基于随机森林算法的城市不透水面信息提取——以长春市为例

为了快速、准确地掌握不透水面的空间分布及满足动态变化信息现实需求,本文基于多分类器集成学习的思想,引入随机森林算法,以Landsat8影像为数据源,长春市为实验区,选取光谱特征、纹理测度、空间变换后的独立分量等25个特征变量进行分类研究,根据OOB误差进行重要性分析并试验得出最优的分类模型,实现高精度不透水面信息的提取,最后与传统参数分类法进行比较。结果表明：随机森林算法的总体精度可以达到94%,高出最大似然分类法5.9%,支持向量机算法0.77%,Kappa系数为0.914 3,均方根误差为0.104 3,不透水面的提取精度达95.54%,可以精确地得出所需信息,为城市建设与规划提供有效的专题数据。     

Mapping impervious surfaces with the integrated use of Landsat Thematic Mapper and radar data: A case study in an urban–rural landscape in the Brazilian Amazon

This research explored the integrated use of Landsat Thematic Mapper (TM) and radar (i.e., ALOS PALSAR L-band and RADARSAT-2 C-band) data for mapping impervious surface distribution to examine the roles of radar data with different spatial resolutions and wavelengths. The wavelet-merging technique was used to merge TM and radar data to generate a new dataset. A constrained least-squares solution was used to unmix TM multispectral data and multisensor fusion images to four fraction images (high-albedo, low-albedo, vegetation, and soil). The impervious surface image was then extracted from the high-albedo and low-albedo fraction images. QuickBird imagery was used to develop an impervious surface image for use as reference data to evaluate the results from TM and fusion images. This research indicated that increasing spatial resolution by multisensor fusion improved spatial patterns of impervious surface distribution, but cannot significantly improve the statistical area accuracy. This research also indicated that the fusion image with 10-m spatial resolution was suitable for mapping impervious surface spatial distribution, but TM multispectral image with 30 m was too coarse in a complex urban–rural landscape. On the other hand, this research showed that no significant difference in improving impervious surface mapping performance by using either PALSAR L-band or RADARSAT C-band data with the same spatial resolution when they were used for multi-sensor fusion with the wavelet-based method.     

Mapping the human footprint from satellite measurements in Japan

Due to increasing global urbanization and climate change, the quantification of “human footprints” has become an urgent goal in the fields of biodiversity conservation and regional environment management. A human footprint is defined as the impact of a particular human activity on the Earth’s surface, which can be represented mainly by impervious surfaces (related to industry and urbanization) and cropland (related to agriculture). Here we present a method called sorted temporal mixture analysis with post-classification (STMAP) for mapping impervious surfaces and cropland simultaneously at the subpixel level to fill the demand for precise human footprint information on a national scale. The STMAP method applies a four-endmember sorted temporal mixture analysis to provide the initial fractions of evergreen forests, deciduous forests, cropland, and impervious surfaces as a first step. Endmembers are selected from the sorted temporal profiles of the MODIS-normalized difference vegetation index (NDVI), as guided by a principal component analysis. The yearly maximum land surface temperatures and averaged stable nighttime light are then statistically analyzed to provide the thresholds for post-classification to further separate cropland from deciduous forest and bare land from impervious surface. As the four outputs of STMAP, the fractions of forest, cropland, impervious surfaces and bare land are derived. We used the reference maps of impervious surfaces and cropland obtained from the Landsat/TM and ALOS precise land-use/land-cover map at the subpixel level to evaluate the performance of the proposed method, respectively. Historical satellite images with high spatial resolution were used to further evaluate the cropland results derived with the STMAP method. The results showed that the STMAP method has promising accuracy for estimating impervious surfaces and cropland in Japan. The root mean square errors obtained with the STMAP method were 6.3% for the estimation of impervious surfaces and 9.8% for the estimation of cropland. Our findings can extend the applications of remote sensing technologies in ecological research and environment management on a large scale.     

