Hyperspectral Satellite Data in Mapping Salt-Affected Soils Using Linear Spectral Unmixing Analysis

Development of salt-affected soils in the irrigated lands of arid and semi-arid region is major cause of land degradation. Hyperion hyperspectral remote sensing data (EO-1) was used in the present study for characterization and mapping of salt-affected soils in a part of irrigation command area of Indo-Gangetic alluvial plains. Linear spectral mixture analysis approach was used to map various categories of salt affected soils represented by spectral endmembers of slightly, moderately and highly salt-affected soils. These endmembers were related to surface expression of various categories of salt-affected soils in the area. The endmembers were selected by performing minimum noise fraction (MNF) transformation and pixel purity index (PPI) on Hyperion (EO-1) data with reference to high resolution LISS IV data and field data. The results showed that various severity classes of salt-affected soils could be reliably mapped using linear spectral unmixing analysis. A low RMSE value (0.0193) over the image was obtained that revealed a good fit of the model in identification and classification of endmembers of various severities of salt affected soils. The overall classification accuracies for slight, moderate and highly salt-affected soils were estimated of 78.57, 79.81 and 84.43% respectively.     

基于多特征融合与典型降维方法的高光谱影像分类

高光谱影像的冗余信息给影像的分类效果带来一定的负面影响。本文利用CB法(CfsSubsetEval评估器结合Best-First搜索策略)与PCA变换两种降维方法,分别结合随机森林分类器对4种多特征融合方案(共8种组合)进行高光谱影像分类对比,基于分类的总体精度、Kappa系数探究提高高光谱影像分类的最佳组合方法。结果表明:①多特征融合可提升高光谱影像的分类效果,两种降维方法的分类精度均随地理特征、纹理特征、指数特征的加入而逐渐提高。②两种降维方法中,经CB法降维后的分类精度均比通过PCA变换降维的分类精度高。在构造的8种组合中,基于所有特征信息(光谱特征、地理特征、纹理特征、指数特征)的CB法分类精度最高,其总体精度为98.01%;Kappa系数为0.969 9。     

Spectral reflectance characteristics of salt-affected arid soils of Rajasthan

The spectral reflectance characteristics of different types of natural and anthropogenic salt-affected soils have been studied under field conditions. The spectral reflectance value for non-saline and all types of salt-affected soils was maximum in near infra red region (800–1000 nm). The natural salt-affected soils having surface salt encrustation showed highest reflectance value followed by the sodic soils (formed due to high residual sodium carbonate water irrigation) natural saline soils and saline soils due to saline water irrigation. Soil texture, pH, CaC0₃ and organic matter together accounted for 29.6% variation in the maximum reflectance percentage value out of which only pH accounted for more than half (14.2% variation).     

Delineating salt-affected soils in the ganges plain by digital analysis of landsat data

A study has been conducted to determine the feasibility of delineating salt-affected soils using computer-aided analysis of Landsat-1 data in an area of the Ganges Plain. The multispectral scanner data have been obtained on 2nd December 1972 Landsat pass. Both supervised and unsupervised classification techniques are used. Four spectral classes of salt-affected soils have been separated. The results indicate that Landsat data can be successfully used for differentiating salt-affected soils.     

面向对象的旱区植被遥感精细分类研究

针对旱区植被分类尺度过大、种群无法准确提取的问题,该文提出了面向对象的CFS-RF分类模型,即利用CFS算法对先验样本数据集进行特征优选,结合随机森林构建分类规则,完成分类过程。以新疆阿勒泰为研究区,利用GF-2数据,通过CFS、ReliefF两种不同特征选择方法和J48、SVM、RF 3种分类算法构造出6种面向对象分类方案来实现小尺度植被种群提取。结果表明,经过特征选择,上述分类方案的精度和效率均得到了提升。其中,CFS-RF算法最优,总体精度达到92.41%,Kappa系数为0.90,更适用于旱区植被遥感精细分类。     

Efficient paddy field mapping using Landsat-8 imagery and object-based image analysis based on advanced fractel net evolution approach

