基于多视图边界判别投影的高光谱图像分类

高光谱图像分类是遥感领域研究的热点问题,其关键在于利用高光谱图谱合一的 优势,同时融合高光谱图像中各个像元位置的光谱信息和空间信息,提高光谱图像分类精度。 针对高光谱图像特征维数高和冗余信息多等问题,采用多视图子空间学习方法进行特征降维, 提出了图正则化的多视图边界判别投影算法。将每个像元处的光谱特征看作一个视图,该像元 处的空间特征看作另一个视图,通过同时优化每个视图上的投影方向来寻找最优判别公共子空 间。公开测试数据集上的分类实验表明,多视图学习在高光谱图像空谱融合分类方面具有显著 的优越性,在多视图降维算法中,该算法具有最高的分类准确性。     

Review Article Principles of field spectroscopy

Abstract

Field spectroscopy involves the study of the interrelationships between the spectral characteristics of objects and their biophysical attributes in the field environment. It is a technique of fundamental importance in remote sensing, yet its full potential is rarely exploited. In this article the principles of the subject are explained and its historical development reviewed with reference to the instruments and methods adopted. Field spectroscopy has a role to play in at least three areas of remote sensing. Firstly, it acts as a ridge between laboratory measurements of spectral reflectance and the field situation and is thus useful in the calibration of airborne and satellite sensors. Secondly, it is useful in predicting the optimum spectral bands, viewing configuration and time to perform a particular remote sensing task. Thirdly, it provides a tool for the development, refinement and testing of models relating biophysical attributes to remotely-sensed data.     

An automated binary change detection model using a calibration approach

An automated binary change detection model using a threshold-based calibration approach was introduced in the study. The burdensome processes required in binary change detection, including calibration, calculation of accuracy, extraction of optimum threshold(s), generation of a binary change mask, and removal of “salt-and-pepper” noise were integrated and automated in the model. For practical purpose, the model was implemented as a dynamic linked library in ESRI ArcMap 9.1 using Visual Basic. This study demonstrated the model with a variety of single and multiple variables (layers) extracted from multiple-date QuickBird imagery for three study sites in Las Vegas, NV and two study sites in Tucson, AZ. The use of multiple variables in binary change detection resulted in significantly better performance than single variables.     

成像光谱遥感定标模型的分析与评价

通过对目前国际上流行的几种光谱定标模型的分析研究，发现：基于图像结构特征的定标模型具有丢失光谱特征的缺点；基于ＲＴ定标模型对水汽过分敏感；基于ＥＬ的定标模型对地形要求严格；而基于光谱混合理论的定标模型其内部算法仍需改进，等等。由此，在实际工作中，根据实际工作条件和应用要求进行定标模型的取舍是十分重要的     

高光谱数据特征选择与特征提取研究

高光谱遥感数据的最主要特点是: 传统图像维与光谱维信息融合为一体, 即“图谱合一”。针对高光谱数据波段多、数据量大、冗余度大等特点, 论述了特征选择和特征提取的若干算法, 分析了各自的优缺点。重点研究了导数光谱算法, 并针对二值编码的不足研究了其改进算法-- 四值编码算法。最后用编码技术和导数光谱技术提取了地物的光谱特征参数; 试验表明: 四值编码算法比二值编码算法效果更佳; 光谱导数阶数越高, 对地物特征的表达越有效。     

基于Mask R-CNN改进的遥感图像舰船检测

遥感图像中舰船朝向不确定性,舰船种类的多样性以及和其他海上及港口物体之间的相似性,使舰船检测的性能下降严重。针对这一问题,使用一种简单且有效的方法来训练有旋转不变性和Fisher判别的Mask R-CNN舰船检测模型,通过优化模型的目标函数以提高舰船检测性能,在保持原有检测模型结构不变的基础上引入两个正则化器,第一个正则化器加强训练样本旋转之前和之后的特征联系,第二个正则化器限制卷积神经网络有小的类内散度和大的类间散度。实验中,在Kaggle遥感图像船只检测数据集上验证了所提出的方法提高了检测遥感图像中舰船目标的性能。     

