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.     

基于改进最小噪声分离变换的特征提取与分类

在最小噪声分离变换的基础上,引入核方法,采用小波核函数代替传统核函数对最小噪声分离变换予以改进。小波核函数的多分辨率分析特性可进一步提高算法的非线性映射能力。相关向量机高光谱图像分类是一种较新的高光谱图像分类方法,将新型核最小噪声分离变换方法与相关向量机相结合,对高光谱影像数据进行分类实验。仿真实验结果表明,基于小波核最小噪声分离变换的方法体现了高光谱影像的非线性特征,将所提出的方法应用于HYDICE系统在Washington DC Mall上空拍摄的数据,与对照算法相比,分类精度可提高3%~8%,并可有效地提高小样本区域的分类精度。     

PCA与移动窗小波变换的高光谱决策融合分类

目的 高光谱数据具有较高的谱间分辨率和相关性,给分类处理带来了一定的困难.为了提高分类精度,提出一种结合PCA与移动窗小波变换的高光谱决策融合分类算法.方法 首先,利用相关系数矩阵对原始高光谱数据进行波段分组;然后,利用主成分分析对每组数据进行谱间降维;再根据提出的移动窗小波变换法进行空间特征提取;最后,采用线性意见池(LOP)决策融合规则对多分类器的分类结果进行融合.结果 采用两组来自不同传感器的数据进行实验,所提算法的分类精度和Kappa系数均高于已有的5种分类算法.与SVM-RBF算法相比,本文算法的分类精度高出了8％左右.结论 实验结果表明,本文算法充分挖掘了高光谱图像的谱间-空间信息,能有效提高分类正确率,在小样本情况下和噪声环境中也具有良好的分类性能.     

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...     

基于生成对抗网络的高光谱图像分类

针对高光谱图像分类领域中特征利用不足的问题,提出了一种基于生成对抗网络（Generative Adversarial Networks,GANs）的高光谱图像分类方法。根据高光谱图像空间域和光谱域的相关性,利用GANs方法,挖掘其深层特征,生成可分性更高的高光谱图像,并通过支持向量机（Support Vector Machine,SVM）对生成的高光谱图像进行分类。使用两组高光谱数据进行实验,结果表明,该方法能够在少量高光谱波段的情况下,对抗学习到较好的生成模型,使得生成的高光谱图像在地物分类实验中具有更高的分类精度。     

高光谱遥感图像分类算法中的应用研究

针对高光谱遥感图像数据量大、维数高、数据之间冗余量大的特点,提出一种基于决策边界特征提取(Decision Bounda-ry Feature Extraction,DBFE)的SVM高光谱遥感图像分类算法。首先采用DBFE对高光谱遥感图像进行特征提取,消除特征之间相关性,并降低特征维数,然后采用GA对SVM参数进行优化,找到最优分类模型参数,最后采用最优分类模型对待分类的高光谱遥感图像进行分类。仿真结果表明,高光谱遥感图像分类算法提高了高光谱遥感图像分类的效率和分类正确率,说明分类方法是有效、可行的。     

Classification of complex environments using pixel level fusion of satellite data

The present study reports classification and analysis of composite land features using fusion images obtained by fusing two original hyperspectral and multispectral datasets. The high spatial-spectral resolution, multi-instrument and multi-period satellite images were used for fusion. Three pixel level fusion based techniques, Color Normalized Spectral Sharpening (CNSS), Principal Component Spectral Sharpening Transform (PCSST) and Gram-Schmidt Transform (GST), were implemented on the datasets. Performance evaluations of three fusion algorithms were done using classification results. The Support Vector Machine (SVM) and Gaussian Maximum Likelihood Classification (MLC) were used for classification using five types of images, viz. hyperspectral, multispectral and three fused images. Number of classes considered was eight. Sufficient number of ground field data for each class has also been acquired which was needed for supervise based classification. The accuracy was improved from 74.44 to 97.65% when the fused images were considered with SVM classifier. Similarly, the results were improved from 69.25 to 94.61% with original and fused data using MLC classifier. The fusion image technique was found to be superior to the single original image and the SVM is better than the MLC method.

