多源遥感图像融合发展现状与未来展望

近年来,随着遥感技术的发展,高光谱、红外、雷达等多源遥感成像手段在精准农业、资源调查、环境监测、军事国防等重要领域发挥着越来越重要的作用。同一场景多源遥感图像观测的地物对象相同,但观测的维度不同,图像的空间、光谱与时间分辨率存在差异,提供的信息既具有冗余性,又具有互补性和合作性。多源遥感图像融合能够综合利用不同来源获取的遥感图像信息,实现更精准、更全面的对地观测,是遥感对地观测领域的核心关键技术。本文从多源遥感图像的数据来源出发,综述了多源遥感图像融合的研究现状与未来发展趋势:首先介绍了国内外现有多源遥感图像的主要来源、图像特性与典型应用;然后,对不同类型多源遥感图像融合的研究现状和挑战性难题进行了归纳和总结;最后,对多源遥感图像融合的未来发展趋势进行了展望。     

A Novel Remote Sensing Image Classification Scheme Based on Data Fusion, Multiple Features and Ensemble Learning

In this paper, we propose a novel scheme to improve the accuracy of remote sensing image classification by integrating data fusion, multiple feature combination and ensemble learning. Intensity-Hue-Saturation (IHS), Gram-Schmidt (GS), Brovey and wavelet fusion methods are first performed to obtain the optimal fusion images of high resolution and multispectral images. Support Vector Machine (SVM) classifier is then adopted to classify the fused image with different feature sets, and ensemble learning algorithm based on dynamic classifier selection (DCS) is finally used to integrate multiple classification maps. The proposed classification scheme is implemented with three remote sensing data sets, obtaining the highest overall accuracy and kappa coefficient in all cases (92.63% and 0.8917 for BJ-1 data set, 81.89% and 0.7513 for Landsat TM and SPOT4 data set, 92.21% and 0.8838 for ALOS data set respectively). The experimental results show that the integration of data fusion, feature combination and ensemble learning improves the classification performance obviously and has great potential in practical uses.     

Mapping natural and urban environments using airborne multi-sensor ADS40–MIVIS–LiDAR synergies

The recent and forthcoming availability of high spatial resolution imagery from satellite and airborne sensors offers the possibility to generate an increasing number of remote sensing products and opens new promising opportunities for multi-sensor classification. Data fusion strategies, applied to modern airborne Earth observation systems, including hyperspectral MIVIS, color-infrared ADS40, and LiDAR sensors, are explored in this paper for fine-scale mapping of heterogeneous urban/rural landscapes. An over 1000-element array of supervised classification results is generated by varying the underlying classification algorithm (Maximum Likelihood/Spectral Angle Mapper/Spectral Information Divergence), the remote sensing data stack (different multi-sensor data combination), and the set of hyperspectral channels used for classification (feature selection). The analysis focuses on the identification of the best performing data fusion configuration and investigates sensor-derived marginal improvements. Numerical experiments, performed on a 20-km stretch of the Marecchia River (Italy), allow for a quantification of the synergies of multi-sensor airborne data. The use of Maximum Likelihood and of the feature space including ADS40, LiDAR derived normalized digital surface, texture layers, and 24 MIVIS bands represents the scheme that maximizes the classification accuracy on the test set. The best classification provides high accuracy (92.57% overall accuracy) and demonstrates the potential of the proposed approach to define the optimized data fusion and to capture the high spatial variability of natural and human-dominated environments. Significant inter-class differences in the identification schemes are also found by indicating possible sub-optimal solutions for landscape-driven mapping, such as mixed forest, floodplain, urban, and agricultural zones.     

基于支持向量机的SPIN－2影像与SPOT－4多光谱影像融合研究

遥感影像融合是解决多源海量数据富集表示的有效途径之一。针对高分辨率遥感数据SPIN-2(2m)与多光谱遥感数据SPOT-4(20m)的影像融合，提出了基于支持向量机(SVM)的遥感影像融合的新方法。建立了基于SVM的遥感影像融合模型，并进行了分类融合实验，实验效果较好。最后给出了分类融合评价。结果表明，支持向量机可用于遥感影像融合，且分类融合精度较高。     

