Mapping freshwater marsh species distributions using WorldView-2 high-resolution multispectral satellite imagery

Freshwater wetlands are highly diverse, spatially heterogeneous, and seasonally dynamic systems that present unique challenges to remote sensing. Maximum likelihood and support vector machine-supervised classification were compared to map wetland plant species distributions in a deltaic environment using high-resolution WorldView-2 satellite imagery. The benefits of the sensor’s new coastal blue, yellow, and red-edge bands were tested for mapping coastal vegetation and the eight-band results were compared to classifications performed using band combinations and spatial resolutions characteristic of other available high-resolution satellite sensors. Unlike previous studies, this study found that support vector machine classification did not provide significantly different results from maximum likelihood classification. The maximum likelihood classifier provided the highest overall classification accuracy, at 75%, with user’s and producer’s accuracies for individual species ranging from 0% to 100%. Overall, maximum likelihood classification of WorldView-2 imagery provided satisfactory results for species distribution mapping within this freshwater delta system and compared favourably to results of previous studies using hyperspectral imagery, but at much lower acquisition cost and greater ease of processing. The red-edge and coastal blue bands appear to contribute the most to improved vegetation mapping capability over high-resolution satellite sensors that employ only four spectral bands.     

HSRS-SC:面向遥感场景分类的高光谱图像数据集

目的 场景分类是遥感领域一项重要的研究课题，但大都面向高分辨率遥感影像。高分辨率影像光谱信息少，故场景鉴别能力受限。而高光谱影像包含更丰富的光谱信息，具有强大的地物鉴别能力，但目前仍缺少针对场景级图像分类的高光谱数据集。为了给高光谱场景理解提供数据支撑，本文构建了面向场景分类的高光谱遥感图像数据集（hyperspectral remote sensing dataset for scene classification，HSRS-SC）。方法 HSRS-SC来自黑河生态水文遥感试验航空数据，是目前已知最大的高光谱场景分类数据集，经由定标系数校正、大气校正等处理形成。HSRS-SC分为5个类别，共1 385幅图像，且空间分辨率较高（1 m），波长范围广（380~1 050 nm），同时蕴含地物丰富的空间和光谱信息。结果 为提供基准结果，使用AlexNet、VGGNet-16、GoogLeNet在3种方案下组织实验。方案1仅利用可见光波段提取场景特征。方案2和方案3分别以加和、级联的形式融合可见光与近红外波段信息。结果表明有效利用高光谱影像不同波段信息有利于提高分类性能，最高分类精度达到93.20%。为进一步探索高光谱场景的优势，开展了图像全谱段场景分类实验。在两种训练样本下，高光谱场景相比RGB图像均取得较高的精度优势。结论 HSRS-SC可以反映详实的地物信息，能够为场景语义理解提供良好的数据支持。本文仅利用可见光和近红外部分波段信息，高光谱场景丰富的光谱信息尚未得到充分挖掘。后续可在HSRS-SC开展高光谱场景特征学习及分类研究。     

Monitoring salt crusts on an AMD contaminated coastal wetland using hyperspectral Hyperion data (Estuary of the River Odiel,SW Spain)

The aim of this work is to establish preliminary spectral trends focused on the development of salt crusts in the marsh located at the mouth of the River Odiel (SW Spain) based on maps from archive Hyperion data. Temporal monitoring of salt efflorescence on the marshes at the mouth of the contaminated river is carried out using hyperspectral space imagery. Climate variability relationships are made based on well-known spectral features related to vegetation and shallow water, using both archive spectral libraries and field local spectra. The observations point to spectral and geomorphological indicators related to salt crust development that can be monitored through image processing supported by field and laboratory spectral data, on a repeatable basis. Future mapping of a larger sequence of images under different climate regimes and wider tidal ranges would improve the estimation of spectral features and thus ensure routine monitoring of salt crusts with hyperspectral data. The study of acid and salt environments, which limit biota development, could be improved by monitoring that employs hyperspectral remote sensing as a useful tool.     

