Efficiency of the spectral-spatial classification of hyperspectral imaging data

The efficiency of methods of the spectral-spatial classification of similarly looking types of vegetation on the basis of hyperspectral data of remote sensing of the Earth, which take into account local neighborhoods of analyzed image pixels, is experimentally studied. Algorithms that involve spatial pre-processing of the raw data and post-processing of pixel-based spectral classification maps are considered. Results obtained both for a large-size hyperspectral image and for its test fragment with different methods of training set construction are reported. The classification accuracy in all cases is estimated through comparisons of ground-truth data and classification maps formed by using the compared methods. The reasons for the differences in these estimates are discussed.     

Classification of Hyperspectral Images with Different Methods of Training Set Formation

The efficiency of the methods of controlled spectral and spectral-spatial classification of vegetation types on the basis of hyperspectral pictures with different methods of training set formation is evaluated. The dependence of the classification accuracy on the number of spectral features is considered. It is shown that simultaneous allowance for spatial and spectral features ensures highquality classification of similarly looking types of vegetation by merely using training sets with the maximum degree of the pixel distribution over the image.     

高光谱遥感图像空谱联合分类方法研究

在遥感影像研究领域里,高光谱数据分类是一个热点问题。近年来,在这个问题上涌现出很多研究方法,然而,大多数方法都是用浅层的方法提取原始数据的特征。将深度学习的方法引入高光谱图像分类中,提出一种新的基于深信度网络(DBN)的特征提取方法和图像分类架构用于高光谱数据分析。将谱域-空域特征提取和分类器相结合提高分类精度。使用高光谱数据进行实验,结果表明该分类器优于当前的一些先进的分类方法。此外,本文还揭示了深度学习系统在高光谱图像分类研究中具有的巨大潜力。     

Spectral-Spatial Methods for Hyperspectral Image Classification. Review

Various methods of spectral-spatial classification of hyperspectral data are reviewed. Papers devoted to the most popular ways of using spatial information for increasing the accuracy of classification maps are considered. It is shown that the best results are obtained by using preprocessing of “raw” data before the procedures of pixel-wise spectral classification. Disadvantages, limits, and possible directions for developing existing methods are investigated and analyzed.     

高光谱图像分类的研究进展

高光谱图像分类是利用高光谱数据图谱合一且光谱信息丰富的特点,对图像中的每个像素进行分门别类,以达到对地物目标进行高精度分类和自动化识别的目的,是对地观测的重要组成部分。在分析高光谱图像特点的基础上,本文从普通机器学习和深度学习这两方面对高光谱图像像素级分类的研究进展及效果进行总结、评述和比较,通过具体实验的结果对比,直观地展现各种算法的优劣。针对高光谱分类问题,本文从两个方面对今后的研究方向及发展前景进行了分析和展望。一方面,在算法研究上,高光谱图像分类算法可在保证分类精度的前提下降低算法的复杂度,利用多源遥感数据、多特征综合、多尺度复合,提升小样本、少参数分类模型的分类精度,适应智能化、快速化高光谱遥感对地观测的发展要求;另一方面要紧密结合市场应用需求,重视高光谱图像在实际中的应用,研究具有市场竞争力的高效分类算法,提升高光谱图像分类在遥感技术应用领域的竞争力。     

基于云模型的高光谱遥感图像的分类研究

现有的分类方法没有考虑或者没有彻底考虑高光谱遥感图像数据的不确定性,因此提出了一种基于云模型的高光谱遥感图像分类方法。云分类时,首先根据训练样本集,由逆向云发生器生成每类地物的多维云模型,然后利用X条件云发生器计算出各测试像素对每类地物的隶属度,最终采用极大判定法实现对每个测试样本的分类。仿真结果表明,该方法简单、计算量小,可以取得高于传统方法的分类精度,具有很好的发展前景。     

