Refugee Camp Mapping Using Very High Spatial Resolution Satellite Sensor Images

Abstract

Short time‐intervals for complex response in unfamiliar areas cause refugee‐relief organisations to have a strong need for timely and up‐to‐date geographic information of the environment during humanitarian operations. The objective of this study is to provide an overview of relief organisations' need for detailed geographic information, and to assess the potential of the upcoming very high spatial resolution (VHSR) satellite sensors to provide this geographic information by mapping refugee camps and their environment on an operational basis. To demonstrate the use of VHSR satellite technology in relief operations, a pilot proof‐of‐concept study using a 1992 Russian KVR‐lOOO 2 m resolution panchromatic image of the six refugee camps in the Qala en Nahal settlement scheme in the Sudan was performed. The VHSR satellite sensor image was found to be useful for mapping refugee camp environmental parameters, such as land use, roads, rivers, and water sources, as well as camp infrastructure, including geographic positioning of camps, housing, and street network. The image also allowed for detailed camp area estimates. In addition, a statistically significant relationship between camp area and population was revealed for refugee camps included in this study. In operational use of VHSR satellite sensor data, relief agencies should be aware of the limitations of optical satellite images, in particular their reduced applicability during cloudy conditions.     

Assessing Optimal Image Fusion Methods for Very High Spatial Resolution Satellite Images to Support Coastal Monitoring

This study examines best image fusion approaches for generating pansharpened very high resolution (VHR) multispectral images to be utilized for monitoring coastal barrier island development. Selected fusion techniques assessed in this research come from the three categories of spectral substitution (e.g., Brovey transform and multiplicative merging), arithmetic merging (e.g., modified intensity-hue-saturation and principal component analysis), and spatial domain (e.g., high-pass filter, and subtractive resolution merge). The image fusion methods selected for this study were capable of producing pansharpened VHR images with more than three bands. Comparisons of fusion techniques were applied to images from three satellite sensors: United States commercial satellites IKONOS and QuickBird, and the Korean KOMPSAT II. Pansharpened VHR multispectral images were assessed by spectral and spatial quality measurements. Results satisfying both spectral and spatial quality revealed optimum pansharpened techniques necessary for regular coastal mapping of barrier islands. These techniques may also be used to assess the quality of recently available VHR imagery acquired by numerous international, government, and commercial VHR satellite programs.     

LiDAR辅助下利用超高分辨率影像提取建筑物轮廓方法

以精确自动提取建筑物轮廓为目标,提出一种LiDAR辅助下利用超高分辨率影像进行轮廓提取的新方法.其要点分为4步:① 预处理,检测LiDAR中建筑物点并分割成每栋建筑物的点集;② 建立轮廓提取区,针对每栋建筑物做缓冲区和外接矩形,通过缓冲区过滤和外接矩形切割,建立轮廓提取感兴趣区域;③ 线段提取,借助LiDAR估算出建筑物概略主方向,并在该方向的约束下,自动、鲁棒地检测出建筑物的主方向和建筑物的线段;④ 轮廓筛选,基于LiDAR密度分析与Kmeans聚类动态筛选出精确轮廓.本方法所提取的建筑物轮廓定位精确、细节完好,轮廓提取准确率91%.     

基于高分辨率影像城市建筑物研究

建筑物是城市的重要组成部分,近年来城市化进程不断加快,城市人口与城市建筑物日益增多,及时获取建筑物的空间分布以及建筑覆盖率、建筑容积率等相关指标,有利于城市居住环境状况进行科学评价,促进土地利用优化配置,还可为交通与通讯等科学规划提供参考.随着高分辨率影像应用的日益推广以及信息提取技术的不断提高,利用高分辨率卫星影像提取城市建筑物及建筑覆盖率、建筑容积率等指标与传统手段相比具有快速、高效等特点,得到广泛应用并取得丰硕成果.本文在前人研究的基础上,对基于高分辨率城市建筑物提取及相关研究的理论基础、存在问题、发展趋势进行了深入分析,对于高分辨率影像城市建筑物研究系统化、促进城市遥感的深化具有重要意义.     

A Multilevel Parcel-Based Approach to Change Detection in Very High Resolution Multitemporal Images

This letter presents a novel parcel-based context-sensitive technique for unsupervised change detection in very high geometrical resolution images. In order to improve pixel-based change-detection performance, we propose to exploit the spatial-context information in the framework of a multilevel approach. The proposed technique models the scene (and hence changes) at different resolution levels defining multitemporal and multilevel ldquoparcelsrdquo (i.e., small homogeneous regions shared by both original images). Change detection is achieved by applying a multilevel change vector analysis to each pixel of the considered images. This technique properly analyzes the multilevel and multitemporal parcel-based context information of the considered spatial position. The adaptive nature of multitemporal parcels and their multilevel representation allow one a proper modeling of complex objects in the investigated scene as well as borders and details of the changed areas. Experimental results confirm the effectiveness of the proposed approach.     

