Effect of remote sensing spatial resolution on interpreting tower-based flux observations

Validation comparisons between satellite-based surface energy balance models and tower-based flux measurements over heterogeneous landscapes can be strongly influenced by the spatial resolution of the remote sensing inputs. In this paper, a two-source energy balance model developed to use thermal and visible /near-infrared remotely sensed data is applied to Landsat imagery collected during the 2004 Soil Moisture Experiment (SMEX04) conducted in southern Arizona. Using a two dimensional flux-footprint algorithm, modeled surface fluxes are compared to tower measurements at three locations in the SMEX04 study area: two upland sites, and one riparian site. The effect of pixel resolution on evaluating the performance of the land surface model and interpreting spatial variations of land surface fluxes over these heterogeneous areas is evaluated. Three Landsat scenes were examined, one representing the dry season and the other two representing the relatively wet monsoon season. The model was run at three resolution scales: namely the Landsat visible/near-infrared band resolution (30 m), the Landsat 5 thermal band resolution (120 m), and 960 m, which is nominally the MODIS thermal resolution at near-nadir. Comparisons between modeled and measured fluxes at the three tower sites showed good agreement at the 30 m and 120 m resolutions — pixel scales at which the source area influencing the tower measurement (∼ 100 m) is reasonably resolved. At 960 m, the agreement is relatively poor, especially for the latent heat flux, due to sub-pixel heterogeneity in land surface conditions at scales exceeding the tower footprint. Therefore in this particular landscape, thermal data at 1-km resolution are not useful in assessing the intrinsic accuracy of the land-surface model in comparison with tower fluxes. Furthermore, important spatial patterns in the landscape are lost at this resolution. Currently, there are no definite plans supporting high resolution thermal data with regular global coverage below ∼ 700 m after Landsat 5 and ASTER fail. This will be a serious problem for the application and validation of thermal-based land-surface models over heterogeneous landscapes.     

面向遥感影像的深度语义哈希检索

目的 哈希检索旨在将海量数据空间中的高维数据映射为紧凑的二进制哈希码,并通过位运算和异或运算快速计算任意两个二进制哈希码之间的汉明距离,从而能够在保持相似性的条件下,有效实现对大数据保持相似性的检索。但是,遥感影像数据除了具有影像特征之外,还具有丰富的语义信息,传统哈希提取影像特征并生成哈希码的方法不能有效利用遥感影像包含的语义信息,从而限制了遥感影像检索的精度。针对遥感影像中的语义信息,提出了一种基于深度语义哈希的遥感影像检索方法。方法 首先在具有多语义标签的遥感影像数据训练集的基础上,利用两个不同配置参数的深度卷积网络分别提取遥感影像的影像特征和语义特征,然后利用后向传播算法针对提取的两类特征学习出深度网络中的各项参数并生成遥感影像的二进制哈希码。生成的二进制哈希码之间能够有效保持原始高维遥感影像的相似性。结果 在高分二号与谷歌地球遥感影像数据集、CIFAR-10数据集及FLICKR-25K数据集上进行实验,并与多种方法进行比较和分析。当编码位数为64时,相对于DPSH（deep supervised Hashing with pairwise labels）方法,在高分二号与谷歌地球遥感影像数据集、CIFAR-10数据集、FLICKR-25K数据集上,mAP（mean average precision）指标分别提高了约2%、6%7%、0.6%。结论 本文提出的端对端的深度学习框架,对于带有一个或多个语义标签的遥感影像,能够利用语义特征有效提高对数据集的检索性能。     

一种新的遥感图像机密信息隐藏算法

为了防止遥感图像包含的机密信息被泄露,将基于样本的图像修补方法用于遥感图像机密信息隐藏。该方法从遥感图像中选择与机密信息图像块最大相似区域,覆盖机密信息块,从而达到机密信息隐藏的目的。该方法不仅具有很强的不觉察性,而且对于遥感图像的使用价值影响较小。结合数字水印技术,实现了根据用户权限来决定用户能否看到隐藏的机密信息,从而方便了遥感图像的使用。仿真实验结果表明,该方法是可行的,能够提高遥感图像使用的安全性。     