     

基于双通道变分自编码器的高光谱图像分类

针对现有高光谱图像变分自编码器（variational autoencoder,VAE）分类算法存在空间和光谱特征利用效率低的问题,提出一种基于双通道变分自编码器的高光谱图像深度学习分类算法。通过构建一维条件变分自编码器（conditional variational autoencoder,CVAE）特征提取框架和二维循环通道条件变分自编码（channel-recurrent conditional variational autoencoders,CRCVAE）特征提取框架分别提取高光谱图像的光谱特征和空间特征,将光谱特征向量和空间特征向量叠加形成空谱联合特征向量,将联合特征送入Softmax分类器中进行分类。在Indian pines和Pavia University两种高光谱数据集上进行了分析验证,实验结果显示,与其他算法相比,提出的算法在总分类精度、平均分类精度和Kappa系数等评价指标上至少提高了3.40、2.75和3.57个百分点,结果显示提出的算法得到了最高的分类精度和更好的可视化效果。     

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。
     

一种改进的降噪自编码神经网络不平衡数据分类算法

针对少数类样本合成过采样技术(Synthetic Minority Over-Sampling Technique, SMOTE)在合成少数类新样本时会带来噪音问题,提出了一种改进降噪自编码神经网络不平衡数据分类算法(SMOTE-SDAE)。该算法首先通过SMOTE方法合成少数类新样本以均衡原始数据集,考虑到合成样本过程中会产生噪音的影响,利用降噪自编码神经网络算法的逐层无监督降噪学习和有监督微调过程,有效实现对过采样数据集的降噪处理与数据分类。在UCI不平衡数据集上实验结果表明,相比传统SVM算法,该算法显著提高了不平衡数据集中少数类的分类精度。     

一种用于高光谱遥感影像分类的改进多类支持向量机

将支持向量机(SVM)用于高光谱遥感影像分类的研究,采用决策边界特征提取(DBFE)算法对高光谱影像进行维数约简,以径向基函数(RBF)作为SVM模型的核函数,把混沌优化搜索技术引入到PSO算法中,以基本PSO算法为主体流程,对种群中最好的粒子进行给定步数的混沌优化搜索,以改进基本PSO算法进化后期收敛速度慢、易陷入局部极小值的缺陷。利用改进的混合粒子群优化算法(PSO)来实现SVM模型参数的自动选择,继而构建了一种参数最优的粒子群优化支持向量机(PSO-SVM)多类分类模型。选用220波段的AVIRIS高光谱遥感影像进行了分类试验。结果表明,与采用基于留一法(LOO)网格搜索策略的传统SVM相比,改进后的PSO-SVM算法可以提高分类精度约8.8%。该方法对于小样本、非均衡条件下的遥感影像数据分类非常有效。     

Projection Support Vector Machine Generators

Large-scale Support Vector Machine (SVM) classification is a very active research line in data mining. In recent years, several efficient SVM generation algorithms based on quadratic problems have been proposed, including: Successive OverRelaxation (SOR), Active Support Vector Machines (ASVM) and Lagrangian Support Vector Machines (LSVM). These algorithms have been used to solve classification problems with millions of points. ASVM is perhaps the fastest among them. This paper compares a new projection-based SVM algorithm with ASVM on a selection of real and synthetic data sets. The new algorithm seems competitive in terms of speed and testing accuracy.     

