Using low‐spectral‐resolution images to acquire simulated hyperspectral images

We propose a method to acquire simulated hyperspectral images using low‐spectral‐resolution images. Hyperspectral images provide more spectral information than low‐spectral‐resolution images, because of the additional spectral bands used for data acquisition in hyperspectral imaging. Unfortunately, original hyperspectral images are more expensive and more difficult to acquire. However, some research questions require an abundance of spectral information for ground monitoring, which original hyperspectral images can easily provide. Hence, we need to propose a method to acquire simulated hyperspectral images, when original hyperspectral images are especially necessary. Since low‐spectral‐resolution images are readily available and cheaper, we develop a method to acquire simulated hyperspectral images using low‐spectral‐resolution images. With simulated hyperspectral images, we can acquire more ‘hidden’ information from low‐spectral‐resolution images. Our method uses the principles of pixel‐mixing to understand the compositional relationship of spectrum data to an image pixel, and to simulate radiation transmission processes. To this end, we use previously obtained data (i.e. spectrum library) and the sorting data of objects that are derived from a low‐spectral‐resolution image. Using the simulation of radiation transmission processes and these different data, we acquire simulated hyperspectral images. In addition, previous analyses of simulated remotely sensed images do not use quantitative statistical measures, but use qualitative methods, describing simulated images by sight. Here, we quantitatively assess our simulation by comparing the correlation coefficients of simulated images and real images. Finally, we use simulated hyperspectral images, real Hyperion images, and their corresponding ALI images to generate several classification images. The classification results demonstrate that simulated hyperspectral data contain additional information not available in the multispectral data. We find that our method can acquire simulated hyperspectral images quickly.     

双卷积池化结构的3D-CNN高光谱遥感影像分类方法

目的 高光谱遥感影像数据包含丰富的空间和光谱信息,但由于信号的高维特性、信息冗余、多种不确定性和地表覆盖的同物异谱及同谱异物现象,导致高光谱数据结构呈高度非线性。3D-CNN（3D convolutional neural network）能够利用高光谱遥感影像数据立方体的特性,实现光谱和空间信息融合,提取影像分类中重要的有判别力的特征。为此,提出了基于双卷积池化结构的3D-CNN高光谱遥感影像分类方法。方法 双卷积池化结构包括两个卷积层、两个BN（batch normalization）层和一个池化层,既考虑到高光谱遥感影像标签数据缺乏的问题,也考虑到高光谱影像高维特性和模型深度之间的平衡问题,模型充分利用空谱联合提供的语义信息,有利于提取小样本和高维特性的高光谱影像特征。基于双卷积池化结构的3D-CNN网络将没有经过特征处理的3D遥感影像作为输入数据,产生的深度学习分类器模型以端到端的方式训练,不需要做复杂的预处理,此外模型使用了BN和Dropout等正则化策略以避免过拟合现象。结果 实验对比了SVM（support vector machine）、SAE（stack autoencoder）以及目前主流的CNN方法,该模型在Indian Pines和Pavia University数据集上最高分别取得了99.65%和99.82%的总体分类精度,有效提高了高光谱遥感影像地物分类精度。结论 讨论了双卷积池化结构的数目、正则化策略、高光谱首层卷积的光谱采样步长、卷积核大小、相邻像素块大小和学习率等6个因素对实验结果的影响,本文提出的双卷积池化结构可以根据数据集特点进行组合复用,与其他深度学习模型相比,需要更少的参数,计算效率更高。     