一种基于深度学习的遥感图像目标检测算法

遥感图像分析在国土资源管理、海洋监测等领域有着极为广阔的应用前景。深度学习技术已在图像处理领域取得突破性进展,然而,遥感图像固有的尺寸大、目标小而密集等特点,使得将面向普通图像的深度学习方法用于遥感目标检测普遍存在定位不准确、小目标检测难、大图检测精度差等问题。针对上述难题, 提出了一种新型遥感图像目标检测算法DFS。与传统机器学习方法相比,DFS 设计了新的维度聚类模块、定制损失函数和滑动窗口分割检测机制。其中,维度聚类模块通过设计聚类机制优化定制先验框,提高定位精度;定制损失函数提高对船只等小目标的检测精度;滑动窗口分割检测解决大图检测精度低的问题。在经典遥感数据集上开展的实验对比表明,与YOLOv2相比,DFS算法的mAP提高了256%,小目标检测效率及大图检测效能大幅提高。     

参数合成空间变换网络的遥感图像一致性配准

目的 遥感图像配准是对多组图像进行匹配和叠加的过程。该技术在地物检测、航空图像分类和卫星图像融合等方面发挥着重要作用，主要有传统方法和基于深度学习的方法。其中，传统遥感图像配准算法在进行配准时会耗费大量人力，并且运行时间过长。而基于深度学习的遥感图像配准算法虽然减少了人工成本，提高了模型自适应学习的能力，但是算法的配准精度和运行时间仍有待提高。针对基于深度学习的配准算法存在的问题，本文提出了参数合成的空间变换网络对遥感图像进行双向一致性配准。方法 通过增加空间变换网络的深度、合成网络内部的参数对空间变换模型进行改进，并将改进后的模型作为特征提取部分的骨干网络，有效地提高网络的鲁棒性。同时，将单向配准方法改为双向配准方法，进行双向的特征匹配和特征回归，保证配准方向的一致性。然后将回归得到的双向参数加权合成，提高模型的可靠性和准确性。结果 将本文实验结果与两种经典的传统方法SIFT（scale-invariant feature transform）、SURF（speeded up robust features）对比，同时与近3年提出的CNNGeo（convolutional neural network architecture for geometric matching）、CNN-Registration（multi-temporal remote sensing image registration）和RMNet（robust matching network）3种最新的方法对比，配准结果表明本文方法不仅在定性的视觉效果上较为优异，而且在定量的评估指标上也有不错的效果。在Aerial Image Dataset数据集上，本文使用"关键点正确评估比例"与以上5种方法对比，精度分别提高了36.2%、75.9%、53.6%、29.9%和1.7%；配准时间分别降低了9.24 s、7.16 s、48.29 s、1.06 s和4.06 s。结论 本文所提出的配准方法适用于时间差异变化（多时相）、视角差异（多视角）与拍摄传感器不同（多模态）的3种类型的遥感图像配准应用。在这3种类型的配准应用下，本文算法具有较高的配准精度和配准效率。     

Accelerated genetic algorithm based on search-space decomposition for change detection in remote sensing images

Detecting change areas among two or more remote sensing images is a key technique in remote sensing. It usually consists of generating and analyzing a difference image thus to produce a change map. Analyzing the difference image to obtain the change map is essentially a binary classification problem, and can be solved by optimization algorithms. This paper proposes an accelerated genetic algorithm based on search-space decomposition (SD-aGA) for change detection in remote sensing images. Firstly, the BM3D algorithm is used to preprocess the remote sensing image to enhance useful information and suppress noises. The difference image is then obtained using the logarithmic ratio method. Secondly, after saliency detection, fuzzy c-means algorithm is conducted on the salient region detected in the difference image to identify the changed, unchanged and undetermined pixels. Only those undetermined pixels are considered by the optimization algorithm, which reduces the search space significantly. Inspired by the idea of the divide-and-conquer strategy, the difference image is decomposed into sub-blocks with a method similar to down-sampling, where only those undetermined pixels are analyzed and optimized by SD-aGA in parallel. The category labels of the undetermined pixels in each sub-block are optimized according to an improved objective function with neighborhood information. Finally the decision results of the category labels of all the pixels in the sub-blocks are remapped to their original positions in the difference image and then merged globally. Decision fusion is conducted on each pixel based on the decision results in the local neighborhood to produce the final change map. The proposed method is tested on six diverse remote sensing image benchmark datasets and compared against six state-of-the-art methods. Segmentations on the synthetic image and natural image corrupted by different noise are also carried out for comparison. Results demonstrate the excellent performance of the proposed SD-aGA on handling noises and detecting the changed areas accurately. In particular, compared with the traditional genetic algorithm, SD-aGA can obtain a much higher degree of detection accuracy with much less computational time.     