Multi-Feature Classification Approach for High Spatial Resolution Hyperspectral Images

High spatial resolution hyperspectral images not only contain abundant radiant and spectral information, but also display rich spatial information. In this paper, we propose a multi-feature high spatial resolution hyperspectral image classification approach based on the combination of spectral information and spatial information. Three features are derived from the original high spatial resolution hyperspectral image: the spectral features that are acquired from the auto subspace partition technique and the band index technique; the texture features that are obtained from GLCM analysis of the first principal component after principal component analysis is performed on the original image; and the spatial autocorrelation features that contain spatial band X and spatial band Y, with the grey level of spatial band X changing along columns and the grey level of spatial band Y changing along rows. The three features are subsequently combined together in Support Vector Machine to classify the high spatial resolution hyperspectral image. The experiments with a high spatial resolution hyperspectral image prove that the proposed multi-feature classification approach significantly increases classification accuracies.     

Automatic Change Detection in Very High Resolution Images With Pulse-Coupled Neural Networks

A novel approach based on pulse-coupled neural networks (PCNNs) for image change detection is presented. PCNNs are based on the implementation of the mechanisms underlying the visual cortex of small mammals, and, with respect to more traditional NNs architectures, such as multilayer perceptron, own interesting advantages. In particular, they are unsupervised and context sensitive. This latter property may be particularly useful when very high resolution images are considered as, in this case, an object analysis might be more suitable than a pixel-based one. The qualitative and more quantitative results are reported. The performance of the algorithm has been evaluated on a pair of QuickBird images taken over the test area of Tor Vergata University, Rome.      

基于高分辨率遥感影像的城市地表信息提取研究

针对高分辨率遥感影像在城市地表信息提取中存在的若干问题,发展了一种基于影像对象最优特征组合的城市地表信息提取方法。该方法首先基于面向对象的思想,抽象出城市地表信息所对应的影像对象的各种特征,然后,基于先验知识和样本分析选择最优特征组合,建立有效的影像对象特征集,最后,采用基于知识规则的模糊逻辑分类器快速准确地检测、识别和提取城市各类地表信息。实验结果表明,该方法具有较好的分类精度,其分类结果可为土地利用变化监测和GIS数据库更新提供依据。     

基于高分辨率影像的城市三维建模

介绍了利用倾斜摄影影像和垂直摄影影像相结合的三维城市重建方法,分析了利用有理多项式(RPC)恢复IKONOS立体影像的模型,在VirtuoZo上实现了基于有理多项式(RPC)恢复IKONOS立体影像的模型方法,并利用其快速影像匹配技术,实现了数字地面模型DEM和正射影像,实现了手动和半自动人工地物的采集,如房屋等三维几何坐标和结构的采集;自动获取了基于不同传感器所获得影像的建筑物表面纹理,从而实现了基于多种影像快速三维城市建模。     

利用遥感影像划分城乡过渡带方法的研究

提出了一个将 Ｔ Ｍ 影像与突变检测方法结合划分城乡过渡带的方法。首先采用二级结构分类方法从 Ｔ Ｍ 影像中提取城市用地信息;其次以城市用地比率进行窗口平滑处理,突出城市用地比率的圈层变化特征;最后用均值突变检验中的滑动ｔ检验方法对各方向的城乡断面上的城市用地比率进行突变检测,进而根据突变点的空间分布划分出城乡过渡带内、外边界的位置。利用北京１９８４ 年和１９９６ 年的 Ｔ Ｍ 影像进行验证,结果证明上述方法是可行的     

基于RPC模型的高分辨率卫星影像精确定位

介绍高分辨率卫星影像RPC模型的定义及其解算方法,推导RPC模型立体定位的基本方程,在此基础上对RPC模型的区域网平差进行深入研究。IKONOS卫星数据的实验结果表明,RPC模型误差呈现较强的系统性,但通过物方或像方的补偿立体定位可达到优于1.3 M的定位精度,区域网平差是最优的定位方法,精度可达1.1 M。     

基于高分SAR影像的城市用地变化检测

SAR技术的发展使得该技术在人们生活和生产中发挥着越来越重要的作用,而且高分辨率SAR影像的使用推动了SAR技术在各个方面的研究和应用,其中对城市用地的变化监测效果十分明显。本文采用4景前后时间相差11个月的Terra SAR-X数据,运用对数比值法构造差异影像,最后使用马尔科夫随机场模型提取出城市建筑物用地变化区域。最终得到的结果与人工目视解译结果的重合率达到80%以上,表明该方法行之有效,可以推广生产。     

Improved IHS Algorithm for Fusing High Resolution Satellite Images of Urban Areas

