Urban land use mapping and zoning of Bombay Metropolitan Region using remote sensing data

Bombay Metropolitan Region covering an area of about 4,360 sq. km. was selected for urban land use studies and for urban land use zoning. Urban land use mapping was carried out using SPOT multispectral linear array imagery on 1∶25,000 scale employing visual analysis tehcniques. Fifteen maps were prepared depicting the spatial distribution of various urban classes in the Greater Bombay and New Bombay regions. Sixteen urban land use maps were also prepared using Landsat TM data showing the distribution of land use pattern on 1∶50,000 scale for the entire metropolitan region. Urban land use zoning was carried out based upon suitability index on 1∶250,000 scale. This map provides information on the areas to be used for construction and areas to be kept under green belt in the metropolitan region. This study is a joint venture of Space Applications Centre with Bombay Metropolitan Development authority.     

Object-based habitat mapping using very high spatial resolution multispectral and hyperspectral imagery with LiDAR data

This study investigated the combined use of multispectral/hyperspectral imagery and LiDAR data for habitat mapping across parts of south Cumbria, North West England. The methodology adopted in this study integrated spectral information contained in pansharp QuickBird multispectral/AISA Eagle hyperspectral imagery and LiDAR-derived measures with object-based machine learning classifiers and ensemble analysis techniques. Using the LiDAR point cloud data, elevation models (such as the Digital Surface Model and Digital Terrain Model raster) and intensity features were extracted directly. The LiDAR-derived measures exploited in this study included Canopy Height Model, intensity and topographic information (i.e. mean, maximum and standard deviation). These three LiDAR measures were combined with spectral information contained in the pansharp QuickBird and Eagle MNF transformed imagery for image classification experiments. A fusion of pansharp QuickBird multispectral and Eagle MNF hyperspectral imagery with all LiDAR-derived measures generated the best classification accuracies, 89.8 and 92.6% respectively. These results were generated with the Support Vector Machine and Random Forest machine learning algorithms respectively. The ensemble analysis of all three learning machine classifiers for the pansharp QuickBird and Eagle MNF fused data outputs did not significantly increase the overall classification accuracy. Results of the study demonstrate the potential of combining either very high spatial resolution multispectral or hyperspectral imagery with LiDAR data for habitat mapping.     

月球遥感制图回顾与展望

对月球探测任务、月球遥感制图技术与产品进行综述。从1958年开始,全世界已开展126次(其中70次成功)月球探测工程任务,其中月球遥感制图是其必需的基础性工作。由于月球环境的特殊性,其遥感制图技术与对地观测制图相比具有很大的挑战和更大的难度。目前,中国嫦娥二号轨道器获取的7 m分辨率立体影像是覆盖全月球分辨率最高的立体影像数据,美国月球侦察轨道器LRO任务的激光雷达高度计LOLA数据是精度和密度最高的激光测高数据,LRO NAC影像的分辨率最高(0.5—2 m)但未覆盖全球。在各个探测任务中,基于月球遥感数据和摄影测量技术,已经制作了大量的全球及区域的影像拼图、正射影像图和数字高程模型等制图产品。对月球遥感制图技术发展进行展望,探讨了利用国际多探测任务数据建立新一代控制网和进行精细制图的必要性及技术思路。     

Automated analysis of ultra high resolution remote sensing data for biotope type mapping: new possibilities and challenges

The advent of very high-resolution satellite programs and digital airborne cameras with ultra high resolution offers new possibilities for very accurate mapping of the environment. With these sensors of improved spatial resolution, however, the user community faces a new problem in the analysis of this type of image data. Standard classification techniques have to be augmented with appropriate analysis procedures because the required homogeneity of landuse/landcover classes can no longer be achieved by the integration effect of large pixel sizes (e.g., 20–80 m). New intelligent techniques will have to be developed that make use of multisensor approaches, geographic information system (GIS) integration and context-based interpretation schemes.The ideal goal should be that GIS ‘intelligence’ (e.g., object and analysis models) should be used to automate the classification process. In return, GIS objects can be extracted from a remote sensing image to update the GIS database. This paper presents the development of an automated procedure for biotope type mapping from ultra high-resolution airborne scanner data (HRSC-A). The hierarchical procedure incorporates a priori GIS information, a digital surface model (DSM) and multispectral image data. The results of this study will serve as a basis for a continuous environmental monitoring process in the tidally influenced region of the Elbe River, Germany.     