基于小波域压缩感知的遥感图像超分辨算法

针对单字典表达复杂多样的图像纹理存在一定的局限性的问题,利用压缩感知和小波理论建立了一种多字典遥感图像超分辨算法。首先,对训练图像在小波域的不同频带利用K-奇异值分解（K-SVD）算法建立不同的字典;然后,利用全局限制求取高分辨率图像的初始解;最后,利用正交匹配追踪算法（OMP）对初始解在小波域进行多字典稀疏求解。实验结果表明,相比基于单字典的超分辨重建算法,结果图像的主观视觉效果有很大提高,客观评价指标的峰值信噪比（PSNR）和结构相似度（SSIM）分别提高2.8 dB以上和0.01以上。字典可一次建立重复使用,降低了运算时间。     

基于图像类推的遥感图像超分辨率技术

由于卫星上相机距离拍摄景物较远,所以遥感图像分辨率一般较低。为了获得较高分辨率的图像。提出将图像类推技术(IA)与立方卷积插值法相结合的方法;并在学习样本集合建立过程中引入一种新的思路,直接对高分辨率图像的高频细节信息进行学习。实验结果表明,该方法不仅提高了放大图像的清晰程度,而且较一般的图像类推算法,能产生更为合理的细节以增强图像,使放大后的遥感图像更为逼真。     

遥感图像Contourlet变换域压缩融合

基于传统分块压缩感知(BCS)的图像融合中,由于空间域BCS采样缺乏考虑图像的全局特性,导致融合图像重构质量差,且存在分块效应。首先将输入图像在Contourlet变换(CT)域稀疏表示,并对CT分解系数进行分块压缩感知;再对压缩采样线性加权融合;最后用迭代阈值投影(ITP)方法重构融合图像,并消除分块效应。提出了基于Contourlet变换域分块压缩感知(CTBCS)的遥感图像压缩融合方法,并给出算法的详细实现流程。基于BCS和CTBCS进行压缩采样,再用ITP算法进行图像重构,仿真结果显示,与BCS相比,CTBCS采样有效考虑了图像的全局特性,基于CTBCS的ITP重构收敛速度更快,重构计算复杂度更小,重构精度更好,对应的重构图像峰值信噪比(PSNR)更高;实际资料测试结果表明,基于CTBCS的压缩融合效果比基于BCS的压缩融合效果更好,更接近常规CT融合效果。CTBCS压缩融合用较少量采样点获得与常规CT相比拟的融合结果,有效实现了大数据量遥感图像的压缩融合。     

遥感图像变化区域的无监督压缩感知

传统的基于结构特征的遥感图像变化检测方法,易受成像稳定性的影响而误差很大。针对图像内在的稀疏性结构信息,提出基于压缩感知(CS)的遥感图像变化检测方法。通过自适应构造超完备字典将图像局部信息投影到高维空间中,实现图像的稀疏表示,并运用随机矩阵得到了数据在高维空间中的低维特征子空间。最后利用模糊C均值(FCM)聚类算法进行无监督聚类,实现遥感图像变化区域信息的重构。实验结果表明,本文方法不仅能够很好的检测出图像的轮廓变化和图像的区域变化,而且对噪声具有很好的鲁棒性。     