Hyperspectral Multiple Features Optimization Using Improved Firefly Algorithm

The utilization of hyperspectral remote sensing image is mainly based on the spectral information,and the spatial information is always be ignored.To solve this problem,a novel hyperspectral multiple features optimization approach based on improved firefly algorithm is presented.Firstly,four spatial features,the local statistical features,gray level co-occurrence matrix features,Gabor filtering features and morphological features of hyperspectral remote sensing image are extracted,and some spectral bands are selected and then combined with these spatial features,and the feature set is constructed.Then,the firefly algorithm is used to optimize the extracted features.In view of the slow convergence speed of firefly algorithm,we use the random inertia weight from particle swarm optimization algorithm to modifiy the location update formula of firefly algorithm,and JM(Jeffreys-Matusita)distance and Fisher Ratio are used as the objective function.Two urban hyperspectral datasets are used for performance evaluation,and the classification results derived from spectral information and spectral-spatial information are compared.The experiments show that random inertia weight can improve the speed of FA-based feature selection algorithm,the performance with multiple features is better than that of spectral information for urban land cover classification,The statistical results of the two sets of experimental data indicate that the selected number of morphological features are the most in the four spatial features.The local statistical features and morphological features are more helpful to the classification of hyperspectral remote sensing images than GLCM and Gabor features.     

Combining vegetation indices, constrained ordination and fuzzy classification for mapping semi-natural vegetation units from hyperspectral imagery

Vegetation mapping of plant communities at fine spatial scales is increasingly supported by remote sensing technology. However, combining ecological ground truth information and remote sensing datasets for mapping approaches is complicated by the complexity of ecological datasets. In this study, we present a new approach that uses high spatial resolution hyperspectral datasets to map vegetation units of a semiarid rangeland in Central Namibia. Field vegetation surveys provide the input to the workflow presented in this study. The collected data were classified by hierarchical cluster analysis into seven vegetation units that reflect different ecological states occurring in the study area. Spectral indices covering vegetation and soil characteristics were calculated from hyperspectral remote sensing imagery and used as environmental variables in a constrained ordination by applying redundancy analysis (RDA). The resulting statistical relationships between vegetation data and spectral indices were transferred into images of ordination axes, which were subsequently used in a supervised fuzzy c-means classification approach relying on a k-NN distance metric. Membership images for each vegetation unit as well as a confusion image of the classification result allowed a sound ecological interpretation of the resulting hard classification map. Classification results were validated with two independent reference datasets. For an internal and external validation dataset, overall accuracy reached 98% and 64% with kappa values of 0.98 and 0.53, respectively. Critical steps during the mapping workflow were highlighted and compared with similar mapping approaches.     

The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas

Remote sensing hyperspectral sensors are important and powerful instruments for addressing classification problems in complex forest scenarios, as they allow one a detailed characterization of the spectral behavior of the considered information classes. However, the processing of hyperspectral data is particularly complex both from a theoretical viewpoint [e.g. problems related to the Hughes phenomenon (Hughes, 1968) and from a computational perspective. Despite many previous investigations that have been presented in the literature on feature reduction and feature extraction in hyperspectral data, only a few studies have analyzed the role of spectral resolution on the classification accuracy in different application domains. In this paper, we present an empirical study aimed at understanding the relationship among spectral resolution, classifier complexity, and classification accuracy obtained with hyperspectral sensors for the classification of forest areas. We considered two different test sets characterized by images acquired by an AISA Eagle sensor over 126 bands with a spectral resolution of 4.6 nm, and we subsequently degraded its spectral resolution to 9.2, 13.8, 18.4, 23, 27.6, 32.2 and 36.8 nm. A series of classification experiments were carried out with bands at each of the degraded spectral resolutions, and bands selected with a feature selection algorithm at the highest spectral resolution (4.6 nm). The classification experiments were carried out with three different classifiers: Support Vector Machine, Gaussian Maximum Likelihood with Leave-One-Out-Covariance estimator, and Linear Discriminant Analysis. From the experimental results, important conclusions can be made about the choice of the spectral resolution of hyperspectral sensors as applied to forest areas, also in relation to the complexity of the adopted classification methodology. The outcome of these experiments are also applicable in terms of directing the user towards a more efficient use of the current instruments (e.g. programming of the spectral channels to be acquired) and classification techniques in forest applications, as well as in the design of future hyperspectral sensors.     

不同森林植被的高光谱特征分析

“生态水(层)”富水特征特殊,各信息指标参数难以用常规方法进行量化和反演,高光谱遥感由于其波段多、光谱信息丰富的优点为生态水(层)各信息指标参数的量化反演提供有效的数据源及方法。利用高光谱遥感技术进行植被分析时,其光谱特征的分析和敏感波段提取非常重要。针对“生态水”信息指标植被参数有关量化反演需要,对研究区部分典型植被叶片进行了光谱采集,利用微分方法对光谱数据进行处理,分析了不同植被叶片光谱的原始、一阶微分和二阶微分光谱曲线,从中提取差异大的波段区分不同植被。同时,采用距离统计分析方法对所选择的不同波段进行有效性验证。研究结果表明:虽然3种方法提取的波段有差异,但存在共同点;选择的光谱特征波段可有效地区分不同植被,在近红外波段尤为明显,分别是1 814~1 823 nm,1 874~1 883 nm和1 890~1 899 nm附近。     

