空谱结构保持的高光谱图像分类

高光谱遥感图像具有特征（波段）数多、冗余度高等特点,因此特征选择成为高光谱分类的研究热点。针对此问题,提出了空间结构与光谱结构同时保持的高光谱数据分类算法。考虑高光谱图像的物理特性,首先对图像进行加权空谱重构,使图像的空间结构信息自动融入光谱特征,形成空谱特征集;对利用最小二乘回归模型保存数据集的全局相似性结构的基础上,加入局部流形结构正则项,使挑选的特征子集更好地保存数据集的内在本质结构;讨论了窗口大小和正则参数对分类精度的影响。对Indian Pines、PaviaU和Salinas数据集的实验表明,该算法得到的特征子集的总体分类精度达到93.22%、96.01%和95.90%。该算法不仅充分利用了高光谱图像的空间结构信息,而且深入挖掘了数据集的内在本质结构,从而得到更有鉴别性的特征子集,相比传统方法明显提高了分类精度。     

Representative band selection for hyperspectral image classification

High dimensional curse for hyperspectral images is one major challenge in image classification. In this work, we introduce a novel spectral band selection method by representative band mining. In the proposed method, the distance between two spectral bands is measured by using disjoint information. For band selection, all spectral bands are first grouped into clusters, and representative bands are selected from these clusters. Different from existing clustering-based band selection methods which select bands from each cluster individually, the proposed method aims to select representative bands simultaneously by exploring the relationship among all band clusters. The optimal representative band selection is based on the criteria of minimizing the distance inside each cluster and maximizing the distance among different representative bands. These selected bands can be further applied in hyperspectral image classification. Experiments are conducted on the 92AV3C Indian Pine data set. Experimental results show that the disjoint information-based spectral band distance measure is effective and the proposed representative band selection approach outperforms state-of-the-art methods for high dimensional image classification.     

利用背景残差数据检测高光谱图像异常

针对高光谱图像微小目标检测中存在的严重背景干扰问题,提出了一种基于背景残差数据的非线性异常检测算法.首先利用提取的背景光谱端元对图像各像元进行光谱解混,实现了目标信息和复杂背景信息的分离;接着将含有丰富目标信息的解混残差数据非线性映射到高维特征空间,可以充分挖掘高光谱图像波段间隐含的非线性信息,并在特征空间利用RX算子完成目标的检测,从而在抑制大概率背景信息的基础上有效地利用了高光谱图像波段间的非线性统计特性.为了验证算法的有效性,利用真实的AVIRIS数据进行了实验研究,并与经典RX算法、未抑制背景的特征空间核RX算法的检测结果相比较,结果表明基于背景残差数据的检测算法具有良好的检测性能和较低的虚警,且运算复杂度较低.     

Extraction of Spectral Channels From Hyperspectral Images for Classification Purposes

This paper proposes a procedure to extract spectral channels of variable bandwidths and spectral positions from the hyperspectral image in such a way as to optimize the accuracy for a specific classification problem. In particular, each spectral channel ("s-band") is obtained by averaging a group of contiguous channels of the hyperspectral image ("h-bands"). Therefore, if one wants to define m s-bands, the problem can be formulated as the optimization of the related m starting and m ending h-bands. Toward this end, we propose to adopt, as an optimization criterion, an interclass distance computed on a training set and to generate a sequence of possible solutions by one of three possible search strategies. As the proposed formalization of the problem makes it analogous to a feature-selection problem, the proposed three strategies have been derived by modifying three feature-selection strategies, namely: 1) the "sequential forward selection", 2) the "steepest ascent," and 3) the "fast constrained search". Experimental results on a well-known hyperspectral data set confirm the effectiveness of the approach, which yields better results than other widely used methods. The importance of this kind of procedure lies in feature reduction for hyperspectral image classification or in the case-based design of the spectral bands of a programmable sensor. It represents a special case of feature extraction that is expected to be more powerful than feature selection. The kind of transformation used allows the interpretability of the new features (i.e., the spectral bands) to be saved     