结合超像元和子空间投影支持向量机的高光谱图像分类

目的 高光谱图像包含了丰富的空间、光谱和辐射信息,能够用于精细的地物分类,但是要达到较高的分类精度,需要解决高维数据与有限样本之间存在矛盾的问题,并且降低因噪声和混合像元引起的同物异谱的影响。为有效解决上述问题,提出结合超像元和子空间投影支持向量机的高光谱图像分类方法。方法 首先采用简单线性迭代聚类算法将高光谱图像分割成许多无重叠的同质性区域,将每一个区域作为一个超像元,以超像元作为图像分类的最小单元,利用子空间投影算法对超像元构成的图像进行降维处理,在低维特征空间中执行支持向量机分类。本文高光谱图像空谱综合分类模型,对几何特征空间下的超像元分割与光谱特征空间下的子空间投影支持向量机（SVMsub）,采用分割后进行特征融合的处理方式,将像元级别转换为面向对象的超像元级别,实现高光谱图像空谱综合分类。结果 在AVIRIS（airbone visible/infrared imaging spectrometer）获取的Indian Pines数据和Reflective ROSIS（optics system spectrographic imaging system）传感器获取的University of Pavia数据实验中,子空间投影算法比对应的非子空间投影算法的分类精度高,特别是在样本数较少的情况下,分类效果提升明显;利用马尔可夫随机场或超像元融合空间信息的算法比对应的没有融合空间信息的算法的分类精度高;在两组数据均使用少于1%的训练样本情况下,同时融合了超像元和子空间投影的支持向量机算法在两组实验中分类精度均为最高,整体分类精度高出其他相关算法4%左右。结论 利用超像元处理可以有效融合空间信息,降低同物异谱对分类结果的不利影响;采用子空间投影能够将高光谱数据变换到低维空间中,实现有限训练样本条件下的高精度分类;结合超像元和子空间投影支持向量机的算法能够得到较高的高光谱图像分类精度。     

A new fast algorithm for multiclass hyperspectral image classification with SVM

The support vector machine (SVM) has been a dominant machine-learning technique in the last decade and has demonstrated its efficiency in many applications. Research on classification of hyperspectral images have shown the efficiency of this method to overcome the Hughes phenomenon for classification of such images. A major drawback of classification by SVM is that this classifier was originally developed to solve binary problems, and the algorithms for multiclass problems usually have a high-computational load. In this article, a new and fast method for multiclass problems is proposed. This method has two stages. In the first stage, samples are classified by a maximum likelihood (ML) classifier, and in the second stage, SVM selects the final label of a sample among high-probability classes for that sample by a tree structure. So, for each sample, only some classes must be searched by SVM to find its label. The uncertainty of ML classification for a sample is obtained by the entropy of probabilities, and the number of classes that must be searched by SVM for a sample is obtained based on the uncertainty of that sample in the primary ML classification. This approach is compared with two widely used multiclass algorithms: one-against-one (OAO) and directed acyclic graph (DAGSVM). The obtained results on real data from the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) revealed less computational time and better accuracy compared to these multiclass algorithms.     

Comparing six pixel-wise classifiers for tropical rural land cover mapping using four forms of fully polarimetric SAR data

This study evaluates four commonly used forms of synthetic aperture radar (SAR) data for land-cover classification in tropical rural areas. The backscatter coefficient of linearly polarized L-band SAR was compared to two distinctive feature sets derived from Eigen-based and model-based decompositions. The performance of six classifiers available in Orfeo Toolbox (OTB), that is, Bayes, artificial neural networks (ANNs), Support Vector Machine (SVM), decision trees, Random Forests (RFs), and gradient boosting trees (GBTs), was investigated to distinguish five and seven land-cover classes, with particular attention given to several types of woody vegetation: forest, mixed garden, rubber, oil palm, and tea plantations. Classifiers reacted differently to ingested forms of SAR data, and careless use of data input yielded a negative impact. The results showed that SVM provided the highest overall accuracy although the performance was not significantly better than the others. Tuning the parameters, however, significantly improved the accuracy of ANN and SVM, while RF and GBT did not respond well. Responses of two SVM parameters (cost and kernel type) fluctuated somewhat, which required further attention. ANN accuracy was improved when the number of neurons in the hidden layer was set between 10 and 12. We found that accuracy imbalance existed between designated land-cover classes, especially in woody vegetation. Imbalance can partially be reduced by tuning specific classifiers. We showed that classifier tuning can lead to significantly improved accuracy, especially for classes having medium or low accuracies. This research also demonstrated that freely available toolkits such as OTB and QGIS can be beneficial for mapping activities in developing countries, achieving a reasonable accuracy if the classification parameters are tuned properly.     

