Integration of hyperspectral and LiDAR data for mapping small water bodies

Inland water bodies are globally threatened by environmental degradation and climate change. On the other hand, new water bodies can be designed during landscape restoration (e.g. after coal mining). Effective management of new water resources requires continuous monitoring; in situ surveys are, however, extremely time-demanding. Remote sensing has been widely used for identifying water bodies. However, the use of optical imagery is constrained by accuracy problems related to the difficulty in distinguishing water features from other surfaces with low albedo, such as tree shadows. This is especially true when mapping water bodies of different sizes. To address these problems, we evaluated the potential of integrating hyperspectral data with LiDAR (hereinafter “integrative approach”). The study area consisted of several spoil heaps containing heterogeneous water bodies with a high variability of shape and size. We utilized object-based classification (Support Vector Machine) based on: (i) hyperspectral data; (ii) LiDAR variables; (iii) integration of both datasets. Besides, we classified hyperspectral data using pixel-based approaches (K-mean, spectral angle mapper). Individual approaches (hyperspectral data, LiDAR data and integrative approach) resulted in 2–22.4 % underestimation of the water surface area (i.e, omission error) and 0.4–1.5 % overestimation (i.e., commission error).The integrative approach yielded an improved discrimination of open water surface compared to other approaches (omission error of 2 % and commission error of 0.4 %). We also evaluated the success of detecting individual ponds; the integrative approach was the only one capable of detecting the water bodies with both omission and commission errors below 10 %. Finally, the assessment of misclassification reasons showed a successful elimination of shadows in the integrative approach. Our findings demonstrate that the integration of hyperspectral and LiDAR data can greatly improve the identification of small water bodies and can be applied in practice to support mapping of restoration process.     

Spectral Overlap Correction Using Weighted Deconvolution for Improved Dark Object Technique for Correction of EO1-Hyperion Data

We present a critical modification to improved dark object technique for correcting hyperspectral data (EO1-Hyperion). The modification is required in improved dark object technique as the original method does not take into account overlap of spectral response functions of two adjacent bands of hyperspectral sensor. We used weighted deconvolution for correcting the original overlap affected path radiance correction propagation factors. Further, we compared the reduction in correction factors—in different conditions—because of the overlap. We calculated the path radiance for April 22 Hyperion image and compared it with other methods such as 6SV. We found noticeable difference in corrected and uncorrected path radiance propagation factors with “clear” to “very clear” atmospheric models. For the other models (“moderate”, “hazy”, “very hazy”), the difference is negligible and can be ignored and improved dark object technique can be applied without any overlap correction.     

Producing Intermediate Contours from Digitized Contours

Contour lines on existing maps are often the only source of information about the terrain relief. In an effective digital mapping environment, the generation of intermediate contours is one of many essential capabilities. These intermediate contours can be generated in the original units or in some other units. During the digitization process, errors are introduced into the cartographic data, and data manipulation processes may introduce additional errors. A new six-step method is presented here to reduce the data manipulation errors during the process of generating intermediate contours. In our method, the original digitized contours serve not only as a data source, but also as a control on the interpolation process. This process utilizes one- and two-dimensional filters to determine the differences between original and modeled contours. The interpolated contours are adjusted to the original contours thus preserving both general and local shape of the original relief representations. The most frequent application of this method likely will be in the conversion of “foot” contours to “meter” contours.     

An assessment of independent component analysis for detection of military targets from hyperspectral images

Hyperspectral data acquired over hundreds of narrow contiguous wavelength bands are extremely suitable for target detection due to their high spectral resolution. Though spectral response of every material is expected to be unique, but in practice, it exhibits variations, which is known as spectral variability. Most target detection algorithms depend on spectral modelling using a priori available target spectra In practice, target spectra is, however, seldom available a priori. Independent component analysis (ICA) is a new evolving technique that aims at finding out components which are statistically independent or as independent as possible. The technique therefore has the potential of being used for target detection applications. A assessment of target detection from hyperspectral images using ICA and other algorithms based on spectral modelling may be of immense interest, since ICA does not require a priori target information. The aim of this paper is, thus, to assess the potential of ICA based algorithm vis a vis other prevailing algorithms for military target detection. Four spectral matching algorithms namely Orthogonal Subspace Projection (OSP), Constrained Energy Minimisation (CEM), Spectral Angle Mapper (SAM) and Spectral Correlation Mapper (SCM), and four anomaly detection algorithms namely OSP anomaly detector (OSPAD), Reed–Xiaoli anomaly detector (RXD), Uniform Target Detector (UTD) and a combination of Reed–Xiaoli anomaly detector and Uniform Target Detector (RXD–UTD) were considered. The experiments were conducted using a set of synthetic and AVIRIS hyperspectral images containing aircrafts as military targets. A comparison of true positive and false positive rates of target detections obtained from ICA and other algorithms plotted on a receiver operating curves (ROC) space indicates the superior performance of the ICA over other algorithms.     