近红外高光谱图像数据预测技术

目的 受到传感器光谱响应范围的影响,可见光区域和近红外区域（400~2 500 nm）的高光谱数据通常使用不同的感光芯片进行成像,现有这一光谱区域典型的高光谱成像系统,如AVIRIS （airborne visible infrared imaging spectrometer）成像光谱仪,通常由多组感光芯片组成,整个成像系统成本和体积通常比较大,严重限制了该谱段高光谱探测技术的发展。为了能够扩展单感光芯片成像系统获得的高光谱图像的光谱范围,本文探索基于卷积神经网络的近红外光谱数据预测技术。方法 结合AVIRIS成像光谱仪的光谱配置,设计了基于残差学习的红外谱段图像预测网络,利用计算成像的方式从可见光范围的高光谱图像预测出近红外波段的光谱图像,并在典型的卫星高光谱遥感数据上进行红外光谱预测重构和基于重构的数据分类实验,以验证论文提出的红外光谱数据预测技术的可行性以及有效性。结果 本文设计的预测网络在Cuprite数据集上得到的预测近红外图像峰值信噪比为40.145 dB,结构相似度为0.996,光谱角为0.777 rad;在Salinas数据集上得到的预测近红外图像峰值信噪比为39.55 dB,结构相似性为0.997,光谱角为1.78 rad。在分类实验中,相比于只使用可见光图像,利用预测的近红外图像使得支持向量机（support vector machine,SVM）的准确率提升了0.6%,LeNet的准确率提升了1.1%。结论 基于AVIRIS传感器获取的两组典型卫星高光谱数据实验表明,本文提出的红外光谱数据预测技术不仅可基于计算成像的方式扩展可见光光谱成像系统的光谱成像范围,对于减小成像系统体积和质量具有重要意义,而且可有效提高可见光区域光谱图像数据在典型应用中的处理性能,对于提高高光谱数据处理精度提供新的技术支撑。     

先验终端像元库支持下的GF-4多光谱影像自动云检测

高分四号卫星是我国第一颗地球同步轨道遥感卫星,以其高频、宽幅的特点,可为我国农业、林业、减灾、气象、环保和水利等应用提供快速、稳定的光学遥感影像,高效的影像自动云检测有助于进一步提高高分四号影像的利用效率。CDAG（Cloud Detection Algorithm-Generating）是一种基于像元组分光谱分析的自动云检测算法,能有效降低混合像元、复杂表面结构和大气等因素的影响。为了探索CDAG算法对于高分4号多光谱影像（GF4-PMS）的云检测应用能力,首先,从高光谱影像（AVIRIS）上选取不同的云类型和各种地表覆盖类型,建立云像元库和地物像元库;其次,基于高光谱像元库和GF4-PMS传感器光谱响应函数模拟出多光谱影像像元库;然后,根据碎云、薄云、厚云及非云像元的光谱差异性分析,将GF4-PMS影像的待检测像元与终端像元进行相似概率分析,实现基于最佳阈值自动迭代的GF4-PMS影像云检测;最后,从云像元正确率、晴空像元正确率、误判率、漏判率等多个指标进行云检测精度验证。结果表明：AVIRIS影像可以有效提取适用于GF4-PMS影像云检测的终端像元库,基于CDAG算法能较好地识别GF4-PMS影像上各种类型的云,对于不同时相、不同下垫面的碎云、薄云、厚云的检测精度可达90%以上。因此,基于先验终端像元库的云检测法对于提升GF4-PMS影像的利用效率具有较好的应用价值。     

Automatic Cloud Detection of GF4 Multispectral Imagery Supported by the Priori Terminal Pixel Library

The GaoFen4 (GF4) satellite is China’s first geo-synchronous orbit remote sensing satellite. With the advantages of high frequency and wide width, it can provide fast and stable optical remote sensing images for agricultural, forestry, disaster reduction, meteorology, environmental protection, water conservancy and other applications in China. Efficient image automatic cloud detection helps to further improve the utilization efficiency of GaoFen4 images. CDAG（Cloud Detection Algorihtm-Generating）Cloud detection is an automatic cloud detection algorithm based on spectral analysis of pixel components, which can effectively reduce the influence of mixed pixels, complex surface structure and atmosphere. This paper aims to explore the application of CDAG algorithm in cloud detection of GaoFen4 multispectral imagery (GF4-PMS). Firstly, different cloud types and surface cover types were selected from hyperspectral images (AVIRIS) to establish cloud pixel library and clear sky pixel library. Next, the pixel library of multispectral images was simulated based on Hyperspectral pixel library and spectral response function of GF4-PMS sensor. Then, according to the spectral difference analysis of broken cloud, thin cloud, thick cloud and non-cloud pixel, the similarity probability analysis was performed on the to-be-detected pixel of the GF4-PMS image and the terminal pixel, and the GF4-PMS image cloud detection based on the optimal threshold automatic iteration was realized. Finally, cloud detection accuracy verification was carried out from multiple indicators such as cloud pixel correct rate, clear sky pixel correct rate, false positive rate and missed rate. The results show that AVIRIS images can effectively extract terminal pixel libraries for GF4-PMS image cloud detection. Clouds of Various types on GF4-PMS images can be better identified based on the CDAG algorithm. The accuracy of detection results for broken clouds, thin clouds and thick clouds with different time phases and different underlying surfaces can reach more than 90%. Therefore, the cloud detection method based on the priori terminal pixel library has a good application value for improving the utilization efficiency of GF4-PMS images.     

