基于三维Saab变换的高光谱图像压缩方法

高光谱图像中存储了丰富的光谱信息,具有极大的应用价值,但现有大部分高光谱图像压缩方法难以同时兼顾图像中的空间冗余与谱间冗余,导致压缩性能受到局限。针对该问题,提出了一种基于三维修正偏置的子空间(Saab)变换的高光谱图像压缩方法。采用三维Saab变换对高光谱图像的分块进行空间光谱信息融合的降维操作,同时去除谱间冗余和局部空间冗余;利用高效率视频编码(HEVC)中的帧内编码模块进一步去除空间冗余和统计冗余;实现低失真、高比率的高光谱图像压缩。在多个高光谱图像数据集上的实验结果表明,所提方法在同码率下重建图像的信噪比(SNR)比采用主成分分析(PCA)降维的方法至少提高0.62 dB,在高码率的情况下性能优于张量分解的压缩方法。同时,验证了不同降维方法对分类任务的性能影响,结果表明,所提方法更好地保留了图像中的重要特征,在低码率的情况下仍可以保持较高的分类精度。      

基于记忆关联学习的小样本高光谱图像分类方法

高光谱图像（HSI）分类是遥感领域的基础应用之一。该任务旨在根据部分带类别标签的像素样本训练分类器，预测图像中剩余像素对应的类别标签。在实际应用中，由于人工标记样本成本过高，只能获得少量带标签的样本。针对少量样本无法准确描述数据分布从而导致训练过程过拟合的问题，提出一种基于记忆关联学习的小样本高光谱图像分类方法。考虑到无标签样本中包含大量与数据分布相关的信息，构建基于有标签样本记忆模块，并根据样本间的特征关联，利用不断更新的记忆模块学习无标签样本的潜在类别分布，构建无监督分类模型，并与传统的有监督分类模型进行联合学习。在多个高光谱图像分类数据集上的实验结果表明，所提方法能有效提升小样本高光谱图像分类的准确性。      

Fractal signatures for multiscale processing of hyperspectral image data

A multiscale approach to hyperspectral image data analysis using fractal signatures was proposed and implemented in the Interactive Data Language (IDL). For 2-D hyperspectral curves, fractal signature measures the changes in curve length with changing scale. Using NASA’s Earth Observing-1 (EO-1) Hyperion image from a study area near Denton, Texas, USA, the capabilities of fractal signatures in discriminating different land cover types were presented in three different ways: (1) fractal signature curves, (2) distances between fractal signatures, and (3) fractal signature images. The asymmetry in length measurement was found to be effective in handling hyperspectral curves obtained from Hyperion radiance data. The contribution of fractal signature images was shown through comparison of image classification results. The results from the Hyperion radiance data suggest that fractal signatures at certain scales can reveal important differences in land cover types.     

Selection of classification techniques for land use/land cover change investigation

The concerns over land use/land cover (LULC) change have emerged on the global stage due to the realisation that changes occurring on the land surface also influence climate, ecosystem and its services. As a result, the importance of accurate mapping of LULC and its changes over time is on the increase. Landsat satellite is a major data source for regional to global LULC analysis. The main objective of this study focuses on the comparison of three classification tools for Landsat images, which are maximum likelihood classification (MLC), support vector machine and artificial neural network (ANN), in order to select the best method among them. The classifiers algorithms are well optimized for the gamma, penalty, degree of polynomial in case of SVM, while for ANN minimum output activation threshold and RMSE are taken into account. The overall analysis shows that the ANN is superior to the kernel based SVM (linear, radial based, sigmoid and polynomial) and MLC. The best tool (ANN) is then applied on detecting the LULC change over part of Walnut Creek, Iowa. The change analysis of the multi temporal images indicates an increase in urban areas and a major shift in the agricultural practices.     

An approach to multi-temporal MODIS image analysis using image classification and segmentation

This paper discusses an approach for river mapping and flood evaluation based on multi-temporal time series analysis of satellite images utilizing pixel spectral information for image classification and region-based segmentation for extracting water-covered regions. Analysis of MODIS satellite images is applied in three stages: before flood, during flood and after flood. Water regions are extracted from the MODIS images using image classification (based on spectral information) and image segmentation (based on spatial information). Multi-temporal MODIS images from “normal” (non-flood) and flood time-periods are processed in two steps. In the first step, image classifiers such as Support Vector Machines (SVM) and Artificial Neural Networks (ANN) separate the image pixels into water and non-water groups based on their spectral features. The classified image is then segmented using spatial features of the water pixels to remove the misclassified water. From the results obtained, we evaluate the performance of the method and conclude that the use of image classification (SVM and ANN) and region-based image segmentation is an accurate and reliable approach for the extraction of water-covered regions.     