Cesium框架多源电子地图瓦片数据混搭方案设计

针对现有的商业地理信息系统平台难以灵活整合多源影像数据融合使用的问题,深入研究Cesium平台下多种数据源的空间参考差异和瓦片组织规则,针对不同空间参考的瓦片数据源进行混搭设计,提出基于Cesium的多源本地瓦片数据静态和动态加载方案。实验结果表明,单一瓦片数据源加载方案、静态和动态多源瓦片混搭方案的展示效果较好;静态瓦片混搭方案在加载不同空间参考瓦片数据时容易造成变形;动态多源、多空间参考瓦片混搭方案能有效克服变形问题且展示效果佳。本文实现了在开源GIS平台下的多源影像数据的融合使用,为地理信息系统与遥感类项目应用提供了一个低成本、高灵活性的解决方案,具有较为明显的实际应用价值。     

Using pan-sharpened high resolution satellite data to improve impervious surfaces estimation

Impervious surface is an important environmental and socio-economic indicator for numerous urban studies. While a large number of researches have been conducted to estimate the area and distribution of impervious surface from satellite data, the accuracy for impervious surface estimation (ISE) is insufficient due to high diversity of urban land cover types. This study evaluated the use of panchromatic (PAN) data in very high resolution satellite image for improving the accuracy of ISE by various pan-sharpening approaches, with a further comprehensive analysis of its scale effects. Three benchmark pan-sharpening approaches, Gram-Schmidt (GS), PANSHARP and principal component analysis (PCA) were applied to WorldView-2 in three spots of Hong Kong. The on-screen digitization were carried out based on Google Map and the results were viewed as referenced impervious surfaces. The referenced impervious surfaces and the ISE results were then re-scaled to various spatial resolutions to obtain the percentage of impervious surfaces. The correlation coefficient (CC) and root mean square error (RMSE) were adopted as the quantitative indicator to assess the accuracy. The accuracy differences between three research areas were further illustrated by the average local variance (ALV) which was used for landscape pattern analysis. The experimental results suggested that 1) three research regions have various landscape patterns; 2) ISE accuracy extracted from pan-sharpened data was better than ISE from original multispectral (MS) data; and 3) this improvement has a noticeable scale effects with various resolutions. The improvement was reduced slightly as the resolution became coarser.     

Most similar neighbor imputation of forest attributes using metrics derived from combined airborne LIDAR and multispectral sensors

In the context of predicting forest attributes using a combination of airborne LIDAR and multispectral (MS) sensors, we suggest the inclusion of normalized difference vegetation index (NDVI) metrics along with the more traditional LIDAR height metrics. Here the data fusion method consists of back-projecting LIDAR returns onto original MS images, avoiding co-registration errors. The prediction method is based on non-parametric imputation (the most similar neighbor). Predictor selection and accuracy assessment include hypothesis tests and over-fitting prevention methods. Results show improvements when using combinations of LIDAR and MS compared to using either of them alone. The MS sensor has little explanatory capacity for forest variables dependent on tree height, already well determined from LIDAR alone. However, there is potential for variables dependent on tree diameters and their density. The combination of LIDAR and MS sensors can be very beneficial for predicting variables describing forests structural heterogeneity, which are best described from synergies between LIDAR heights and NDVI dispersion. Results demonstrate the potential of NDVI metrics to increase prediction accuracy of forest attributes. Their inclusion in the predictor dataset may, however, in a few cases be detrimental to accuracy, and therefore we recommend to carefully assess the possible advantages of data fusion on a case-by-case basis.     

利用雷达干涉数据进行城市不透水层百分比估算

人工不透水层是城市地区的重要特征.作为城市生态环境的关键指数,不透水层百分比(Impervious Surfaces Percentage, ISP)常用于城市水文过程模拟、水质面源污染及城市专题制图等研究中.本文利用ERS-1/2 重复轨道雷达干涉数据,采用分类与回归树(CART)算法探究了雷达遥感在城市ISP估算中的可行性和潜力,并与SPOT5 HRG光学遥感图像的估算结果进行了分析比较.香港九龙港岛实验区的初步研究结果表明,雷达干涉数据在城市不透水层研究中具有一定的应用潜力,特别是裸土和稀疏植被的ISP估算结果要好于光学遥感,这主要得益于雷达干涉数据(特别是长时间相干图像)在人工建筑物和裸土或稀疏植被之间具有很强的区分能力,另外,雷达干涉数据和光学遥感数据间的融合能够提高ISP估算精度.     