结合灰度和基于动态窗口的纹理特征的遥感影像分类

在基于灰度共生矩阵提取遥感影像纹理特征的基础上,针对固定窗口算法的局限性,提出了动态窗口算法;并将不同滑动窗口算法提取的纹理特征与影像灰度组合进行支持向量机(SVM)分类,对分类结果进行定性和定量比较分析。实验结果表明:影像灰度结合动态窗口算法提取的纹理特征进行SVM分类的分类精度优于灰度结合固定窗口算法提取的纹理特征的分类精度。因此,提出的算法较传统的固定窗口算法更具优势,是一种有效纹理信息提取方法。     

遥感影像决策级融合方法实验研究

遥感影像融合是遥感图像处理中的研究热点和难点之一。对下列两种遥感影像决策级融合方法进行了实验研究:一种是基于支持向量机(SVM),另一种是基于自组织神经网络。融合实验分别采用这两种方法对Landsat TM多光谱数据(30 m/像素)与IRS-C全色数据(5.8 m/像素)间分别进行影像融合。融合结果表明:基于SVM的方法可有效地融合不同影像的信息,并且可获得较高的融合分类精度。在分类精度方面,基于SVM方法的融合影像明显优于基于自组织神经网络方法的融合影像。     

全球高分辨率数字高程模型研究进展与展望

简要介绍了数字高程模型（digital elevation model,DEM）的起源与定义,根据4种不同的观测平台分类介绍了DEM数据获取方法,给出目前国际上发布的高分辨率全球DEM的主要性质和特点。重点介绍了9大类全球DEM,分析了DEM质量评估相关的评定方法和精度指标。论述了DEM在地质灾害监测、海岸带脆弱性分析方面的应用,以美国地质勘探局和德国航空太空中心正在开展的DEM项目为例,讨论了高精度、高分辨率全球同质DEM和地形测深高程模型的最新需求,最后总结展望全球高分辨率DEM的发展趋势。     

高光谱-LiDAR多级融合城区地表覆盖分类

城市地区地表覆盖分类在城市研究中是一个十分重要的方向。遥感作为获取地物物理属性的一种重要技术手段,已初步应用于分类研究中。然而,随着城镇化的不断推进,城市内部地物类型越来越复杂,单一的遥感影像已无法满足城区地表覆盖分类中高精度的要求。高光谱影像和LiDAR数据能够分别表征地物的光谱信息及高程而被广泛应用。因此,根据两者之间互补的优势,本文提出了基于高光谱影像和LiDAR数据多级融合的城区地表覆盖分类方法。首先对两幅影像分别进行特征提取,将提取到的光谱、空间及高程信息进行层叠实现特征级融合。对得到的特征影像的所有像素点进行分类,然后利用LiDAR点云数据提取的建筑物掩膜,对非建筑物部分进行分类,再次实现特征级融合,以此改善建筑物区域与非建筑物区域的混淆。然后将未使用掩膜得到的分类结果与利用掩膜得到的分类结果进行投票实现决策级融合。最后利用条件随机场模型对分类结果进行后处理操作,达到平滑图像去除噪声点的目的。     

土地覆盖制图：基于最优化遥感数据的支撑向量机分类

遥感数据具有在不同空间、光谱和时间尺度上获取地表测量信息的能力,使其成为获取土地覆盖信息的一个主要数据源。影像分类即把卫星影像上的相关像元划分给某类已知的土地覆盖类型的过程。支撑向量机（SVMs）是一种土地覆盖分类的新技术。三种常用的SVMs是：基于线性和多项式的SVM以及具有高斯核函数的SVM分类器,分类能否成功地应用有赖于其各自选择的最佳参数。但是海量的遥感数据使得这些参数的确定速度十分缓慢。本文研究了一种新的基于最优化遥感数据压缩技术的SVM分类方法。研究显示用于获取SVM参数的数据量能够在不影响土地覆盖的分类精度的前提下进行压缩。数据压缩成功的应用于多项式和高斯核函数的SVM分类,而线性SVM的分类精度却非常低。     

Discrimination and classification of mangrove forests using EO-1 Hyperion data: a case study of Indian Sundarbans

In remote sensing the identification accuracy of mangroves is greatly influenced by terrestrial vegetation. This paper deals with the use of specific vegetation indices for extracting mangrove forests using Earth Observing-1 Hyperion image over a portion of Indian Sundarbans, followed by classification of mangroves into floristic composition classes. Five vegetation indices (three new and two published), namely Mangrove Probability Vegetation Index, Normalized Difference Wetland Vegetation Index, Shortwave Infrared Absorption Index, Normalized Difference Infrared Index and Atmospherically Corrected Vegetation Index were used in decision tree algorithm to develop the mangrove mask. Then, three full-pixel classifiers, namely Minimum Distance, Spectral Angle Mapper and Support Vector Machine (SVM) were evaluated on the data within the mask. SVM performed better than the other two classifiers with an overall precision of 99.08%. The methodology presented here may be applied in different mangrove areas for producing community zonation maps at finer levels.     