空间与谱间相关性分析的NMF高光谱解混

非负矩阵分解(NMF)技术是高光谱像元解混领域的研究热点。为了充分利用高光谱图像中丰富的空间与光谱相关性特征,改善基于NMF的高光谱解混算法性能,提出一种结合了空间与谱间相关性分析的NMF解混算法。算法针对NMF的通用性和局部极小问题,引入并结合高光谱图像两种典型的相关性特征,具体包括:基于马尔可夫随机场(MRF)模型,建立描述相邻像元空间相关特征的约束;通过复杂度映射技术,建立描述相邻波段谱间相关(光谱分段平滑)特征的约束;并将上述两种约束同时引入NMF解混目标函数中。实验结果表明,对于一般自然地物场景或人造地物场景,相对于分段平滑和稀疏约束的非负矩阵分解(PSNMFSC)、交互投影子梯度的非负矩阵分解(APSNMF)和最小体积约束的非负矩阵分解(MVCNMF)这3种代表性NMF解混参考算法,该算法可进一步提高高光谱解混精度;对于空间相关或谱间相关特征中某一种不显著的特殊场景,也具有更好的适应能力。通过将空间相关和谱间相关特征相结合,较全面地反映了高光谱数据与解混相关的重要特征,能够对绝大多数真实高光谱数据进行高精度解混,对高光谱解混及后续应用领域相关研究均具有参考价值。     

Analysis of Spectral Vegetation Signal Characteristics as a Function of Soil Moisture Conditions Using Hyperspectral Remote Sensing

The assessment and quantification of spatio-temporal soil characteristics and moisture patterns are important parameters in the monitoring and modeling of soil landscapes. Remote-sensing techniques can be applied to characterize and quantify soil moisture patterns, but only when dealing with bare soil. For soils with vegetation, it is only possible to quantify soil-moisture characteristics through indirect vegetation indicators, i.e. the “vitality” of plants. The “vitality” of vegetation is a sum of many indicators, whereby different stress factors can induce similar changes to the biochemical and physiological characteristics of plants. Analysis of the cause and effect of soil-moisture properties, patterns and stress factors can therefore only be carried out using an experimental approach that specifically separates the causes. The study describes an experimental approach and the results from using an imaging hyperspectral sensor AISA-EAGLE (400–970 nm) and a non-imaging spectral sensor ASD (400–2,500 nm) under controlled and comparable conditions in a laboratory to study the spectral response compared to biochemical and biophysical vegetation parameters (“vitality”) as a function of soil moisture characteristics over the entire blooming period of Ash trees. At the same time that measurements were taken from the hyperspectral sensors, the following vegetation variables were also recorded: leaf area index (LAI), chlorophyll meter value — SPAD-205, vegetation height, C/N content and leaf water content as indicators of the “vitality” and the state of the vegetation. The spectrum of each hyperspectral image was used to calculate a range of vegetation indices (VI’s) with relationships for soil moisture characteristics and stress factors. The relationship between vegetation indices and plant “vitality” indicators was analysed using a Generalized Additive Model (GAM). The results show that leaf water content is the most appropriate vegetation indicator for assessing the “vitality” of vegetation. With the Water Index (WI) it was possible to differentiate between the moisture treatments of the control, moisture drought stress and the moisture flooding treatment over the entire growing season of the plants (R ²?=?0.94). There is a correlation between the “vitality” vegetation parameters (LAI, C/N content and vegetation height) and the indicators NDVI, WI, PRI and Vog2. In our study with Ash trees the vegetation parameter chlorophyll was found not to be a suitable indicator for detecting the “vitality” of plants using the spectral indicators. There is a possibility that the sensitivity of the indicators selected was too low compared to changes in the chlorophyll content of Ash trees. Adding the co-variable ‘time’ strengthens the correlation, whereas incorporating time and moisture treatment only improves the model very slightly. This shows that changes to the biochemical and biophysical characteristics caused by phenology, overlay a differentiation of the moisture treatments.     

