基于简约集支持向量机的高光谱影像分类

针对高光谱影像支持向量机分类的预侧过程中需要花费大量计算时间的问题,提出了一种利用简约集算法提高高光谱影像分类预测效率的方法。采用径向基核函数,使用一对一构造多类支持向量机分类器,通过交叉验证网格搜索法对参数进行模型参数选择,并利用简约集算法来减少分类预测过程计算量。通过高光谱影像分类试验表明,保持支持向量机的泛化能力并不需要使用所有计算得到的支持向量,简约集算法能够在保持分类预测精度的同时,大大提高高光谱影像分类预测的速度。     

基于MapReduce改进离散型萤火虫算法和多重分形的属性约简方法

针对大数据环境下属性约简问题,提出基于MapReduce改进离散型萤火虫算法(IDGSO)和多重分形(MFD)的属性约简方法.首先,通过对萤火虫个体的移动方式进行离散化改进,引入迁徙策略和高斯变异策略,避免陷入局部最优,并提出改进离散型萤火虫算法.然后,将IDGSO结合MFD应用于属性约简中.最后,针对大数据环境下属性约简问题,采用MapReduce编程模式,实现对IDGSO和MFD的并行化.在UCI数据集和实际气象数据集上的实验表明,文中算法约简性能较优,运行效率较快,具有较好的有效性和可行性.     

Feature extraction method based on spectral dimensional edge preservation filtering for hyperspectral image classification

ABSTRACT

A large amount of spectral and spatial information contained in hyperspectral imagery has provided a great opportunity to effectively characterize and identify the surface materials of interest. Feature extraction plays a very important role for hyperspectral data classification, which can reduce noise from the original data and improve the separability of land classes. A novel feature extraction technique based on spectral dimensional edge preserving filter is proposed in this paper. A series of Gaussian filters are applied in the spatial domain of the hyperspectral image to produce the guidance image, then, the edge preserving filter which is guided by the guidance image is adopted and applied in the spectral domain of the hyperspectral data to get the feature. For the feature is produced by filtering in the spectral domain, the spectral curves of the feature are more continues, which avoids the spectral discontinuity problems result from the traditional two-dimensional spatial filter. The guidance image is obtained by filtering the original image in the spatial domain, so, the spatial and the spectral information are integrated together in the following spectral edge preserving filtering process. We carefully adjusted the parameters of the filter and applied it to different real hyperspectral remote sensing images, with the support vector machine, multinomial logistic regression, and random forest serving as the classifier, by comparing with other feature extraction methods presented in recent literature, the results indicate that the proposed methodology always has a great performance in different kinds of cases.     

一种新高斯过程分类算法

由于需要利用高斯函数逼近潜变量函数的后验概率, 传统高斯过程分类算法通常都存在计算复杂度高的问题. 对此, 提出一种新高斯过程分类算法. 该算法的基本思想为: 首先, 利用Parzen 窗方法估计出每个训练样本的后验概率; 然后, 通过所得到的后验概率将原始分类问题变换为回归问题; 进而分析地得到潜变量函数后验概率的显式表达式, 以避免逼近后验概率所面临的高计算复杂度问题. 仿真实验结果表明, 所提出的算法在分类精度上优于已有的高斯过程分类算法.

     

Bayesian classification of hyperspectral images using spatially-varying Gaussian mixture model

We propose a spatially-varying Gaussian mixture model for joint spectral and spatial classification of hyperspectral images. The model provides a robust estimation framework for small sample size training sets. Defining prior distributions for the mean vector and the covariance matrix enables us to regularize the parameter estimation problem. More specifically, we can obtain invertible positive definite covariance matrices by the help of this regularization. Moreover, the proposed model also takes into account the spatial alignments of the pixels by using spatially-varying mixture proportions. The spatially-varying mixture model is based on spatial multinomial logistic regression. The classification results obtained on Indian Pines, Pavia Centre, Pavia University, and Salinas data sets show that the proposed methods perform better especially for small-sized training sets compared to the state-of-the-art classifiers.     

A novel active learning approach for the classification of hyperspectral imagery using quasi-Newton multinomial logistic regression

In this article, a novel active learning approach is proposed for the classification of hyperspectral imagery using quasi-Newton multinomial logistic regression/Davidon, Fletcher, and Powell selective variance (MLR-DFP-SV). The proposed approach consists of two main steps: (1) a fast solution for the MLR classifier, where the logistic regressors are obtained by the use of the quasi-Newton algorithm; and (2) selection of the most informative unlabelled samples. The SV method is applied to select the most informative unlabelled samples, based on the posterior density distributions. Experiments on two real hyperspectral data sets confirmed that the proposed approach can effectively select the most informative unlabelled samples and improve the classification accuracy. Three different methods – the maximum information (MI), breaking ties (BT), and minimum error (ME) methods – were also used to obtain the most informative unlabelled samples, and it was found that the new sample selection method – SV – can select more informative samples than the BT, MI, and ME methods.     

