基于DS聚类的高光谱图像集成分类算法

针对高光谱遥感图像维数高、样本少导致分类精度低的问题,提出一种基于DS聚类的高光谱图像集成分类算法(DSCEA)。首先,根据高光谱数据特点,从整体波段中随机选择一定数量的波段,构成不同的训练样本;其次,分析图像的空谱信息,构造无向加权图,利用优势集(DS)聚类方法得到最大特征差异的波段子集;最后,根据不同样本,利用支持向量机训练具有差异的单个分类器,采用多数表决法集成最终分类器,实现对高光谱遥感图像的分类。在Indian Pines数据集上DSCEA算法的分类精度最高可达到84.61%,在Pavia University数据集上最高可达到91.89%,实验结果表明DSCEA算法可以有效的解决高光谱分类问题。     

聚类与自适应波段选择结合的高光谱图像降维

针对自适应波段选择法(adaptive band selection,ABS)对高光谱图像降维后得到的最优波段子集用于地物目标分类处理时,分类精度不理想的问题,提出一种K-means聚类与ABS结合的高光谱图像降维方法。算法采用K-means聚类算法对所有波段进行聚类,聚类中分别采用相关系数和欧氏距离2种相似性度量,选取各聚类中ABS指数最大的波段,作为最优波段子集。通过实验,将所提方法与ABS进行分类精度比较。实验结果表明,所提方法在分类精度上优于ABS法,以相关系数作为相似性度量的K-means聚类与ABS结合的降维方法分类效果更好。     

基于波段影像统计信息量加权K-means聚类的高光谱影像分类

针对分类过程中如何合理利用高光谱影像波段问题,提出一种基于波段影像统计量加权K-means聚类的高光谱影像分类算法.该算法的核心思想在于:由波段含有的信息量及波段间的相关性确定各波段权重,同时考虑各波段对各聚类的重要性.首先,根据波段影像的熵、标准差及均值定义波段信息量函数,根据相邻波段影像互信息定义相关性函数;其次,由上述波段信息量函数及波段间相关性函数定义波段权重函数;然后,结合波段权重和波段-类属权重定义规则化目标函数;最后,依据参数特性设计目标函数求解方案.对Salinas高光谱影像和Pavia Centre高光谱影像分别采用所提出的算法与传统K-means算法、PCA$+K$-means算法及子空间波段选择$+K$-means算法进行对比实验,对于总精度及Kappa系数,所提出的算法都高于其他3种对比算法,结果验证了所提出算法的有效性.相对于其他3种算法而言,所提出的算法可有效改善高光谱影像分类的性能.     

基于最大最小距离的高光谱遥感图像波段选择

为减少高光谱遥感图像光谱空间冗余,降低后续处理的计算复杂度,提出一种基于最大最小距离的高光谱图像波段选择算法。首先计算波段标准差,选定标准差最大的波段作为初始中心;然后使用最大最小距离算法得到相对距离较远的聚类中心,对波段进行聚类;最后使用K中心点算法更新聚类中心。实验仿真结果表明:通过基于最大最小距离算法选择的波段,能够选出同时满足信息量大、相关性小的要求的波段子集,并将获得的波段组合用于高光谱图像分类时,可以得到较好的分类精度。     

波段聚类和改进递归滤波的高光谱图像分类

针对高光谱图像分类任务中的Hughes现象及噪声问题,提出了联合波段聚类和改进递归滤波的高光谱图像分类方法。首先,利用相对熵对高光谱图像的光谱波段进行K-means聚类,对聚类后的光谱波段进行高斯滤波,得到模糊化图像,将其作为递归滤波的引导图像;然后,对聚类后的光谱波段递归滤波处理,从而增强高光谱图像的轮廓特征;最后,利用支持向量机对递归滤波后的特征图像进行分类。在2个真实数据集上的实验结果表明,该方法降低了高光谱图像的维度,去除了噪声并阻止了信息跨越强边缘传播,与传统高光谱图像分类方法相比,提高了分类精度。     

基于SNMF聚类与类间可分性因子的高光谱波段选择

高光谱图像的波段范围广、光谱分辨率高,能为图像分类研究提供丰富的信息,但同时也给计算和存储带来了较大困难.论文提出一种基于SNMF聚类与类间可分性因子的方法来进行高光谱图像波段选择,以降低计算和存储开销.首先是数据预处理工作,将高光谱数据进行三维转二维表达,然后利用SNMF聚类算法得到波段的各个类簇,最后以各波段的类间可分性因子为指标在类簇内进行波段选择.实验采用波段子集的平均信息熵、平均相关系数和平均相对熵三类指标进行定量评价,并采用SVM分类器进行分类验证.     

