基于多种空间信息的高光谱遥感图像分类方法

在高光谱遥感图像分类方法中,空间特征和光谱特征的融合可以有效地改善分类效果。针对单一空间特征的信息表达不充分问题,提出了一种联合多种空间特征的高光谱图像空谱分类方法。利用超像素信息对分类结果进行后处理去掉椒盐噪声,并创造性地将超像素信息应用于分类前处理,提出了一种利用超像素信息对像素点的特征向量进行线性加权融合的方法。试验结果表明,所提方法的性能优于目前的通常方法。     

Development and testing of a statistical texture model for land cover classification of the Black Sea region with MODIS imagery

A statistical model is proposed for analysis of the texture of land cover types for global and regional land cover classification by using texture features extracted by multiresolution image analysis techniques. It consists of four novel indices representing second-order texture, which are calculated after wavelet decomposition of an image and after texture extraction by a new approach that makes use of a four-pixel texture unit. The model was applied to four satellite images of the Black Sea region, obtained by Terra/MODIS and Aqua/MODIS at different spatial resolution. In single texture classification experiments, we used 15 subimages (50 × 50 pixels) of the selected classes of land covers that are present in the satellite images studied. These subimages were subjected to one-level and two-level decompositions by using orthonormal spline and Gabor-like spline wavelets. The texture indices were calculated and used as feature vectors in the supervised classification system with neural networks. The testing of the model was based on the use of two kinds of widely accepted statistical texture quantities: five texture features determined by the co-occurrence matrix (angular second moment, contrast, correlation, inverse difference moment, entropy), and four statistical texture features determined after the wavelet transformation (mean, standard deviation, energy, entropy). The supervised neural network classification was performed and the discrimination ability of the proposed texture indices was found comparable with that for the sets of five GLCM texture features and four wavelet-based texture features. The results obtained from the neural network classifier showed that the proposed texture model yielded an accuracy of 92.86% on average after orthonormal wavelet decomposition and 100% after Gabor-like wavelet decomposition for texture classification of the examined land cover types on satellite images.     

基于三维Saab变换的高光谱图像压缩方法

高光谱图像中存储了丰富的光谱信息,具有极大的应用价值,但现有大部分高光谱图像压缩方法难以同时兼顾图像中的空间冗余与谱间冗余,导致压缩性能受到局限。针对该问题,提出了一种基于三维修正偏置的子空间(Saab)变换的高光谱图像压缩方法。采用三维Saab变换对高光谱图像的分块进行空间光谱信息融合的降维操作,同时去除谱间冗余和局部空间冗余;利用高效率视频编码(HEVC)中的帧内编码模块进一步去除空间冗余和统计冗余;实现低失真、高比率的高光谱图像压缩。在多个高光谱图像数据集上的实验结果表明,所提方法在同码率下重建图像的信噪比(SNR)比采用主成分分析(PCA)降维的方法至少提高0.62 dB,在高码率的情况下性能优于张量分解的压缩方法。同时,验证了不同降维方法对分类任务的性能影响,结果表明,所提方法更好地保留了图像中的重要特征,在低码率的情况下仍可以保持较高的分类精度。     

基于自适应注入模型的遥感图像融合方法

遥感图像融合的目的是融合高光谱分辨率、低空间分辨率的多光谱（MS）图像和高空间分辨率、低光谱分辨率的全色（PAN）图像,得到高光谱分辨率与高空间分辨率的融合图像。遥感图像的注入模型中如何确定注入细节及注入系数是该技术研究的关键。针对注入细节优化,先通过模拟MS传感器的特性来定义一种多尺度高斯滤波器,再用该滤波器卷积PAN图像以提取细节,得到与MS图像高度相关的细节。针对注入系数优化,综合考虑光谱信息与细节信息提出一种自适应的注入量系数。为更好地保留边缘信息,提出一种新的边缘保持权重矩阵,实现光谱信息与空间的双保真。将优化后的注入系数与注入细节相乘注入到上采样后的MS图像中,得到融合结果。对所提方法进行性能分析,并在各卫星数据集上进行大量测试,与一些先进的遥感图像融合方法进行对比,实验结果表明,所提方法在主观与综合客观指标上都能达到最优。      