Detection of impervious surface change with multitemporal Landsat images in an urban–rural frontier

Mapping and monitoring impervious surface dynamic change in a complex urban-rural frontier with medium or coarse spatial resolution images is a challenge due to the mixed pixel problem and the spectral confusion between impervious surfaces and other non-vegetation land covers. This research selected Lucas do Rio Verde County in Mato Grosso State, Brazil as a case study to improve impervious surface estimation performance by the integrated use of Landsat and QuickBird images and to monitor impervious surface change by analyzing the normalized multitemporal Landsat-derived fractional impervious surfaces. This research demonstrates the importance of two-step calibrations. The first step is to calibrate the Landsat-derived fraction impervious surface values through the established regression model based on the QuickBird-derived impervious surface image in 2008. The second step is to conduct the normalization between the calibrated 2008 impervious surface image with other dates of impervious surface images. This research indicates that the per-pixel based method overestimates the impervious surface area in the urban-rural frontier by 50%-60%. In order to accurately estimate impervious surface area, it is necessary to map the fractional impervious surface image and further calibrate the estimates with high spatial resolution images. Also normalization of the multitemporal fractional impervious surface images is needed to reduce the impacts from different environmental conditions, in order to effectively detect the impervious surface dynamic change in a complex urban-rural frontier. The procedure developed in this paper for mapping and monitoring impervious surface area is especially valuable in urban-rural frontiers where multitemporal Landsat images are difficult to be used for accurately extracting impervious surface features based on traditional per-pixel based classification methods as they cannot effectively handle the mixed pixel problem.     

Multi-resolution integration of land cover for sub-pixel estimation of urban impervious surface and forest cover

Abstract

A methodology is presented for estimating percent coverage of impervious surface (IS) and forest cover (FC) within Landsat thematic mapper (TM) pixels of urban areas. High-resolution multi-spectral images from Quickbird (QB) play a key role in the sub-pixel mapping process by providing information on the spatial distributions of ISs and FCs at 2.4 m ground sampling intervals. Thematic classifications, also derived from the Landsat imagery, have then been employed to define relationships between 30 m Landsat-derived greenness values and percent IS and FC. By also utilizing land cover/land use classification derived from Landsat and defining unique relationships for urban sub-classes (i.e. residential, commercial/industrial, open land), confusion between impervious and fallow agricultural lands has been overcome. Test results are presented for Ottawa-Gatineau, an urban area that encompasses many aspects typical of the North American urban landscape. Multiple QB scenes have been acquired for this urban centre, thereby allowing us to undertake an in-depth study of the error budgets associated with the fractional inference process.     

Sentinel+Landsat融合影像的城市不透水面积参数获取

不透水面是衡量城市化的发展程度和评价城市生态环境质量的重要指标之一。南昌市作为环鄱阳湖生态经济圈的典型代表区域城市之一,准确、及时、高效地获取其不透水面信息对经济发展和生态规划提供全新的决策参考具有重大意义。现有的不透水面研究大多集中在针对单一光学遥感影像数据提取不透水面信息,但受影像数据源的影响,其分类结果往往存在光谱混淆和“椒盐”现象,限制了不透水面分类精度的进一步提高。为了改善这一局面,本文以南昌市为研究区,综合考虑多源遥感影像数据各自具有的影像特征优势,探究基于Sentinel+Landsat影像提取不透水面信息的适用性与优劣性。     

基于多源高分辨率遥感影像的2 m不透水面一张图提取

不透水率是衡量城市生态环境状况的一个重要指标。当前全球范围内仅有1 km和30 m分辨率尺度的不透水面专题信息,无法满足城市尺度水文模型建模、海绵城市规划和建设需求。提出了图谱信息融合的不透水面提取模型,实现了基于深度学习的不透水面提取新方法,研制了不透水面遥感全流程提取和监测软件。基于多源高分辨率遥感影像首次完成了中国31个省（直辖市、自治区）的2 m不透水面专题信息提取,形成全国不透水面一张图,为海绵城市和生态城市的建设提供了基础数据支撑和技术监测手段。     