局部保护降维与高斯混合模型的高光谱图像分类

高光谱图像具有高谱间分辨率和低空间分辨率的特点,传统的分类方法难以得到较高的分类精度。针对该问题,该文研究了两种局部保护降维法——局部保护投影(LPP)和局部保护非负矩阵分离(LPNMF)对高光谱图像降维,这两种方法能很好地保护输入空间相邻像素间的局部特征。由于高光谱图像各类间的统计分布多为复杂的多模型结构,文中采用高斯混合模型(GMM)分类器对降维后的数据进行分类。实验结果表明,将局部保护降维与高斯混合模型相结合的高光谱图像分类算法不但在小样本情况下能有效地提高分类精度,而且在背景像素混合的情况下和高斯白噪声环境中具有一定的鲁棒性。     

面向高光谱图像分类的空谱判别分析

针对传统的基于特征提取的高光谱图像地物分类算法大多只考虑光谱信息而忽略空间信息的问题,提出了一种面向高光谱分类的半监督空谱全局与局部判别分析(S3 GLDA)算法。该算法首先利用少量标记样本保存数据集的线性可分性和全局判别信息,再依靠较多的无标记的空间局部近邻像元来揭示局部判别信息和非线性局部流形,使高光谱遥感图像的光谱域全局判别结构和空间域局部判别结构在低维特征空间同时得以保留,并在输出特征中自动融入了空间信息,构成了半监督的空谱判别分析。在Indian Pines和PaviaU数据集的实验表明,总体分类精度分别达到76.24%和82.96%。与现有几种算法比较,该算法有效提高了输出特征在低维空间的判别能力,更好地揭示了数据集的内在非线性多模本质,有效提升了高光谱图像数据集的地物分类精度。     

A framework of quasiconformal mapping-based kernel machine with its application to hyperspectral remote sensing

Kernel machine is a feasible and effective nonlinear feature extraction method on data analysis, for example, hyperspectral sensing data. Kernel trick improves largely the performance of learning system including recognition, clustering, prediction through the nonlinear kernel mapping from the input data space to output data space. The performance of kernel-based system is largely influenced by the function and parameter of kernel. Optimizing only the parameters is not effective to promote the kernel-based learning system, because the data distribution is not changed only changing the kernel parameter. Moreover, no any universal single kernel is very adaptive to all applications. We present a framework of quasiconformal mapping-based kernel learning machine under single kernel and multiple kernels for hyperspectral image data classification. The performance of learning system is improved largely owing to the two facts: quasiconformal kernel structure changes the data structure in the kernel empirical space; quasiconformal multikernels characterize precisely the data for improving performance on solving complex visual learning tasks. The learning framework is applied to the hyperspectral image classification, and some experiments are implemented on two hyperspectral image databases.     

利用区域增长技术的自适应高光谱图像分类

针对面向对象的高光谱分类方法中分割参数设置问题,提出了一种基于区域增长技术的自适应高光谱分类算法。首先提出了带约束的区域增长方法,利用已知训练样本的空间信息,提供有效约束,从而降低区域增长过程中区域标记的错误传播率,以提高分类性能;其次,提出了自适应阈值计算方法,通过分析已知训练样本光谱的分布规律,自适应地计算出合理的区域划分阈值,从而代替经验阈值,提高算法的鲁棒性;最后,采用K近邻算法(KNN),对划分后各区域中心进行分类。实验结果表明:对于不同图像,提出的算法计算出的自适应阈值均与其经验值相符合,且其分类效果优于其他算法,来自AVIRIS传感器的高光谱数据Indian Pines在10%的已知训练样本下总体分类精度达92.94%、kappa系数达0.919 5,来自ROSIS传感器的高光谱数据Pavia University在5%的已知训练样本下总体分类精度达95.78%、kappa系数达0.944 0。该算法不仅增强了算法的鲁棒性,同时有效提高了分类性能,在高光谱应用中具有较强的实用性。     

空-谱协同流形重构的高光谱影像分类

鉴于传统高光谱影像分类大都采用监督学习方法,且仅利用了光谱信息,未考虑影像空间特征和流形结构。提出一种基于空-谱协同流形重构误差的高光谱影像分类方法,该算法基于高光谱影像中地物分布的空间一致性,利用少量标记的样本和大量的无标记空间近邻样本来进行半监督学习,并利用测试样本在每一子流形上的重构误差来表征相似性,实现鉴别分类。在Indian Pines和University of Pavia数据集上的实验结果表明,本文方法的分类精度在各种条件下要优于其他分类算法,其最高总体精度分别达到了95.67%和91.92%。该算法将高光谱遥感影像中的空间-光谱信息融入不同地物的子流形结构表征,在训练样本数量较少时仍能得到好的分类效果,有效提升了分类性能。     