高光谱遥感岩矿识别填图的技术流程与主要技术方法综述

自20世纪80年代以来,伴随着多种航空和航天成像光谱仪的研制成功和投入运行,一系列的图像光谱基本处理手段和实验室岩矿光谱分析技术方法,如最小噪声分量(MNF)变换-像元纯度指数(Pixel Purity Index,PPI)-N维可视化(N-Dimensional Visualization)、岩石类型系统光谱分类、多变量统计分析、矿物光谱特征确认的概率分析、MGM技术等相继发展起来,从而为形成成像光谱岩矿填图的完整技术流程打下了坚实的技术基础。分析了多种岩矿光谱分析的技术方法,同时指出,不同方法具有各自的优、缺点,针对不同应用目标需要不同的矿物识别与岩矿填图方案;混合方法的开发应用和从可见光到微波波段的融合应用在未来更为重要。     

融入邻域作用的高斯混合分割模型及简化求解

目的 基于高斯混合模型（GMM）的图像分割方法易受噪声影响,为此采用马尔可夫随机场（MRF）将像素邻域关系引入GMM,提高算法抗噪性。针对融入邻域作用的高斯混合分割模型结构复杂、参数估计困难,难以获得全局最优分割解等问题,提出一种融入邻域作用的高斯混合分割模型及其简化求解方法。方法 首先,构建融入邻域作用的GMM。为了提高GMM的抗噪性,采用MRF建模混合模型权重系数的先验分布。然后,利用贝叶斯理论建立图像分割模型,即品质函数;由于品质函数中参数较多（包括权重系数,均值,协方差）、函数结构复杂,导致参数求解困难。因此,将品质函数中的均值和协方差定义为权重系数的函数,由此简化模型结构并方便其求解;虽然品质函数中仅包含参数权重系数,但结构比较复杂,难以求得参数的解析式。最后,采用非线性共轭梯度法（CGM）求解参数,该方法仅需利用品质函数值和参数梯度值,降低了参数求解的复杂性,并且收敛快,可以得到全局最优解。结果 为了有效而准确地验证提出的分割方法,分别采用本文算法和对比算法对合成图像和高分辨率遥感图像进行分割实验,并定性和定量地评价和分析了实验结果。实验结果表明本文方法的有效抗噪性,并得到很好的分割结果。从参数估计结果可以看出,本文算法有效简化了模型参数,并获得全局最优解。结论 提出一种融入邻域作用的高斯混合分割模型及其简化求解方法,实验结果表明,本文算法提高了算法的抗噪性,有效地简化了模型参数,并得到全局最优参数解。本文算法对具有噪声的高分辨率遥感影像广泛适用。     

多门限二进制编码方法在TM 图像处理中的应用

不同类型的地物具有不同的反射光谱, 在多维光谱空间中构成不同的特征向量, 这便是遥感多光谱图像分析与识别的物理依据。传统方法中有基于单个像元波段亮度的、空间纹理的、变换空间的多光谱图像特征提取与分析方法, 但这些方法并没有直接描述地物的最本质特征-反射光谱曲线。从20 世纪80 年代开始, 当二进制编码的方法提出并在多光谱匹配识别中获得成功应用后,多光谱图像分析处理便可以在这种特征提取的基础上, 研究新的方法。提出一种基于多门限二进制编码的光谱形状描述方法, 这种方法的核心就是将多光谱的亮度范围细分成若干个灰度区间, 也称为多门限, 分别将各波段光谱亮度与多门限进行比较, 从而建立一列能够较详细描述光谱形状的二进制编码, 我们将这种新的特征描述方法应用于多光谱图像的分类、信息提取和变化检测。遥感图像处理实验的结果表明, 这种方法是有效的。     

典型地物波谱数据库设计与实现

地物波谱数据是定量遥感的理论基础。根据典型地物波谱数据的多源异质特点,在需求分析基础上,对典型地物波谱数据库的功能和结构进行了设计,将数据库划分为波谱数据采集和输入、波谱数据编辑与处理、波谱数据查询与检索、波谱曲线绘制与显示以及波谱数据挖掘与融和等功能模块,并应用Visual C＋＋开发工具,实现了各模块功能,为典型地物波谱数据的管理和分析提供了一个新的技术平台。     

Remote estimation of chlorophyll a in optically complex waters based on optical classification