融合高时空分辨率数据估算植被净初级生产力

植被净初级生产力NPP(Net Primary Production)遥感估算与分析,有赖于高时空分辨率的遥感数据,但目前中高分辨率的遥感数据受卫星回访周期及天气的影响,在中国南方地区难以获取连续时间序列的数据,从而影响了高精度的区域植被净初级生产力的遥感估算。为此,提出一种基于多源遥感数据时空融合技术与CASA模型估算高时空分辨率NPP的方法。首先,利用多源遥感数据,即Landsat8 OLI数据与MODIS13Q1数据,采用遥感数据时空融合方法,获得了时间序列的Landsat8 OLI融合数据;然后,基于Landsat8 OLI时空融合数据,并采用CASA模型,以长株潭城市群核心区为例,进行区域植被NPP的遥感估算。研究结果表明,基于时间序列Landsat融合数据估算的30m分辨率的NPP具有良好的空间细节信息,且估算值与实测值的相关系数达0.825,与实测NPP数据保持了较好的一致性。     

基于ENVI的高分辨率遥感影像城市绿地信息提取研究

近年来众多高分辨率遥感卫星的发射为城市绿地信息提取提供了高效的手段,如何充分利用高分辨率遥感影像对现代城市进行规划和生态环境评价具有重要意义。文中介绍一个完整的遥感工程在ENVI下的实现过程,包含高分辨率数据的处理、高分辨率信息提取流程的合理安排、FX模块面向对象信息提取等内容,可全面快速掌握城市绿地总量与分布现状,为绿地系统规划与日常管理决策提供参考,对生态城市建设具有重要意义。     

高分辨率遥感影像建筑区域局部几何特征提取

及时准确地获取城市建筑区域的空间分布及其变化信息对于城市规划、空间地理数据库建设及区域社会经济分析具有重要意义。本文提出一种基于多尺度Gabor变换和感知聚类方法即张量投票TV (Tensor Voting)相结合的自适应局部几何不变特征检测方法,并将其应用于高空间分辨率遥感影像建筑区域提取。首先,考虑到高分辨率遥感影像复杂的几何结构特征,使用Gabor滤波器组对影像进行多尺度多方向变换检测奇异性特征。然后,在感知聚类框架下,根据张量投票理论将不同方向子带系数位置编码为相应的二阶对称方向张量,为了突出影像几何特征,对不同尺度、不同方向子带中任意像素位置方向张量使用滤波器响应系数加权并求和完成多尺度特征融合。再次,对张量特征分解得到点结构与线结构显著性图并使用非极大抑制提取相应角点和曲线等局部几何特征,同时生成约束准则筛选角点以确定建筑物坐标。最后,利用概率密度估计结合局部角点特征生成全局概率密度场描述影像中像素从属于建筑目标的概率,并使用最大类间方差法(Otsu)阈值分割自动提取居民地多边形区域。使用分辨率分别为0.49 m、0.98 m的Google Earth及0.8 m的高分二号等影像数据集进行实验,实验结果表明本文方法相对于已有的Harris和HSCD点检测算法,在建筑区域提取质量上(Quality)上分别提高了4.79%,5.96%;1.47%,3.76%和1.91%,4.08%。     

