不同降维策略下的高光谱影像多特征分类

由于物体表面的空间分布通常是富有规律且局部连续的,在高光谱影像分类中应充分利用其光谱和空间信息.本文在对高光谱影像立方体进行降维处理的基础上,提出了一种联合空域和谱域信息的高光谱影像高效分类方法.首先,分别选用主成分分析(Principal Component Analysis,PCA)和正交投影波段选择(Orthog...     

Analyzing fine-scale wetland composition using high resolution imagery and texture features

In order to monitor natural and anthropogenic disturbance effects to wetland ecosystems, it is necessary to employ both accurate and rapid mapping of wet graminoid/sedge communities. Thus, it is desirable to utilize automated classification algorithms so that the monitoring can be done regularly and in an efficient manner. This study developed a classification and accuracy assessment method for wetland mapping of at-risk plant communities in marl prairie and marsh areas of the Everglades National Park. Maximum likelihood (ML) and Support Vector Machine (SVM) classifiers were tested using 30.5 cm aerial imagery, the normalized difference vegetation index (NDVI), first and second order texture features and ancillary data. Additionally, appropriate window sizes for different texture features were estimated using semivariogram analysis. Findings show that the addition of NDVI and texture features increased classification accuracy from 66.2% using the ML classifier (spectral bands only) to 83.71% using the SVM classifier (spectral bands, NDVI and first order texture features).     

利用TM数据提取含金蚀变带的方法研究─以冀北东卯地区为例

卫星遥感技术是一种利用电磁波作载体从高空探测地面信息的技术。在遥感地质找矿中, 环境因素对成矿条件信息的增强和提取来说可以认为是干扰因素。这种环境干扰因素在空间上可分为集中分布的和分散分布的两类。本文是用图像分割的方法从TM的7个波段原始数据中去掉集中分布的环境因素, 用PC统计数据的二维散点图所表达的数据特征, 把地质目标信息和分散分布的环境干扰因素分开, 实现排除二类环境干扰因素, 从而增强提取含金蚀变带信息的目的。     

Novel Folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensing

As a widely used approach for feature extraction and data reduction, Principal Components Analysis (PCA) suffers from high computational cost, large memory requirement and low efficacy in dealing with large dimensional datasets such as Hyperspectral Imaging (HSI). Consequently, a novel Folded-PCA is proposed, where the spectral vector is folded into a matrix to allow the covariance matrix to be determined more efficiently. With this matrix-based representation, both global and local structures are extracted to provide additional information for data classification. Moreover, both the computational cost and the memory requirement have been significantly reduced. Using Support Vector Machine (SVM) for classification on two well-known HSI datasets and one Synthetic Aperture Radar (SAR) dataset in remote sensing, quantitative results are generated for objective evaluations. Comprehensive results have indicated that the proposed Folded-PCA approach not only outperforms the conventional PCA but also the baseline approach where the whole feature sets are used.     

Mapping alteration mineral zones and lithological units in Antarctic regions using spectral bands of ASTER remote sensing data

Abstract

Geological mapping is one of the primary tasks of remote sensing. Remote sensing applications are especially useful when extreme environmental conditions inhibit direct survey such as in Antarctica. In this investigation, a satellite-based remote sensing approach was used for mapping alteration mineral zones and lithological units using Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data in the Oscar II coast area, north-eastern Graham Land, Antarctic Peninsula. Specialized band ratios and band combinations were developed using visible and near infrared, shortwave infrared (SWIR) and thermal infrared spectral bands of ASTER for detecting alteration mineral assemblages and lithological units in Antarctic environments. Constrained Energy Minimization, Orthogonal Subspace Projection and Adaptive Coherence Estimator algorithms were tested to ASTER SWIR bands for detecting sub-pixels’ abundance of spectral features related to muscovite, kaolinite, illite, montmorillonite, epidote, chlorite and biotite. Results indicate valuable applicability of ASTER data for Antarctic geological mapping.     

