高光谱数据截断加权核范数稀疏解混

受仪器和观测条件限制,高光谱数据易受噪声污染,给数据解译带来挑战。针对传统稀疏解混模型抗噪性能差的问题,本文提出一种截断加权核范数稀疏解混方法,利用高光谱图像像元之间的相关性减轻噪声对丰度估计的干扰。该方法借助低秩表示在挖掘数据内在低维结构方面的优势,在稀疏解混中加入基于截断加权核范数的低秩约束,并结合加权稀疏技术,在稀疏正则项中引入空间邻域权重。截断加权核范数对丰度矩阵的奇异值向量分段处理,可以更好地实现丰度矩阵的低秩逼近,使丰度图像保持空间一致性并保留更多细节信息,空间加权策略则增强了丰度图像的空间连续性。模拟高光谱数据、Cuprite矿区真实数据和红树林高光谱数据实验表明,与其他先进的稀疏解混方法相比,所提方法具有更好的抗噪性,能够提高解混精度。     

Multiple spectral similarity metrics for surface materials identification using hyperspectral data

Modern hyperspectral imaging and non-imaging spectroradiometer has the capability to acquire high-resolution spectral reflectance data required for surface materials identification and mapping. Spectral similarity metrics, due to their mathematical simplicity and insensitiveness to the number of reference labelled spectra, have been increasingly used for material mapping by labelling reflectance spectra in hyperspectral data labelling. For a particular hyperspectral data set, the accuracy of spectral labelling depends considerably upon the degree of unambiguous spectral matching achieved by the spectral similarity metric used. In this work, we propose a new methodology for quantifying spectral similarity for hyperspectral data labelling for surface materials identification. Developed adopting the multiple classifier system architecture, the proposed methodology unifies into a single framework the differential performances of eight different spectral similarity metrics for the quantification of spectral matching for surface materials. The proposed methodology has been implemented on two types of hyperspectral data viz. image (airborne hyperspectral images) and non-image (library spectra) for numerous surface materials identification. Further, the performance of the proposed methodology has been compared with the support vector machines (SVM) approach, and with all the base spectral similarity metrics. The results indicate that, for the hyperspectral images, the performance of the proposed methodology is comparable with that of the SVM. For the library spectra, the proposed methodology shows a consistently higher (increase of about 30% when compared to SVM) classification accuracy. The proposed methodology has the potential to serve as a general library search method for materials identification using hyperspectral data.     

Understanding the Unique Spectral Signature of Winter Rape

Driven by significant technological developments in the hyperspectral imaging, material mapping using reference spectra has received renewed interest of the remote sensing community. The applicability of reference spectral signatures in image classification depends mainly on the material type and its spectral signature behaviour. Identification and spectral characterization of materials which exhibit unique spectral behaviour is the first step in this approach. Consequently there have been active researches for the identification of surface materials which exhibit unique spectral signatures. The uniqueness of reflectance signature of winter rape relative to its co-occurring crop species was reported in this study. Reflectance spectral libraries constructed from field spectral reflectance measurements collected over five agricultural crops (alfalfa, winter barley, winter rape, winter rye, and winter wheat) during four subsequent growing seasons were classified by the linear discriminant analysis (LDA). Further, the reference field spectral database was used for the spectral feature fitting and classification of a historical HyMAP airborne hyperspectral imagery acquired at a separate site, by spectral library search. Results indicate the existence of a meaningful spectral matching between image and field spectra for winter rape and demonstrate the potential for transferring spectral library for hyperspectral image classification. The observed consistency in the discrimination of winter rape demonstrates experimentally the fundamental principle of remote sensing which suggests the theoretical existence of unique spectral signatures for materials which can be incorporated as reference spectral signatures for hyperspectral image classification.     