Mapping lake CDOM by satellite remote sensing

Given the importance of coloured dissolved organic matter (CDOM) for the structure and function of lake ecosystems, a method to estimate the amount of CDOM in lake waters over large geographic areas would be highly desirable. Advanced Land Imager (ALI) images were acquired in southern Finland (in 2002) and southern Sweden (in 2003) together with in situ measurements of bio-optical properties of 34 lakes (39 measuring stations). Based on this dataset, a band-ratio type algorithm was developed using ALI band 2 and band 3 for estimating CDOM content (absorption of filtrated water at 420 nm) in lakes. Correlation between in situ measured CDOM and the remote sensing estimate of CDOM was high, r²=0.73. The CDOM retrieval algorithm obtained on the basis of two images and in situ data was validated on a third ALI image (eastern Finland, 2002) that was available in the ALI image archive. In situ water-colour monitoring data from 22 lakes (27 measuring stations) in the third image were available in a database of the Finnish Environment Administration. The water-colour data were converted to CDOM absorption values, which were then compared to the results from a third ALI image. The correlation between remotely estimated and in situ CDOM values in the algorithm validation image was high, r²=0.83. These results support the conclusion that CDOM content in lakes over a wide range of concentrations (a_CDOM(420) between 0.68 and 11.13 m⁻¹) can be mapped using Advanced Land Imager data.     

基于Contourlet域的遥感图像超分辨率复原技术

通过Contourlet域对遥感图像进行超分辨复原,采用了具有的更好方向性和各向异性特点的Contourlet系数作为特征表示,并通过最小欧氏距离进行全局的匹配选择。根据匹配的高频细节信息分布特点,引入了隐马尔可夫树（HMT）模型对遥感图像的Contourlet系数建模,运用期望最大（EM）算法对其进行参数估计,并结合贝叶斯估计原理,对叠加后的Contourlet系数进行修复、反变换后,最终完成了对低分辨率遥感图像的超分辨率复原。     

Analysis of classification accuracy for pre-filtered multichannel remote sensing data

Noise is one of the main factors degrading the quality of original multichannel remote sensing data and its presence influences classification efficiency, object detection, etc. Thus, pre-filtering is often used to remove noise and improve the solving of final tasks of multichannel remote sensing. Recent studies indicate that a classical model of additive noise is not adequate enough for images formed by modern multichannel sensors operating in visible and infrared bands. However, this fact is often ignored by researchers designing noise removal methods and algorithms. Because of this, we focus on the classification of multichannel remote sensing images in the case of signal-dependent noise present in component images. Three approaches to filtering of multichannel images for the considered noise model are analysed, all based on discrete cosine transform in blocks. The study is carried out not only in terms of conventional efficiency metrics used in filtering (MSE) but also in terms of multichannel data classification accuracy (probability of correct classification, confusion matrix). The proposed classification system combines the pre-processing stage where a DCT-based filter processes the blocks of the multichannel remote sensing image and the classification stage. Two modern classifiers are employed, radial basis function neural network and support vector machines. Simulations are carried out for three-channel image of Landsat TM sensor. Different cases of learning are considered: using noise-free samples of the test multichannel image, the noisy multichannel image and the pre-filtered one. It is shown that the use of the pre-filtered image for training produces better classification in comparison to the case of learning for the noisy image. It is demonstrated that the best results for both groups of quantitative criteria are provided if a proposed 3D discrete cosine transform filter equipped by variance stabilizing transform is applied. The classification results obtained for data pre-filtered in different ways are in agreement for both considered classifiers. Comparison of classifier performance is carried out as well. The radial basis neural network classifier is less sensitive to noise in original images, but after pre-filtering the performance of both classifiers is approximately the same.     