Combining Classifiers in the Problem of Thematic Processing of Hyperspectral Aerospace Images

This paper describes a problem of thematic processing of hyperspectral aerospace images. A recommended technique is based on a decoding algorithm and makes it possible to construct an effective algorithm of multiclass classification based on combining standard algorithms of binary classification of various complexity. The reason for choosing the configuration of the classification algorithm is given. Test calculations based on model and real data are used to show the effectiveness of the proposed approach to recognizing objects from hyperspectral images.     

加权空-谱与最近邻分类器相结合的高光谱图像分类

提出了一种基于加权空-谱距离(WSSD)的相似性度量方法 ,并将其应用到最近邻分类器(KNN)中,导出了一种新的高光谱图像分类算法。该算法利用高光谱图像的物理特性,通过引入空间窗口和光谱因子这两个参数来挖掘出图像中的空间信息与光谱信息,利用空间近邻点对中心像元进行重构。在最大限度减少图像冗余信息的基础上,增大了同类像元间的相似性以及异类像元间的差异性,获得了更为有效的鉴别特征,从而更好地实现了数据间的相似性度量。基于Indian Pines和PaviaU高光谱数据集进行了实验,结果表明:将提出的WSSD-KNN算法应用于高光谱图像分类时,其分类精度高于其他算法,总体分类精度分别达到了91.72%和96.56%。由于算法较好地融合了图像中的空间-光谱信息,提取出了更为有效的鉴别特征,故不仅有效地改善了高光谱数据的地物分类精度,而且可在训练样本较少时,保持较高的识别率。     

Neural network classification of hyperspectral images on the basis of the Hilbert–Huang transform

The method of image classification with its preliminary transformation to principal components and with the use of the Hilbert–Huang transform is studied by an example of neural network classification of a hyperspectral image. The efficiency of the method is demonstrated through comparisons with traditional methods of neural network classification with the use of spectral components and principal components without involving spatial information as features. Radial-basis and complex neural networks are used for classification.     

基于约束线性判别分析的非监督高光谱影像分类方法

针对高光谱影像非监督分类问题,从特征提取的角度提出了一种用于高光谱混合像元分类的非监督约束线性判别分析算法（UCLDA）。该算法首先利用顶点成分分析（VCA）提取端元,然后用光谱角匹配方法（SAM）构造训练样本并基于约束线性判别分析（CLDA）进行特征提取,最后用最小距离法分类。整个算法实现了非监督分类。对模拟的高光谱数据和真实的遥感影像进行了仿真研究,研究结果表明．UCLDA略优于最小二乘光谱混合分析技术．但明显好干经典的井．谱角匹配分娄．     

高光谱遥感岩矿识别的研究进展

分析与综述了当前高光谱遥感岩矿识别研究的进展。论述了岩矿光谱特征的作用机理以及岩矿光谱的特征测量与分析方法。归纳和总结了目前以及未来几年可用于岩矿识别的高光谱遥感探测器件和仪器的特点。对基于光谱吸收特征、完全波形匹配和混合像元分解的3类岩矿识别方法进行了归纳与对比,重点介绍了近年来这类技术的重要成果以及研究热点。最后,从理论、数据、方法以及应用4个方面对当前高光谱遥感岩矿识别面临的主要问题和发展趋势进行了剖析。作者认为,高光谱遥感岩矿识别的整体发展趋势为定性识别向定量化分析发展,在此发展过程中,混合光谱模型的建立与解混、面向岩矿识别的新型高光谱传感器的研制、岩矿信息提取的智能化以及复杂地质环境下的岩矿识别将成为研究的主要方向。     