An optimal selection of probability distribution functions for unsupervised land cover classification of PALSAR-2 data

Different types of classification techniques are available in the literature for the classification of Synthetic Aperture Radar (SAR) data into various land cover classes. Various SAR images are available for land cover classification such as ALOS PALSAR (PALSAR-1, PALSAR-2), RADARSAT and ENVISAT. In this paper, we have attempted to explore probability distribution function (pdf) based land cover classification using PALSAR-2 data. Over 20 different statistical distribution functions are analyzed for different classes based on statistical parameters. Probability distribution functions are selected based on Chi-squared goodness of fit test for each individual class. A decision tree based classifier is developed for classification based on the selected pdf functions and its statistical parameters. The proposed classification approach has an accuracy of 83.93%.     

Development and testing of a statistical texture model for land cover classification of the Black Sea region with MODIS imagery

A statistical model is proposed for analysis of the texture of land cover types for global and regional land cover classification by using texture features extracted by multiresolution image analysis techniques. It consists of four novel indices representing second-order texture, which are calculated after wavelet decomposition of an image and after texture extraction by a new approach that makes use of a four-pixel texture unit. The model was applied to four satellite images of the Black Sea region, obtained by Terra/MODIS and Aqua/MODIS at different spatial resolution. In single texture classification experiments, we used 15 subimages (50 × 50 pixels) of the selected classes of land covers that are present in the satellite images studied. These subimages were subjected to one-level and two-level decompositions by using orthonormal spline and Gabor-like spline wavelets. The texture indices were calculated and used as feature vectors in the supervised classification system with neural networks. The testing of the model was based on the use of two kinds of widely accepted statistical texture quantities: five texture features determined by the co-occurrence matrix (angular second moment, contrast, correlation, inverse difference moment, entropy), and four statistical texture features determined after the wavelet transformation (mean, standard deviation, energy, entropy). The supervised neural network classification was performed and the discrimination ability of the proposed texture indices was found comparable with that for the sets of five GLCM texture features and four wavelet-based texture features. The results obtained from the neural network classifier showed that the proposed texture model yielded an accuracy of 92.86% on average after orthonormal wavelet decomposition and 100% after Gabor-like wavelet decomposition for texture classification of the examined land cover types on satellite images.     

基于多种空间信息的高光谱遥感图像分类方法

在高光谱遥感图像分类方法中,空间特征和光谱特征的融合可以有效地改善分类效果。针对单一空间特征的信息表达不充分问题,提出了一种联合多种空间特征的高光谱图像空谱分类方法。利用超像素信息对分类结果进行后处理去掉椒盐噪声,并创造性地将超像素信息应用于分类前处理,提出了一种利用超像素信息对像素点的特征向量进行线性加权融合的方法。试验结果表明,所提方法的性能优于目前的通常方法。     

Crater detection via genetic search methods to reduce image features

Recent approaches to crater detection have been inspired by face detection’s use of gray-scale texture features. Using gray-scale texture features for supervised machine learning crater detection algorithms provides better classification of craters in planetary images than previous methods. When using Haar features it is typical to generate thousands of numerical values from each candidate crater image. This magnitude of image features to extract and consider can spell disaster when the application is an entire planetary surface. One solution is to reduce the number of features extracted and considered in order to increase accuracy as well as speed. Feature subset selection provides the operational classifiers with a concise and denoised set of features by reducing irrelevant and redundant features. Feature subset selection is known to be NP-hard. To provide an efficient suboptimal solution, four genetic algorithms are proposed to use greedy selection, weighted random selection, and simulated annealing to distinguish discriminate features from indiscriminate features. Inspired by analysis regarding the relationship between subset size and accuracy, a squeezing algorithm is presented to shrink the genetic algorithm’s chromosome cardinality during the genetic iterations. A significant increase in the classification performance of a Bayesian classifier in crater detection using image texture features is observed.     