遥感图像道路提取方法综述

道路信息在现代社会中扮演着重要的角色,研究遥感图像的道路提取方法具有重要科学意义。回顾了道路提取方法的发展历程,按实现形式的不同,将已有道路提取方法分为基于像元、面向对象、深度学习三大类,并以此为线索,分析比较各类方法的适用范围与优缺点。设计实验,以多幅高分辨率卫星遥感图像为实验对象,验证对比各类典型道路提取方法的实际性能,实验结果表明,基于深度学习的道路提取方法效果最佳。最后,结合当下热门的遥感大数据与人工智能相关理论,展望了未来遥感图像道路提取方法的发展趋势。     

高分辨率遥感影像空间结构特征建模方法综述

高分辨率遥感影像能够提供详细的地面信息,具有复杂的空间结构特征。有效地描述和建模这种结构特征对实现影像解译、目标识别与提取以及场景理解等具有重要的作用。首先介绍了高分影像结构特征的概念和内涵,将结构特征划分为像元结构、目标结构和场景结构3个层次;然后对高分影像结构特征描述与建模方法进行了系统的综述,介绍了这些方法的基本思想、分析了其研究现状,并指出了存在的一些问题;最后给出了总结和展望。     

云环境下基于秘密共享的海洋遥感影像认证方案

云存储模式的出现为海量海洋遥感影像的存储和管理带来了机遇,越来越多的用户选择将海洋遥感影像数据移植到云中,但云存储环境的开放性对海洋遥感影像数据的安全性提出了挑战。以保障云环境下海洋遥感敏感数据的安全性为前提,提出一种影像认证方案,将哈希函数与(k,n)门限秘密共享方法相结合,检测敏感区影像信息变化,并对加密前和恢复后的影像进行一致性验证,保护加密影像数据的机密性。同时,为避免n个子秘密中,因多于n-k个子秘密的篡改或丢失,造成敏感区影像不可恢复情况的发生,采用对敏感区影像进行分块的策略,对每个子影像块做进一步的秘密共享处理,以保证部分影像的无损恢复。实验对比分析表明,所提出的安全认证方案可以有效防止秘密恢复过程中的欺诈行为,同时可获得比传统方法更高的遥感影像云存储安全性。     

VDM-RS: A visual data mining system for exploring and classifying remotely sensed images

Remotely sensed imagery has become increasingly important in several applications domains, such as environmental monitoring, change detection, fire risk mapping and land use, to name only a few. Several advanced image classification techniques have been developed to analyze such imagery and in particular to improve the accuracy of classifying images in the context of such applications. However, most of the proposed classifiers remain a black box to users, leaving them with little to no means to explore and thus further improve the classification process, in particular for misclassified pixel samples. In this paper, we present the concepts, design and implementation of VDM-RS, a visual data mining system for classifying remotely sensed images and exploring image classification processes. The system provides users with two classes of components. First, visual components are offered that are specific to classifying remotely sensed images and provide traditional interfaces, such as a map view and an error matrix view. Second, the decision tree classifier view provides users with the functionality to trace and explore the classification process of individual pixel samples. This feature allows users to inspect how a sample has been correctly classified using the classifier, but more importantly, it also allows for a detailed exploration of the steps in which a sample has been misclassified. The integration of these features into a coherent, user-friendly system not only helps users in getting more insights into the data, but also to better understand and subsequently improve a classifier for remotely sensed images. We demonstrate the functionality of the system's components and their interaction for classifying imagery using a hyperspectral image dataset.     

加强类别关系的农作物遥感图像语义分割

目的 遥感图像处理技术在农作物规划、植被检测以及农用地监测等方面具有重要的作用。然而农作物遥感图像上存在类别不平衡的问题,部分样本中农作物类间相似度高、类内差异性大,使得农作物遥感图像的语义分割更具挑战性。为了解决这些问题,提出一种融合不同尺度类别关系的农作物遥感图像语义分割网络CRNet(class relation network)。方法 该网络将ResNet-34作为编码器的主干网络提取图像特征,并采用特征金字塔结构融合高阶语义特征和低阶空间信息,增强网络对图像细节的处理能力。引入类别关系模块获取不同尺度的类别关系,利用一种新的类别特征加强注意力机制(class feature enhancement, CFE)结合通道注意力和加强位置信息的空间注意力,使得农作物类间的语义差异和农作物类内的相关性增大。在解码器中,将不同尺度的类别关系融合,增强了网络对不同尺度农作物特征的识别能力,从而提高了对农作物边界分割的精度。通过数据预处理、数据增强和类别平衡损失函数(class-balanced loss, CB loss)进一步缓解了农作物遥感图像中类别不平衡的问题。结果 在Barley...