Accurate assessment of phytoplankton chlorophyll a (Chla) concentration in turbid waters by means of remote sensing is challenging due to optically complexity and significant variability of case 2 waters, especially in inland waters with multiple optical types. In this study, a water optical classification algorithm is developed, and two semi-analytical algorithms (three- and four-band algorithm) for estimating Chla are calibrated and validated using four independent datasets collected from Taihu Lake, Chaohu Lake, and Three Gorges Reservoir. The optical classification algorithm is developed using the dataset collected in Taihu Lake from 2006 to 2009. This dataset is also used to calibrate the three- and four-band Chla estimation algorithms. The optical classification technique uses remote sensing reflectance at three bands: Rrs(G), Rrs(650), and Rrs(NIR), where G indicates the location of reflectance peak in the green region (around 560 nm), and NIR is the location of reflectance peak in the near-infrared region (around 700 nm). Optimal reference wavelengths of the three- and four-band algorithm are located through model tuning and accuracy optimization. The three- and four-band algorithm accuracy is further evaluated using other three independent datasets. The improvement of optical classification in Chla estimation is revealed by comparing the performance of the two algorithms for non-classified and classified waters.Using the slopes of the three reflectance bands, the 138 reflectance spectra samples in the calibration dataset are classified into three classes, each with a specific spectral shape character. The three- and four-band algorithm performs well for both non-classified and classified waters in estimating Chla. For non-classified waters, strong relationships are yielded between measured and predicted Chla, but the performance of the two algorithms is not satisfactory in low Chla conditions, especially for samples with Chla below 30 mg m^− 3. For classified waters, the class-specific algorithms perform better than for non-classified waters. Class-specific algorithms reduce considerable mean relative error from algorithms for non-classified waters in Chla predicting. Optical classification makes that there is no need to adjust the optimal position to estimate Chla for other waters using the class-specific algorithms. The findings in this study demonstrate that optical classification can greatly improve the accuracy of Chla estimation in optically complex waters.     

Efficient radiative transfer model inversion for remote sensing applications

A simple method for efficient inversion of arbitrary radiative transfer models for image analysis is presented. The method operates by representing the shape of the function that maps model parameters to spectral reflectance by an adaptive look-up tree (ALUT) that evenly distributes the discretization error of tabulated reflectances in spectral space. A post-processing step organizes the data into a binary space partitioning tree that facilitates an efficient inversion search algorithm. In an example shallow water remote sensing application, the method performs faster than an implementation of previously published methodology and has the same accuracy in bathymetric retrievals. The method has no user configuration parameters requiring expert knowledge and minimizes the number of forward model runs required, making it highly suitable for routine operational implementation of image analysis methods. For the research community, straightforward and robust inversion allows research to focus on improving the radiative transfer models themselves without the added complication of devising an inversion strategy.     

基于相位一致特征的CBERS-02B遥感图像自动配准

以CBERS-02B卫星HR高分辨率和CCD多光谱遥感图像数据为基础,针对基于特征的自动配准方法中的特征检测与特征匹配两个关键步骤,通过引入性能优良的相位一致特征检测方法和特征相似与空间关系相结合的特征匹配策略,实现了一种基于相位一致特征的遥感图像高精度自动配准方法。实验结果表明,该方法对遥感图像亮度和对比度具有不变性,能稳定可靠提取HR高分辨率和CCD多光谱遥感图像显著的点特征,精确匹配相位一致特征点,实现了CBERS-02B卫星不同谱段,不同传感器和不同时相遥感图像间高精度自动配准,所进行实验的自动配准精度均到达了优于0.3 像元的系统配准精度。因此,该自动配准方法适合应用于有高配准精度要求的遥感图像间自动配准。     

基于GEPSO模型的面向对象遥感图像分类

针对演化算法的寻优能力,提出了基于GEPSO(GEP Optimized by PSO)模型的面向对象遥感图像分类方法.先对遥感图像进行分割,选择特征集,然后利用GEPSO算法为每类图像对象构造一个类中心.构造类中心的过程先利用GEP搜索一个次优解,再根据这个次优解利用PSO搜索最优解.实验结果表明,基于GEPSO模型的面向对象遥感图像分类方法具有较高的分类精度.     

Multispectral and hyperspectral analysis and modelling of the absorbance characteristics of marine algal pigments

The techniques of remote sensing in spectral bands and hyperspectral remote sensing were modelled with laboratory experiments on marine algal pigments obtained from four species of green micro‐algae of the eastern coast of India. The spectral absorbance was measured within the visible range of wavelength for chlorophyll mixtures of different concentrations and also for chromatographically separated pigments. The intention was to simulate and compare the expected nature of results obtained with remote sensing in wavebands and hyperspectral sensing involving a fine resolution in wavelength. Therefore, the absorbance was measured both with filters of three different visible spectral bands, viz. blue, green, and red, and with a continuous scan of wavelength. The algal species were distinguishable with both types of measurements. However, the hyperspectral technique was found to be more suitable in revealing the individual contribution of pigments. Based on the experimental results, a computational model was developed with Gaussian variation of absorbance as a function of wavelength. The experimental results were simulated with that model explaining the comparative spectroscopic results obtained from band and hyperspectral sensing.     