基于增强空谱特征网络的空间感知协同表示算法

高光谱图像具有高维度、带间相关性较高、样本数量较少等诸多问题,直接利用表示学习算法对高光谱图像进行分类会导致严重的维数灾难.对于高光谱图像,不是所有的光谱带都可用于特定的分类任务.因此,文中提出基于增强空谱特征网络的空间感知协同表示算法.依据高光谱图像内在的低维流形构建基于空谱特征的分层网络.利用训练的网络对高维数据进...     

The effect of fusing Sentinel-2 bands on land-cover classification

The Sentinel-2 satellite currently provides freely available multispectral bands at relatively high spatial resolution but does not acquire the panchromatic band. To improve the resolution of 20 m bands to 10 m, existing pansharpening methods (Brovey transform [BT], intensity–hue–saturation [IHS], principal component analysis [PCA], the variational method [P + XS], and the wavelet method) required adjustment, which was achieved using higher resolution multispectral bands in the role of a panchromatic band to fuse bands at a lower spatial resolution. After preprocessing, six bands at lower resolution were divided into two groups because some image fusion methods (e.g. BT, IHS) are limited to a maximum of three input bands of a lower resolution at a time. With respect to the spectral range, the higher resolution band for the first group was synthesized from bands 4 and 8, and band 8 was selected for the second group. Given that one of the main remote sensing applications is land-cover classification, the classification accuracy of the fusion methods was assessed as well as the comparison with reference bands and pixels. The supervised classification methods were Maximum Likelihood Classifier, artificial neural networks, and object-based image analysis. The classification scheme contained five classes: water, built-up, bare soil, low vegetation, and forest. The results showed that most of the fusion methods, particularly P + XS and PCA, improved the overall classification accuracy, especially for the classes of forest, low vegetation, and bare soil and in the detection of coastlines. The least satisfying results were obtained from the wavelet method.     

基于独立分量分析的高光谱遥感影像决策树分类

为解决高光谱遥感影像波段众多所带来的信息丰富与“维数灾难”间的矛盾并提高分类精度,针对传统特征选择方法信息损失大的缺陷,基于EO-1 Hyperion高光谱遥感影像,采用独立分量分析(ICA)和决策树分类(DTC)方法联合运作流程,开展影像的地物分类实验研究,提出了ICA-DTC模型。首先运用ICA方法对影像进行特征提取,并以所提取的独立分量特征及其他地理辅助要素组成分类指标集;继而选择适当的指标组合和阈值设定判别规则,建立DTC模型进行影像的地物分类;最后将分类结果与传统最大似然分类法进行比对。结果显示：从分类的总体精度看,前者可达89.34%,高出后者18.8%;从单一地物的分类精度看,前者仅水体的精度略低于后者,而其他11种地物的精度都高于后者。理论分析与实验结果均表明,ICA-DTC模型可有效提高复杂地形条件下的地物分类精度。     

基于特征加权的高光谱图像融合分类

在对高光谱图像监督分类中, 传统的监督学习方法对高光谱数据进行分类时需要获取足够的有标记样本作为训练样本, 这样可以有效的避免Hughes效应. 实际情况下的高光谱数据拥有较多的波段和相对较小的训练样本集给传统的遥感图像分类方法带来了挑战. 因此, 提出了一种基于特征组合以及特征加权的高光谱图像分类算法, 针对纹理特征分析难度较大的现实, 利用一阶直方图的统计特征描述图像纹理特征, 通过类内散度矩阵的逆矩阵作为特征加权矩阵构造组合核函数将高光谱光谱特征和空间特征融合起来, 同时利用特征加权的方法用于提高小训练样本的监督分类精度. 实验结果表明, 本文所提的方法对小样本的高光谱数据分类具有良好的效果.     