基于双重L2稀疏编码的高光谱图像分类

目的 为了有效提高高光谱图像分类的精度,提出了双重L2稀疏编码的高光谱图像分类方法。方法 首先对高光谱图像进行预处理,充分结合图像的空间信息和光谱信息,利用像元的空间连续性,用L2稀疏编码重建图像中每个像元。针对重建的图像数据,依据L2稀疏编码的最小误差和编码系数实现分类。结果 在公开的数据库AVIRIS高光谱图像上进行验证,分类精度为99.44%,与支持向量机（SVM）、K最近邻（KNN）和L1稀疏编码方法比较,有效地提高了分类的准确性。结论 实验结果表明,提出的方法应用于高光谱图像分类具有较好的分类效果。     

Spectral index-based dynamic threshold technique for detecting cloud contamination in ocean colour data

ABSTRACT

Coastal and lagoon water colour products are often greatly contaminated by clouds and accompanying shadows. Adjacency effects due to the strong reflection from contiguous cloud pixels can introduce further uncertainty into the water-leaving radiance retrieval process. This study aims to propose a robust cloud-index dynamic-threshold (CIDT) algorithm based on the spectral and spatial characteristics of the clouds and evaluate its performance in comparison with results obtained from the existing algorithms using multispectral and hyperspectral images from the lagoon and coastal water zones. Detection of cloud contamination from these images is performed before applying atmospheric correction in order to prevent significant loss of valuable data and ensure the quality of higher-level products. The CIDT starts with data pre-processing (in order to avoid misclassification across the clouds and non-cloud regions) by excluding signatures other than the cloud and non-cloud (water and land) pixels. Based on the spectral and spatial variability characteristic of clouds, a new cloud index is then introduced that uses the top-of-atmosphere reflectance in conjugation with the dynamic threshold values to detect the cloud pixels. For quantitative and qualitative analyses, CIDT is tested on a number of scenes provided by Landsat 8 Operational Land Imager (OLI) and Hyperspectral Imager for the Coastal Ocean (HICO) sensors over the coastal and lagoon zones. According to the comparison of the algorithm results with the reference cloud flags, CIDT shows a significant improvement in identifying clouds of varying opacity, achieves a higher cloud detection accuracy, and reduces the number of the previously misclassified pixels by other algorithms in different coastal and lagoon water regions. The CIDT is extensively tested in mid-latitude and tropical areas and CIDT can be applied to both multispectral and hyperspectral images over the lagoon and coastal zones without the need for ancillary information.     

Feature extraction method based on spectral dimensional edge preservation filtering for hyperspectral image classification

ABSTRACT

A large amount of spectral and spatial information contained in hyperspectral imagery has provided a great opportunity to effectively characterize and identify the surface materials of interest. Feature extraction plays a very important role for hyperspectral data classification, which can reduce noise from the original data and improve the separability of land classes. A novel feature extraction technique based on spectral dimensional edge preserving filter is proposed in this paper. A series of Gaussian filters are applied in the spatial domain of the hyperspectral image to produce the guidance image, then, the edge preserving filter which is guided by the guidance image is adopted and applied in the spectral domain of the hyperspectral data to get the feature. For the feature is produced by filtering in the spectral domain, the spectral curves of the feature are more continues, which avoids the spectral discontinuity problems result from the traditional two-dimensional spatial filter. The guidance image is obtained by filtering the original image in the spatial domain, so, the spatial and the spectral information are integrated together in the following spectral edge preserving filtering process. We carefully adjusted the parameters of the filter and applied it to different real hyperspectral remote sensing images, with the support vector machine, multinomial logistic regression, and random forest serving as the classifier, by comparing with other feature extraction methods presented in recent literature, the results indicate that the proposed methodology always has a great performance in different kinds of cases.     