Patch-based active learning (PTAL) for spectral-spatial classification on hyperspectral data

Active learning (AL) has been shown to be a useful approach to improving the efficiency of the classification process for remote-sensing imagery. Current AL methods are essentially based on pixel-wise classification. In this paper, a new patch-based active learning (PTAL) framework is proposed for spectral-spatial classification on hyperspectral remote-sensing data. The method consists of two major steps. In the initialization stage, the original hyperspectral images are partitioned into overlapping patches. Then, for each patch, the spectral and spatial information as well as the label are extracted. A small set of patches is randomly selected from the data set for annotation, then a patch-based support vector machine (PTSVM) classifier is initially trained with these patches. In the second stage (close-loop stage of query and retraining), the trained PTSVM classifier is combined with one of three query methods, which are margin sampling (MS), entropy query-by-bagging (EQB), and multi-class level uncertainty (MCLU), and is subsequently employed to query the most informative samples from the candidate pool comprising the rest of the patches from the data set. The query selection cycle enables the PTSVM model to select the most informative queries for human annotation. Then, these informative queries are added to the training set. This process runs iteratively until a stopping criterion is met. Finally, the trained PTSVM is employed to patch classification. In order to compare this to pixel-based active learning (PXAL) models, the prediction label of a patch by PTSVM is transformed into a pixel-wise label of a pixel predictor to get the classification maps. Experimental results show better performance of the proposed PTAL methods on classification accuracy and computational time on three different hyperspectral data sets as compared with PXAL methods.     

Dirichlet Gaussian mixture model: Application to image segmentation

Gaussian mixture model based on the Dirichlet distribution (Dirichlet Gaussian mixture model) has recently received great attention for modeling and processing data. This paper studies the new Dirichlet Gaussian mixture model for image segmentation. First, we propose a new way to incorporate the local spatial information between neighboring pixels based on the Dirichlet distribution. The main advantage is its simplicity, ease of implementation and fast computational speed. Secondly, existing Dirichlet Gaussian model uses complex log-likelihood function and require many parameters that are difficult to estimate. The total parameters in the proposed model lesser and the log-likelihood function have a simpler form. Finally, to estimate the parameters of the proposed Dirichlet Gaussian mixture model, a gradient method is adopted to minimize the negative log-likelihood function. Numerical experiments are conducted using the proposed model on various synthetic, natural and color images. We demonstrate through extensive simulations that the proposed model is superior to other algorithms based on the model-based techniques for image segmentation.     

基于多类邻域三支决策模型的不平衡数据分类

不平衡数据分类是一种重要的数据分类问题。对于不平衡数据中规模较小的类,传统的分类算法的分类效果较差。对此,提出一种多类邻域三支决策模型的不平衡数据分类算法。首先,将传统的三支决策在混合数据和多个类的情形下进行推广,提出了混合数据的多类邻域三支决策模型;然后,在该模型中给出一种自适应代价函数的设定方法,并基于该方法提出了多类邻域三支决策模型的不平衡数据分类算法。仿真实验的结果表明,所提出的分类算法对于不平衡数据具有更好的分类性能。     

双卷积池化结构的3D-CNN高光谱遥感影像分类方法

目的 高光谱遥感影像数据包含丰富的空间和光谱信息,但由于信号的高维特性、信息冗余、多种不确定性和地表覆盖的同物异谱及同谱异物现象,导致高光谱数据结构呈高度非线性。3D-CNN（3D convolutional neural network）能够利用高光谱遥感影像数据立方体的特性,实现光谱和空间信息融合,提取影像分类中重要的有判别力的特征。为此,提出了基于双卷积池化结构的3D-CNN高光谱遥感影像分类方法。方法 双卷积池化结构包括两个卷积层、两个BN（batch normalization）层和一个池化层,既考虑到高光谱遥感影像标签数据缺乏的问题,也考虑到高光谱影像高维特性和模型深度之间的平衡问题,模型充分利用空谱联合提供的语义信息,有利于提取小样本和高维特性的高光谱影像特征。基于双卷积池化结构的3D-CNN网络将没有经过特征处理的3D遥感影像作为输入数据,产生的深度学习分类器模型以端到端的方式训练,不需要做复杂的预处理,此外模型使用了BN和Dropout等正则化策略以避免过拟合现象。结果 实验对比了SVM（support vector machine）、SAE（stack autoencoder）以及目前主流的CNN方法,该模型在Indian Pines和Pavia University数据集上最高分别取得了99.65%和99.82%的总体分类精度,有效提高了高光谱遥感影像地物分类精度。结论 讨论了双卷积池化结构的数目、正则化策略、高光谱首层卷积的光谱采样步长、卷积核大小、相邻像素块大小和学习率等6个因素对实验结果的影响,本文提出的双卷积池化结构可以根据数据集特点进行组合复用,与其他深度学习模型相比,需要更少的参数,计算效率更高。     