利用SVM的全极化、双极化与单极化SAR图像分类性能的比较

支持向量机(SVM)以其在小训练样本时良好的分类性能,目前已广泛应用于多个领域.本文在极化SAR图像特征提取基础上,将SVM应用于极化SAR图像分类,定性和定量地比较了全极化、双极化和单极化SAR图像的分类性能,分析了不同的极化组合对分类结果的影响,并根据地物极化散射特性分析了分类精度差异的成因.实测极化SAR数据的实验结果表明,全极化数据能获得最好的分类性能,双极化次之,单极化最低,且在某些情况下,双极化与全极化分类性能接近.     

高光谱和LiDAR联合反演森林生物量研究

估算森林地上生物量(AGB)对于全球实现碳中和目标至关重要。本文以美国缅因州Howland森林为研究区域,借助地面实测样地数据,对比分析协同不同数据源(高光谱和LiDAR)和机器学习算法(随机森林、支持向量机、梯度提升决策树和K最邻近回归)的研究,以改善Howland森林的生物量估计精度。结果表明,采用LiDAR和高光谱植被指数变量模型的最佳精度分别为0.874和0.868,协同高光谱和LiDAR变量并采用梯度提升决策树回归模型的精度为0.927,即多源遥感数据要优于单一数据源。高光谱和LiDAR数据的协同使用对于提高类似于Howland地区或更广泛区域的生物量估计的准确性,具有普遍的适用性与一定的应用前景。     

Optimizing support vector machine learning for semi-arid vegetation mapping by using clustering analysis

In remote sensing communities, support vector machine (SVM) learning has recently received increasing attention. SVM learning usually requires large memory and enormous amounts of computation time on large training sets. According to SVM algorithms, the SVM classification decision function is fully determined by support vectors, which compose a subset of the training sets. In this regard, a solution to optimize SVM learning is to efficiently reduce training sets. In this paper, a data reduction method based on agglomerative hierarchical clustering is proposed to obtain smaller training sets for SVM learning. Using a multiple angle remote sensing dataset of a semi-arid region, the effectiveness of the proposed method is evaluated by classification experiments with a series of reduced training sets. The experiments show that there is no loss of SVM accuracy when the original training set is reduced to 34% using the proposed approach. Maximum likelihood classification (MLC) also is applied on the reduced training sets. The results show that MLC can also maintain the classification accuracy. This implies that the most informative data instances can be retained by this approach.     

Research on SAR data integrated processing methodology oriented on earth environment factor inversions

ABSTRACT

As an important advanced technique in the field of Earth observations, Synthetic Aperture Radar (SAR) plays a key role in the study of global environmental change, resources exploration, disaster mitigation, urban environments, and even lunar exploration. However, studies on imaging, image processing, and Earth factor inversions have often been conducted independently for a long time, which significantly limits the application effectiveness of SAR remote sensing due to the lack of an overall integrated design scheme and integrated information processing. Focusing on this SAR application issue, this paper proposes and describes a new SAR data processing methodology – SAR data integrated processing (DIP) oriented on Earth environment factor inversions. The simple definition, typical integrated modes and overall implementation ideas are introduced. Finally, focusing on building information extraction (man-made targets) and sea ice classification (natural targets) applications, three SAR DIP methods and experiments are conducted. Improved results are obtained under the guidance of the SAR DIP framework. Therefore, the SAR DIP theoretical framework and methodology represent a new SAR science application mode that has the capability to improve the SAR remote sensing quantitative application level and promote the development of new theories and methodologies.     