基于单次散射反照率的矿物高光谱稀疏解混

矿物的混合多属于致密型混合,在可见光—短波红外波段的混合呈现非线性特征,同时由于矿物混合的复杂性以及图像中完全纯净的像元可能不存在等原因,使得从图像上提取端元具有较大不确定性。本文根据矿物单次散射反照率的线性可加性,提出一种基于矿物单次散射反照率光谱库的稀疏解混算法,利用Hapke模型将矿物反射率转换成矿物单次散射反照率,构建矿物单次散射反照率光谱库,以半监督的方式通过稀疏回归的方法从光谱库中寻找最优端元组合,并估算混合像元中各端元的丰度。利用RELAB矿物混合光谱库进行算法验证,结果表明,丰度反演的平均绝对误差为3.12%;将本文方法应用于美国内华达州铜矿区的AVIRIS高光谱图像数据,所得丰度图与美国地质勘探局USGS矿物识别结果具有较好的一致性。本文算法不需要从图像提取端元,并且考虑到了矿物的非线性混合特征,能够得到较高的反演精度,在近地行星和卫星表面岩矿成分的探测等领域具有较好的应用前景。     

面向灾害识别的专题波谱库设计与开发

介绍了专题波谱库可视化程序设计与开发的方法。以土壤盐碱化为例,详细阐述了专题波谱库的设计思想及关键技术。可为环境与减灾卫星高光谱数据的业务化运行提供光谱数据支撑,提高了高光谱遥感在防灾减灾领域的定量反演应用能力。     

Evaluation of MIVIS Hyperspectral Data for Mapping Soil Degradation in an Upland Ecosystem of Southern Italy

Abstract

This paper describes the first stage of an experiment aiming to evaluate the potential and limitations of MIVIS data for mapping the degradational state of soils in a sub‐scene of a southern Apennines study area (Italy). After radiometric rectification of the image data and the collection of a field/laboratory spectral library, linear spectral mixture modelling (SMA) was used to decompose image spectra into fractions of spectrally distinct mixing components. Spectral endmember selection was based upon a principal component analysis (PCA) applied to a set of soil spectra, collected from the spectral library. The resulting abundance estimates (fractions) trough SMA were then analysed to identify soil conditions and to obtain an improved measure of dry and green vegetation cover. A map of soil conditions and dry‐green vegetation abundance, based upon MIVIS data was then derived from normalised fractions of soil‐vegetation endmembers obtained from SMA.     

Spectral identification of materials by reflectance spectral library search

Spectral library search is emerging as a viable approach for material identification and mapping by reusing spectral knowledge gained from hyperspectral remote sensing across space and time. The potential of retrieving meaningful spectral material identifications in the presence of reflectance of spectra of various material types and with various similarity metrics has been assessed in this study. Test reflectance spectra of various vegetation, minerals, soils and urban material types are identified by searching through the composite reflectance spectral library obtained by combining various institutional reflectance spectral libraries. The accuracy of material identifications under various conditions: (i) in the presence of identical, similar and dissimilar spectra; (ii) in the presence of only identical and dissimilar spectra; and (iii) in the presence of only dissimilar spectra has been assessed with several similarity metrics. Results indicate the possibility of obtaining 100% accurate material identifications by library search if the spectral library contains identical spectra. However, the presence of a large number of similar spectra, despite the presence of identical spectra, is found to increase false positives, thereby reducing the accuracy of retrievals to 82% at best. Further, the accuracy of material identifications in the presence of similar spectra is similarity metric-dependent and varied from about 52% (obtained from Binary Encoding) to 82% (obtained from Normalized Spectral Similarity Score). Overall, results support the possibility of using independent reflectance spectral libraries for material identification while calling for robust spectral similarity metrics.     