Advanced fractal approach for unsupervised classification of SAR images

Unsupervised classification of Synthetic Aperture Radar (SAR) images is the alternative approach when no or minimum apriori information about the image is available. Therefore, an attempt has been made to develop an unsupervised classification scheme for SAR images based on textural information in present paper. For extraction of textural features two properties are used viz. fractal dimension D and Moran’s I. Using these indices an algorithm is proposed for contextual classification of SAR images. The novelty of the algorithm is that it implements the textural information available in SAR image with the help of two texture measures viz. D and I. For estimation of D, the Two Dimensional Variation Method (2DVM) has been revised and implemented whose performance is compared with another method, i.e., Triangular Prism Surface Area Method (TPSAM). It is also necessary to check the classification accuracy for various window sizes and optimize the window size for best classification. This exercise has been carried out to know the effect of window size on classification accuracy. The algorithm is applied on four SAR images of Hardwar region, India and classification accuracy has been computed. A comparison of the proposed algorithm using both fractal dimension estimation methods with the K-Means algorithm is discussed. The maximum overall classification accuracy with K-Means comes to be 53.26% whereas overall classification accuracy with proposed algorithm is 66.16% for TPSAM and 61.26% for 2DVM.     

Comparison of Landsat OLI,ASTER, and Sentinel 2A data in lithological mapping : A Case study of Rich area (Central High Atlas,Morocco)

The eastern part of the Rich area consists of the massive Paleozoic and Meso-Cenozoic cover formations that present the geodynamic development of the study area, where is characterized by various carbonate facies of Jurassic age. The geographical characteristic of the study area leaves the zone difficult to map by conventional methods. The objective of this work focuses on the mapping of the constituent lithological units of the study area using multispectral data of Landsat OLI, ASTER, and Sentinel 2A MSI. The processing of these data is based on a precise methodology that distinguishs and highlights the limits of the different lithological units that have an approximate similarity of spectral signature. Three techniques were used to enhance the image including Principal Component Analysis (PCA), Minimum Noise Fraction (MNF), and Independent Component Analysis (ICA). Lithological mapping was performed using two types of supervised classification : Maximum likelihood classifier (MLC) and Support Vector Machine (SVM).The results of processing data show the effectiveness of Sentinel 2A data in mapping of lithological units than the ASTER and Landsat OLI data. The classification evaluation of two methods of the Sentinel 2A MSI image showed that the SVM method give a better classification with an overall accuracy of 93,93% and a Kappa coefficient of 0.93, while the MLC method present an overall accuracy of 82,86% and a Kappa coefficient of 0.80. The results of mapping obtained show a good correlation with the geological map of the study area as well as the efficiency of remote sensing in identification of different lithological units in the Central High Atlas.     

基于串行支持向量分类器的模拟电路故障诊断

介绍了支持向量机的基本原理,提出一种新型支持向量多类分类器,其中多个二类分类器组成串行结构,每个二类分类器均带有非线性主元素分析特征提取器.描述了其训练与分类算法,并将其应用于非线性电路的部件级诊断.和传统BP网和RBF网分类器相比,支持向量方法在分类准确率上表现出明显的优势,其中串行支持向量多类分类器无论在训练和分类速度方面,还是在诊断准确率方面,都要优于传统并行结构的多类分类器.      

基于局部线性嵌入的高光谱影像特征提取算法

特征提取能够消除冗余信息,提高高光谱数据处理的精度和计算效率,是分类等分析必要的预处理手段.传统特征提取算法基于线性变换,无法准确描述高、低维特征空间的关系,因此采用一种新型非线性特征提取算法,即局部线性嵌入(LLE,Locally Linear Em-bedding),挖掘高光谱影像的本征信息.针对分类问题,使用训练样本类别属性修正距离矩阵,并借鉴LLE计算未知样本低维映射的方法求解测试样本的特征向量,实现监督局部线性嵌入(SLLE,Supervised Locally Linear Embedding).使用机载可见光/红外成像光谱仪数据,与3种分类算法结合进行测试,实验结果表明:SLLE优于线性特征提取算法,能够解决高光谱影像的小样本分类问题.     