高分二号异轨立体数据的森林高度提取

森林植被碳储量的空间分布格局及其动态变化是陆地生态系统碳收支核算的基础。作为森林地上生物量的重要指示因子,森林高度的精确估算是提高森林植被碳储量估算精度的关键。现有研究已证明,由专业星载摄影测量系统获取的立体观测数据可用于森林高度提取,但光学遥感数据最大的问题是受云雨等天气因素的影响严重。区域森林地上生物量产品的生产需要充分挖掘潜在数据源。国产高分二号卫星(GF-2)虽然不是为获取立体观测数据而设计的专业星载摄影测量系统,但其获取的图像空间分辨率可达0.8 m,且具备±35°的的侧摆能力,在重复观测区域可构成异轨立体观测。本文以分别获取于2015年6月20日和2016年7月19的GF-2数据作为立体像对,其标称轨道侧摆角分别为0.00118°和20.4984°,以激光雷达数据获取的林下地形(DEM)和森林高度(CHM)为参考,对利用GF-2立体观测数据进行森林高度提取进行了研究。通过对立体处理得到的摄影测量点云的栅格化得到DSM,以激光雷达数据提供的DEM作为林下地形,得到了GF-2的CHM。结果表明GF-2提取的CHM与激光雷达CHM空间分布格局较为一致,两者之间存在明显的相关性,像素对像素的线性相关性(R2)达到0.51,均方根误差(RMSE)为3.6 m。研究结果表明,在林下地形已知的情况下,GF-2立体观测数据可用于森林高度估算。     

Broad-scale spatial pattern of forest landscape types in the Guiana Shield

Detecting broad scale spatial patterns across the South American rainforest biome is still a major challenge. Although several countries do possess their own, more or less detailed land-cover map, these are based on classifications that appear largely discordant from a country to another. Up to now, continental scale remote sensing studies failed to fill this gap. They mostly result in crude representations of the rainforest biome as a single, uniform vegetation class, in contrast with open vegetations. A few studies identified broad scale spatial patterns, but only when they managed to map a particular forest characteristic such as biomass. The main objective of this study is to identify, characterize and map distinct forest landscape types within the evergreen lowland rainforest at the sub-continental scale of the Guiana Shield (north-east tropical South-America 10° North-2° South; 66° West-50° West). This study is based on the analysis of a 1-year daily data set (from January 1st to December 31st, 2000) from the VEGETATION sensor onboard the SPOT-4 satellite (1-km spatial resolution). We interpreted remotely sensed landscape classes (RSLC) from field and high resolution remote sensing data of 21 sites in French Guiana. We cross-analyzed remote sensing data, field observations and environmental data using multivariate analysis. We obtained 33 remotely sensed landscape classes (RSLC) among which five forest-RSLC representing 78% of the forested area. The latter were classified as different broad forest landscape types according to a gradient of canopy openness. Their mapping revealed a new and meaningful broad-scale spatial pattern of forest landscape types. At the scale of the Guiana Shield, we observed a spatial patterns similarity between climatic and forest landscape types. The two most open forest-RSLCs were observed mainly within the north-west to south-east dry belt. The three other forest-RSLCs were observed in wetter and less anthropized areas, particularly in the newly recognized “Guianan dense forest arch”. Better management and conservation policies, as well as improvement of biological and ecological knowledge, require accurate and stable representations of the geographical components of ecosystems. Our results represent a decisive step in this way for the Guiana Shield area and contribute to fill one of the major shortfall in the knowledge of tropical forests.     

Spatial statistical techniques for aggregating point objects extracted from high spatial resolution remotely sensed imagery

 Using a local maximum filter, individual trees were extracted from a 1 m spatial resolution IKONOS image and represented as points. The spatial pattern of individual trees was determined to represent forest age (a surrogate for forest structure). Point attributes, based on the spatial pattern of trees, were generated via nearest neighbour statistics and used as the basis for aggregating points into forest structure units. The forest structure units allowed for the mapping of a forested area into one of three age categories: young (1–20 years), intermediate (21–120 years), and mature (>120 years). This research indicates a new approach to image processing, where objects generated from the processing of image data (rather than pixels or spectral values) are subjected to spatial statistical analysis to estimate an attribute relating an aspect of forest structure. Received: 22 April 2002 / Accepted: 23 November 2002     