基于聚类的高光谱图像无损压缩

高光谱海量数据的有效压缩成为遥感技术发展中需要迫切解决的问题。该文提出了一种基于聚类的高光谱图像无损压缩算法。针对高光谱图像不同频谱波段间相关性不同的特点,根据相邻波段相关性大小进行波段分组。由于高光谱图像波段数量较多,采用自适应波段选择算法对高光谱图像进行降维,以获取信息量较大的部分波段,利用k均值算法对降维后的波段谱矢量进行聚类。采用多波段预测的方案对各组中的波段进行预测,对于各个分类中的每个像素,分别选取与其空间相邻的已编码的部分同类点进行训练,从而获得当前像素的谱间最优预测系数。对AVIRIS型高光谱图像的实验结果表明,该算法可显著降低压缩后的平均比特率。     

Unsupervised Linear Feature-Extraction Methods and Their Effects in the Classification of High-Dimensional Data

This paper presents an analysis and a comparison of different linear unsupervised feature-extraction methods applied to hyperdimensional data and their impact on classification. The dimensionality reduction methods studied are under the category of unsupervised linear transformations: principal component analysis, projection pursuit (PP), and band subset selection. Special attention is paid to an optimized version of the PP introduced in this paper: optimized information divergence PP, which is the maximization of the information divergence between the probability density function of the projected data and the Gaussian distribution. This paper is particularly relevant with current and the next generation of hyperspectral sensors that acquire more information in a higher number of spectral channels or bands when compared to multispectral data. The process to uncover these high-dimensional data patterns is not a simple one. Challenges such as the Hughes phenomenon and the curse of dimensionality have an impact in high-dimensional data analysis. Unsupervised feature extraction, implemented as a linear projection from a higher dimensional space to a lower dimensional subspace, is a relevant process necessary for hyperspectral data analysis due to its capacity to overcome some difficulties of high-dimensional data. An objective of unsupervised feature extraction in hyperspectral data analysis is to reduce the dimensionality of the data maintaining its capability to discriminate data patterns of interest from unknown cluttered background that may be present in the data set. This paper presents a study of the impact these mechanisms have in the classification process. The impact is studied for supervised classification even on the conditions of a small number of training samples and unsupervised classification where unknown structures are to be uncovered and detected     

基于信息论准则的高光谱波段选择方法

与传统多光谱遥感图像相比,高光谱图像是在一定波段范围内窄波段成像的,提供了丰富的光谱信息,拓展了遥感技术的应用范围,但同时存在数据含量大、波段间相关性高等问题,在进行处理时需要对高光谱图像进行降维。通过分析现有高光谱波段选择方法 ,本文提出了一种基于信息论准则的高光谱波段选择方法 ,结合波段信息熵与波段间的相关性,采用粒子群优化算法(PSO)进行波段优选,克服了采用单一使用信息量为适应度的片面性。最后使用AVIRIS图像对提出的算法进行试验,并利用支持向量机分类方法进行分类验证,总体分类精度达到91.0%。     

基于四阶累积量的波段子集高光谱图像异常检测

针对由于高光谱图像光谱和空间分布的复杂性导致核RX算法检测性能不高这一问题,提出了基于四阶累积量的波段子集非线性异常检测算法。首先先依据各相邻波段间的相关系数,将原始图像数据划分为多组波段子集;然后,利用主成分分析(PCA)构造的正交子空间对各波段子集进行背景抑制,得到图像误差数据;在此基础上,再次利用PCA提取各波段子集的特征信息,使异常目标信息集中于前面几个波段;最后,提取各子集主成分中含有最大四阶累积量值的波段,构成最优波段子集,并与核RX算法结合进行异常检测。利用真实的AVIRIS高光谱图像对算法进行仿真,结果表明,本文算法检测精度高,虚警率低,性能明显优于核RX算法。     

Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries

At the core of most hyperspectral processing algorithms are distance metrics that compare two spectra and return a scalar value based on some notion of similarity. The two most common distance metrics in hyperspectral processing are the spectral angle mapper (SAM) and the Euclidean minimum distance (EMD), and each metric possesses distinct mathematical and physical properties. In this paper, we enumerate the characteristics of both metrics, and, based on an exact decomposition of SAM, we derive a technique called band add-on (BAO) that iteratively selects bands to increase the angular separation between two spectra. Unlike other feature selection algorithms, BAO exploits a mathematical decomposition of SAM to incrementally add bands. We extend BAO to the more practical problem of increasing the angular separability between two classes of spectra. This scenario parallels the material identification problem where quite often only a small number (<10) of ground-truth measurements are collected for each material class, and statistical classification methods are inapplicable. Two algorithms for selecting bands and class templates are presented to increase the angular separation between two classes. The techniques are compared with several other metric-based approaches in binary discrimination tests with real data. The results demonstrate that band selection can improve the discrimination of very similar targets, while using only a fraction of the available spectral bands.     

基于特征重要性的高光谱图像分类

为了减少高光谱图像中的冗余以及进一步挖掘潜在的分类信息,本文提出了一种基于特征重要性的卷积神经网络（convolutional neural networks,CNN）分类模型。首先,利用贝叶斯优化训练得到的随机森林模型（random forest,RF）对高光谱遥感图像进行特征重要性评估;其次,依据评估结果选择合适数目的高光谱图像波段,以作为新的训练样本;最后,利用三维卷积神经网络对所得样本进行特征提取并分类。基于两个实测的高光谱遥感图像数据,实验结果均表明:相比原始光谱信息直接采用支持向量机（support vector machine,SVM）和卷积神经网络的分类效果,本文所提基于特征重要性的高光谱分类模型能够在降维的同时有效提高高光谱图像的分类精度。     

Multi-resolution analysis techniques and nonlinear PCA for hybrid pansharpening applications

Hyperspectral images have a higher spectral resolution (i.e., a larger number of bands covering the electromagnetic spectrum), but a lower spatial resolution with respect to multispectral or panchromatic acquisitions. For increasing the capabilities of the data in terms of utilization and interpretation, hyperspectral images having both high spectral and spatial resolution are desired. This can be achieved by combining the hyperspectral image with a high spatial resolution panchromatic image. These techniques are generally known as pansharpening and can be divided into component substitution (CS) and multi-resolution analysis (MRA) based methods. In general, the CS methods result in fused images having high spatial quality but the fused images suffer from spectral distortions. On the other hand, images obtained using MRA techniques are not as sharp as CS methods but they are spectrally consistent. Both substitution and filtering approaches are considered adequate when applied to multispectral and PAN images, but have many drawbacks when the low-resolution image is a hyperspectral image. Thus, one of the main challenges in hyperspectral pansharpening is to improve the spatial resolution while preserving as much as possible of the original spectral information. An effective solution to these problems has been found in the use of hybrid approaches, combining the better spatial information of CS and the more accurate spectral information of MRA techniques. In general, in a hybrid approach a CS technique is used to project the original data into a low dimensionality space. Thus, the PAN image is fused with one or more features by means of MRA approach. Finally the inverse projection is used to obtain the enhanced image in the original data space. These methods, permit to effectively enhance the spatial resolution of the hyperspectral image without relevant spectral distortions and on the same time to reduce the computational load of the entire process. In particular, in this paper we focus our attention on the use of Nonlinear Principal Component Analysis (NLPCA) for the projection of the image into a low dimensionality feature space. However, if on one hand the NLPCA has been proved to better represent the intrinsic information of hyperspectral images in the feature space, on the other hand an analysis of the impact of different fusion techniques applied to the nonlinear principal components in order to define the optimal framework for the hybrid pansharpening has not been carried out yet. More in particular, in this paper we analyze the overall impact of several widely used MRA pansharpening algorithms applied in the nonlinear feature space. The results obtained on both synthetic and real data demonstrate that an accurate selection of the pansharpening method can lead to an effective improvement of the enhanced hyperspectral image in terms of spectral quality and spatial consistency, as well as a strong reduction in the computational time.     