Large-scale mapping of the riverbanks,mud flats and salt marshes of the Scheldt basin,using airborne imaging spectroscopy and LiDAR

For maintaining the tidal waterways in the Scheldt basin, including the rivers Rupel and Durme and a large part of the Nete catchment, and for ecological monitoring of the mud flats, salt marshes and riverbank vegetation, the Flemish government needs detailed maps of these rivers and their bank structures. These maps indicate not only vegetation types, plant associations and sediment types but also hard structures, such as quays, locks, sluices and roads. Different remote sensing techniques were used to collect the data necessary to produce the required detailed maps. During the months of July and August 2007 an airborne flight campaign took place to collect hyperspectral and LiDAR data of the Scheldt basin and the Nete catchments. These rivers have a total length of about 240 km. The Airborne Imaging Spectrometer for Applications (AISA) Eagle sensor acquired hyperspectral data in 32 spectral bands covering the visible/near-infrared (VIS/NIR) part of the electromagnetic spectrum with a ground resolution of 1 m. A multiple binary classification algorithm based on Fisher's linear discriminant analysis (LDA) was used to map the salt marshes and riverbank vegetation. Ground truth information, that is vegetation and sediment types, together with their geographical locations collected around the time of the flight campaign, was used to train the classifier in the later classification step. Laser scanning was performed using the Riegl LMS-Q560. The LiDAR dataset obtained had a resolution of at least 1 point per m² and was used to produce a digital elevation model (DEM) that contains all elements of the terrain. From this DEM a digital terrain model (DTM) was derived by applying appropriate filtering techniques. The elevation models were used primarily to derive information on the height, slope and aspect of the banks and dikes, but they also served as expert knowledge in the classification of the mud flats and bank vegetation.

Overall, this work illustrates how airborne hyperspectral and LiDAR data can be used to derive highly detailed maps of the sediments, vegetation and hard structures along tidal rivers in large river basins. It also shows how large datasets can be handled in an expert system, in combination with different classification techniques, to produce the required result and accuracy.     

融合BOVW和复杂网络的高光谱遥感图像分类

为挖掘高光谱遥感图像的深层光谱特征,获取优化特征空间以提高分类准确率,提出了一种基于视觉词典和复杂网络的高光谱遥感图像分类的光谱特征提取方法.通过改进视觉词典方法,使用K-Means方法计算各类样本的聚类中心作为词典,并计算各待测试样本的光谱像素值与词典光谱向量中相同光谱波段的差值,计算出单个待测样本点的词频直方图.同...     

基于反卷积高层特征的遥感地物图像分类

目前利用深度卷积神经网络提取图像底层特征后分类效果已比较优秀,但是对于数据量大、波段多、波段间相关性高的多光谱遥感图像并非完全适用。针对多光谱遥感地物分类中常常出现的Hughes现象,即当训练样本一定时,模型的预测能力随着维度的增加而减小,提出了一种结合高层特征空间和迁移学习网络的遥感地物图像分类算法,利用两层堆叠的反卷积网络来提取目标数据集的高层特征,利用VGG16模型的卷积层权重来构建迁移网络模型,将高层特征导入迁移网络中加强训练得到更加优越的训练模型,利用训练模型可对多光谱遥感数据集更加准确分类。实验结果表明,在Satellite、NWPU和UC Merced实验数据中,冰川、建筑群和海滩分类精度得到有效提高,达到92%左右,针对沙漠、岩石、水域等特殊环境遥感图像,总体分类精度提高5%左右。部分多光谱遥感数据的底层特征和中层特征在训练器中表现并不理想,波段的增多也会导致信息的冗余和数据处理复杂性的提高,反而高层特征在这部分数据中保留了地物信息的轮廓,能更好地适应分类器,得到更加优越的分类结果。     

遥感影像的分类自校正方法研究

遥感图像分类是遥感图像研究的主要内容之一,分类精度高低直接关系到遥感数据的可靠性和实用性。多分类器系统可以提高单分类器分类的精度,但往往要求组成的子分类器分类误差相互独立,子分类器选择困难。支持向量机是新发展起来的一种非参数分类器,其分类原理和传统的基于统计的分类方法不同,表现出一定的独立性。为此本文尝试基于支持向量机和目前使用最广泛的最大似然法,构建一个性能高效且组合方式简单的复合分类器(称为遥感影像分类自校正方法)。同时,为了验证该分类器的性能,在北京市2006年4月27日的SPOT2图像上选择了一个研究区,分别利用最大似然法、支持向量机法和分类自校正方法进行分类对比试验。结果显示分类自校正方法的总体分类精度最高,比最大似然法和支持向量机法分别提高了4.35%和6.6%,而且各种地物类型的分类精度相对最大似然和支持向量机法都有提高。本文提出的分类自校正方法是一种性能高效且操作简单的分类方法。     