Spectral unmixing of vegetation,soil and dry carbon cover in arid regions: Comparing multispectral and hyperspectral observations

Remote measurements of the fractional cover of photosynthetic vegetation (PV), non-photosynthetic vegetation (NPV) and bare soil are critical to understanding climate and land-use controls over the functional properties of arid and semi-arid ecosystems. Spectral mixture analysis is a method employed to estimate PV, NPV and bare soil extent from multispectral and hyperspectral imagery. To date, no studies have systematically compared multispectral and hyperspectral sampling schemes for quantifying PV, NPV and bare soil covers using spectral mixture models. We tested the accuracy and precision of spectral mixture analysis in arid shrubland and grassland sites of the Chihuahuan Desert, New Mexico, USA using the NASA Airborne Visible and Infrared Imaging Spectrometer (AVIRIS). A general, probabilistic spectral mixture model, Auto-MCU, was developed that allows for automated sub-pixel cover analysis using any number or combination of optical wavelength samples. The model was tested with five different hyperspectral sampling schemes available from the AVIRIS data as well as with data convolved to Landsat TM, Terra MODIS, and Terra ASTER optical channels. Full-range (0.4-2.5 w m) sampling strategies using the most common hyperspectral or multispectral channels consistently over-estimated bare soil extent and under-estimated PV cover in our shrubland and grassland sites. This was due to bright soil reflectance relative to PV reflectance in visible, near-IR, and shortwave-IR channels. However, by utilizing the shortwave-IR2 region (SWIR2; 2.0-2.3 w m) with a procedure that normalizes all reflectance values to 2.03 w m, the sub-pixel fractional covers of PV, NPV and bare soil constituents were accurately estimated. AVIRIS is one of the few sensors that can provide the spectral coverage and signal-to-noise ratio in the SWIR2 to carry out this particular analysis. ASTER, with its 5-channel SWIR2 sampling, provides some means for isolating bare soil fractional cover within image pixels, but additional studies are needed to verify the results.     

自适应权重注入机制遥感图像融合

目的 遥感图像融合是将一幅高空间分辨率的全色图像和对应场景的低空间分辨率的多光谱图像,融合成一幅在光谱和空间两方面都具有高分辨率的多光谱图像。为了使融合结果在保持较高空间分辨率的同时减轻光谱失真现象,提出了自适应的权重注入机制,并针对上采样图像降质使先验信息变得不精确的问题,提出了通道梯度约束和光谱关系校正约束。方法 使用变分法处理遥感图像融合问题。考虑传感器的物理特性,使用自适应的权重注入机制向多光谱图像各波段注入不同的空间信息,以处理多光谱图像波段间的差异,避免向多光谱图像中注入过多的空间信息导致光谱失真。考虑到上采样的图像是降质的,采用局部光谱一致性约束和通道梯度约束作为先验信息的约束,基于图像退化模型,使用光谱关系校正约束更精确地保持融合结果的波段间关系。结果 在Geoeye和Pleiades卫星数据上同6种表现优异的算法进行对比实验,本文提出的模型在2个卫星数据上除了相关系数CC（correlation coefficient）和光谱角映射SAM（spectral angle mapper）评价指标表现不够稳定,偶尔为次优值外,在相对全局误差ERGAS（erreur relative globale adimensionnelle de synthèse）、峰值信噪比PSNR（peak signal-to-noise ratio）、相对平均光谱误差RASE（relative average spectral error）、均方根误差RMSE（root mean squared error）、光谱信息散度SID（spectral information divergence）等评价指标上均为最优值。结论 本文模型与对比算法相比,在空间分辨率提升和光谱保持方面都取得了良好效果。     