高分辨率遥感影像快速去雾

针对含雾遥感影像在军事航空侦查、地物判读等方面使用率低、有效性差的问题,以及现有去雾算法中存在计算复杂耗时、色彩失真的弊端,结合遥感影像景深变化小、不含天空背景等特点,本文提出一种改进的暗原色先验去雾算法。首先,对影像中白色场景灰度值进行统计并设定阈值划分为失效区,分离水域与非水域减少蓝色波段在水域的占比,合成新的蓝色波段,以改进暗通道值的获取方法;其次,采用导向滤波替代软抠图法优化透射率提升处理时间;然后,对关键参数进行适应性改进试验并采用自动色阶恢复去雾后的影像色彩;最后,利用含雾的无人机影像和GF-2影像进行了试验,并进行了定量评价。试验结果表明,在同等试验条件下,本文方法处理单幅影像的时间比暗原色先验去雾算法的提升4倍以上,且去雾后影像的灰度均值、标准差、信息熵、平均梯度等指标比暗原色先验去雾算法得到的值均有提高,能有效提高有雾影像的清晰度,增强影像色彩和细节。     

A cloud mask methodology for high resolution remote sensing data combining information from high and medium resolution optical sensors

This study presents a novel cloud masking approach for high resolution remote sensing images in the context of land cover mapping. As an advantage to traditional methods, the approach does not rely on thermal bands and it is applicable to images from most high resolution earth observation remote sensing sensors. The methodology couples pixel-based seed identification and object-based region growing. The seed identification stage relies on pixel value comparison between high resolution images and cloud free composites at lower spatial resolution from almost simultaneously acquired dates. The methodology was tested taking SPOT4-HRVIR, SPOT5-HRG and IRS-LISS III as high resolution images and cloud free MODIS composites as reference images. The selected scenes included a wide range of cloud types and surface features. The resulting cloud masks were evaluated through visual comparison. They were also compared with ad-hoc independently generated cloud masks and with the automatic cloud cover assessment algorithm (ACCA). In general the results showed an agreement in detected clouds higher than 95% for clouds larger than 50 ha. The approach produced consistent results identifying and mapping clouds of different type and size over various land surfaces including natural vegetation, agriculture land, built-up areas, water bodies and snow.     

高分遥感影像的围填海变化图斑自动提取方法

针对已有的围填海图斑提取方法精度不高、普适性不强、自动提取结果不理想等问题,该文提出了通过构建归一化差异水体指数(NDWI)进行围填海变化图斑自动提取的方法。以高分辨率QuickBird影像和HJ-1卫星影像为数据源,首先,根据研究区的用海类型进行5种易混淆地物的波谱特征分析;然后,根据水体与非水体的光谱特征差异,构建2009、2011年两个时相的NDWI指数;最后,将两时相NDWI指数影像进行空间相减,设置判断阈值,识别围填海变化图斑,并以目视提取结果作为依据验证其自动提取效果。对比分析结果表明:利用该文构建的两期NDWI指数可以将大部分围填海区域准确、自动地探测出来,可以将该方法纳入到沿海地区围填海变化监测的业务中。     

A multi-level context-guided classification method with object-based convolutional neural network for land cover classification using very high resolution remote sensing images

Classification of very high resolution imagery (VHRI) is challenging due to the difficulty in mining complex spatial and spectral patterns from rich image details. Various object-based Convolutional Neural Networks (OCNN) for VHRI classification have been proposed to overcome the drawbacks of the redundant pixel-wise CNNs, owing to their low computational cost and fine contour-preserving. However, classification performance of OCNN is still limited by geometric distortions, insufficient feature representation, and lack of contextual guidance. In this paper, an innovative multi-level context-guided classification method with the OCNN (MLCG-OCNN) is proposed. A feature-fusing OCNN, including the object contour-preserving mask strategy with the supplement of object deformation coefficient, is developed for accurate object discrimination by learning simultaneously high-level features from independent spectral patterns, geometric characteristics, and object-level contextual information. Then pixel-level contextual guidance is used to further improve the per-object classification results. The MLCG-OCNN method is intentionally tested on two validated small image datasets with limited training samples, to assess the performance in applications of land cover classification where a trade-off between time-consumption of sample training and overall accuracy needs to be found, as it is very common in the practice. Compared with traditional benchmark methods including the patch-based per-pixel CNN (PBPP), the patch-based per-object CNN (PBPO), the pixel-wise CNN with object segmentation refinement (PO), semantic segmentation U-Net (U-NET), and DeepLabV3+(DLV3+), MLCG-OCNN method achieves remarkable classification performance (> 80 %). Compared with the state-of-the-art architecture DeepLabV3+, the MLCG-OCNN method demonstrates high computational efficiency for VHRI classification (4–5 times faster).     