基于子空间中主成分最优线性预测的高光谱波段选择

针对高光谱遥感图像的异常检测问题,为了使高光谱降维数据能更完整地保留其光谱信息,提出了基于子空间中主成分最优线性预测的波段选择方法.采用改进相关性度量的谱聚类方法将高光谱波段划分为不同的子空间,并对各子空间中的波段进行主成分分析(PCA),选择主要分量作为重构目标;以子空间追踪法为搜索策略,从各子空间中选择数个波段对其重构目标进行联合最优线性预测;合并各子空间中的所选波段得到最佳波段子集.实验结果表明,该方法选择的波段子集可以较完整地重构原始数据,与原始数据以及自适应波段选择(ABS)方法、线性预测(LP)方法、最大方差主成分分析(MVPCA)方法、自相关矩阵波段选择(ACMBS)方法、组合因子最优波段选择(OCFBS)方法得到的波段子集相比,其波段子集具有更好的异常检测性能.     

Customizing kernel functions for SVM-based hyperspectral image classification.

Previous research applying kernel methods such as support vector machines (SVMs) to hyperspectral image classification has achieved performance competitive with the best available algorithms. However, few efforts have been made to extend SVMs to cover the specific requirements of hyperspectral image classification, for example, by building tailor-made kernels. Observation of real-life spectral imagery from the AVIRIS hyperspectral sensor shows that the useful information for classification is not equally distributed across bands, which provides potential to enhance the SVM's performance through exploring different kernel functions. Spectrally weighted kernels are, therefore, proposed, and a set of particular weights is chosen by either optimizing an estimate of generalization error or evaluating each band's utility level. To assess the effectiveness of the proposed method, experiments are carried out on the publicly available 92AV3C dataset collected from the 220-dimensional AVIRIS hyperspectral sensor. Results indicate that the method is generally effective in improving performance: spectral weighting based on learning weights by gradient descent is found to be slightly better than an alternative method based on estimating "relevance" between band information and ground truth.     

基于稀疏表示及光谱信息的高光谱遥感图像分类

该文结合稀疏表示及光谱信息提出了一种新的高光谱遥感图像分类算法。首先提出利用高光谱遥感图像数据集构造学习字典,然后根据学习字典计算每个像元的稀疏系数,从而获得像元的稀疏表示特征,最后根据稀疏表示特征和光谱信息分别构造随机森林,通过投票机制得到最终的分类结果。在AVIRIS高光谱遥感图像上的实验结果表明:该文所提方法能够提高分类效果,且其分类总精度和Kappa系数要高于光谱信息和稀疏表示特征方法。     

基于稀疏表示的高光谱数据压缩算法

如何降低高光谱图像大规模数据的存储和传输代价一直是学者们关心的问题。该文提出一种基于稀疏表示的高光谱数据压缩算法,通过一种波段选择算法构造训练样本集合,利用训练得到的基函数字典对高光谱数据所有波段进行稀疏编码,并对表示结果中非零元素的位置和数值进行量化和熵编码,从而实现高光谱图像压缩。实验结果表明该文算法与3维小波相比具有更好的非线性逼近性能,其率失真性能明显优于3D-SPIHT,并且在光谱信息保留上具有巨大的优势。     