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。     

傅里叶变换通道注意力网络的胆管癌高光谱图像分割

目的 胆管癌高光谱图像的光谱波段丰富但存在冗余,造成基于深度神经网络高光谱图像分割方法的分割精度下降,虽然一些基于通道注意力机制的网络能够关注重要通道,但在处理通道特征时存在信息表示不足问题,因此本文研究构建一种新的通道注意力机制深度网络,以提高分割准确性。方法 提出了傅里叶变换多频率通道注意力机制（frequency selecting channel attention,FSCA）。FSCA对输入特征进行2维傅里叶变换,提取部分频率特征,再通过两层全连接层得到通道权重向量,将通道权重与对应通道特征相乘,获得了融合通道注意力信息的输出。针对患癌区域和无癌区域数据不平衡问题引入了Focal损失,结合Inception模块,构建基于Inception-FSCA的胆管癌高光谱图像分割网络。结果 在采集的胆管癌高光谱数据集上进行实验,Inception-FSCA网络的准确率（accuracy）、精度（precision）、敏感性（sensitivity）、特异性（specificity）、Kappa系数分别为0.978 0、0.965 4、0.958 6、0.985 2、0.945 6,优于另外5种对比方法。与合成的假彩色图像的分割结果相比,高光谱图像上的实验指标分别提高了0.058 4、0.105 8、0.087 5、0.039 0、0.149 3。结论 本文所提出的傅里叶变换多频率通道注意力机制能够更有效地利用通道信息,基于Inception-FSCA的胆管癌高光谱图像分割网络能够提升分割效果,在胆管癌医学辅助诊断方面具有研究和应用价值。     

波段自适应细节注入的高分五号与Sentinel-2遥感影像空谱融合

目的 针对当前空谱融合方法应用到高光谱图像融合时,出现的空间细节信息提升明显但光谱失真,或者光谱保真度高但空间细节信息提升不足的问题,本文提出一种波段自适应细节注入的高分五号（GF-5）高光谱图像（30 m）与Sentinel-2多光谱图像（10 m）的遥感影像空谱融合方法。方法 首先,为了解决两个多波段图像不便于直接融合的问题,提出一种波段自适应的融合策略,对多光谱图像波谱范围以外的高光谱图像波段,以相关系数为标准将待融合图像进行分组。其次,针对传统Gram-Schmidt （GS）融合方法用平均权重系数模拟低分辨率图像造成的光谱失真问题,使用最小均方误差估计计算线性拟合系数,再将拟合图像作为第1分量进行GS正变换,提升融合图像的光谱保真度。最后,为了能同时注入更多的空间细节信息,通过非下采样轮廓波变换将拟合图像、空间细节信息图像和多光谱图像的空间、光谱信息融入到重构的高空间分辨率图像中,再将其与其他GS分量一起进行逆变换,最终得到10 m分辨率的GF-5融合图像。结果 通过与当前用于高光谱图像空谱融合的典型方法比较,本文方法对于受时相影响较小的城镇区域,在提升空间分辨率的同时有较好的光谱保真度,且不会出现噪点;对于受时相变化影响大的植被密集区域,本文方法融合图像有较好的清晰度和地物细节信息,且没有噪点出现。本文方法的CC （correlation coefficient）、ERGAS （erreur relative globale adimensionnelle de synthèse）和SAM （spectral angle mapper）相比于传统GS方法分别提升8%、26%和28%,表明本文方法的光谱保真度大大提高。结论 本文方法的结果空间上没有噪点且光谱曲线与原始光谱曲线基本保持一致,是一种兼具高空间分辨率和高光谱保真度的高光谱图像融合方法。     

