高光谱遥感图像的单形体分析方法

将n个波段的高光谱图像像元与n维空间里的散点联系起来，结合凸体几何中单形体概念研究高光谱遥感图像纯净像元提取方法，实现图像的地物精确分类识别及像元波谱分解。寻找高光谱遥感图像n维空间里的单形体并认知分析单形体是该研究方法的重要环节。通过MNF(minimum noise fraction)变换和PPI(pixel purity index)计算技术寻找到单形体，基于单形体进行像元分解分析单形体，并结合应用实例和SAM(spectral angle mapper)分类技术完成高光谱图像地物精确分类制图，验证了该研究方法的可操作性。该研究方法的优点在于不需要用户提供地物波谱信息，用于制图和波谱分解的终端单元可由图像本身得到，并由用户控制分类制图和波谱分解的详细程度。     

A Family of Inexpensive Sampling Schemes

To improve image quality in computer graphics, antialiazing techniques such as supersampling and multisampling are used. We explore a family of inexpensive sampling schemes that cost as little as 1.25 samples per pixel and up to 2.0 samples per pixel. By placing sample points in the corners or on the edges of the pixels, sharing can occur between pixels, and this makes it possible to create inexpensive sampling schemes. Using an evaluation and optimization framework, we present optimized sampling patterns costing 1.25, 1.5, 1.75 and 2.0 samples per pixel.     

The effect of spectral and spatial degradation of hyperspectral imagery for the Sclerophyll tree species classification

Hyperspectral imaging can be a useful remote-sensing technology for classifying tree species. Prior to the image classification stage, effective mapping endeavours must first identify the optimal spectral and spatial resolutions for discriminating the species of interest. Such a procedure may contribute to improving the classification accuracy, as well as the image acquisition planning. In this work, we address the effect of degrading the original bandwidth and pixel size of a hyperspectral and hyperspatial image for the classification of Sclerophyll forest tree species. A HySpex-VNIR 1600 airborne-based hyperspectral image with submetric spatial resolution was acquired in December 2009 for a native forest located in the foothills of the Andes of central Chile. The main tree species of this forest were then sampled in the field between January and February 2010. The original image spectral and spatial resolutions (160 bands with a width of 3.7 nm and pixel sizes of 0.3 m) were systematically degraded by resampling using a Gaussian model and a nearest neighbour method, respectively (until reaching 39 bands with a width of 14.8 nm and pixel sizes of 2.4 m). As a result, 12 images with different spectral and spatial resolution combinations were created. Subsequently, these images were noise-reduced using the minimum noise fraction procedure and 12 additional images were created. Statistical class separabilities from the spectral divergence measure and an assessment of classification accuracy of two supervised hyperspectral classifiers (spectral angle mapper (SAM) and spectral information divergence (SID)) were applied for each of the 24 images. The best overall and per-class classification accuracies (>80%) were observed when the SAM classifier was applied on the noise-reduced reflectance image at its original spectral and spatial resolutions. This result indicates that pixels somewhat smaller than the tree canopy diameters were the most appropriate to represent the spatial variability of the tree species of interest. On the other hand, it suggests that noise-reduced bands derived from the full image spectral resolution rendered the best discrimination of the spectral properties of the tree species of interest. Meanwhile, the better performance of SAM over SID may result from the ability of the former to classify tree species regardless of the illumination differences in the image. This technical approach can be particularly useful in native forest environments, where the irregular surface of the uppermost canopy is subject to a differentiated illumination.     

基于多阶抽样谱图聚类彩色图像分割

针对谱聚类应用于图像分割时权矩阵的谱难以计算的实际问题,设计了一个图像多阶抽样谱图聚类算法.首先,给出了采样数定理及其证明,并推导出与聚类类别数和最小聚类数相关的最小采样数目;其次,根据最小采样数数目,对像素点进行均匀采样,并利用谱聚类对采样点进行聚类,设计一个罚函数,通过多次抽样,消除抽样对谱聚类模型稳定性的影响;最后,定义了像素点和类之间的距离,对剩余的点按距离最近原则进行聚类.实验结果表明了算法的有效性.     