Use of field reflectance data for crop mapping using airborne hyperspectral image

Recent developments in hyperspectral remote sensing technologies enable acquisition of image with high spectral resolution, which is typical to the laboratory or in situ reflectance measurements. There has been an increasing interest in the utilization of in situ reference reflectance spectra for rapid and repeated mapping of various surface features. Here we examined the prospect of classifying airborne hyperspectral image using field reflectance spectra as the training data for crop mapping. Canopy level field reflectance measurements of some important agricultural crops, i.e. alfalfa, winter barley, winter rape, winter rye, and winter wheat collected during four consecutive growing seasons are used for the classification of a HyMAP image acquired for a separate location by (1) mixture tuned matched filtering (MTMF), (2) spectral feature fitting (SFF), and (3) spectral angle mapper (SAM) methods. In order to answer a general research question “what is the prospect of using independent reference reflectance spectra for image classification”, while focussing on the crop classification, the results indicate distinct aspects. On the one hand, field reflectance spectra of winter rape and alfalfa demonstrate excellent crop discrimination and spectral matching with the image across the growing seasons. On the other hand, significant spectral confusion detected among the winter barley, winter rye, and winter wheat rule out the possibility of existence of a meaningful spectral matching between field reflectance spectra and image. While supporting the current notion of “non-existence of characteristic reflectance spectral signatures for vegetation”, results indicate that there exist some crops whose spectral signatures are similar to characteristic spectral signatures with possibility of using them in image classification.     

基于高光谱数据和专家决策法提取红树林群落类型信息

高光谱遥感是进行地表植被观测的强有力工具,研究并验证有效的算法和数据支撑技术,对于合理利用高光谱数据进行地表植被监测与分析至关重要。在光谱特征分析和地面调查的基础上,基于决策树方法和高光谱分析方法的组合,以深圳市福田国家级自然保护区为例,利用高光谱数据进行红树林群落信息提取的实证研究。结果证实了Hymap数据对于红树林群落类型信息提取的数据支撑能力,以及相关方法用于红树林分类研究方面的有效性。     

Spectral material mapping using hyperspectral imagery: a review of spectral matching and library search methods

Imaging spectroscopy is an emerging and versatile technique that finds applications in diverse fields concerned with remote identification, discrimination and mapping of materials. The large amount of spectral data produced by hyperspectral imaging necessitates the development of automated techniques that convert imagery directly into thematic maps. Spectral library search method, a method of choice for organic compound identification by the mass spectroscopy, has caught the attention of researchers as one of the appropriate methods for an efficient exploitation of high quality spectral data available from the hyperspectral imaging systems. Given the apparent increase in the number of papers appearing on the subject as well as the variety of methods proposed, it is reasonable to say that the field of automated interpretation of reflectance spectral data has passed its infancy now gaining important space in the scientific community. We present an overall view of the literature relevant to the development of library search method, the various search algorithms and systems available in the purview for developing an automated hyperspectral data analysis system for material identification.     

Multi range spectral feature fitting for hyperspectral imagery in extracting oilseed rape planting area

Spectral feature fitting (SFF) is a commonly used strategy for hyperspectral imagery analysis to discriminate ground targets. Compared to other image analysis techniques, SFF does not secure higher accuracy in extracting image information in all circumstances. Multi range spectral feature fitting (MRSFF) from ENVI software allows user to focus on those interesting spectral features to yield better performance. Thus spectral wavelength ranges and their corresponding weights must be determined. The purpose of this article is to demonstrate the performance of MRSFF in oilseed rape planting area extraction. A practical method for defining the weighted values, the variance coefficient weight method, was proposed to set up criterion. Oilseed rape field canopy spectra from the whole growth stage were collected prior to investigating its phenological varieties; oilseed rape endmember spectra were extracted from the Hyperion image as identifying samples to be used in analyzing the oilseed rape field. Wavelength range divisions were determined by the difference between field-measured spectra and image spectra, and image spectral variance coefficient weights for each wavelength range were calculated corresponding to field-measured spectra from the closest date. By using MRSFF, wavelength ranges were classified to characterize the target's spectral features without compromising spectral profile's entirety. The analysis was substantially successful in extracting oilseed rape planting areas (RMSE ≤ 0.06), and the RMSE histogram indicated a superior result compared to a conventional SFF. Accuracy assessment was based on the mapping result compared with spectral angle mapping (SAM) and the normalized difference vegetation index (NDVI). The MRSFF yielded a robust, convincible result and, therefore, may further the use of hyperspectral imagery in precision agriculture.     