Aqueous alteration mapping in Rishabdev ultramafic complex using imaging spectroscopy

Hyperspectral remote sensing/imaging spectroscopy has enabled precise identification and mapping of hydrothermal alteration mineral assemblages based on diagnostic absorption features of minerals. In the present study, we use Airborne Visible InfraRed Imaging Spectrometer-Next Generation (AVIRIS-NG) datasets acquired over Rishabdev ultramafic suite to derive surficial mineral map using least square based spectral shape matching in wavelength range of diagnostic absorption features of minerals. Resulting mineral map revealed presence of hydrothermally altered serpentine group of minerals and associated alteration products (talc and dolomite) along with clays and phyllosilicates. Mineral maps are validated using field spectral measurements and published geological map. Involvement of low temperature (<350 °C) hydrothermal fluid in serpentinization of ultramafic rocks in the region is inferred from analysis of deepest absorption features of muscovites at 2.20 μm, spectral abundance of lizardite and absence of prenhite-pumpyllite facies mineral assemblages. Talc was found to be the most common alteration product of serpentines followed by dolomites. Intense alteration of serpentines to talc along the fracture zone is attributed to the circulation of carbon dioxide rich hydrothermal fluids along these conduits. Kaolinite and halloysite are primarily associated with granites and are the result of hydrothermal alteration of plagioclase feldspar in granites while muscovite and illites are generally associated with phyllites and quartzites . The study demonstrates the potential of imaging spectroscopy for mapping hydrothermal alteration mineral assemblages in ultramafic complex.     

A Hierarchical Hybrid SVM Method for Classification of Remotely Sensed Data

The focus of this work is on developing a new hierarchical hybrid Support Vector Machine (SVM) method to address the problems of classification of multi or hyper spectral remotely sensed images and provide a working technique that increases the classification accuracy while lowering the computational cost and complexity of the process. The paper presents issues in analyzing large multi/hyper spectral image data sets for dimensionality reduction, coping with intra pixel spectral variations, and selection of a flexible classifier with robust learning process. Experiments conducted revealed that a computationally cheap algorithm that uses Hamming distance between the pixel vectors of different bands to eliminate redundant bands was quite effective in helping reduce the dimensionality. The paper also presents the concept of extended mathematical morphological profiles for segregating the input pixel vectors into pure or mixed categories which will enable further computational cost reductions. The proposed method’s overall classification accuracy is tested with IRS data sets and the Airborne Visible Infrared Imaging Spectroradiometer Indian Pines hyperspectral benchmark data set and presented.     

Channel bar feature extraction for a mining-contaminated river using high-spatial multispectral remote-sensing imagery

Mapping and monitoring changes of geomorphological features over time are important for understanding fluvial process and effects of its controlling factors. Using high spatial resolution multispectral images has become common practice in the mapping as these images become widely available. Traditional pixel-based classification relies on statistical characteristics of single pixels and performs poorly in detailed mapping using high resolution multispectral images. In this work, we developed a hybrid method that detects and maps channel bars, one of the most important geomorphological features, from high resolution multispectral aerial imagery. This study focuses on the Big River which drains the Ozarks Plateaus region in southeast Missouri and the Old Lead Belt Mining District which was one of the largest producers of lead worldwide in the early and middle 1900s. Mapping and monitoring channel bars in the Big River is essential for evaluating the fate of contaminated mining sediment released to the Big River. The dataset in this study is 1 m spatial resolution and is composed of four bands: Red (Band 3), Green (Band 2), Blue (Band 1) and Near-Infrared (Band 4). The proposed hybrid method takes into account both spectral and spatial characteristics of single pixels, those of their surrounding contextual pixels and spatial relationships of objects. We evaluated its performance by comparing it with two traditional pixel-based classifications including Maximum Likelihood (MLC) and Support Vector Machine (SVM). The findings indicate that derived characteristics from segmentation and human knowledge can highly improve the accuracy of extraction and our proposed method was successful in extracting channel bars from high spatial resolution images.     

基于波段子集的独立分量分析的特征提取的高光谱遥感影像分类

针对高光谱影像数据具有波段众多、数据量较大的特点,本文提出了一种基于波段子集的独立分量分析(ICA)特征提取的高光谱遥感影像分类的新方法。以北京昌平小汤山地区的高光谱影像为例,根据高光谱遥感影像的相邻波段的相关性进行子空间划分,在各个波段子集上采用ICA算法进行特征提取,将各个子空间提取的特征合并组成特征向量,采用支持向量机(SVM)分类器进行分类。结果表明:该方法分类精度最佳(分类精度89.04%,Kappa系数0.8605,明显优于其它特征提取方法的SVM分类,有效地提高了高光谱数据的分类精度。     

Assessing the performance of two unsupervised dimensionality reduction techniques on hyperspectral APEX data for high resolution urban land-cover mapping