面向对象的高分辨率遥感影像地理要素提取

应用面向对象影像分类方法进行空间目标特征提取和分析,实现利用遥感影像建立与更新地理空间数据库,对于正在进行的数字城市建设和国情监测具有重要的意义和作用。本文阐述了高空间分辨率影像特征提取的关键技术,采用面向对象的特征提取技术和影像分类方法,开展了基于ADS40航空影像的地理要素提取实验,获得了比较满意的专题信息。     

高分遥感卫星数据在东昆仑成矿带找矿预测中的应用

为研究高分辨率(简称"高分")遥感卫星数据在东昆仑成矿带找矿预测中的应用,通过遥感地质解译与蚀变异常信息提取,从宏观和多角度开展大型矿集区快速预选和找矿有利地段圈定。以东昆仑成矿带红水河地区为研究区,以World View-2卫星图像为主要数据源,通过运用图像纠正、假彩色合成、图像增强、数据融合、遥感蚀变异常信息提取、野外验证、化学分析和地质信息综合研究等方法,对研究区进行了遥感地质解译和找矿预测。结果表明,以高分遥感卫星数据为主的数据源,能够快速圈定找矿有利地段,满足我国西部干旱—半干旱地区的矿产资源勘查和资源评价需求,并为当地矿产勘查工作部署提供基础资料和参考依据。     

A numerical technique for delineation of soil mapping units using multi-spectral remote sensing data

A numerical technique for transformation of ground based sail spectral information into soil mapping — unit information, in terms of the total information content index has been proposed. The study carried out on 14 surface soil samples. widely differing in their physical appearance of colour and collected from different parts of India, revealed that total information content index could distinctly discriminate between the contrasting soil physiographic units with black cotton, red and sandy soil types. A comparison of the proposed index with the conventionally used two or three waveband specific indices (e.g. NIR/Red and NIR-Red/Red-Green) showed that the proposed index was more characteristic of the various soil types studied. Further, unlike the conventional 2-D indices, the proposed, numerical technique lead to the complete compression of the information contained in the entire reflectance spectrum (irrespective of the number of wavebands) to a single characteristic value in 1-D Space and a simplified 1-D clustering analysis.     

高分辨率遥感图像道路交叉口自动提取

道路交叉口是道路网络(简称路网)的重要组成元素,获取道路交叉口对提取路网信息、影像匹配和车辆导航等有重要作用。然而,基于遥感图像对道路交叉口自动提取的研究尚不多。针对高分辨率遥感图像中道路交叉口的特点,提出一种自动识别道路交叉口的方法。在图像预处理的基础上,首先对图像进行多尺度圆形均匀区检测,使用梯度变换和形态学变换提取可能存在道路交叉口的候选区;然后对候选区进行特征提取和进一步筛选,得到候选道路交叉口的位置中心;最后提取位置中心的角度纹理信息,通过波谷检测判断其连接属性,识别出道路交叉口。结果表明,该方法能有效提取出城市地区的道路交叉口,对于较复杂地区的道路交叉口提取也有一定的效果。     