Hyperion高光谱影像波段选择方法比较研究

Hyperion影像的光谱分辨率高,数据体积庞大,而且相邻波段之间的相关性强,信息冗余度较高, 给数据处理与解译带来了很多问题。鉴于此,提出了通过将分段主成分分析和波段指数相结合来开展波段选择与降维研究的思想。 同时采用自适应波段选择法、波段指数法和主成分分析累计贡献率方法进行了波段选择方法的对比研究;对4种波段选择方法所得到的结 果进行了最佳波段组合、地物可分性和图像变换比较分析。实验结果表明,分段主成分分析与波段指数综合方法可以有效抑制由于全局变换造成局部重要光谱被滤除的现象 ,同时还可兼顾自适应分区后各子区间及区间内波段之间的相关性,有效降低高光谱数据的维度。由此可见,该方法的波段选择效 果优于传统的自适应波段选择方法、波段指数法以及主成分分析累计贡献率方法。     

基于双向预测的高光谱图像无损压缩

提出了一种基于双向预测的高光谱图像无损压缩算法。该算法首先采用自适应波段选择算法选出信息量较大的波段,然后利用聚类算法对这些波段的谱向矢量进行分类预处理。为了便于组织谱间预测过程,根据相邻波段相关性大小进行自适应波段分组,采用双向预测的方法去除谱间相关性。通过在参考波段和预测波段中定义三维上下文预测结构,在聚类结果的基础上,对各个像素分别训练最优的预测系数,从而实现当前波段的有效预测。对AVIRIS型高光谱图像的实验结果表明,该方法可获得较好的无损压缩性能。     

3维卷积递归神经网络的高光谱图像分类方法

为了针对高光谱图像中空间信息与光谱信息的不同特性进行特征提取，提出一种3维卷积递归神经网络(3-D-CRNN)的高光谱图像分类方法。首先采用3维卷积神经网络提取目标像元的局部空间特征信息，然后利用双向循环神经网络对融合了局部空间信息的光谱数据进行训练，提取空谱联合特征，最后使用Softmax损失函数训练分类器实现分类。3-D-CRNN模型无需对高光谱图像进行复杂的预处理和后处理，可以实现端到端的训练，并且能够充分提取空间与光谱数据中的语义信息。结果表明，与其它基于深度学习的分类方法相比，本文中的方法在Pavia University与Indian Pines数据集上分别取得了99.94%和98.81%的总体分类精度，有效地提高了高光谱图像的分类精度与分类效果。该方法对高光谱图像的特征提取具有一定的启发意义。     

基于波段指数的高光谱影像波段选择算法

为了去除高光谱影像的数据冗余,提高高光谱影像处理的精度和效率,提出了一种基于波段指数的高光谱影像波段选择算法。采用小波变换对高光谱图像数据进行去噪处理,依据联合偏度-峰度指数将波段进行分组,再根据波段指数的大小确定相对较小指数的波段,并将其作为冗余波段进行去除,从而得到最小波段集。结果表明,利用该波段集和全波段所选的端元是一致的,在不影响端元提取的前提下,最大程度地去除了冗余波段,而且该波段集与全波段的分类精度较接近。该算法在波段选择过程中具有可行性与有效性,为降低高光谱影像维数提供了一种帮助。     

基于压缩感知的高光谱遥感影像重构方法研究

高光谱遥感影像包含丰富的空间、辐射以及光谱信息,同时海量的数据也引发了高光谱成像技术在传输和存储方面的诸多问题。针对这一问题,根据高光谱遥感影像谱间相关性强的特性,提出了一种结合谱间多向预测的基于压缩感知的高光谱遥感影像重构方法。首先,根据高光谱遥感影像的谱间相关性对高光谱遥感影像的波段进行分组,每组确定一个参考波段,使用平滑l_0范数算法重构每组的参考波段。其次,根据重构恢复的相邻组内的参考波段,建立了一个非参考波段预测模型,用来计算非参考波段的预测测量值;然后,计算实际测量值与预测测量值的差值,使用SL0算法重构该差值得到差值向量;最后,利用得到的差值向量迭代更新预测测量值,直到恢复该波段原始图像。仿真实验结果表明,该方法提高了高光谱遥感影像的重构效果。