基于多时相遥感观测的板栗林分布提取研究

板栗林在欧亚、北美等地广泛分布,具有良好的生态价值和经济效益。我国板栗产量居世界首位,是重要的经济树种。使用遥感影像建立板栗林空间分布提取方法能够为其科学管理和高效经营提供定量数据,但树种分类是遥感分类的难点,并且针对板栗林的遥感提取研究较少。以河北省宽城满族自治县为研究区,结合MODIS高时间分辨率特征和Landsat数据较高空间分辨率的特征,研究板栗林提取的最佳时相以及分类特征,并采用多时相观测基于支持向量机算法实现板栗林的提取。结果表明：①4月至6月各地类光谱差异最大,是板栗林提取的关键物候期;②蓝、绿、红、近红外和短波红外波段地表反射率是分类的有效波段,NDI、NDVI、NDWI、RSI和RVI等植被指数增强了植被信息,是板栗林提取的有效分类特征;③单一时相板栗林分类中,生长季前期6月精度最高,生长季后期9月次之,非生长季1月分类结果较差;④结合生长季6月、9月和非生长季1月遥感影像的分类精度最佳,板栗林制图和用户精度分别为89.90%和87.25%。与林业局板栗林面积统计数据相比,精度可达93.45%。     

A Review on Estimating Fractional Cover of Non-photosynthetic Vegetation by Using Remote Sensing

The quantitative estimation of fractional cover of photosynthetic vegetation(f PV),non-photosynthetic vegetation(f NPV),and bare soil(f BS) is critical for grassland ecosystem carbon storage,vegetation productivity,soil erosion and wildfire monitoring.The ecological importance of NPV has driven considerable research on quantitatively estimating NPV in diverse ecosystems including croplands,forests,grasslands savannah,and shrublands using remote sensing.This paper reviews the research progress in estimating f NPV using hyperspectral and multisspcetral remote sensing data,and hightlights discusses the theoretical bases of PV,NPV and BS spectral characteristics.based on the existing methods for estimating f NPV,this article groupd into two categories:empirical relationship between spectral index and NPV cover,and Spectral mixture analysis.Meanwhile,also discuss applications.of hyperspectral and multisspcetral remote sensing data.Finally,the existential problems and research trends for NPV estimation are analyzed.     

基于SSAE深度学习特征表示的高光谱遥感图像分类方法

针对遥感图像中高光谱数据的分类问题,提出一种基于堆叠稀疏自动编码器(SSAE)深度学习特征表示的高光谱遥感图像分类方法。首先,将光谱数据样本进行预处理和归一化。然后,将其输入到SSAE中进行特征表示学习,并通过网格搜索来获得最优网络参数,以此获得有效的特征表示。最后通过支持向量机(SVM)分类器对输入图像特征进行分类,最终实现遥感图像中像素的分类。在两个标准数据集上的实验结果表明,该方法能够实现准确的高光谱地物分类。     

Spectral characteristics and feature selection of hyperspectral remote sensing data

Hyperspectral remote sensing data with bandwidth of nanometre (nm) level have tens or even several hundreds of channels and contain abundant spectral information. Different channels have their own properties and show the spectral characteristics of various objects in image. Rational feature selection from the varieties of channels is very important for effective analysis and information extraction of hyperspectral data. This paper, taking Shunyi region of Beijing as a study area, comprehensively analysed the spectral characteristics of hyperspectral data. On the basis of analysing the information quantity of bands, correlation between different bands, spectral absorption characteristics of objects and object separability in bands, a fundamental method of optimum band selection and feature extraction from hyperspectral remote sensing data was proposed.     

A hybrid classification scheme for mining multisource geospatial data

Supervised learning methods such as Maximum Likelihood (ML) are often used in land cover (thematic) classification of remote sensing imagery. ML classifier relies exclusively on spectral characteristics of thematic classes whose statistical distributions (class conditional probability densities) are often overlapping. The spectral response distributions of thematic classes are dependent on many factors including elevation, soil types, and ecological zones. A second problem with statistical classifiers is the requirement of the large number of accurate training samples (10 to 30 × |dimensions|), which are often costly and time consuming to acquire over large geographic regions. With the increasing availability of geospatial databases, it is possible to exploit the knowledge derived from these ancillary datasets to improve classification accuracies even when the class distributions are highly overlapping. Likewise newer semi-supervised techniques can be adopted to improve the parameter estimates of the statistical model by utilizing a large number of easily available unlabeled training samples. Unfortunately, there is no convenient multivariate statistical model that can be employed for multisource geospatial databases. In this paper we present a hybrid semi-supervised learning algorithm that effectively exploits freely available unlabeled training samples from multispectral remote sensing images and also incorporates ancillary geospatial databases. We have conducted several experiments on Landsat satellite image datasets, and our new hybrid approach shows over 24% to 36% improvement in overall classification accuracy over conventional classification schemes.