Pixel- and feature-level fusion of hyperspectral and lidar data for urban land-use classification

The complexity of urban areas makes it difficult for single-source remotely sensed data to meet all urban application requirements. Airborne light detection and ranging (lidar) can provide precise horizontal and vertical point cloud data, while hyperspectral images can provide hundreds of narrow spectral bands which are sensitive to subtle differences in surface materials. The main objectives of this study are to explore: (1) the performance of fused lidar and hyperspectral data for urban land-use classification, especially the contribution of lidar intensity and height information for land-use classification in shadow areas; and (2) the efficiency of combined pixel- and object-based classifiers for urban land-use classification. Support vector machine (SVM), maximum likelihood classification (MLC), and object-based classifiers were used to classify lidar, hyperspectral data and their derived features, such as the normalized digital surface model (nDSM), normalized difference vegetation index (NDVI), and texture measures, into 15 urban land-use classes. Spatial attributes and rules were used to minimize misclassification of the objects showing similar spectral properties, and accuracy assessments were carried out for the classification results. Compared with hyperspectral data alone, hyperspectral–lidar data fusion improved overall accuracy by 6.8% (from 81.7 to 88.5%) when the SVM classifier was used. Meanwhile, compared with SVM alone, the combined SVM and object-based method improved OA by 7.1% (from 87.6 to 94.7%). The results suggest that hyperspectral–lidar data fusion is effective for urban land-use classification, and the proposed combined pixel- and object-based classifiers are very efficient and flexible for the fusion of hyperspectral and lidar data.     

Effective compression of hyperspectral imagery using an improved 3D DCT approach for land-cover analysis in remote-sensing applications

Although hyperspectral imagery (HSI), which has been applied in a wide range of applications, suffers from very large volumes of data, its uncompressed representation is still preferred to avoid compression loss for accurate data analysis. In this paper, we focus on quality-assured lossy compression of HSI, where the accuracy of analysis from decoded data is taken as a key criterion to assess the efficacy of coding. An improved 3D discrete cosine transform-based approach is proposed, where a support vector machine (SVM) is applied to optimally determine the weighting of inter-band correlation within the quantization matrix. In addition to the conventional quantitative metrics signal-to-noise ratio and structural similarity for performance assessment, the classification accuracy on decoded data from the SVM is adopted for quality-assured evaluation, where the set partitioning in hierarchical trees (SPIHT) method with 3D discrete wavelet transform is used for benchmarking. Results on four publically available HSI data sets have indicated that our approach outperforms SPIHT in both subjective (qualitative) and objective (quantitative) assessments for land-cover analysis in remote-sensing applications. Moreover, our approach is more efficient and generates much reduced degradation for subsequent data classification, hence providing a more efficient and quality-assured solution in effective compression of HSI.     

超光谱遥感图像有监督LPP特征提取研究

在局部保留投影(LPP)特征提取算法的基础上,利用样本标签信息提出了一种有监督的局部保留投影算法(SPLPP),该算法的邻接图的权值不仅考虑了LPP算法中的相似性权值,而且加入了监督类的相关权值。SPLPP算法主要步骤是先用PCA去除高维超光谱遥感图像的冗余信息,再把监督机制引入到LPP中,实现图像的特征提取,将高维超光谱遥感图像投影到低维空间中,利于分类。应用SPLPP算法对高维的遥感原始超光谱图像进行特征提取后,利用支持向量机(SVM)和最近邻分类器(KNN)对降维后的遥感图像数据进行分类;并与PCA、LPP、LDA等特征提取算法进行了比较实验。实验表明:结合了LPP局部信息保留能力和全域标签信息的SPLPP算法,有更好的局部信息保留能力和类判别能力,使分类器分类精度更高,分类效果更好。     

改进的二叉树支持向量机在多分类中的应用

在多分类问题中,分类算法的优劣直接影响到最终分类结果的好坏。现有的多分类算法中,基于支持向量机的多分类算法在综合性能方面要优于其他算法,但是,这些较优算法同样面临一些多分类中常见的问题,如不可分问题和效率低问题。针对这些问题,文中提出了一种改进的二叉树支持向量机多分类算法,该算法综合考虑了两个类之间的距离和分布情况对可分离性的影响,并采用最容易分离的类最先分割出来的策略来建立树的结构。通过在不同的数据集上进行测试,表明该方法不仅解决了多分类的不可分问题,还能提高分类的效率和准确度,可更好地解决现实中的多分类问题。