Using spectrum differentiation and combination for target detection of minerals

Among the techniques that have been developed in spectroscopy, derivative analysis is particularly promising for use with remote sensing data. In the first step of this research we apply the derivative spectrum in a real hyperspectral image and introduce a new target detection approach called “DCEM”. For this purpose, 1st to 5th orders of derivative spectrum were applied to the DCEM. The outcome of this research has shown that the application of derivative spectrum in target detection is perfectly advisable in a specific derivative order for each target. This order can be introduced as an optimized order or the Best DCEM. The spectrum differentiation eliminates low frequency components of the spectrum. Despite the little information included in those low frequency components of a signal or spectrum, their complete elimination cause an information loss problem. Hence, in the second step of this research an ensemble classifier approach was employed for the combined use of both spectra and the best derivative order. This simultaneous use of the derivative and zero order spectra is introduced as “ECEM”. Experiments were conducted via a HyMap hyperspectral airborne image in eastern Iran. The detection results show that both proposed methods significantly outperform CEM in ROC and AUC values. The best performance upgrade in DCEM detection was about 24% for Kaolinite target and about 28% for Alunite target in ECEM.     

Multi-Feature Classification Approach for High Spatial Resolution Hyperspectral Images

High spatial resolution hyperspectral images not only contain abundant radiant and spectral information, but also display rich spatial information. In this paper, we propose a multi-feature high spatial resolution hyperspectral image classification approach based on the combination of spectral information and spatial information. Three features are derived from the original high spatial resolution hyperspectral image: the spectral features that are acquired from the auto subspace partition technique and the band index technique; the texture features that are obtained from GLCM analysis of the first principal component after principal component analysis is performed on the original image; and the spatial autocorrelation features that contain spatial band X and spatial band Y, with the grey level of spatial band X changing along columns and the grey level of spatial band Y changing along rows. The three features are subsequently combined together in Support Vector Machine to classify the high spatial resolution hyperspectral image. The experiments with a high spatial resolution hyperspectral image prove that the proposed multi-feature classification approach significantly increases classification accuracies.     

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.     

高光谱遥感影像SVM分类中训练样本选择的研究

支持向量机(SVM)分类的关键是发现分类最优超平面及类别间隔,而混合像元比纯净像元更接近类别边界,更容易找出最优超平面。本文针对SVM分类器的特点,在高光谱数据分类中采用混合像元作为训练样本对SVM进行训练,试验表明采用类别边界上的混合像元作为训练样本是可行的,能够获得与纯净训练样本接近的分类精度,进一步验证了SVM分类对训练样本空间分布依赖度较低的特点。     

Object-based classification of hyperspectral data using Random Forest algorithm

This paper presents a new framework for object-based classification of high-resolution hyperspectral data. This multi-step framework is based on multi-resolution segmentation (MRS) and Random Forest classifier (RFC) algorithms. The first step is to determine of weights of the input features while using the object-based approach with MRS to processing such images. Given the high number of input features, an automatic method is needed for estimation of this parameter. Moreover, we used the Variable Importance (VI), one of the outputs of the RFC, to determine the importance of each image band. Then, based on this parameter and other required parameters, the image is segmented into some homogenous regions. Finally, the RFC is carried out based on the characteristics of segments for converting them into meaningful objects. The proposed method, as well as, the conventional pixel-based RFC and Support Vector Machine (SVM) method was applied to three different hyperspectral data-sets with various spectral and spatial characteristics. These data were acquired by the HyMap, the Airborne Prism Experiment (APEX), and the Compact Airborne Spectrographic Imager (CASI) hyperspectral sensors. The experimental results show that the proposed method is more consistent for land cover mapping in various areas. The overall classification accuracy (OA), obtained by the proposed method was 95.48, 86.57, and 84.29% for the HyMap, the APEX, and the CASI data-sets, respectively. Moreover, this method showed better efficiency in comparison to the spectral-based classifications because the OAs of the proposed method was 5.67 and 3.75% higher than the conventional RFC and SVM classifiers, respectively.     