Multiple statistical approaches for the discrimination of mangrove species of Rhizophoraceae using transformed field and laboratory hyperspectral data

This study aims at discriminating eight mangrove species of Rhizophoraceae family of Indian east coast using field and laboratory spectra in spectral range (350–2500 nm). Parametric and non-parametric statistical analyses were applied on spectral data in four spectral modes: (i) reflectance (ii) continuum removed, (iii) additive inverse and (iv) continuum removed additive inverse. We introduced continuum removal of inverse spectra to utilize the advantage of continuum removal in reflectance region. Non-parametric test gave better separability than parametric test. Principal component analysis and stepwise discriminant analysis were applied for feature reduction and to identify optimal wavelengths for species discrimination. To quantify the separability, Jeffries–Matusita distance measure was derived. Green (550 nm), red edge (680–720 nm) and water absorption region (1470 and 1850 nm) were found to be optimal wavelengths for species discrimination. The continuum removal of additive inverse spectra gave better separability than the continuum removed spectra.     

基于权重光谱解混方法的高光谱矿物填图

提出了一种基于Fisher权重分析的迭代光谱解混方法(WLSMA),该方法首先对高光谱图像进行区域分割,在分割后的各子块中自动提取端元;再次对提取的端元进行聚类,从光谱的整体特征上将不同类别的端元区分开,针对聚类结果中的每一类别各选取几个具有代表性的端元光谱,并对最优光谱进行窗口卷积处理,结合In_CoB指标构建端元光谱样本库;最后对图像进行迭代光谱解混处理,在丰度反演过程中引入基于Fisher准则的补偿权值矩阵以提高反演精度。AVIRIS高光谱数据实验证明,WLSMA不需要大量先验信息,利用Fisher准则和迭代光谱分析理论增强了相似性矿物的可分性,为加强对矿区地表岩性的认识和模拟提供了更大的灵活性和可能性,对高光谱矿物填图有一定的借鉴意义。     

Mapping the distribution of mangrove species in the Core Zone of Mai Po Marshes Nature Reserve,Hong Kong,using hyperspectral data and high-resolution data

Mangrove species compositions and distributions are essential for conservation and restoration efforts. In this study, hyperspectral data of EO-1 HYPERION sensor and high spatial resolution data of SPOT-5 sensor were used in Mai Po mangrove species mapping. Objected-oriented method was used in mangrove species classification processing. Firstly, mangrove objects were obtained via segmenting high spatial resolution data of SPOT-5. Then the objects were classified into different mangrove species based on the spectral differences of HYPERION image. The classification result showed that in the top canopy, Kandelia obovata and Avicennia marina dominated Mai Po Marshes Natural Reserve, with area of 196.8 ha and 110.8 ha, respectively, Acanthus ilicifolius and Aegiceras corniculatum were mixed together and living at the edge of channels with an area of 11.7 ha. Additionally, mangrove species shows clearly zonations and associations in the Mai Po Core Zone. The overall accuracy of our mangrove map was 88% and the Kappa confidence was 0.83, which indicated great potential of using hyperspectral and high-resolution data for distinguishing and mapping mangrove species.     