多源遥感影像像素级融合分类与决策级分类融合法的研究

首先探讨了基于像素的多源遥感影像高频调制融合法，根据成像系统特性和Heisenberg测不准原理，设计的高斯滤波器对高分辨率影像滤波的方法是合理有效的。在研究BP神经网络的基础上，采用动量法和学习率自适应调整的策略，提高了BP神经网络学习算法收敛速度，并增强了算法的可靠性。提出并实现了多源遥感影像像素级融合分类与决策级分类融合两种分类方法，并进行了比较。采用Landsat TM3，4，5和航空SAR影像进行试验，结果表明两种分类方法是行之有效的，均适用于多源遥感影像分类。     

机载LiDAR数据和航空影像基于角特征的配准

机载激光雷达(Light Detection And Ranging,LiDAR)系统近年来逐渐成为一种新兴的测量手段,是一种可以直接提供大量地面离散点的高精度三维信息的主动式遥感技术,具有依赖控制测量条件少、受天气影响小、自动化水平高等优点。然而LiDAR获取的数据主要是离散激光点云,具有高精度的空间结构信息而缺少纹理和光谱信息。将LiDAR数据和遥感影像数据进行融合将是当今测绘科学研究的方向之一。融合影像数据和点云数据的关键步骤就是将两者进行高精度的配准。     

NWFE结合纹理特征的SVM土地覆被分类方法研究

为提高土地覆被分类精度,采用非参数权重特征提取(nonparametric weighted feature extraction,NWFE)结合纹理特征的支持向量机(support vector machines,SVM)的分类法,对新疆玛纳斯河流域绿洲区2006年的土地覆被进行分类,并将该方法与主成分分析(principal component analysis,PCA)结合纹理特征的SVM分类、原始波段结合纹理特征的SVM分类进行对比。结果表明,NWFE结合纹理特征的SVM分类结果优于其他2种分类结果,不仅反映了土地覆被分布的整体情况,而且使不同土地覆被类型得到较好的区分,总体分类精度达89.17%。     

面向地震应急调查的遥感应用现状及趋势分析

地震是一种会造成人类生命财产重大损失的突发性自然灾害,震后第一时间启动应急响应并开展灾情的快速评估能有效地减轻地震灾害带来的破坏。空间对地观测技术为宏观性的地震应急与调查工作提供了便捷、经济的途径,随着空间对地观测技术与数据处理技术的不断发展,各国学者对遥感应急调查开展了大量深入的研究工作,相关研究成果已广泛地应用于地震应急的实际工作中。但是,遥感数据类型与处理技术的多样化也带来了应急信息的散乱,导致遥感快速应急响应系统性不强,使得应急服务不持续,一定程度上限制了遥感技术的效能;为此,针对现阶段遥感技术在地震应急调查中的应用情况,在总结地震应急调查常用遥感技术手段的基础上,分析了遥感快速应急响应面临的技术挑战,重点梳理了地震应急不同阶段对遥感数据及应急专题产品产出类型与时效性的现实需求,结合震后灾区影像数据的情况,系统地分析了光学、雷达、激光雷达遥感技术在地震应急调查应用中的技术现状与存在的问题。在实际地震应用案例分析的基础,总结剖析遥感应急工作存在的问题,并重点从海量数据快速处理、震害信息智能化提取、多源数据协同分析3个技术层面论述了遥感地震应急面临的核心困难,基于此,结合在轨数据实时、海量数据快速处理就灾情智能化识别的多技术联合、多源数据协同分析、发展敏捷卫星等几个方面论述了未来遥感技术在防震减灾中的发展趋势,以期推动遥感监测手段提供动态、实时、持续的空间信息应急服务能力,提高地震应急工作的快速响应、精细化与业务化应用能力。本文的研究可以为多源遥感技术在地震应急调查中的科研及业务应用提供很好的参考,更高效的发挥遥感技术在防震减灾工作中的应用能力与水平。     

Boosting和Bagging算法的高分辨率遥感影像分类探讨

多分类器集成能够有效地提高遥感分类精度、降低结果中的不确定性,基于样本操作的Boosting和Bagging算法是多分类器系统常用的两种算法。针对高分辨率卫星遥感分类的需求,以Qu ickb ird数据为例,分别以BP神经网络、RBF神经网络和决策树为基分类器,对Boosting和Bagging算法的应用效果进行了实验和分析评价,结果表明Boosting算法和Bagging算法能够用于高分辨率遥感影像分类,具有较好的分类性能。