改进协同表示的高光谱图像异常检测算法

针对协同表示的高光谱图像异常检测算法中双窗口中心为异常像元同时背景字典存在同种异常像元的情况,中心像元的输出较小难以与背景区分的问题,提出一种改进协同表示的高光谱图像异常检测算法。为了减小背景字典中异常像元的权重,使用背景字典原子与均值的距离调整原子的权重,从而增大上述情况下中心像元的输出。实验结果表明,提出的算法在不同双窗口下都取得了较好的检测效果,验证了算法的有效性。     

Correcting brightness gradients in hyperspectral data from urban areas

The analysis of airborne hyperspectral data is often affected by brightness gradients that are caused by directional surface reflectance. For line scanners these gradients occur in across-track direction and depend on the sensor's view-angle. They are greatest whenever the flight path is perpendicular to the sun-target-observer plane. A common way to correct these gradients is to normalize the reflectance factors to nadir view. This is especially complicated for data from spatially and spectrally heterogeneous urban areas and requires surface type specific models. This paper presents a class-wise empirical approach that is adapted to meet the needs of such images.Within this class-wise approach, empirical models are fit to the brightness gradients of spectrally pure pixels from classes after a spectral angle mapping (SAM). Compensation factors resulting from these models are then assigned to all pixels of the image, both in a discrete manner according the SAM and in a weighted manner based on information from the SAM rule images. The latter scheme is designed in consideration of the great number of mixed pixels.The method is tested on data from the Hyperspectral Mapper (HyMap) that was acquired over Berlin, Germany. It proves superior to a common global approach based on a thorough assessment using a second HyMap image as reference. The weighted assignment of compensation factors is adequate for the correction of areas that are characterized by mixed pixels.A remainder of the original brightness gradient cannot be found in the corrected image, which can then be used for any subsequent qualitative and quantitative analyses. Thus, the proposed method enables the comparison and composition of airborne data sets with similar recording conditions and does not require additional field or laboratory measurements.     

Using low‐spectral‐resolution images to acquire simulated hyperspectral images

We propose a method to acquire simulated hyperspectral images using low‐spectral‐resolution images. Hyperspectral images provide more spectral information than low‐spectral‐resolution images, because of the additional spectral bands used for data acquisition in hyperspectral imaging. Unfortunately, original hyperspectral images are more expensive and more difficult to acquire. However, some research questions require an abundance of spectral information for ground monitoring, which original hyperspectral images can easily provide. Hence, we need to propose a method to acquire simulated hyperspectral images, when original hyperspectral images are especially necessary. Since low‐spectral‐resolution images are readily available and cheaper, we develop a method to acquire simulated hyperspectral images using low‐spectral‐resolution images. With simulated hyperspectral images, we can acquire more ‘hidden’ information from low‐spectral‐resolution images. Our method uses the principles of pixel‐mixing to understand the compositional relationship of spectrum data to an image pixel, and to simulate radiation transmission processes. To this end, we use previously obtained data (i.e. spectrum library) and the sorting data of objects that are derived from a low‐spectral‐resolution image. Using the simulation of radiation transmission processes and these different data, we acquire simulated hyperspectral images. In addition, previous analyses of simulated remotely sensed images do not use quantitative statistical measures, but use qualitative methods, describing simulated images by sight. Here, we quantitatively assess our simulation by comparing the correlation coefficients of simulated images and real images. Finally, we use simulated hyperspectral images, real Hyperion images, and their corresponding ALI images to generate several classification images. The classification results demonstrate that simulated hyperspectral data contain additional information not available in the multispectral data. We find that our method can acquire simulated hyperspectral images quickly.     

Edge-preserving-based collaborative representation for spectral-spatial classification

Recently, the nearest regularized subspace (NRS) classifier and its spectral–spatial versions such as joint collaborative representation (JCR) and weighted JCR (WJCR) have gained an increasing interest in the hyperspectral image classification. JCR and WJCR average each pixel with its neighbours in a spatial neighbourhood window. The use of spatial information as averaging of pixels in a local window may degrade the classification accuracy in the neighbourhood of discontinuities and class boundaries. We propose the edge-preserving-based collaborative representation (EPCR) classifier in this article, which overcomes this problem by using the edge image estimated by the original full-band hyperspectral image. The estimated edge image is used for calculation of the weights of neighbours and also the final residuals in the collaborative representation classifier. The advantage of multiscale spatial window is also assessed in this work. Moreover, the kernelized versions of NRS and its improved versions are developed in this article. Our experimental results on several popular hyperspectral images indicate that EPCR and its kernelized version are superior to some state-of-the-art classification methods.     