多源高分辨率遥感影像自动匹配算法

提出一种基于同名直线约束的多源高分辨率遥感影像自动匹配方法。对影像建立高斯滤波模型去噪,然后进行边缘检测,在边缘影像上进行Hough变换,通过端点检测的方法来获取直线;通过粗匹配参数进行同名直线粗匹配,应用梯度模型对同名直线进行精匹配;对影像提取特征点,特征点经过同名直线约束后,在对应影像上利用同名直线约束建立匹配范围。采用最小欧式距离准则在给定范围内提取初始同名点;利用RANSAC算法剔除错误同名点对,以获取最终的匹配结果。实验结果表明,与传统的SIFT匹配算法比较,方法具有可靠性好、提取同名点数量多的优点。     

基于高分辨率遥感影像的车道线提取

车道线是自动驾驶高精度地图的组成部分,利用车载摄像头和激光雷达提取车道线的研究已经比较深入。本文探讨了利用高分辨率遥感影像提取车道线的方法。首先依据直方图原则选取合适的阈值进行二值化分割,其次利用道路中线形成的缓冲区去除道路范围外的要素,然后利用形态学算子去除噪声,最后利用方向和面积因子提取不同的车道线。该方法可以降低数据采集的成本,提高采集效率。     

异源高分辨率遥感影像的三维重建

针对在实际应用中难以获得同源高分辨率遥感影像,利用同源高分辨率影像实现高精度、自动化的三维重建仍存在一定困难的现状,该文提出一种利用异源高分辨率遥感影像进行三维重建的方法。采用尺度不变特征变换算法对影像进行匹配以获取同名点,并使用随机抽样一致性算法剔除低精度匹配点;然后利用获取的同名点构建Delaunay三角网;接着根据有理函数反解模型和投影射线联合定位算法解算各个同名点的三维坐标;最后基于Delaunay三角网内插技术求取地物点的高程值,并基于OpenGL技术实现三维显示。试验结果表明,利用该方法可以实现异源高分辨率遥感影像的三维重建,精度上能够满足生产需求。     

Multistage approach in soil mapping using remote sensing techniques

The use of Landsat images at 1∶1 Million and 1∶250,000 scales and aerial photographs at 1∶60,000 scale for preparation of soil maps has been discussed. It was possible to prepare soil maps at Suborder and its association from the Landsat images as the base and Subgroup and its association map using the aerial photographs as base. The compatability of classification of landscape units has been discussed keeping the API map as the standard.     

Disaggregating and mapping crop statistics using hypertemporal remote sensing

Governments compile their agricultural statistics in tabular form by administrative area, which gives no clue to the exact locations where specific crops are actually grown. Such data are poorly suited for early warning and assessment of crop production. 10-Daily satellite image time series of Andalucia, Spain, acquired since 1998 by the SPOT Vegetation Instrument in combination with reported crop area statistics were used to produce the required crop maps. Firstly, the 10-daily (1998–2006) 1-km resolution SPOT-Vegetation NDVI-images were used to stratify the study area in 45 map units through an iterative unsupervised classification process. Each unit represents an NDVI-profile showing changes in vegetation greenness over time which is assumed to relate to the types of land cover and land use present. Secondly, the areas of NDVI-units and the reported cropped areas by municipality were used to disaggregate the crop statistics. Adjusted R-squares were 98.8% for rainfed wheat, 97.5% for rainfed sunflower, and 76.5% for barley. Relating statistical data on areas cropped by municipality with the NDVI-based unit map showed that the selected crops were significantly related to specific NDVI-based map units. Other NDVI-profiles did not relate to the studied crops and represented other types of land use or land cover. The results were validated by using primary field data. These data were collected by the Spanish government from 2001 to 2005 through grid sampling within agricultural areas; each grid (block) contains three 700 m × 700 m segments. The validation showed 68%, 31% and 23% variability explained (adjusted R-squares) between the three produced maps and the thousands of segment data. Mainly variability within the delineated NDVI-units caused relatively low values; the units are internally heterogeneous. Variability between units is properly captured. The maps must accordingly be considered “small scale maps”. These maps can be used to monitor crop performance of specific cropped areas because of using hypertemporal images. Early warning thus becomes more location and crop specific because of using hypertemporal remote sensing.