Evaluating the performance of a new classifier – the GP-OAD: A comparison with existing methods for classifying rock type and mineralogy from hyperspectral imagery

In this study, we compare three commonly used methods for hyperspectral image classification, namely Support Vector Machines (SVMs), Gaussian Processes (GPs) and the Spectral Angle Mapper (SAM). We assess their performance in combination with different kernels (i.e. which use distance-based and angle-based metrics). The assessment is done in two experiments, under ideal conditions in the laboratory and, separately, in the field (an operational open pit mine) using natural light. For both experiments independent training and test sets are used. Results show that GPs generally outperform the SVMs, irrespective of the kernel used. Furthermore, angle-based methods, including the Spectral Angle Mapper, outperform GPs and SVMs when using distance-based (i.e. stationary) kernels in the field experiment. A new GP method using an angle-based (i.e. a non-stationary) kernel – the Observation Angle Dependent (OAD) covariance function – outperforms SAM and SVMs in both experiments using only a small number of training spectra. These findings show that distance-based kernels are more affected by changes in illumination between the training and test set than are angular-based methods/kernels. Taken together, this study shows that independent training data can be used for classification of hyperspectral data in the field such as in open pit mines, by using Bayesian machine-learning methods and non-stationary kernels such as GPs and the OAD kernel. This provides a necessary component for automated classifications, such as autonomous mining where many images have to be classified without user interaction.     

基于Hyperion影像的涩北气田油气信息提取

 对柴达木地区涩北气田地质地理环境下的蚀变矿物进行分析，结合卫星高光谱遥感数据Hyperion的图谱，对已知气田区与背景区光谱特征进行相关分析，确定了932.64~1 346.25 nm与2 002.06~2 385.5 nm为油气信息识别的有利波长范围； 利用光谱角制图（SAM）技术提取了涩北气田油气的空间分布信息和台吉乃尔含气构造等远景区，为高光谱遥感油气勘探提供了有效技术方法与途径。     

Detection of early plant stress responses in hyperspectral images

Early stress detection in crop plants is highly relevant, but hard to achieve. We hypothesize that close range hyperspectral imaging is able to uncover stress related processes non-destructively in the early stages which are invisible to the human eye. We propose an approach which combines unsupervised and supervised methods in order to identify several stages of progressive stress development from series of hyperspectral images. Stress of an entire plant is detected by stress response levels at pixel scale. The focus is on drought stress in barley (Hordeum vulgare). Unsupervised learning is used to separate hyperspectral signatures into clusters related to different stages of stress response and progressive senescence. Whereas all such signatures may be found in both, well watered and drought stressed plants, their respective distributions differ. Ordinal classification with Support Vector Machines (SVM) is used to quantify and visualize the distribution of progressive stages of senescence and to separate well watered from drought stressed plants. For each senescence stage a distinctive set of most relevant Vegetation Indices (VIs) is identified. The method has been applied on two experiments involving potted barley plants under well watered and drought stress conditions in a greenhouse. Drought stress is detected up to ten days earlier than using NDVI. Furthermore, it is shown that some VIs have overall relevance, while others are specific to particular senescence stages. The transferability of the method to the field is illustrated by an experiment on maize (Zea mays).     

高光谱数据的波段序结构分析与应用研究

把高光谱数据近似于连续的细分波段作为波段序列数据,由此提出波段序结构分析技术,主要包括波段序列直方图、左(右)偏度参量分析、相关(似)矩阵分析和回归偏度分析等。通过对波段序结构分析技术在高光谱数据的统计特征分析与数据质量评价、"蚀变异常"信息潜在性评价与特征波段选择及矿物蚀变信息提取等几个方面的应用研究与实践,阐述了这一技术思想的科学性与实用价值。     

Using snakes for the registration of topographic road database objects to ALS features

For historical reasons many national mapping agencies store their topographic data in a dual system consisting of a Digital Landscape Model (DLM) and a Digital Terrain Model (DTM). The DLM contains 2D vector data representing objects on the Earth’s surface, such as roads and rivers, whereas the DTM is a 2.5D representation of the related height information, often acquired by Airborne Laser Scanning (ALS). Today, many applications require reliable 3D topographic data. Therefore, it is advantageous to convert the dual system into a 3D DLM. However, as a result of different methods of acquisition, processing, and modelling, the registration of the two data sets often presents difficulties. Thus, a straightforward integration of the DTM and DLM might lead to inaccurate and semantically incorrect 3D objects.In this paper we propose a new method for the fusion of the two data sets that exploits parametric active contours (also called snakes), focusing on road networks. For that purpose, the roads from a DLM initialise the snakes, defining their topology and their internal energy, whereas ALS features exert external forces to the snake via the image energy. After the optimisation process the shape and position of the snakes should coincide with the ALS features. With respect to the robustness of the method several known modifications of snakes are combined in a consistent framework for DLM road network adaptation. One important modification redefines the standard internal energy and thus the geometrical model of the snake in order to prevent changes in shape or position not caused by significant features in the image energy. For this purpose, the initial shape is utilized creating template-like snakes with the ability of local adaptation. This is one crucial point towards the applicability of the entire method considering the strongly varying significance of the ALS features. Other concepts related to snakes are integrated which enable our method to model network and ribbon-like characteristics simultaneously. Additionally, besides ALS road features information about context objects, such as bridges and buildings, is introduced as part of the image energy to support the optimisation process. Meaningful examples are presented that emphasize and evaluate the applicability of the proposed method.     