基于改进SAM的高光谱影像混合像元分解算法研究

将传统遥感图像分类方法中的光谱角度制图法(Spectral Angle Mapping-SAM)加以变换,改进为一种符合全约束条件下的高光谱遥感图像的混合像元分解模型.新算法在端元丰度比例满足全约束的条件下,通过逼近的方法寻找一种端元丰度的比例组合,使测试光谱与目标光谱的广义夹角最小,从而认为该比例组合就是混合像元分解...     

基于超像素的流形正则化稀疏约束NMF混合像元分解算法

针对传统非负矩阵分解（NMF）法用于高光谱图像混合像元分解时产生的分解结果精度不高、对噪声敏感等问题，提出一种基于超像素的流形正则化稀疏约束NMF混合像元分解算法——MRS-NMF。首先，通过基于熵率的超像素分割来构造高光谱图像的流形结构，把原图像分割为k个超像素块并把每个超像素块中具有相似性质的数据点标上相同的标签，定义像素块内有相同标签的任意两个数据点之间的权重矩阵，然后将权重矩阵应用于NMF的目标函数中以构造出流形正则化约束项；第二，在目标函数中添加二次抛物线函数以完成稀疏约束；最后，采用乘法迭代更新法则求解目标函数以得到端元矩阵和丰度矩阵的求解公式，同时设置最大迭代次数和容忍误差阈值，迭代运算得到最终结果。该方法有效利用了高光谱图像的光谱和空间信息。实验结果表明，在模拟的高光谱数据中，与传统的流形稀疏约束的非负矩阵分解（GLNMF）、L1/2-NMF和顶点成分分析-全约束最小二乘法（VCA-FCLS）等方法相比，MRS-NMF可以提高0.016~0.063的端元分解精度和0.01~0.05的丰度分解精度；而在真实的高光谱图像中，MRS-NMF较传统的GLNMF、顶点成分分析法（VCA）、最小体积约束的非负矩阵分解（MVCNMF）等方法可以平均提高0.001~0.0437的端元分解精度。所提MRS-NMF算法有效地提高了混合像元分解的精度，同时具有较好的抗噪性能。     

Mapping spatial variations of iron oxide by-product minerals from EO-1 Hyperion

This study aimed to map mine waste piles and iron oxide by-product minerals from an Earth Observing 1 (EO-1) Hyperion data set that covers an abandoned mine in southwest Spain. This was achieved by a procedure involving data pre-processing, atmospheric calibration, data post-processing, and image classification.

In several steps, the noise and artefacts in the spectral and spatial domains of the EO-1 Hyperion data set were removed. These steps include the following: (1) angular shift, which was used to translate time sequential data into a spatial domain; (2) along-track de-striping to remove the vertical stripes from the data set; and (3) reducing the cross-track low-frequency spectral effect (smile). The Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH) algorithm in combination with the radiance transfer code MODTRAN4 was applied for quantification and removal of the atmospheric affect and retrieval of the surface reflectance. The data set was post-processed (filtering, spectral polishing) in order to remove the negative values and noise that were produced as the a result of de-striping and atmospheric calibration. The Mahalanobis distance algorithm is used to differentiate the area covered by mine piles from other main land-use classes. The spatial variations of iron oxide and carbonate minerals within the mine area were mapped using the Spectral Feature Fitting (SFF) algorithm.

The pre-processing of the data and atmospheric correction were vital and played a major role on the quality of the final output. The results indicate that the vertical stripes can be removed rather well by the local algorithm compared to the global method and that the FLAASH algorithm for atmospheric correction produces better results than the empirical line algorithm. The results also showed that the method developed for correcting angular shifts has the advantage of keeping the original pixel values since it does not require re-sampling.

The classification results showed that the mine waste deposits can be easily mapped using available standard algorithms such as Mahalanobis Distance. The results obtained from the SFF method suggest that there is an abundance of different minerals such as alunite, copiapite, ferrihydrite, goethite, jarosite, and gypsum within the mine area. From a total number of 754 pixels that cover the mine area, 43 pixels were classified as sulphide and carbonate minerals and 711 pixels remained unclassified, showing no abundance of any dominant mineral within the area presented by these pixels.     