Quality assessment by region in spot images fused by means dual-tree complex wavelet transform

This work is motivated in providing and evaluating a fusion algorithm of remotely sensed images, i.e. the fusion of a high spatial resolution panchromatic image with a multi-spectral image (also known as pansharpening) using the dual-tree complex wavelet transform (DT-CWT), an effective approach for conducting an analytic and oversampled wavelet transform to reduce aliasing, and in turn reduce shift dependence of the wavelet transform. The proposed scheme includes the definition of a model to establish how information will be extracted from the PAN band and how that information will be injected into the MS bands with low spatial resolution. The approach was applied to Spot 5 images where there are bands falling outside PAN’s spectrum. We propose an optional step in the quality evaluation protocol, which is to study the quality of the merger by regions, where each region represents a specific feature of the image. The results show that DT-CWT based approach offers good spatial quality while retaining the spectral information of original images, case SPOT 5. The additional step facilitates the identification of the most affected regions by the fusion process.     

A method in near-surface estimation of air temperature (NEAT) in times following the satellite passing time using MODIS images

Air temperature is one of the most important parameters in environmental, agricultural and water resources studies. This information is not usually always available at the required temporal and spatial resolution. The air temperature is measured at a fixed point in the meteorological stations which are dispersed and may not have the appropriate spatial resolution needed for many applications. On the other hand, MODIS satellite images have relatively acceptable spatial resolution specially for use in environmental studies. There is a methodology with which the near surface air temperature can be extracted from MODIS images at the satellite passing time with an acceptable accuracy. The goal in this study is to find a way to predict the air temperature in times after/before the satellite passing time. The procedure consists of two steps. In the first step, the relationship between the air temperature at a time in a synoptic station and the air temperature in other times up to 5 h later were modeled. In the second step, using these built up relationships, the air temperature extracted from the satellite image at the passing time was extrapolated to the next hours. Finally, the results of this extrapolation method were evaluated using the air temperatures measured at those hours and in the pixels containing some other meteorological stations. The error of the method when applied to a relatively homogeneous surface cover was about 1.5 °C. This error when applied to the next hours, was below 2 °C up to 5 h after satellite passing time. This method can be useful in some agricultural and horticultural applications in which both the spatial and temporal resolution are needed simultaneously. This product is a useful tool for frost prediction, a phenomenon that usually happens at night or early in the morning.     

Application of SVM on satellite images to detect hotspots in Jharia coal field region of India

The present paper deals with the application of Support Vector Machine (SVM) and image analysis techniques on NOAA/AVHRR satellite image to detect hotspots on the Jharia coal field region of India. One of the major advantages of using these satellite data is that the data are free with very good temporal resolution; while, one drawback is that these have low spatial resolution (i.e., approximately 1.1 km at nadir). Therefore, it is important to do research by applying some efficient optimization techniques along with the image analysis techniques to rectify these drawbacks and use satellite images for efficient hotspot detection and monitoring. For this purpose, SVM and multi-threshold techniques are explored for hotspot detection. The multi-threshold algorithm is developed to remove the cloud coverage from the land coverage. This algorithm also highlights the hotspots or fire spots in the suspected regions. SVM has the advantage over multi-thresholding technique that it can learn patterns from the examples and therefore is used to optimize the performance by removing the false points which are highlighted in the threshold technique. Both approaches can be used separately or in combination depending on the size of the image. The RBF (Radial Basis Function) kernel is used in training of three sets of inputs: brightness temperature of channel 3, Normalized Difference Vegetation Index (NDVI) and Global Environment Monitoring Index (GEMI), respectively. This makes a classified image in the output that highlights the hotspot and non-hotspot pixels. The performance of the SVM is also compared with the performance obtained from the neural networks and SVM appears to detect hotspots more accurately (greater than 91% classification accuracy) with lesser false alarm rate. The results obtained are found to be in good agreement with the ground based observations of the hotspots. This type of work will be quite helpful in the near future to develop a hotspots monitoring system using these operational satellites data.     