2D地图的建筑物场景结构提取方法及其在城市增强现实中的应用

城市AR中,场景结构的自动获取,对自适应信息表达具有重要意义,是解决“层叠式”信息表现形式引发的信息指示不明、场景感知混乱等问题的关键步骤。然而,场景结构信息隐藏在场景图像中,直接提取十分困难。2D地图描述了地理实体的位置、轮廓和空间布局,可作为场景结构提取的先验信息。针对城市AR中场景结构获取难、效率低的问题,本文提出一种基于2D地图的建筑物场景结构自动化提取方法。在地理配准的基础上,首先根据2D地图中建筑物的轮廓和属性信息,构建场景图像语义分割的结构线索;然后将其作为过分割处理后场景图像合并的依据,生成多个包含语义信息的图像区域;最后根据图像区域与2D地图中建筑物轮廓之间的映射关系,提取出场景图像中的区域轮廓、场景深度和平面朝向等场景结构信息。试验选取了格拉茨地区32个建筑物场景进行测试。结果表明本文方法能实时地提取建筑物场景结构,且建筑物立面提取的质量明显优于对比方法。提取的场景结构能应用于城市AR多种自适应信息表达方法中,使信息标注更明确,遮挡关系更清晰。     

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(Orthogonal Projection Band Selection,OPBS)两种方法对原始高光谱数据进行预处理,获取降维后的影像数据。然后在其基础上提取扩展形态学特征(Extended Morphology Profiles,EMP)和地物表面纹理特征,组成联合光谱和纹理、形状结构特征。最后,采用支持向量机(Support Vector Machine,SVM)分类器对联合特征进行分类。针对不同真实高光谱数据集的实验结果表明,本文提出的方法运算效率高且具有令人满意的分类性能。     

Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso,Brazil

The adoption of new cropping practices such as integrated Crop-Livestock systems (iCL) aims at improving the land use sustainability of the agricultural sector in the Brazilian Amazon. The emergence of such integrated systems, based on crop and pasture rotations over and within years, challenges the remote sensing community who needs to implement accurate and efficient methods to process satellite image time series (SITS) in order to come up with a monitoring protocol. These methods generally include a SITS preprocessing step which can be time consuming. The aim of this study is to assess the importance of preprocessing operations such as temporal smoothing and computation of phenological metrics on the mapping of main cropping systems (i.e. pasture, single cropping, double cropping and iCL), with a special emphasis on the iCL class. The study area is located in the state of Mato Grosso, an important producer of agriculture commodities located in the Southern Brazilian Amazon. SITS were composed of a set of 16-day composites of MODIS Vegetation Indices (MOD13Q1 product) covering a one year period between 2014 and 2015. Two widely used classifiers, i.e. Random Forest (RF) and Support Vector Machine (SVM), were tested using five data sets issued from a same SITS but with different preprocessing levels: (i) raw NDVI; (ii) raw NDVI + raw EVI; (iii) smoothed NDVI; (iv) NDVI-derived phenometrics; (v) raw NDVI + phenometrics. Both RF and SVM classification results showed that the “raw NDVI + raw EVI” data set achieved the highest performance (RF OA = 0.96, RF Kappa = 0.94, SVM OA = 0.95, SVM Kappa = 0.93), followed closely by the “raw NDVI” and the “raw NDVI + phenometrics” datasets. The “NDVI-derived phenometrics” alone achieved the lowest accuracies (RF OA = 0.58 and SVM OA = 0.66). Considering that the implementation of preprocessing steps is computationally expensive and does not provide significant gains in terms of classification accuracy, we recommend to use raw vegetation indices for mapping cropping practices in Mato Grosso, including the integrated Crop-Livestock systems.