分形理论在遥感中的应用

论述了分形理论在遥感中的三个应用方面:①分析遥感图像的结构信息量,包括不同图像、不同地物类型;②辅助遥感图像分类,对光谱分类的结果利用分形理论进行检验或确定类型;③模拟遥感图像,根据真实图像的分维,利用分形表面产生算法并产生模拟遥感图像。     

遥感影像中多个机密信息的授权使用技术

一般的图像域信息隐藏算法并不适用于遥感影像,将信息隐藏的涵义加以拓广,提出了遥感影像中多个机密信息的授权使用技术,即根据用户的不同权限对遥感影像中的多个机密信息进行不同程度的隐藏,并提出了适用于遥感影像的信息隐藏小波域算法,该算法是盲算法,且基于HVS(human visual system)特性,并自适应于遥感影像特征。能很好地保存机密地物的纹理与光谱特性,复原遥感影像逼真,对遥感影像的应用价值没有影响,且对影像添噪与JPEG有损压缩具有较强的鲁棒性。     

区域化模糊均值高分辨率彩色遥感影像分割方法

基于像素模糊?? 均值算法(FCM) 及其改进算法难以解决高分辨率遥感影像中地物目标光谱测度相似性减弱和几何噪声增大带来的分割难题, 提出一种基于区域的FCM算法. 该方法利用Voronoi 几何划分将影像域划分为子区域, 并用子区域拟合地物目标的几何形状. 在此基础上, 定义区域FCM目标函数, 通过迭代最小化该目标函数实现高分辨率遥感影像分割. 实验结果表明, 与基于像素的FCM和增强FCM方法相比, 所提出方法可以更加精确地实现高分辨率遥感影像分割.

     

基于Terra/MODIS数据的HJ-1B/CCD1交叉定标方法研究

交叉辐射定标是国际上新近发展起来的一种无场地定标方法,它的应用弥补了场地定标成本较高、定标参数更新周期较长的不足。对于我国2008年发射的环境与灾害监测预报小卫星CCD数据而言,探索交叉辐射定标方法的适用性,对及时发现传感器辐射性能的变化,促进CCD遥感数据的定量化应用具有重要意义。本研究以辐射定标精度较高的Terra/MODIS数据为参考,分别使用光线匹配法（RM）和辐射传输模型方法（RTM）对HJ-1B/CCD1数据进行交叉辐射定标,并与相同条件下进行的场地定标结果比较。实验结果表明,使用这两种方法获取的CCD1的第2、3、4波段的定标结果与场地定标结果差异较小,只有第1波段定标结果与场地定标结果差异相对较大,这证明了交叉辐射定标方法的有效性。另外,虽然RTM方法考虑了参考传感器和待定标传感器光谱响应和观测几何的差异,但是由于RTM方法会受到所使用的6S模型本身的误差以及输入的大气参数、地表参数测量误差的影响,该方法并不总是优于RM方法。     

利用FIHS和BT的遥感影像融合改进算法

影像融合可以显著提高影像的空间分辨率,但融合时高频信息的注入势必会造成融合影像的光谱失真。在对FIHS（Fast Intensity-Hue-Saturation）算法和BT（Brovey Transformation）算法光谱失真原理研究的基础上,提出一种能有效减弱光谱失真和提高影像空间分辨率的FIHS-BT算法。该算法通过利用全色影像的低频信息和多光谱影像生成模拟全色影像,减弱全色影像低频信息对融合影像光谱信息的影响,削弱多光谱影像高频信息对融合影像高频信息的干扰;然后,采用FIHS和BT乘积的平方根生成融合影像,以减小饱和度在变换中被拉伸或压缩的程度。选取IKONOS影像为数据源,采用BT等九种融合算法与FIHS-BT算法进行融合比较实验,并对融合结果从光谱保真度和高频信息融入度两个方面进行定性和定量评价。实验结果表明,FIHS-BT算法在光谱保真度和高频信息融入度方面较FIHS算法和BT算法均有显著改善。