利用卷积神经网络的高光谱图像分类

针对高光谱图像分类中对光谱信息利用不足的问题,提出一种基于卷积神经网络在光谱域开展的分类算法。该算法通过构建五层网络结构,逐像素对光谱信息开展分析,将全光谱段集合作为输入,利用神经网络展开代价函数值的计算,实现对光谱特征的提取与分类。实验中采用三组高光谱遥感影像数据进行对比分析,以India Pines数据集为例,提出的基于卷积神经网络的分类方法的分类正确率达到90.16%,比RBF-SVM方法高出2.56%,相比三种传统的深度学习方法高出1%~3%,训练速度也较为理想。实验结果表明,本文所提出的算法充分利用了高光谱图像中逐像素点的光谱域信息,能够有效提高分类正确率。与传统学习算法相比,在较少训练样本的情况下,更能发挥其良好的分类性能。     

Tsunami 2004: the villages of Birek and Seungko Mulat,Indonesia

The purpose of this study was to investigate the potential of imaging spectroscopy for the discrimination between eucalyptus species. High spectral reflectance signatures of 11 eucalyptus species were measured in the laboratory and significant differences at a number of wavelength positions were detected. There were differences in terms of absolute reflectance, depths of absorption features and the relative position of change in terms of the wavelength. The differences between species were more noticeable in the first derivative spectra when compared with the raw spectra. This was attributed to the ability of derivatives to remove the noise from raw reflectance spectra. The results also indicate the possibility of utilizing the common vegetation indices and ratios used in remote sensing for discriminating species and highlight the need to select spectral channels at pertinent positions where the differences are the greatest. This study has identified many of these positions in relation to some eucalyptus species. However, the study also shows that there is no single wavelength which will discriminate between all species and it also shows that even with hyperspectral data, issues with detailed level of mapping will still exist.     

基于小波分量特征值匹配的高光谱影像分类

提出了一种基于小波分量特征值的高光谱影像分类算法。针对每个像素构建一个能反映该分量特征的函数,得到其特征值。再利用这些特征值与参考光谱的特征值进行匹配,从而对整幅影像实现分类。实验证明,该方法比传统的光谱角制图法和交叉相关系数法的分类精度有较大提高。     

Savanna grass nitrogen to phosphorous ratio estimation using field spectroscopy and the potential for estimation with imaging spectroscopy

Determining the foliar N:P ratio provides a tool for understanding nutrient limitation on plant production and consequently for the feeding patterns of herbivores. In order to understand the nutrient limitation at landscape scale, remote sensing techniques offer that opportunity. The objective of this study is to investigate the utility of field spectroscopy and a potential of hyperspectral mapper (HyMap) spectra to estimate foliar N:P ratio. Field spectral measurements were undertaken, and grass samples were collected for foliar N and P extraction. The foliar N:P ratio prediction models were developed using partial least square regression (PLSR) with original spectra and transformed spectra for field and the resampled field spectra to HyMap. Spectral transformations included the continuum removal (CR), water removal (WR), first difference derivative (FD) and log transformation (Log(1/R)). The results showed that CR and WR spectra in combination with PLSR predicted foliar N:P ratio with higher accuracy as compared to FD and R, using field spectra. For HyMap spectral analysis, addition to CR and WR, FD achieved higher estimation accuracy. The performance of FD, CR and WR spectra were attributed to their ability to minimize sensor and water effects on the fresh leaf spectra, respectively. The study demonstrated a potential to predict foliar N:P ratio using field and HyMap simulated spectra and shortwave infrared (SWIR) found to be highly sensitive to foliar N:P ratio. The study recommends the prediction of foliar N:P ratio at landscape level using airborne hyperspectral data and could be used by the resource managers, park managers, farmers and ecologists to understand the feeding patterns, resource selection and distribution of herbivores (i.e. wild and livestock).     

基于实测光谱估测密云水库水体叶绿素a浓度

水中叶绿素a浓度是衡量水体初级生产力和富营养化程度的最基本的指标。利用野外便携式地物光谱仪对密云水库水体进行反射光谱测量并同步采集水样。通过分析叶绿素a浓度与光谱反射特征的相关关系,建立了叶绿素a反演模型。结果表明,利用单波段光谱反射率、光谱比值指数或微分光谱比值能够可靠反演叶绿素a浓度;但微分光谱与叶绿素a浓度相关性更高,更适用于密云水库水体叶绿素a浓度的高光谱反演。