融合邻域色差的PSPNet对遥感影像的分割

传统的遥感影像语义分割利用影像的光谱特性,将具有相似值的像素进行归类,但无法区分具有不同光谱的同一类对象.针对这一问题,提出将邻域的色差信息和原始图像一起输入PSPNet网络中的方法.先将RGB变换到LAB空间,然后采用CIELAB公式计算出每一个像素与周围8个邻域像素的色差值,取平均值作为该像素的邻域色差值.在WHU...     

Selection of classification techniques for land use/land cover change investigation

The concerns over land use/land cover (LULC) change have emerged on the global stage due to the realisation that changes occurring on the land surface also influence climate, ecosystem and its services. As a result, the importance of accurate mapping of LULC and its changes over time is on the increase. Landsat satellite is a major data source for regional to global LULC analysis. The main objective of this study focuses on the comparison of three classification tools for Landsat images, which are maximum likelihood classification (MLC), support vector machine and artificial neural network (ANN), in order to select the best method among them. The classifiers algorithms are well optimized for the gamma, penalty, degree of polynomial in case of SVM, while for ANN minimum output activation threshold and RMSE are taken into account. The overall analysis shows that the ANN is superior to the kernel based SVM (linear, radial based, sigmoid and polynomial) and MLC. The best tool (ANN) is then applied on detecting the LULC change over part of Walnut Creek, Iowa. The change analysis of the multi temporal images indicates an increase in urban areas and a major shift in the agricultural practices.     

基于超像素与多尺度残差U-Net相结合的遥感图像飞机检测方法

遥感图像中存在飞机很小、角度和位置不确定且背景复杂等问题,从遥感图像中检测飞机是一项重要且具有挑战性的任务,因此,提出一种基于超像素与多尺度残差U-Net(Multi-scale Residual U-Net,MSRU-Net)相结合的遥感图像飞机检测方法。首先对遥感图像进行超像素预分割,将位置相邻且像素特征相似的像素点组成若干个超像素,保持图像进一步分割的有效特征;然后构建多尺度残差U-Net,学习其多尺度判别特征。与传统的飞机检测方法相比,该方法用少量的超像素代替大量像素表达图像特征,降低了图像分割的复杂度,再利用MSRU-Net分割遥感超像素图像,有效检测不同尺度的飞机图像。在公共飞机遥感图像数据集上实验,结果表明,该方法能够有效的检测遥感图像不同尺度的飞机图像,检测精确率达到91.2 %。     

A robust object-based shadow detection method for cloud-free high resolution satellite images over urban areas and water bodies

Unwanted contrast in high resolution satellite images such as shadow areas directly affects the result of further processing in urban remote sensing images. Detecting and finding the precise position of shadows is critical in different remote sensing processing chains such as change detection, image classification and digital elevation model generation from stereo images. The spectral similarity between shadow areas, water bodies, and some dark asphalt roads makes the development of robust shadow detection algorithms challenging. In addition, most of the existing methods work on pixel-level and neglect the contextual information contained in neighboring pixels. In this paper, a new object-based shadow detection framework is introduced. In the proposed method a pixel-level shadow mask is built by extending established thresholding methods with a new C₄ index which enables to solve the ambiguity of shadow and water bodies. Then the pixel-based results are further processed in an object-based majority analysis to detect the final shadow objects. Four different high resolution satellite images are used to validate this new approach. The result shows the superiority of the proposed method over some state-of-the-art shadow detection method with an average of 96% in F-measure.     

An object-level strategy for pan-sharpening quality assessment of high-resolution satellite imagery