基于3维上下文预测的高光谱图像无损压缩

如今高光谱数据的有效压缩已成为遥感技术发展中需要迫切解决的问题,为了对高光谱数据进行有效压缩,提出了一种基于3维上下文预测的高光谱图像无损压缩算法。该算法首先根据相邻波段间的相关性大小进行波段分组,同时对各个分组重新进行波段排序;然后采用自适应波段选择算法对高光谱图像进行降维,再利用k-means算法对降维后的波段谱向矢量进行聚类;最后在参考波段和当前波段中通过定义3维上下文预测结构,在聚类结果的基础上,对各个分类分别训练其最优的预测系数。实验结果表明,该方法可显著降低压缩后图像编码的平均比特率。     

基于萤火虫算法的高光谱遥感波段选择方法

高光谱图像在遥感领域中的应用越来越广泛,但由于自身的高数据维、波段间的高冗余度等特性给图像处理带来了一定困难,针对这个问题,提出一种基于类间可分性准则的改进萤火虫仿生算法,进行高光谱遥感波段选择。在分析萤火虫算法机理的基础上,阐述了利用该算法进行高光谱波段选择的思路,并构造波段相似性矩阵,选择欧氏距离、JM距离、光谱信息散度和离散度作为可分性准则来设置目标函数,根据目标函数值的优劣选择优势波段。最后,使用HYDICE Washington DC Mall和 HyMap Purdue Campus两个高光谱遥感影像数据进行实验验证,并利用支持向量机分类器对最佳波段组合进行精度评价,证明该算法的可行性和有效性。
     

基于遗传算法及聚类的基因表达数据特征选择

特征选择是模式识别及数据挖掘等领域的重要问题之一。针对高维数据对象（如基因表达数据）的特征选择，一方面可以提高分类及聚类的精度和效率，另一方面可以找出富含信息的特征子集，如发现与疾病密切相关的重要基因。针对此问题，本文提出了一种新的面向基因表达数据的特征选择方法，在特征子集搜索上采用遗传算法进行随机搜索，在特征子集评价上采用聚类算法及聚类错误率作为学习算法及评价指标。实验结果表明，该算法可有效地找出具有较好可分离性的特征子集，从而实现降维并提高聚类及分类精度。     

基于核模糊粗糙集的高光谱波段选择算法

为了减少高光谱波段图像间的冗余,降低运算时间,为后续分类任务提供有效支持,提出了基于核模糊粗糙集的高光谱波段选择算法。高光谱图像相邻波段间相似性较强,为进一步有效地度量波段的重要性,引入核模糊粗糙集理论。考虑波段中类的分布特性,根据波段的下近似集分布定义波段间的相关性,进而结合波段的信息熵定义波段的重要度。采用最大相关性最大重要度的搜索策略对高光谱图像进行波段选择。最后在常用高光谱数据集Indiana Pines农业区上,采用J48及KNN分类器进行测试。与其他高光谱波段选择算法相比,该算法在两个分类器上的总体平均分类精度分别提升了4.5和6.6个百分点。实验结果表明所提算法在处理高光谱波段选择问题时具有一定优势。     

Phase correlation based redundancy removal in feature weighting band selection for hyperspectral images

Feature weighting based band selection provides a computationally undemanding approach to reduce the number of hyperspectral bands in order to decrease the computational requirements for processing large hyperspectral data sets. In a recent feature weighting based band selection method, a pair‐wise separability criterion and matrix coefficients analysis are used to assign weights to original bands, after which bands identified to be redundant using cross correlation are removed, as it is noted that feature weighting itself does not consider spectral correlation. In the present work, it is proposed to use phase correlation instead of conventional cross correlation to remove redundant bands in the last step of feature weighting based hyperspectral band selection. Support Vector Machine (SVM) based classification of hyperspectral data with a reduced number of bands is used to evaluate the classification accuracy obtained with the proposed approach, and it is shown that feature weighting band selection with the proposed phase correlation based redundant band removal method provides increased classification accuracy compared to feature weighting band selection with conventional cross correlation based redundant band removal.     

基于邻域熵的高光谱波段选择算法

为了减少高光谱图像数据中的冗余信息,优化计算效率,并提升图像数据后续应用的有效性,提出一种基于邻域熵(NE)的高光谱波段选择算法.首先,为了高效计算样本的邻域子集,采用了局部敏感哈希(LSH)作为近似最近邻的搜索策略;然后,引入了NE理论来度量波段和类之间的互信息(MI),并把最小化特征集合与类变量之间的条件熵作为选取...     

A semi-supervised spatially aware wrapper method for hyperspectral band selection

Band selection is widely used to identify relevant bands for land-cover classification of hyperspectral images. The combination of spectral and spatial information can improve the classification performance of hyperspectral images dramatically. Similarly, the fusion of spectral–spatial information should also improve the performance of band selection. In this article, two semi-supervised wrapper-based spectral–spatial band selection algorithms are proposed. The local spatial smoothness of hyperspectral imagery is used to improve the performance of band selection when limited labelled samples available. With superpixel segmentation, the first algorithm uses the statistical characteristics of classification map to predict the classification quality of all samples. Based on the Markov random field model, the second algorithm incorporates the spatial information by the minimization of spectral–spatial energy function. Four widely used real hyperspectral data sets are used to demonstrate the effectiveness of the proposed methods, when compared to cross-validation-based wrapper method, the accuracy is improved by 2% for different data sets.     