Synthesis of mixed pixel hyperspectral signatures

The general method of analysing mixed pixel spectral response is to decompose the actual spectra into several pure spectral components representing the signatures of the endmembers. This work suggests a reverse engineering of standardizing the mixed pixel spectrum for a certain spatial distribution of endmembers by synthesizing spectral signatures with varying proportions of standard spectral library data and matching them with the experimentally obtained mixed pixel signature. The idea is demonstrated with hyperspectral ultraviolet–visible–near-infrared (UV–vis–NIR) reflectance measurements on laboratory-generated model mixed pixels consisting of different endmember surfaces: concrete, soil, brick and vegetation and hyperspectral signatures derived from Hyperion satellite images consisting of concrete, soil and vegetation in different proportions. The experimental reflectance values were compared with the computationally generated spectral variations assuming linear mixing of pure spectral signatures. Good matching in the nature of spectral variation was obtained in most cases. It is hoped that using the present concept, hyperspectral signatures of mixed pixels can be synthesized from the available spectral libraries and matched with those obtained from satellite images, even with fewer bands. Thus enhancing the computational job in the laboratory can moderate the keen requirement of high accuracy of remote-sensor and band resolution, thereby reducing data volume and transmission bandwidth.     

谐波分析光谱角制图高光谱影像分类

目的 针对光谱角制图(SAM)分类算法对高光谱像元光谱曲线的局部特征和其辐射强度不敏感,而且易受噪声和维数灾难影响,致使分类效率低和精度较差等缺陷,将谐波分析(HA)技术引入到SAM高光谱影像分类中,提出一种基于谐波分析的光谱角制图(HA-SAM)高光谱影像分类算法.方法 利用HA技术将高光谱影像从光谱维变换到能量谱特征维空间,并提取低次谐波分量及特征系数(谐波余项、相位和振幅),用特征系数组成的向量代替光谱向量,对高光谱影像进行SAM分类.结果 将SAM和HA-SAM同时应用于EO-1卫星的Hyperion高光谱影像分类,通过对比和分析,验证了HA-SAM的优越性,再选择AVIRIS(airborne visible infrared imaging spectrometer)高光谱影像对HA-SAM进行验证,结果表明该算法具有较强的普适性.结论 HA-SAM提高了传统SAM高光谱影像分类的效率和精度,而且适用性较强具有良好的应用前景.     

A novel iterative shape from focus algorithm based on combinatorial optimization

Shape from focus (SFF) is a technique to estimate the depth and 3D shape of an object from a sequence of images obtained at different focus settings. In this paper, the SFF is presented as a combinatorial optimization problem. The proposed algorithm tries to find the combination of pixel frames which produces maximum focus measure computed over pixels lying on those frames. To reduce the high computational complexity, a local search method is proposed. After the estimate of the initial depth map solution of an object, the neighborhood is defined, and an intermediate image volume is generated from the neighborhood. The updated depth map solution is found from the intermediate image volume. This update process of the depth map solution continues until the amount of improvement is negligible. The results of the proposed SFF algorithm have shown significant improvements in both the accuracy of the depth map estimation and the computational complexity, with respect to the existing SFF methods.     

Integrating visible,near-infrared and short-wave infrared hyperspectral and multispectral thermal imagery for geological mapping at Cuprite,Nevada: a rule-based system

Previous research has shown that integrating hyperspectral visible and near-infrared (VNIR) / short-wave infrared (SWIR) with multispectral thermal infrared (TIR) data can lead to improved mineral and rock identification. However, inconsistent results were found regarding the relative accuracies of different classification methods for dealing with the integrated data set. In this study, a rule-based system was developed for integration of VNIR/SWIR hyperspectral data with TIR multispectral data and evaluated using a case study of Cuprite, Nevada. Previous geological mapping, supplemented by field work and sample spectral measurements, was used to develop a generalized knowledge base for analysis of both spectral reflectance and spectral emissivity. The characteristic absorption features, albedo and the location of the spectral emissivity minimum were used to construct the decision rules. A continuum removal algorithm was used to identify absorption features from VNIR/SWIR hyperspectral data only; spectral angle mapper (SAM) and spectral feature fitting (SFF) algorithms were used to estimate the most likely rock type. The rule-based system was found to achieve a notably higher performance than the SAM, SFF, minimum distance and maximum likelihood classification methods on their own.     