基于超像素锚图二重降维的高光谱聚类算法

针对传统谱聚类算法难以应用于大规模高光谱图像,以及现有的改进谱聚类算法对大规模高光谱图像的处理效果不佳的问题,为降低聚类数据的复杂度,以降低聚类过程的计算成本从而多方面提升聚类性能,提出一种基于超像素锚图二重降维的高光谱聚类算法。首先,对高光谱数据进行主成分分析（PCA）处理,并针对高光谱图像的区域特性对其进行基于超像素切割的降维;其次,通过构造锚图的思想对上一步所得数据进行锚点的选取,并构建邻接锚图来实现二重降维,从而进行谱聚类;同时,为去除算法运行中人为调节参数的环节,在构建锚图时采用一种去除高斯核的无核锚图构造方式以实现自动构图。在Indian Pines数据集和Salinas数据集上的实验结果表明所提算法在保证可用性与低耗时的前提下可提高聚类的整体效果,从而验证了所提算法能提高聚类的质量与性能。     

标准分数降维的3D-CNN高光谱遥感图像分类

针对高光谱图像存在Hughes现象,以及空间和光谱特征利用效率低的问题,提出了一种结合标准分数降维和深度学习的高光谱图像分类算法.利用标准分数对高光谱数据的波段质量进行评价以剔除高光谱遥感图像中的冗余波段,结合优化过的3D-CNN(3D Convolutional Neural Network)分类方法,通过使用大步距...     

ICA mixture model algorithm for unsupervised classification of remote sensing imagery

Conventional remote sensing classification algorithms assume that the data in each class can be modelled using a multivariate Gaussian distribution. As this assumption is often not valid in practice, conventional algorithms do not perform well. In this paper, we present an independent component analysis (ICA)‐based approach for unsupervised classification of multi/hyperspectral imagery. ICA used for a mixture model estimates the data density in each class and models class distributions with non‐Gaussian (sub‐ and super‐Gaussian) probability density functions, resulting in the ICA mixture model (ICAMM) algorithm. Independent components and the mixing matrix for each class are found using an extended information‐maximization algorithm, and the class membership probabilities for each pixel are computed. The pixel is allocated to the class having maximum class membership probability to produce a classification. We apply the ICAMM algorithm for unsupervised classification of images obtained from both multispectral and hyperspectral sensors. Four feature extraction techniques are considered as a preprocessing step to reduce the dimensionality of the hyperspectral data. The results demonstrate that the ICAMM algorithm significantly outperforms the conventional K‐means algorithm for land cover classification produced from both multi‐ and hyperspectral remote sensing images.     

Variational Bayesian multinomial logistic Gaussian process classification

Multimedia Tools and Applications - The multinomial logistic Gaussian process is a flexible non-parametric model for multi-class classification tasks. These tasks are often involved in solving a...     

基于SVM概率输出与证据理论的多分类方法

单一技术无法有效解决多类分类问题。为此,提出一种基于一对多支持向量机(SVM)的基本概率分配输出方法,并与置信最大熵模型的D-S证据组合方法结合,给出基于SVM概率输出和证据理论的多分类模型。在3种UCI标准数据集上的仿真结果表明,该方法的分类精度优于传统的一对多和一对一硬输出方法,是一种有效的多类分类方法。     

A multi-class classification strategy for Fisher scores: Application to signer independent sign language recognition

Fisher kernels combine the powers of discriminative and generative classifiers by mapping the variable-length sequences to a new fixed length feature space, called the Fisher score space. The mapping is based on a single generative model and the classifier is intrinsically binary. We propose a multi-class classification strategy that applies a multi-class classification on each Fisher score space and combines the decisions of multi-class classifiers. We experimentally show that the Fisher scores of one class provide discriminative information for the other classes as well. We compare several multi-class classification strategies for Fisher scores generated from the hidden Markov models of sign sequences. The proposed multi-class classification strategy increases the classification accuracy in comparison with the state of the art strategies based on combining binary classifiers. To reduce the computational complexity of the Fisher score extraction and the training phases, we also propose a score space selection method and show that, similar or even higher accuracies can be obtained by using only a subset of the score spaces. Based on the proposed score space selection method, a signer adaptation technique is also presented that does not require any re-training.     