有限训练样本下的多尺度空洞密集网络高光谱影像分类

为了在有限训练样本情况下充分提取高光谱影像的空间光谱特征,提高分类精度,提出一种结合空洞卷积和密集网络 的高光谱影像分类方法。 首先,构建多尺度空洞特征提取模块,引入不同数量的空洞卷积层和普通卷积层通过级联的方式增大 模型的感受野,并提取多尺度特征。 然后,在多尺度空洞特征提取模块之间建立密集连接,实现特征复用的同时缓解梯度消失 问题,而模块内部无密集连接,避免构建深度网络而导致网络参数过多的问题。 最后,将得到的特征依次通过池化层,全连接层 和 Softmax 层完成分类。 另外,本文在全连接层后加入 dropout 正则化防止出现过拟合。 在 Indian Pines 和 WHU-Hi-Longkou 数 据集上与经典分类方法进行对比,本文方法 OA 分别为 98. 75% 和 98. 82% 。 实验结果表明,本文设计的网络模型在有限训练样 本情况下,分类效果最优。     

Feature selection by merging sequential bidirectional search into relevance vector machine in condition monitoring

For more accurate fault detection and diagnosis, there is an increasing trend to use a large number of sensors and to collect data at high frequency. This inevitably produces large-scale data and causes difficulties in fault classification. Actually, the classification methods are simply intractable when applied to high-dimensional condition monitoring data. In order to solve the problem, engineers have to resort to complicated feature extraction methods to reduce the dimensionality of data. However, the features transformed by the methods cannot be understood by the engineers due to a loss of the original engineering meaning. In this paper, other forms of dimensionality reduction technique(feature selection methods) are employed to identify machinery condition, based only on frequency spectrum data. Feature selection methods are usually divided into three main types: filter, wrapper and embedded methods. Most studies are mainly focused on the first two types, whilst the development and application of the embedded feature selection methods are very limited. This paper attempts to explore a novel embedded method. The method is formed by merging a sequential bidirectional search algorithm into scale parameters tuning within a kernel function in the relevance vector machine. To demonstrate the potential for applying the method to machinery fault diagnosis, the method is implemented to rolling bearing experimental data. The results obtained by using the method are consistent with the theoretical interpretation, proving that this algorithm has important engineering significance in revealing the correlation between the faults and relevant frequency features. The proposed method is a theoretical extension of relevance vector machine, and provides an effective solution to detect the fault-related frequency components with high efficiency.     

基于多尺度分割的高光谱图像稀疏表示与分类

针对高光谱特征的稀疏表示,提出了一种基于多尺度分割的空间加权算法用于高光谱图像分类。该算法采用更合理的邻域定义挖掘空间先验信息,优化类边缘像元的稀疏表示。首先,通过多尺度分割提供邻域空间约束;结合拉普拉斯尺度混合(LSM)先验,分别对每个邻域组内像元进行空间加权的稀疏表示。然后,采用概率支持向量机(SVM)分类,同时提供像元的分类标签及其置信度。最后,以此置信度为权重,对多尺度分类图进行加权融合,生成最终的分类图。实验显示,本文算法能够增强光谱特征表示的稀疏性和鲁棒性,提高总体分类精度;在小样本训练下,单类的分类精度可提升30%左右,表明该算法在高光谱应用中具有较强的实用性。     

半监督多图嵌入的高光谱影像特征提取

针对传统图嵌入方法仅采用单一图结构无法有效表征高维数据中复杂本征结构,本文提出了一种半监督多图嵌入(SSMGE)方法,并应用于高光谱影像特征提取。该方法首先利用标记样本的类内、类间近邻点来构建类内超图、类间超图、类内普通图、类间普通图,然后通过无标记样本的近邻点和远离点构建无监督本征超图和惩罚超图,并以多图协同方式来表征高维数据间的复杂几何关系,实现鉴别特征提取。本文提出的SSMGE方法不仅能有效揭示数据点间超图和普通图的结构,而且在低维嵌入空间中增强同类数据聚集性和非同类数据的远离性,提取的鉴别特征可改善地物分类精度。在PaviaU和Urban高光谱数据集上进行了分类实验,本文方法的总体分类精度分别可达到85.92%和79.74%。相比普通图嵌入和超图方法,该算法明显提升了地物的分类性能。