Hierarchical object oriented classification using very high resolution imagery and LIDAR data over urban areas

Urban land cover information extraction is a hot topic within urban studies. Heterogeneous spectra of high resolution imagery—caused by the inner complexity of urban areas—make it difficult. In this paper a hierarchical object oriented classification method over an urban area is presented. Combining QuickBird imagery and light detection and ranging (LIDAR) data, nine kinds of land cover objects were extracted. The Spectral Shape Index (SSI) method is used to distinguish water and shadow from black body mask, with 100% classification accuracy for water and 95.56% for shadow. Vegetation was extracted by using a Normalized Difference Vegetation Index (NDVI) image at first, and then a more accurate classification result of shrub and grassland is obtained by integrating the height information from LIDAR data. The classification accuracy of shrub was improved from 85.25% to 92.09% and from 82.86% to 97.06% for grassland. More granularity of this classification can be obtained by using this method. High buildings and low buildings can, for example, be distinguished from the original building class. Road class can also be further classified into roads and crossroads. The comparison of the classification accuracy between this method and the traditional pixel-based method indicates that the total accuracy is improved from 69.12% to 89.40%.     

Novel method for reconstruction of hyperspectral resolution images from multispectral data for complex coastal and inland waters

Hyperspectral resolution image products of a synthetic sensor featuring the high spatial resolution of the space-borne sensor can offer cost-effective means for enhancing our current capabilities in terms of providing an array of images in lieu of designing an expensive system for image acquisition, which can serve the expanding needs of the scientific and user communities for various critical water color applications. Despite several studies on enhancing the capability of land remote sensing sensors, full spectrum reconstruction of water color images with varying spectral bands is hampered by the lack of methods and accurate atmospheric correction procedures. In the present work, a novel method is developed for reconstruction of hyperspectral resolution images from high spatial-resolution Sentinel 2 Multispectral Instrument (MSI) data representative of many complex waters in coastal and inland zones. This method uses a deep neural network (DNN) with multiple blocks of deconvolution and dense layers. The spectral reconstruction of hyperspectral resolution images from multispectral data was based on rigorous training data from the atmospherically-corrected and validated HICO normalized water-leaving radiance products (with spectral resolution 438-868 nm sampled at 5.7 nm) of diverse water types. The generalizability and versatility of the DNN method was tested and evaluated systematically by means of various qualitative and quantitative analyses using concurrent space-borne (MSI and HICO) and in-situ measurements from different regional waters. Reconstructed hyperspectral resolution radiances obtained from the MSI images closely matched with independent HICO and MSI measurements within the desired accuracy. Successful reconstruction and validation of the hyperspectral radiances indicate that the proposed state-of-the-art method provides possible future directions for enhancing our current capabilities of space-borne sensors for various research purposes and societal applications at local, regional and global scales.     

超谱遥感图像降维方法研究现状与分析

随着成像光谱仪的发展 ,超谱遥感图像的研究已进入到一个新的阶段———对获取的超谱数据进行有效处理和利用的阶段。目前的处理方法主要集中在对超谱图像的数值分析处理上 ,比如大气校正、降低数据维数、信息提取、分类与压缩等方面。而超谱图像降维方法的研究是做好后继处理的一个关键步骤 ,降维方式的正确选取与使用 ,对于发展和完善那些针对超谱海量数据和丰富信息特点的算法和软件有极大的好处。文章从波段选择、划分数据源、特征提取和融合等 4个角度对目前超谱图像的各种降维方法进行了综合归纳和分析。力图为超谱图像处理寻找突破点 ,加强此领域的研究力度     

基于样本类别确定度的半监督分类

在对遥感图像进行分类时,全监督算法往往需要足够的标记样本进行训练,然而标记的过程是耗时和昂贵的,相反收集大量的无标记样本是很容易的。为了在学习过程中能够有效利用未标记样本的信息,本文提出了基于样本类别确定度（CCS）的半监督分类算法。首先,利用多分类支持向量机（SVM）得到未标记样本属于各类别的确定度,有效地衡量了未标记样本类别可靠性;其次,对样本类别确定度进行预处理,提升利用未标记样本的安全性;最后,基于样本类别确定度设计了半监督线性判别分析（LDA）降维算法并对其进行核化,使得样本在降维后的子空间更具有可分性,并根据降维后的数据特点,采用最近邻分类器对新样本进行分类。利用真实的合成孔径雷达（SAR）图像进行测试,验证了在标记样本较少的情况下,本文算法在性能上优于全监督和其他半监督算法,并能够快速收敛。