基于多核模糊粗糙集与蝗虫优化算法的高光谱波段选择

波段选择能有效减少高光谱数据的空间冗余,为后续分类提供有效的支持。多核模糊粗糙集模型能够对包含不确定性的数值数据进行分析和近似描述,而蝗虫优化算法对优化问题求解具有较强的探索和开发能力,因而将多核模糊粗糙集模型引入高光谱的不确定性分析建模中,采用蝗虫优化算法对波段子集进行选择,提出了一种基于多核模糊粗糙集与蝗虫优化算法的高光谱波段选择算法。首先,使用多核算子来进行相似性度量,提高模型对数据分布的适应性。定义基于核模糊粗糙集的波段相关性度量,通过模糊粗糙集中不同像素点地物上的下近似分布来度量波段之间的相关性。然后,综合考虑波段依赖度、波段信息熵、波段间相关性来定义波段子集的适应度函数。最后,在常用高光谱数据集Indiana Pines农业区上,采用J48和K近邻(KNN)作为分类算法,把所提算法与波段相关性分析(BCA)、标准化互信息(NMI)算法进行分类性能比较。实验结果表明,在选取较少波段个数时,所提算法的总体平均分类精度提高了2.46和1.54个百分点。     

Gray Wolf Optimizer for hyperspectral band selection

In this paper, we propose a new optimization-based framework to reduce the dimensionality of hyperspectral images. One of the most problems in hyperspectral image classification is the Hughes phenomenon caused by the irrelevant spectral bands and the high correlation between the adjacent bands. The problematic is how to find the relevant bands to classify the pixels of hyperspectral image without reducing the classification accuracy rate. We propose to reformulate the problem of band selection as a combinatorial problem by modeling an objective function based on class separability measures and the accuracy rate. We use the Gray Wolf Optimizer, which is a new meta-heuristic algorithm more efficient than Practical Swarm Optimization, Gravitational Search Algorithm, Differential Evolution, Evolutionary Programming and Evolution Strategy. The experimentations are performed on three widely used benchmark hyperspectral datasets. Comparisons with the state-of-the-art approaches are also conducted. The analysis of the results proves that the proposed approach can effectively investigate the spectral band selection problem and provides a high classification accuracy rate by using a few samples for training.     

An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine

With the development and popularization of the remote-sensing imaging technology, there are more and more applications of hyperspectral image classification tasks, such as target detection and land cover investigation. It is a very challenging issue of urgent importance to select a minimal and effective subset from those mass of bands. This paper proposed a hybrid feature selection strategy based on genetic algorithm and support vector machine (GA–SVM), which formed a wrapper to search for the best combination of bands with higher classification accuracy. In addition, band grouping based on conditional mutual information between adjacent bands was utilized to counter for the high correlation between the bands and further reduced the computational cost of the genetic algorithm. During the post-processing phase, the branch and bound algorithm was employed to filter out those irrelevant band groups. Experimental results on two benchmark data sets have shown that the proposed approach is very competitive and effective.     

分段2维主成分分析的超光谱图像波段选择

目的 超光谱图像具有极高的谱间分辨率,巨大的数据量给分类识别等后续处理带来很大压力。为了有效降低图像数据维数,提出基于分段2DPCA的超光谱图像波段选择算法。方法 首先根据谱间相关性对原始图像进行波段分组,然后根据主成分反映每个光谱波段的信息比重分别对每组图像进行波段选择,从而实现超光谱图像的谱间降维。结果 该算法有效降低了超光谱图像的光谱维数,选择的波段明显反映出不同地物像元矢量的区别。结论 实验结果表明,该波段选择算法相对传统算法速度更快,并且较好地保留了原始图像的局部重要信息,对后续处理有积极意义。     

New framework for hyperspectral band selection using modified wind-driven optimization algorithm

The presence of irrelevant and highly correlated spectral bands significantly reduces the classification accuracy of the hyperspectral images. Therefore, the selection of suitable bands from the set of available spectral bands plays a crucial role in improving the classification accuracy. In this paper, a novel band selection approach is proposed based on nature inspired meta-heuristic algorithm to mitigate the effect of curse of dimensionality. Wind-driven optimization (WDO), among other meta-heuristic algorithms, has proven to be more efficient in solving global optimization problems. However, WDO is prone to premature convergence when solving the global optimization problem due to loss of diversity of air particles. Therefore, a modified WDO (MWDO) is proposed for band selection, which is able to avoid the premature convergence and control the exploration–exploitation search trade-off. Finally, in order to further improve the performance of the classification, the selected bands are fed into the deep learning architecture to extract the high-level useful features. The experiments are carried on three widely used standard datasets such as Indian Pines, Pavia University, and Salinas. The experimental results show that the proposed approach selects an optimal subset of bands with good convergence characteristics and provide high classification accuracy with fewer bands in comparison with other approaches. The proposed method achieves an overall accuracy of 93.26%, 94.76%, and 95.96% for Indian Pines, Pavia University, and Salinas datasets, respectively.