Despite the high richness of information content provided by airborne hyperspectral data, detailed urban land-cover mapping is still a challenging task. An important topic in hyperspectral remote sensing is the issue of high dimensionality, which is commonly addressed by dimensionality reduction techniques. While many studies focus on methodological developments in data reduction, less attention is paid to the assessment of the proposed methods in detailed urban hyperspectral land-cover mapping, using state-of-the-art image classification approaches. In this study we evaluate the potential of two unsupervised data reduction techniques, the Autoassociative Neural Network (AANN) and the BandClust method – the first a transformation based approach, the second a feature-selection based approach – for mapping of urban land cover at a high level of thematic detail, using an APEX 288-band hyperspectral dataset. Both methods were tested in combination with four state-of-the-art machine learning classifiers: Random Forest (RF), AdaBoost (ADB), the multiple layer perceptron (MLP), and support vector machines (SVM). When used in combination with a strong learner (MLP, SVM) BandClust produces classification accuracies similar to or higher than obtained with the full dataset, demonstrating the method’s capability of preserving critical spectral information, required for the classifier to successfully distinguish between the 22 urban land-cover classes defined in this study. In the AANN data reduction process, on the other hand, important spectral information seems to be compromised or lost, resulting in lower accuracies for three of the four classifiers tested. Detailed analysis of accuracies at class level confirms the superiority of the SVM/Bandclust combination for accurate urban land-cover mapping using a reduced hyperspectral dataset. This study also demonstrates the potential of the new APEX sensor data for detailed mapping of land cover in spatially and spectrally complex urban areas.     

Hydrothermal Alteration Mapping Using ASTER Data for Reconnaissance Porphyry Copper Mineralization in the Ahar Area, NW Iran

The Ahar area is located in East Azarbaijan province, and covers an area of about 2,500 km². Spectral mapping techniques were applied on VNIR and SWIR of ASTER data for discriminating between hydrothermal alteration zones and the identification of high potential mineralized lithological unit associated with hydrothermal porphyry copper mineralization in the Ahar. In this research to remove atmospheric and topographic effects from ASTER data, the log-residual method (LRM) was used. Four methods, Relative Band Depth Ratios (RBD), Principal Component Analysis (PCA), Minimum Noise Fraction (MNF) and matched filtering (MF), were used to processing and interpretation of remote sensing data in the study area. Results show that ASTER images provide preliminary mineralogy information and geo-referenced alteration maps at low cost and with high accuracy for reconnaissance porphyry copper mineralizations.     

结合PCA、多尺度分割及SVM的ASTER遥感蚀变信息提取

为了利用遥感影像进行更加精确的找矿预测,本文选择新疆东天山尾亚地区ASTER数据进行矿化蚀变信息提取方法研究.为了提高信息提取精度,本文提出了结合主成分分析(PCA)、多尺度分割和支持向量机(SVM)的遥感矿化蚀变信息提取方法.首先,分析ASTER数据的特征,选取各矿化蚀变信息的特征波段,对组合波段进行主成分分析,获得...     

Lithological Mapping in the Eastern Part of the Central Iranian Volcanic Belt Using Combined ASTER and IRS data

The study area is located in the eastern part of the central Iranian volcanic belt. Advanced Space-borne Thermal Emission and Reflection Radiometer (ASTER) and Indian Remote Sensing Satellite (IRS ) pan images were used for applying several image classification methods for lithological mapping. ASTER visible-near infrared and shortwave infrared bands were sharpened using IRS pan image. We used classification methods such as Maximum likelihood, Spectral Angle Mapper (SAM) and Spectral Information Divergence (SID) in order to evaluate the usefulness of these methods for geological mapping. The classification results showed that MLC has the best accuracy and the classified image closely resembles the previously prepared geology map of the area.     

Lithological mapping from hyperspectral data by improved use of spectral angle mapper

The spectral angle mapper (SAM), as a spectral matching method, has been widely used in lithological type identification and mapping using hyperspectral data. The SAM quantifies the spectral similarity between an image pixel spectrum and a reference spectrum with known components. In most existing studies a mean reflectance spectrum has been used as the reference spectrum for a specific lithological class. However, this conventional use of SAM does not take into account the spectral variability, which is an inherent property of many rocks and is further magnified in remote sensing data acquisition process. In this study, two methods of determining reference spectra used in SAM are proposed for the improved lithological mapping. In first method the mean of spectral derivatives was combined with the mean of original spectra, i.e., the mean spectrum and the mean spectral derivative were jointly used in SAM classification, to improve the class separability. The second method is the use of multiple reference spectra in SAM to accommodate the spectral variability. The proposed methods were evaluated in lithological mapping using EO-1 Hyperion hyperspectral data of two arid areas. The spectral variability and separability of the rock types under investigation were also examined and compared using spectral data alone and using both spectral data and first derivatives. The experimental results indicated that spectral variability significantly affected the identification of lithological classes with the conventional SAM method using a mean reference spectrum. The proposed methods achieved significant improvement in the accuracy of lithological mapping, outperforming the conventional use of SAM with a mean spectrum as the reference spectrum, and the matching filtering, a widely used spectral mapping method.     