基于加权K近邻和卷积神经网络的高光谱图像分类

传统的谱空联合分类算法通常定义一个邻域空间作为空间信息,忽略空间中非邻域空间信息,且容易将异类像元也考虑在内。针对于高光谱图像分类问题,提出了一种加权K近邻算法能够自适应地提取空间信息,首先定义光谱和空间坐标组成的特征空间,利用该特征空间寻找目标像元的K个相似像元,并对这些像元根据特征空间进行加权;将加权后的像元按照一定方式组合成三维张量表示最终的谱空联合信息,使用三维卷积神经网络对其进行训练,得到最终分类结果。从实验结果来看,相对于改进前的算法,在总体分类精度上得到了一定的提升,与原始的三维卷积神经网络相比,在收敛速度上也得到大大提升,为高光谱图像的谱空联合分类提供了一种更加实用的方法。     

A Bayesian approach to visualization-oriented hyperspectral image fusion

In this paper, we propose a Bayesian approach towards fusion of hyperspectral images for the purpose of efficient visualization. Fusion has been posed as an estimation problem where the observed hyperspectral bands have been related to the fused image through a first order model of image formation. The parameters of the model indicate the quality of the pixel captured locally. As visualization is our primary aim of fusion, we expect higher contribution of the “visually important” pixels towards the final fused image. We propose a two-step framework for fusion of hyperspectral image, where the first step identifies the quality of each pixel of the data based on some of the local quality measures of the hyperspectral data. Subsequently, we formulate the problem of the estimation of the fused image in a MAP framework. We incorporate the total variation (TV) norm-based prior which preserves the sharp discontinuities in the fused image. The fused images, thus, appear sharp and natural where the edges and boundaries have been retained. We have provided visual as well as quantitative results to substantiate the effectiveness of the proposed technique.     

基于双重L2稀疏编码的高光谱图像分类

目的 为了有效提高高光谱图像分类的精度,提出了双重L2稀疏编码的高光谱图像分类方法。方法 首先对高光谱图像进行预处理,充分结合图像的空间信息和光谱信息,利用像元的空间连续性,用L2稀疏编码重建图像中每个像元。针对重建的图像数据,依据L2稀疏编码的最小误差和编码系数实现分类。结果 在公开的数据库AVIRIS高光谱图像上进行验证,分类精度为99.44%,与支持向量机（SVM）、K最近邻（KNN）和L1稀疏编码方法比较,有效地提高了分类的准确性。结论 实验结果表明,提出的方法应用于高光谱图像分类具有较好的分类效果。     

基于离群点检测的图形图象噪声滤除算法

图形图象噪声过滤与修正,在媒体制作、图象分析与信息提取中起着十分重要的作用.虽然基于小波变换的算法能够对高斯噪声进行较好的滤噪处理,但对于随机分布于图象中的各种非高斯噪声仍没有普遍适用的滤噪方法.为了对这种随机分布于图象中的噪声进行有效的检测与滤除,采用对数字图象像素进行解析化描述的方法,从离群点检测的角度给出噪声的定义,并在此基础上构造了相应的图象噪声检测与滤除算法.实验结果表明,这一新方法对图象类型具有广泛的适应性和较好的噪声滤除效果,在大规模图形图象处理应用中具有实用价值.     

Combining medium and coarse spatial resolution satellite data to improve the estimation of sub-pixel NDVI time series

The potential of multitemporal coarse spatial resolution remotely sensed images for vegetation monitoring is reduced in fragmented landscapes, where most of the pixels are composed of a mixture of different surfaces. Several approaches have been proposed for the estimation of reflectance or NDVI values of the different land-cover classes included in a low resolution mixed pixel. In this paper, we propose a novel approach for the estimation of sub-pixel NDVI values from multitemporal coarse resolution satellite data. Sub-pixel NDVIs for the different land-cover classes are calculated by solving a weighted linear system of equations for each pixel of a coarse resolution image, exploiting information about within-pixel fractional cover derived from a high resolution land-use map. The weights assigned to the different pixels of the image for the estimation of sub-pixel NDVIs of a target pixel i are calculated taking into account both the spatial distance between each pixel and the target and their spectral dissimilarity estimated on medium-resolution remote-sensing images acquired in different periods of the year. The algorithm was applied to daily and 16-day composite MODIS NDVI images, using Landsat-5 TM images for calculation of weights and accuracy evaluation.Results showed that application of the algorithm provided good estimates of sub-pixel NDVIs even for poorly represented land-cover classes (i.e., with a low total cover in the test area). No significant accuracy differences were found between results obtained on daily and composite MODIS images. The main advantage of the proposed technique with respect to others is that the inclusion of the spectral term in weight calculation allows an accurate estimate of sub-pixel NDVI time series even for land-cover classes characterized by large and rapid spatial variations in their spectral properties.