The intensity-hue-saturation method is used frequently in image fusion due to its efficiency and high spatial quality. The main shortage is its spectral distortion stemmed from replacement of intensity band with higher resolution image. In this study, a new method is introduced to improve the spectral quality of the Intensity-Hue-Saturation (IHS) algorithm. The goal of this study is to produce the fused image that has a better spectral and spatial quality with respect to the original images in term of visual comparison and the classification result. In this regard, an improved statistical approach is developed to combine an intensity band from IHS algorithm and an input high resolution image such as SAR or Panchromatic image. Then the intensity image is replaced by the combined image band. Final fused images are attained using the inverse IHS algorithm. The proposed fusion algorithm is tested on two data sets of: a) panchromatic and multi spectral bands of IKONOS image with the same acquisition date, and b) multi spectral and HH bands of IKONOS and TerraSAR-X images respectively with different acquisition dates. Moreover, the obtained results are compared with other fusion methods like IHS, Gungor, Brovey and synthetic variable ratio. The results show less spectral discrepancy of the proposed method comparing to other methods. Finally, the outcome of proposed method is classified and classification overall accuracy is improved by 5.6 and 2 percentage for data set ‘a’ and ‘b’ respectively.     

Comparison of Fusion Techniques for Very High Resolution Data for Extraction of Urban Land-Cover

This paper aims in presenting a thorough comparison of performance of pan sharpening techniques, belonging to spatial, spectral, scale-space and spatial-frequency domain, for Very High Resolution Satellite Data. With the availability of new Very High Resolution sensors, especially, World View-2 sensor, which provides data at sub-meter level, the need for fusion of Panchromatic (PAN) and Multispectral (MS) images has to be further investigated. Pan-sharpening techniques namely, Hue-Saturation-Intensity, Brovey Transform, Principal Components Analysis, Discrete Wavelet Transform, Stationary Wavelet Transform, Non Sub-sampled contourlet Transform and Pseudo Wigner Distribution (PWD) fusion method have been selected for the fusion of PAN and MS images of World View-2 sensor. Further, the comparison of performance of each of the techniques have been carried out by using various evaluation indicators, such as, Root Mean Square Error, Peak Signal-to-Noise Ratio, Correlation Coefficient, Universal Image Quality Index. It is found that PWD based fusion technique gives good result with a good trade-off between the preservation of spectral information and enhancement of spatial resolution.     

高分辨率遥感图像分类方法在LUCC中的研究进展

高空间分辨率遥感图像在土地利用/覆盖(LUCC)变化研究中的应用,促进了遥感分类技术的进一步发展,表现在遥感分类对象、分类特征和分类器3个方面。本文对其研究进展情况进行了综述,介绍了具有代表性的分类方法,并对各种方法的特点进行了分析。最后,对遥感分类的相关研究进行了总结和展望。     

智能优化学习的高空间分辨率遥感影像语义分割

高空间分辨率遥感影像正被广泛应用,而传统分类算法在高分遥感影像上的精度和效率较差,深度学习语义分割算法在实际分类中泛化性较差。为了适应大范围高分遥感影像的特点,提出了一种基于U-Net网络的模拟退火超参数优化与深度可分离卷积语义分割模型。首先在U-Net网络基础上使用了深度可分离卷积模块来进行特征提取,在保持高效性的同时减少模型的参数量和计算量,然后利用基于模拟退火的智能优化学习模型搜索网络超参数的全局最优解,自动优化网络训练初始点,最后在ISPRS2D和GID(Gaofen image dataset)数据集上进行实验。对比实验结果表明,在ISPRS2D数据集的分类结果中,建筑物、低植被和汽车及总体分类精度均有提高,在GID数据集的分类结果中,水域、草地、森林及总体分类精度均有大幅提高。实验结果验证了所提模型的高效性、高精度性与鲁棒性。     

基于形态重建的高分辨率遥感影像城市道路提取

根据城市道路在高分辨率遥感影像中的形态特性,提出一种基于形态重建的提取方法。试验结果表明,该方法能有效地从高分辨率遥感影像中提取出城市道路网。     

DEM精度对高分辨率卫星影像纠正的影响

简单介绍WorldView卫星的基本情况及其影像的RPC模型,重点研究DEM精度对整个测区影像的纠正带来的影响,试验结果表明DEM精度的提升能有效消除RPC模型的系统误差,提高影像的成图精度。     

高分辨率遥感影像纠正处理

随着高分辨率遥感卫星日益普及,其应用面也在不断地扩大.城市高分辨率正射影像图以其分辨率高、直观、生产更新周期短等优点,越来越受到城市管理、规划建设部门的青睐,同时也被广泛使用.本文结合重点城市1:10 ooo DLG更新项目,在波段组合、融合处理、正射纠正等方面进行了探讨.     

长春市利用高分辨率卫星正射影像生产城市专题地理信息工程技术实践

高分辨率卫星遥感影像是城市空间地理信息的重要数据源,可通过遥感影像信息提取技术获取以满足城市规划、城市园林、市政公共管理等部门所需的城市专题地理信息数据。本文阐述了长春市利用高分辨率卫星正射影像,采用人机交互目视解译方法批量生产城市专题地理信息的技术实践。