Evaluation of classifiers for processing Hyperion (EO-1) data of tropical vegetation

There is an urgent necessity to monitor changes in the natural surface features of earth. Compared to broadband multispectral data, hyperspectral data provides a better option with high spectral resolution. Classification of vegetation with the use of hyperspectral remote sensing generates a classical problem of high dimensional inputs. Complexity gets compounded as we move from airborne hyperspectral to Spaceborne technology. It is unclear how different classification algorithms will perform on a complex scene of tropical forests collected by spaceborne hyperspectral sensor. The present study was carried out to evaluate the performance of three different classifiers (Artificial Neural Network, Spectral Angle Mapper, Support Vector Machine) over highly diverse tropical forest vegetation utilizing hyperspectral (EO-1) data. Appropriate band selection was done by Stepwise Discriminant Analysis. The Stepwise Discriminant Analysis resulted in identifying 22 best bands to discriminate the eight identified tropical vegetation classes. Maximum numbers of bands came from SWIR region. ANN classifier gave highest OAA values of 81% with the help of 22 selected bands from SDA. The image classified with the help SVM showed OAA of 71%, whereas the SAM showed the lowest OAA of 66%. All the three classifiers were also tested to check their efficiency in classifying spectra coming from 165 processed bands. SVM showed highest OAA of 80%. Classified subset images coming from ANN (from 22 bands) and SVM (from 165 bands) are quite similar in showing the distribution of eight vegetation classes. Both the images appeared close to the actual distribution of vegetation seen in the study area. OAA levels obtained in this study by ANN and SVM classifiers identify the suitability of these classifiers for tropical vegetation discrimination.     

Impact of feature selection on the accuracy and spatial uncertainty of per-field crop classification using Support Vector Machines

Crop mapping is one major component of agricultural resource monitoring using remote sensing. Yield or water demand modeling requires that both, the total surface that is cultivated and the accurate distribution of crops, respectively is known. Map quality is crucial and influences the model outputs. Although the use of multi-spectral time series data in crop mapping has been acknowledged, the potentially high dimensionality of the input data remains an issue. In this study Support Vector Machines (SVM) are used for crop classification in irrigated landscapes at the object-level. Input to the classifications is 71 multi-seasonal spectral and geostatistical features computed from RapidEye time series. The random forest (RF) feature importance score was used to select a subset of features that achieved optimal accuracies. The relationship between the hard result accuracy and the soft output from the SVM is investigated by employing two measures of uncertainty, the maximum a posteriori probability and the alpha quadratic entropy. Specifically the effect of feature selection on map uncertainty is investigated by looking at the soft outputs of the SVM, in addition to classical accuracy metrics. Overall the SVMs applied to the reduced feature subspaces that were composed of the most informative multi-seasonal features led to a clear increase in classification accuracy up to 4.3%, and to a significant decline in thematic uncertainty. SVM was shown to be affected by feature space size and could benefit from RF-based feature selection. Uncertainty measures from SVM are an informative source of information on the spatial distribution of error in the crop maps.     

Mapping forest leaf area index using reflectance and textural information derived from WorldView-2 imagery in a mixed natural forest area in Florida,US