This paper proposes an efficient paddy field mapping method using object-based image analysis and a bitemporal data set acquired by Landsat-8 Operational Land Imager. In the proposed approach, image segmentation is the first step and its quality has a serious impact on the accuracy of paddy field classification. In order to improve segmentation quality, a new segmentation algorithm based on a frequently used method, fractal net evolution approach, is developed, with improvement mainly in merging criteria. In order to automate the process of scale parameter determination, an unsupervised scale selection method is utilized to determine the optimal scale parameter for the proposed image segmentation approach. After segmentation, four types of object-based features including geometric, spectral, textural, and contextual information are extracted and input into the subsequent classification procedure. By using a random forest classifier, paddy fields and nonpaddy fields are separated. The proposed image segmentation method and the final classification result are both quantitatively evaluated. Our segmentation method outperformed two popular algorithms according to three supervised evaluation criteria. The classification result with overall accuracy of 91.00% and kappa statistic of 0.82 validated the effectiveness of the proposed framework. Further analysis on feature importance indicated that spectral features made the most contribution as compared to the other three types of object-based features.     

火烧迹地信息遥感快速提取方法研究

利用福建省福州地区ETM图像，在分析火烧迹地光谱特征的基础上，研究了火烧迹地信息遥感快速提取方法。文中设置了4种提取方案，即监督分类法、NDVI参与的监督分类法、NDVI差值法及谱间关系法，最后，对提取结果进行了精度评价。     

Visualizing uncertainty — How fuzzy logic approach can help to explore iron ore deposits?

Uncertainties in Geovisualaization / GIScience spatial data can minimize but not completely provided by the different image processing classification methods. The methods of image processing techniques are purely dependent on spectral signature values. In the present study, we collected end member spectral values from both satellite data and field signatures and applied in supervised and fuzzy classification of image processing techniques to discriminate the iron ore formations and associated land cover features of part of Godumalai hill region of Salem District, Tamil Nadu State, India. The result of analysis shows that the fuzzy classified image discriminated the iron formation with better appearance and distinct boundary between the associated features than the analyses results obtained by supervised methods.     

融合像素—多尺度区域特征的高分辨率遥感影像分类算法

针对基于像素多特征的高分辨率遥感影像分类算法的"胡椒盐"现象和面向对象影像分析方法的"平滑地物细节"现象,提出了一种融合像素特征和多尺度区域特征的高分辨率遥感影像分类算法。(1)首先采用均值漂移算法对原始影像进行初始过分割,然后对初始过分割结果进行多尺度的区域合并,形成多尺度分割结果。根据多尺度区域合并RMI指数变化和分割尺度对分类精度的影响,确定最优分割尺度。(2)融合光谱特征、像元形状指数PSI(Pixel Shape Index)、初始尺度和最优尺度区域特征,并对多类型特征进行归一化,最后结合支持向量机(SVM)进行分类。实验结果表明该算法既能有效减少基于像素多特征的高分辨率遥感影像分类算法的"胡椒盐"现象,又能保持地物对象的完整性和地物细节信息,提高易混淆类别(如阴影和街道,裸地和草地)的分类精度。     

Multiband Versus Multispectral Supervised Classification of Architectural Images

For the conservation of historic monuments, there may be considerable value in automating the methods of detection and analysis of surface condition and deterioration. This paper describes tests using a range of multiband and multispectral images for the assessment of architectural façade cover by means of supervised image classifications. From the spectral training sets, both pairwise distances (the Euclidean distance and the Jeffries-Matusita (J-M) distance) are calculated and are used to predict the a posteriori accuracy of image classification. Furthermore, the effects of increasing the number of spectral bands (blue, green, red and near-infrared) in the supervised maximum-likelihood classification procedures are also analysed, as are the benefits of applying principal components. The resultant multiband datasets increased both the J-M distance and the classification accuracy of the architectural façade, and thus enabled better identification and recognition of the different kinds of façade-cover features.     

Hyperspectral image classification by a variable interval spectral average and spectral curve matching combined algorithm

Classification of hyperspectral images has been receiving considerable attention with many new applications reported from commercial and military sectors. Hyperspectral images are composed of a large number of spectral channels, and have the potential to deliver a great deal of information about a remotely sensed scene. However, in addition to high dimensionality, hyperspectral image classification is compounded with a coarse ground pixel size of the sensor for want of adequate sensor signal to noise ratio within a fine spectral passband. This makes multiple ground features jointly occupying a single pixel. Spectral mixture analysis typically begins with pixel classification with spectral matching techniques, followed by the use of spectral unmixing algorithms for estimating endmembers abundance values in the pixel. The spectral matching techniques are analogous to supervised pattern recognition approaches, and try to estimate some similarity between spectral signatures of the pixel and reference target. In this paper, we propose a spectral matching approach by combining two schemes—variable interval spectral average (VISA) method and spectral curve matching (SCM) method. The VISA method helps to detect transient spectral features at different scales of spectral windows, while the SCM method finds a match between these features of the pixel and one of library spectra by least square fitting. Here we also compare the performance of the combined algorithm with other spectral matching techniques using a simulated and the AVIRIS hyperspectral data sets. Our results indicate that the proposed combination technique exhibits a stronger performance over the other methods in the classification of both the pure and mixed class pixels simultaneously.     