结合超像元和子空间投影支持向量机的高光谱图像分类

目的 高光谱图像包含了丰富的空间、光谱和辐射信息,能够用于精细的地物分类,但是要达到较高的分类精度,需要解决高维数据与有限样本之间存在矛盾的问题,并且降低因噪声和混合像元引起的同物异谱的影响。为有效解决上述问题,提出结合超像元和子空间投影支持向量机的高光谱图像分类方法。方法 首先采用简单线性迭代聚类算法将高光谱图像分割成许多无重叠的同质性区域,将每一个区域作为一个超像元,以超像元作为图像分类的最小单元,利用子空间投影算法对超像元构成的图像进行降维处理,在低维特征空间中执行支持向量机分类。本文高光谱图像空谱综合分类模型,对几何特征空间下的超像元分割与光谱特征空间下的子空间投影支持向量机（SVMsub）,采用分割后进行特征融合的处理方式,将像元级别转换为面向对象的超像元级别,实现高光谱图像空谱综合分类。结果 在AVIRIS（airbone visible/infrared imaging spectrometer）获取的Indian Pines数据和Reflective ROSIS（optics system spectrographic imaging system）传感器获取的University of Pavia数据实验中,子空间投影算法比对应的非子空间投影算法的分类精度高,特别是在样本数较少的情况下,分类效果提升明显;利用马尔可夫随机场或超像元融合空间信息的算法比对应的没有融合空间信息的算法的分类精度高;在两组数据均使用少于1%的训练样本情况下,同时融合了超像元和子空间投影的支持向量机算法在两组实验中分类精度均为最高,整体分类精度高出其他相关算法4%左右。结论 利用超像元处理可以有效融合空间信息,降低同物异谱对分类结果的不利影响;采用子空间投影能够将高光谱数据变换到低维空间中,实现有限训练样本条件下的高精度分类;结合超像元和子空间投影支持向量机的算法能够得到较高的高光谱图像分类精度。     

PCA与移动窗小波变换的高光谱决策融合分类

目的 高光谱数据具有较高的谱间分辨率和相关性,给分类处理带来了一定的困难.为了提高分类精度,提出一种结合PCA与移动窗小波变换的高光谱决策融合分类算法.方法 首先,利用相关系数矩阵对原始高光谱数据进行波段分组;然后,利用主成分分析对每组数据进行谱间降维;再根据提出的移动窗小波变换法进行空间特征提取;最后,采用线性意见池(LOP)决策融合规则对多分类器的分类结果进行融合.结果 采用两组来自不同传感器的数据进行实验,所提算法的分类精度和Kappa系数均高于已有的5种分类算法.与SVM-RBF算法相比,本文算法的分类精度高出了8％左右.结论 实验结果表明,本文算法充分挖掘了高光谱图像的谱间-空间信息,能有效提高分类正确率,在小样本情况下和噪声环境中也具有良好的分类性能.     

PoNet: A universal physical optimization-based spectral super-resolution network for arbitrary multispectral images

Spectral super-resolution is a very important technique to obtain hyperspectral images from only multispectral images, which can effectively solve the high acquisition cost and low spatial resolution of hyperspectral images. However, in practice, multispectral channels or images captured by the same sensor are often with different spatial resolutions, which brings a severe challenge to spectral super-resolution. This paper proposed a universal spectral super-resolution network based on physical optimization unfolding for arbitrary multispectral images, including single-resolution and cross-scale multispectral images. Furthermore, two new strategies are proposed to make full use of the spectral information, namely, cross-dimensional channel attention and cross-depth feature fusion. Experimental results on five data sets show superiority and stability of PoNet addressing any spectral super-resolution situations.     

采用谱间预测的高光谱图像压缩方法研究

高光谱图像具有较高谱分辨率的优越性是以其较大的数据量及较高的数据维为代价的,因此有必要研究有效的高光谱图像压缩方法。探讨一种基于谱间预测的高光谱图像压缩方案。考虑到高光谱图像谱间相关性随分辨率的提高而增强,推导出由多个波段对当前波段进行线性预测的预测器系数求解算法,提出了一种参考波段优化选取方法。实验结果表明,该方法能获得较低的最小均方误差,运算速度快,具有实用价值。     

Super resolution land cover mapping of hyperspectral images using the deep image prior-based approach