The leaf area index (LAI) of plant canopies is an important structural parameter that controls energy, water, and gas exchanges of plant ecosystems. Remote sensing techniques may offer an alternative for measuring and mapping forest LAI at a landscape scale. Given the characteristics of high spatial/spectral resolution of the WorldView-2 (WV2) sensor, it is of significance that the textural information extracted from WV2 multispectral (MS) bands will be first time used in estimating and mapping forest LAI. In this study, LAI mapping accuracies would be compared from (a) spatial resolutions between 2-m WV2 MS data and 30-m Landsat TM imagery, (b) the nature of variables between spectrum-based features and texture-based features, and (c) sensors between TM and WV2. Therefore spectral/textural features (SFs) were first selected and tested; then a canonical correlation analysis was performed with different data sets of SFs and LAI measurement; and finally linear regression models were used to predict and map forest LAI with canonical variables calculated from image data. The experimental results demonstrate that for estimating and mapping forest LAI, (i) using high resolution data (WV2) is better than using relatively low resolution data (TM); (ii) extracted from the same WV2 data, texture-based features have higher capability than that of spectrum-based features; (iii) a combination of spectrum-based features with texture-based features could lead to even higher accuracy of mapping forest LAI than their either one separately; and (iv) WV2 sensor outperforms TM sensor significantly. However, we need to address the possible overfitting phenomenon that might be brought in by using more input variables to develop models. In addition, the experimental results also indicate that the red-edge band in WV2 was the worst on estimating LAI among WV2 MS bands and the WV2 MS bands in the visible range had a much higher correlation with ground measured LAI than that red-edge and NIR bands did.     

Benthic coverage and bottom topography of coral reef environment over Pirotan reef,Gulf of Kachchh region,India

Remote sensing measurements in coral reef environments commonly confront the problem of overlying atmosphere and modification of spectral signal due to water column over the bottom substrates. In order to correct these problems, hyperspectral observations offer an advantage over multispectral observations. Airborne hyperspectral remote sensing data from Airborne Visible Infrared Imaging Spectrometer- Next Generation (AVIRIS-NG) sensor was acquired during low tidal condition on 14 February 2016 at Pirotan reef, Gulf of Kachchh region, India. The objective of this study is to map benthic coverage and bottom topography over Pirotan reef. The methodology involved atmospheric correction, simultaneous retrieval of water parameters, bathymetry, water column correction and mapping. Atmospheric correction was performed by removing path radiance and aerosol contribution and dividing by atmospheric transmittance and incoming solar irradiance to obtain remote sensing reflectance. Model derived error minimization technique was used for simultaneous retrieval of water parameters and bathymetry. Derived water parameters were used to account for water column attenuation and retrieve concomitant true bottom signature.     

Integrating environmental variables and WorldView-2 image data to improve the prediction and mapping of Thaumastocoris peregrinus (bronze bug) damage in plantation forests

This study integrated environmental variables together with high spectral resolution WorldView-2 imagery to detect and map Thaumastocoris peregrinus damage in Eucalypt plantation forests in KwaZulu-Natal, South Africa. The WorldView-2 bands, vegetation indices and environmental variables were entered separately into PLS regression models to predict T. peregrinus damage. The datasets were then integrated to test the collective strength in predicting T. peregrinus damage. Important variables were identified by variable importance (VIP) scores and were re-entered into a PLS regression model. The VIP model was then extrapolated to map the severity of damage and predicted T. peregrinus damage with an R² value of 0.71 and a RMSE of 3.26% on an independent test dataset. The red edge and near-infrared bands of the WorldView-2 sensor together with the temperature dataset were identified as important variables in predicting T. peregrinus damage. The results indicate the potential of integrating WorldView-2 data and environmental variables to improve the mapping and monitoring of insect outbreaks in plantation forests. The result is critical for plantation health monitoring using a new sensor which contains important vegetation wavelengths.     

A Multiple SVM System for Classification of Hyperspectral Remote Sensing Data

With recent technological advances in remote sensing sensors and systems, very high-dimensional hyperspectral data are available for a better discrimination among different complex land-cover classes. However, the large number of spectral bands, but limited availability of training samples creates the problem of Hughes phenomenon or ‘curse of dimensionality’ in hyperspectral data sets. Moreover, these high numbers of bands are usually highly correlated. Because of these complexities of hyperspectral data, traditional classification strategies have often limited performance in classification of hyperspectral imagery. Referring to the limitation of single classifier in these situations, Multiple Classifier Systems (MCS) may have better performance than single classifier. This paper presents a new method for classification of hyperspectral data based on a band clustering strategy through a multiple Support Vector Machine system. The proposed method uses the band grouping process based on a modified mutual information strategy to split data into few band groups. After the band grouping step, the proposed algorithm aims at benefiting from the capabilities of SVM as classification method. So, the proposed approach applies SVM on each band group that is produced in a previous step. Finally, Naive Bayes (NB) as a classifier fusion method combines decisions of SVM classifiers. Experimental results on two common hyperspectral data sets show that the proposed method improves the classification accuracy in comparison with the standard SVM on entire bands of data and feature selection methods.