地物光谱反射率野外测量实验方案改进

针对现有地物光谱反射率野外测量实验方案的不足,提出了地物光谱反射率的各向异性测量、不同环境条件的对比测量、不同时相的对比测量以及地物光谱反射率图像模拟四项实验改进方案。利用ISI921VF-128野外地物光谱辐射计和ArcG IS、ERDAS软件进行了实例测量与验证,揭示了真实地物光谱反射率的特征,模拟生成了"图谱合一"的地物光谱反射率图像,提高了实验教学质量。     

综合聚类和上下文特征的高光谱影像分类

常规高光谱影像逐像素分类往往没有考虑空间相关性,分类结果未体现地物的空间关联和分布特征。为了在分类中充分利用空间特征,利用聚类信息并结合隐马尔可夫随机场模型讨论了高光谱遥感影像光谱-空间分类方法。首先,在不同特征提取方法（最小噪声分离、独立成分分析和主成分分析）下,使用不同聚类方法（k-均值、迭代自组织分析算法和模糊c-均值算法）借助隐马尔可夫随机场获取优化的分割图;然后,采用4连通区域标记法对分割区域标记生成图像对象,并根据支持向量机的逐像素分类结果采用多数投票法对图像对象进行分类;最后,借助凹槽窗口邻域滤波技术改进分类结果,削弱“椒盐”现象。该方法综合了监督分类和非监督分类的优势,通过聚类引入地物空间相关性信息,通过隐马尔可夫随机场引入上下文特征,较好地弥补了单纯基于光谱信息分类的不足。     

Development of fuzzy rule-based parameters for urban object-oriented classification using very high resolution imagery

Urban areas consist of spectrally and spatially heterogeneous features. Advanced information extraction techniques are needed to handle high resolution imageries in providing detailed information for urban planning applications. This study was conducted to identify a technique that accurately maps impervious and pervious surfaces from WorldView-2 (WV-2) imagery. Supervised per-pixel classification algorithms including Maximum Likelihood and Support Vector Machine (SVM) were utilized to evaluate the capability of spectral-based classifiers to classify urban features. Object-oriented classification was performed using supervised SVM and fuzzy rule-based approach to add spatial and texture attributes to spectral information. Supervised object-oriented SVM achieved 82.80% overall accuracy which was the better accuracy compared to supervised per-pixel classifiers. Classification based on the proposed fuzzy rule-based system revealed satisfactory output compared to other classification techniques with an overall accuracy of 87.10% for pervious surfaces and an overall accuracy of 85.19% for impervious surfaces.     

Mapping of waterlogged areas and salt affected soils in the IGNP command area

Visual interpretation of IRS LISS-II data authenticated by ground truth was carried out for detection of waterlogged areas and characterization of salt-affected soils. The deep blue tone depicting surface ponding (stagnant ponded zone) resulted from the seepage and accumulation of irrigation water through the course sandy mass. Such unit was mostly confined to the localized low-lying areas. These data have also revealed interdunal seepage lake within the buried paleo-channel of Saraswati possibly due to submerging of excess Ghaggar floodwater. Flood irrigation, sandy soils, cultivation of high water requirement crops and presence of hard gypsiferrous pans in the shallow depths were responsible for development of waterlogged conditions in the area. The grey to yellowish white patch around the waterlogging features represented surface salt efflorescence. The grey to greyish red represented the potential waterlogging zone. Based on the analytical data, soils were characterized as moderate to highly saline and showed the presence of significant amount of CaCO₃ (>2 mm) throughout the solum. The chemical analysis of water samples revealed the presence of high to very high quantity of soluble salts dominated by chlorides and sulfates of sodium, calcium and magnesium.     