A unified neurofuzzy model for classification

This work proposes a unified neurofuzzy modelling scheme. To begin with, the initial fuzzy base construction method is based on fuzzy clustering utilising a Gaussian mixture model (GMM) combined with the analysis of covariance (ANOVA) decomposition in order to obtain more compact univariate and bivariate membership functions over the subspaces of the input features. The mean and covariance of the Gaussian membership functions are found by the expectation maximisation (EM) algorithm with the merit of revealing the underlying density distribution of system inputs. The resultant set of membership functions forms the basis of the generalised fuzzy model (GFM) inference engine. The model structure and parameters of this neurofuzzy model are identified via the supervised subspace orthogonal least square (OLS) learning. Finally, instead of providing deterministic class label as model output by convention, a logistic regression model is applied to present the classifier’s output, in which the sigmoid type of logistic transfer function scales the outputs of the neurofuzzy model to the class probability. Experimental validation results are presented to demonstrate the effectiveness of the proposed neurofuzzy modelling scheme.     

应用级联多分类器的高光谱图像分类

目的 高光谱分类任务中,由于波段数量较多,图像中存在包含噪声以及各类地物样本分布不均匀等问题,导致分类精度与训练效率不能平衡,在小样本上分类精度低。因此,提出一种基于级联多分类器的高光谱图像分类方法。方法 首先采用主成分分析方法将高度相关的高维特征合成无关的低维特征,以加快Gabor滤波器提取纹理特征的速度;然后使用Gabor滤波器提取图像在各个尺寸、方向上的纹理信息,每一个滤波器会生成一张特征图,在特征图中以待分类样本为中心取一个d×d的邻域,计算该邻域内数据的均值和方差来作为待分类样本的空间信息,再将空间信息和光谱信息融合,以降低光线与噪声的影响;最后将谱—空联合特征输入级联多分类器中,得到预测样本关于类别的概率分布的平均值。结果 实验采用Indian Pines、Pavia University和Salinas 3个数据集,与经典算法如支持向量机和卷积神经网络进行比较,并利用总体分类精度、平均分类精度和Kappa系数作为评价标准进行分析。本文方法总体分类精度在3个数据集上分别达到97.24%、99.57%和99.46%,相对于基于径向基神经网络（RBF）核函数的支持向量机方法提高了13.2%、4.8%和5.68%,相对于加入谱—空联合特征的RBF-SVM （radial basis function-support vector machine）方法提高了2.18%、0.36%和0.83%,相对于卷积神经网络方法提高了3.27%、3.2%和0.3%;Kappa系数分别是0.968 6、0.994 3和0.995 6,亦有提高。结论 实验结果表明,本文方法应用于高光谱图像分类具有较优的分类效果,训练效率较高,无需依赖GPU,而且在小样本上也具有较高的分类精度。     

基于类别可分性的高光谱图像波段选择

高光谱遥感数据具有丰富的光谱信息,应用十分广泛,但其冗余的光谱信息有时会限制高光谱图像的分类等的精度以及计算复杂度.为了提高解译效率,高光谱图像降维不可或缺,这也是高光谱图像处理的研究热点之一.提出了一种基于类别可分性的高光谱图像波段选择方法(Endmember Separability Based band Selection,ESBB),该方法通过Mahalanobis距离最大化图像中各类地物的可分性来确定最优的波段组合.相较于其他监督波段选择算法,该方法不需要大量训练样本,不用对每个组合做分类处理.对波段选择后的结果进行分类的实验结果证明,该方法是一个快速有效的波段选择方法,可以得到一个较好的分类精度.     

Unsupervised classification of hyperspectral data: an ICA mixture model based approach

Conventional unsupervised classification algorithms that model the data in each class with a multivariate Gaussian distribution are often inappropriate, as this assumption is frequently not satisfied by the remote sensing data. In this Letter, a new algorithm based on independent component analysis (ICA) is presented. The ICA mixture model (ICAMM) algorithm that models class distributions as non-Gaussian densities has been employed for unsupervised classification of a test image from the AVIRIS sensor. A number of feature-extraction techniques have also been examined that serve as a pre-processing step to reduce the dimensionality of the hyperspectral data. The proposed ICAMM algorithm results in significant increase in the classification accuracy over that obtained from the conventional K-means algorithm for land cover classification.