ABSTRACT

Due to the instantaneous field-of-view (IFOV) of the sensor and diversity of land cover types, some pixels, usually named mixed pixels, contain more than one land cover type. Soft classification can predict the portion of each land cover type in mixed pixels in the absence of spatial distribution. The spatial distribution information in mixed pixels can be solved by super resolution mapping (SRM). Typically, SRM involves two steps: soft class value estimation, which is similar to the image super resolution of image restoration, and land cover allocation. A new SRM approach utilizes a deep image prior (DIP) strategy combined with a super resolution convolutional neural network (SRCNN) to estimate fine resolution fraction images for each land cover type; then, a simple and efficient classifier is used to allocate subpixel land cover types under the constraint of the generated fine fraction images. The proposed approach can use prior information of input images to update network parameters and no longer require training data. Experiments on three different cases demonstrate that the subpixel classification accuracy of the proposed DIP-based SRM approach is significantly better than the three conventional SRM approaches and a transfer learning-based neural network SRM approach. In addition, the DIP-SRM approach performs very robustly about small-area objects within multiple land cover types and significantly reduces soft classification uncertainty. The results of this paper provide an extension for utilizing SRCNN to address SRM issues in hyperspectral images.     

A novel adaptive fast IHS transform fusion method driven by regional spectral characteristics for Gaofen-2 imagery

ABSTRACT

With the increasing diversity of applications based on the Gaofen-2 satellite imagery, broadly applicable methods to generate high quality fused images is a significant problem to investigate. To obtain an image with high spatial and spectral resolutions from given panchromatic (Pan) images and multispectral (MS) images, most existing fusion algorithms adopt a unified strategy for the whole image. However, regions have distinct characteristics that impact the spatial and spectral resolution processing, on account of their varying regional features. In this article, to satisfy the diverse needs of different regions, a novel fast IHS (Intensity-Hue-Saturation) transform fusion method driven by regional spectral characteristics is proposed to fuse Gaofen-2 imagery. First, by the fast IHS transform framework, the original intensity component is obtained from the upsampled MS imagery. Then, numerous independent regions of upsampled MS imagery are generated by a novel superpixel merging strategy, and the spectral characteristics of these regions are utilized for generating a fusion factor. Next, to acquire a new fused intensity component, the fusion factor is applied to guide the injection of details in the fusion procedure. This fusion factor adapts the method to meet the spatial and spectral resolution needs for each region. Finally, the difference between the new fused intensity component and the original one is regarded as the detail that needs to be injected; these are added equally to the different bands of the upsampled MS imagery to yield the final fused multispectral image. In comparison with other classical algorithms, the visual and statistical analysis reveal that our proposed method can provide better results in improving spatial detail and preserving spectral information.     

粗定位和协同表示的高光谱图像异常检测

目的 由于在军事和民用应用中的重要作用,高光谱遥感影像异常检测在过去的20~30年里一直都是备受关注的研究热点。然而,考虑到异常点往往藏匿于大量的背景像元之中,且只占据很少的数量,给精确检测带来了不小的挑战。针对此问题,基于异常点往往表现在高频的细节区域这一前提,本文提出了一种基于异常点粗定位和协同表示的高光谱遥感影像异常检测算法。方法 对输入的原始高光谱遥感影像进行空间维的降质操作;通过衡量降质后影像与原始影像在空间维的差异,粗略定位可能的异常点位置;将粗定位的异常点位置用于指导像元间的协同表示以重构像元;通过衡量重构像元与原始像元的差异,从而进一步优化异常检测结果。结果 在4个数据集上与6种方法进行了实验对比。对于San Diego数据集,次优算法和本文算法分别取得的AUC （area under curve）值为0.978 6和0.994 0;对于HYDICE （hyperspectral digital image collection equipment）数据集,次优算法和本文算法的AUC值为0.993 6和0.998 5;对于Honghu数据集,次优算法和本文方法的AUC值分别为0.999 2和0.999 3;对Grand Isle数据集而言,尽管本文方法以0.001的差距略低于性能第1的算法,但从目视结果图中可见,本文方法所产生的虚警目标远少于性能第1的算法。结论 本文所提出的粗定位和协同表示的高光谱异常检测算法,综合考虑了高光谱遥感影像的谱间特性,同时还利用了其空间特性以及空间信息的先验分布,从而获得异常检测结果的提升。