is often negligible if the spatial size of the image is large. However, in parallel compression in which the data set is partitioned to multiple independent processing nodes, the overhead may no longer remain negligible. It is shown that a segmented approach to PCA can greatly mitigate the detrimental effects of transform-matrix overhead and can outperform wavelet-based decorrelation which entails no such overhead.     

遥感分析中小型地物波谱数据库系统的设计与实现

随着遥感定量研究的深入和遥感应用的发展,地物波谱数据库的建立对遥感技术的应用具有支撑作用。文章介绍了一个小型波谱数据库系统设计和实现过程,并对建立统一的、标准的地物波谱数据库系统作了探讨和展望。