基于光谱混合分解的流域不透水面提取及其动态分析——以于桥水库为例

不透水面不仅是城市非点源污染的主要来源,还是流域生态环境变化的主要因素之一。不透水面的数量、位置、几何形状、分布格局以及透水率与不透水率的比值,均影响着流域的水文环境,因此成为研究热点。本文以天津于桥水库流域为例,综合遥感(RS)与地理信息系统(GIS)技术,从流域尺度上研究1984~2013年间不透水面覆盖度的变化。在ENVI 5.1软件支持下,利用遥感影像获取1984,1994,2004和2013年4个时相的不透水面信息。采用修正后的归一化水体指数剔除水体信息,排除水体对不透水面提取精度的影响。运用线性光谱混合分析法(Linear Spectral Mixture Analysis,LSMA),提取流域不透水面覆盖度。结果表明:流域内不透水面覆盖度大多集中在1~5级,植被覆盖程度较高。近30年间不透水面比例逐年增加,2013年比1984年增加了2.802%,呈线性增长。中等分辨率的遥感影像适合流域尺度的不透水面提取的结果可作为流域水文及规划管理的重要基础性数据。     

基于混合光谱分解的城市不透水面分布估算

城市化的一个重要表现就是不透水面分布比率的上升,城市内部不透水面分布是城市生态环境的一个重要指标。对于规模较大的大城市,采用高性价比的中等分辨率影像,获取不透水面的分布,是当前国际研究的一个热点。本研究利用Landsat 7的ETM 影像,在线性光谱分解的技术上,提取了上海市的不透水面分布并对其空间特征进行了分析。研究揭示,ETM 影像对于城市尺度的信息提取,其成本是较低的;对于城市地域来说,利用植被、高反照度、低反照度和裸露的土壤四种最终光谱端元的线性组合,可以较好地模拟ETM 波谱特征,而除了水面以外的高反照度、低反照度两种最终光谱端元,可以较好地表达城市不透水表面信息。结果显示,利用中等分辨率影像对上海中心城区不透水面分布提取的精度还是令人满意的,总体上,上海市不透水面分布比率较高,不透水面分布的空间差异进一步揭示了城市土地覆被空间结构以及城市空间扩展的差异性。     

LIDAR在林区送电线路设计中的应用可行性

传统的航空摄影测量方式在林区送电线路中存在一些难题,机载激光雷达系统提供了一种新的解决途径。首先介绍了林区送电线路设计的难点,然后描述植被测量以及DEM获取的原理,最后展望了机载激光雷达系统在林区送电线路设计的应用前景。     

结合影像的LIDAR数据三维建筑物提取

随着LIDAR技术的出现,三维建筑物的提取也受到越来越多的重视。由于LIDAR数据分布的不连续性和不规律性,直接从机载激光扫描测距数据中进行建筑物提取较为困难。本文提出了一种结合灰度影像的LIDAR数据三维建筑物提取方法,分三个步骤:首先对灰度影像进行建筑物二维提取;然后将处理后影像和LIDAR数据粗匹配,初步确定LI-DAR数据中的三维建筑物区域;最后利用一组阈值操作进行三维建筑物的精确提取。实验结果表明该方法简单实用,适应性强。     

面向对象的多源数据建筑物提取

建筑物是城市的重要标志之一,综合利用LiDAR数据和高分辨率遥感影像可以充分发挥不同数据源中提取建筑物的优势。本文基于面向对象分类理论,利用机载LiDAR数据和GeoEye高空间分辨率遥感影像,在多尺度分割的基础上对实验区分类并提取建筑物,进而对提取结果进行精度评价。实验表明,将LiDAR数据与高分辨率影像数据结合能够很好地提取建筑物,建筑物提取精度达89.28%。     

Quantifying urban land cover change between 2001 and 2006 in the Gulf of Mexico region

We estimated urbanization rates (2001–2006) in the Gulf of Mexico region using the National Land Cover Database (NLCD) 2001 and 2006 impervious surface products. An improved method was used to update the NLCD impervious surface product in 2006 and associated land cover transition between 2001 and 2006. Our estimation reveals that impervious surface increased 416 km² with a growth rate of 5.8% between 2001 and 2006. Approximately 1110.1 km² of non-urban lands were converted into urban land, resulting in a 3.2% increase in the region. Hay/pasture, woody wetland, and evergreen forest represented the three most common land cover classes that transitioned to urban. Among these land cover transitions, more than 50% of the urbanization occurred within 50 km of the coast. Our analysis shows that the close-to-coast land cover transition trend, especially within 10 km off the coast, potentially imposes substantial long-term impacts on regional landscape and ecological conditions.