Water logging and drainage Assessment in Ravi-Tawi irrigation command (J&K) using remote sensing approach

Water logging is one of the major land degradation processes that restricts the economic and efficient utilisation of soil and land resources in command areas. Since independence, various irrigation schemes, for providing water for agriculture and drinking have been taken up by Central and State agencies in India. In most of these schemes very little efforts have been made for proper drainage. Obstruction of natural drainage by way of construction of roads, railways, aerodrome, various structures, etc., causes the ponding of monsoon runoff on the upstream of the structures. Periodic monitoring of command areas helps in analysing the extent of water logging, and should help in taking suitable remedial measures. Remote sensing and GIS are powerful tools, which could be effectively used to study the dynamic behaviour of waterlogged areas. In this study, waterlogged and salt-affected areas have been estimated in the command area of Ravi-Tawi Irrigation Complex in Jammu region. About 14% of the total command area is water logged/ salt-affected. Being a new project, this area is likely to grow in future when the project runs with its installed capacity, and as the distributaries expand in the command area. Plausible causes of water logging have been discussed, and remedial measures suggested for reclaiming operations.     

Rule-based classification of high-resolution imagery over urban areas in New York City

This paper describes the integration of results from different feature extraction algorithms using spectral and spatial attributes to detect specific urban features. Methodology includes segmentation of IKONOS data, computing attributes for creating image objects and classifying the objects with fuzzy logic and rule-based algorithms. Previous research reported low class accuracies for two specific classes – dark and grey roofs. A modified per-field approach was employed to extract urban features. New rule-sets were used on image objects having similar or near-similar spectral and spatial characteristics. Different algorithms using spectral and spatial attributes were developed to extract specific urban features from a time-series of Multi-Spectral Scanner (MSS) (4 m × 4 m) IKONOS data. The modified approach resulted in a remarkable improvement in the accuracy of classes that registered low spectral seperability and therefore low accuracy. The spectral and spatial based classification model may be useful in mapping heterogeneous and spectrally similar urban features.     

遥感图像分区自动分类方法研究

对判读区域自然景观复杂,数据时相与质量差异较大的遥感图像用常规的分类方法难以达到令人满意的效果,为此,作者采用了一种通过定义图像判读区,分类管理器和改进监督分类算法等方法来实现遥感图像的分区自动分类,以不同时相的TM拼接图像进行分类试验,结果表明:该方法比传统的监督分类方法有明显改进:(1)与整幅图像用同一个标准进行分类的方案相比,其精度显著提高,(2)可在分类前灵活,任意生成所感兴趣的判读区域,(3)在每个分区内可以采取不同的分类方案进行分类,(4)每个分区的分类结果可以保存在同一个文件中,而不需要另外生成新的操作层.因此分类不受次数的限制,可保证分类结果的完整性,每个分区的分类结果也可以保存为单个分区的分类结果.     

基于多特征的Gaofen-1海冰影像监督分割

冬季沿海地区的海冰检测工作对该地区居民的生产生活具有重要的指导意义,同时可以根据海冰变化检测气候变暖情况.海冰影像分割是海冰检测的基础.在众多海冰影像数据源中,Gaofen-1海冰影像因其丰富的光谱特征、较高的空间分辨率、简单的数据结构,在变化监测中具有重要应用价值.本文提出了一种基于红绿蓝3个光谱通道的灰度共生矩阵,...     

An effective ensemble classification framework using random forests and a correlation based feature selection technique

Accurate classification of heterogeneous land surfaces with homogeneous land cover classes is a challenging task as satellite images are characterized by a large number of features in the spectral and spatial domains. The identifying relevance of a feature or feature set is an important task for designing an effective classification scheme. Here, an ensemble of random forests (RF) classifiers is realized on the basis of relevance of features. Correlation‐based Feature Selection (CFS) was utilized to assess the relevance of a subset of features by studying the individual predictive ability of each feature along with the degree of redundancy between them. Predictability of RF was greatly improved by random selection of the relevant features in each of the splits. An investigation was carried out on different types of images from the Landsat Enhanced Thematic Mapper Plus (Landsat ETM+) and QuickBird sensors. It has been observed that the performance of the RF classifier was significantly improved while using the optimal set of relevant features compared with a few of the most advanced supervised classifiers such as maximum likelihood classifier (MLC), Navie Bayes, multi‐layer perception (MLP), support vector machine (SVM) and bagging.