Current satellite imaging systems offer a trade-off between high spatial and high spectral resolution providing panchromatic images at a higher spatial resolution and multispectral images at a lower spatial resolution but rich in spectral information while a wide range of applications need the highest level of this information, simultaneously. Image fusion techniques as means of enhancing the information content of initial panchromatic and multispectral images produce new images, titled pan-sharpened, which inherent the advantages of the initial images. Considering the impact of fusion accuracy on the quality of corresponding applications, it is necessary to evaluate the quality of these processed images. During the last decade, a lot of quality evaluation metrics have been proposed which are mostly inspired by traditional image quality metrics. These methods are mostly based on applying quality metrics at the pixel level and evaluating final quality value based on averaging of obtained metric values through the whole image. However, obtained results clearly show that the behaviour of image fusion quality is inconsistent amongst different image objects. In this article, by applying image fusion quality metrics (IFQMs) to image objects, an object-level strategy for quality assessment of the image fusion process is proposed. The proposed strategy is applied to different satellite imagery covering residential and agricultural areas. Experimental results show higher capabilities of object-level quality assessment strategy in the quality assessment of the fusion process. Evaluating fusion quality at the object level provides the potential of fusion quality assessment for each individual image object in compliance with different parameters such as the type of objects and the effective size of objects in data set.     

细缝裁减和非均匀映射结合的图像自适应方法

采用将细缝裁减和非均匀映射相结合的图像尺寸自适应框架,提出了一种基于内容的图像重要信息变形的度量方法.首先提取原始图像的重要性像素点,利用细缝裁减去掉一条像素细缝后,相应的重要性像素点会被更新.对于图像中保留的重要性像素点,计算它们的子图像平均偏差(ADSI,Average Difference of Sub Images);对于被移除的重要性像素点,计算它们的平均丢失能量(ALE,Average Lost Energy).通过ADSI和ALE可计算出重要信息变形的度量函数(IIDF,Important Information Deformation Function)的值,通过分析IIDF的趋势得到细缝裁减的终止条件,然后改用非均匀映射方法(non-homogeneous warping)将图像自适应到目标尺寸.实验结果证明,新方法处理的结果图像重要区域变形较小,并且计算效率比较高.     

Deep learning-based framework for monitoring of debris-covered glacier from remotely sensed images

In recent years, deep learning (DL) methods have proven their efficiency for various computer vision (CV) tasks such as image classification, natural language processing, and object detection. However, training a DL model is expensive in terms of both complexities of the network structure and the amount of labeled data needed. In addition, the imbalance among available labeled data for different classes of interest may also adversely affect the model accuracy. This paper addresses these issues using a new convolutional neural network (CNN) based architecture. The proposed network incorporates both spatial and spectral information that combines two sub-networks: spatial-CNN and spectral-CNN. The spectral-CNN extracts spectral information, while spatial-CNN captures spatial information. Moreover, to make the features more robust, a multiscale spatial CNN architecture is introduced using different kernels. The final feature vector is formed by concatenating the outputs obtained from both spatial-CNN and spectral-CNN. To address the data imbalance problem, a generative adversarial network (GAN) was used to generate data for the underrepresented class. Finally, relatively a shallower network architecture was used to reduce the number of parameters in the network and improve the processing speed. The proposed model was trained and tested on Senitel-2 images for the classification of the debris-covered glacier. The results showed that the proposed method is well-suited for mapping and monitoring debris-covered glaciers at a large scale with high classification accuracy. In addition, we compared the proposed method with conventional machine learning approaches, support vector machine (SVM), random forest (RF) and multilayer perceptron (MLP).     

POBI interpolation algorithm for CYGNSS near real time flood detection research: A case study of extreme precipitation events in Henan,China in 2021

In late 2016, NASA launched the first constellation of the global navigation satellite system reflectometry (GNSS-R) small satellites called the Cyclone Global Navigation Satellite System (CYGNSS). The stable data quality and continuous free availability of CYGNSS scientific data provided a new method for flood monitoring. However, owing to the pseudorandom distribution of CYGNSS data, researchers must always choose between high temporal resolution and high spatial resolution during the performance of flood monitoring based on CYGNSS data. For floods caused by extreme precipitation with sudden and short durations, the current flood mapping based on CYGNSS data cannot be updated in near real time. However, the near real time update of the flood distribution range is meaningful for postdisaster emergency response and rapid rescue. This study aimed to address this problem using a newly proposed spatial interpolation method based on previously observed behaviour (POBI). First, a method for calculating the surface reflectivity of the CYGNSS was introduced, followed by the principle of the POBI spatial interpolation method. The applicability of the POBI method in Henan Province, China, was then analysed, and by using the flood in Henan Province, China, in July 2021 as an example, the feasibility of CYGNSS near real time flood mapping based on the POBI method was evaluated. Based on the results, near real time and 3 km flood distribution monitoring results can be obtained using the proposed new method. The results were evaluated using MODIS (Moderate Resolution Imaging Spectroradiometer) images and compared with the observations of SMAP (Soil Moisture Active Passive) and GPM (Global Precipitation Measurement) in the same period. The results show that the flooded areas obtained by CYGNSS correspond to the inundated areas in MODIS images and are also in high agreement with the SMAP. In addition, CYGNSS allows for finer mapping and quantification of inundation areas and flood duration. Moreover, we also discussed the potential of CYGNSS to detect floods in shorter periods of time (a few hours) and did a preliminary evaluation using precipitation data from meteorological stations. The results are also highly consistent.     

卫星遥感图像信息作为姿态敏感器的应用研究

陆标敏感器可以从卫星遥感图像信息中提取卫星的姿态信息,它根据卫星实时图像与基准图像之间的偏移量,计算出卫星的姿态。对陆标敏感器的总体方案进行了设计,在图像匹配技术中采用基于区域特征的先粗匹配、后精匹配的匹配算法,在姿态确定算法中对可能达到的姿态测量精度进行了理论分析,研究表明陆标敏感器可以获得较高精度的卫星姿态信息,作为新型光学姿态敏感器具有重要的研究意义。     

基于高分四号数据的多时相多通道云检测算法

针对高分四号（GF-4）卫星影像波段较少导致传统云检测算法难以区分云与冰雪像元的问题,提出一种多时相多通道云检测算法。该算法首先对GF-4卫星影像进行辐射定标和配准,然后利用云与典型地表的光谱差异得到潜在云像元,之后利用序列GF-4卫星影像之间的差异识别出移动的云像元,最后利用中红外波段反演地表亮度温度来去除冰雪像元。该算法在海南、辽宁和安徽3个研究区域进行验证,并将检测结果与传统单时相云检测算法、支持向量机（SVM）云检测算法和实时差分（RTD）云检测算法的检测结果进行对比。结果表明,该算法优于其他3种云检测算法,准确识别率均达到90%以上,误检率均低于5%,有利于GF-4卫星影像的进一步利用。     

Landsat image data quality studies

The July 1982 launch of Landsat-4 was immediately followed by a two-year comprehensive set of detailed investigations sponsored by the National Aeronautics and Space Administration (NASA) at Goddard Space Flight Center (GSFC). The Landsat Image Data Quality Analysis (LIDQA) research plans for these investigations were specified prior to launch, so that minimum time would be lost in assessing the performance of the long-awaited Thematic Mapper (TM) sensor that Landsat-4 carried in addition to a fourth Multispectral Scanner (MSS). The LIDQA investigations have been substantially completed, and have shown that the TM is a very good spaceborne multispectral radiometer, and has met or exceeded most of its design goals. TM's new short-wave infrared (SWIR) spectral capability yielded improved mineral and plant discrimination compared to the MSS, as anticipated by ground-based and airborne TM simulations. Moreover, the improved spatial resolution and geometric accuracy of Landsat-4 and the TM have resulted in satellite image maps exceeding 1:100,000 U.S. map accuracy standards. Finally, based on an information entropy measure, principal component analysis, and classification results, TM data has been shown to approach its theoretical limit in information content per pixel, exceeding the MSS by at least a factor of two.     

基于混合网络的异源遥感图像变化检测

为了更加准确地进行异源遥感图像的变化检测任务,提出了一种基于混合网络的异源遥感图像变化检测算法。利用伪孪生网络提取异源遥感图像块间空间维度的变化特征,利用早期融合网络提取异源遥感图像块间光谱维度的变化特征,将2支网络提取的特征进行融合,并将融合后的变化特征输入到sigmoid层进行二分类检测。同时,在伪孪生网络中加入对比损失函数,通过优化对比损失函数,使得在特征空间中,未变化图像对的空间特征差异更小,变化图像对的空间特征差异更大,以提升网络的区分能力和收敛速度。