一种面向对象的遥感影像城市绿地提取方法

针对目前面向对象方法在高分辨率遥感影像中提取绿地专题信息的特点,以及受到城市区域范围尺度限制因素的影响,本文提出一种利用高分辨率遥感影像提取城市区域范围绿地专题信息的方法,结合影像分割、影像面向对象模板统计和基于多阀值的模糊分类技术的优势,林地、密草地和疏草地专题信息被提取出来.研究中提出利用基于面向对象多尺度分割算法...     

A method for monitoring building construction in urban sprawl areas using object-based analysis of Spot 5 images and existing GIS data

Urban sprawl has been identified as one of the most negative effects of global population growth on the environment and biodiversity. Frequent monitoring of urban sprawl is needed to limit the impact of this ongoing phenomenon. This paper proposes precise monitoring of building construction using an object-based classification methodology applied to Spot 5 images with a 2.5 m resolution. An application at a regional scale on Reunion Island in the Indian Ocean shows that this building extraction methodology has limitations in the production of reference urban maps because of difficulties in defining the shape and the number of buildings compared to classical photo-interpretation of aerial photography. However, these results are of great value for planning in urban sprawl areas where up-to-date information is lacking because of the rapid pace of house construction and residential development.     

Assessing urbanisation effects on rainfall-runoff using a remote sensing supported modelling strategy

This paper aims at developing a methodology for assessing urban dynamics in urban catchments and the related impact on hydrology. Using a multi-temporal remote sensing supported hydrological modelling approach an improved simulation of runoff for urban areas is targeted. A time-series of five medium resolution urban masks and corresponding sub-pixel sealed surface proportions maps was generated from Landsat and SPOT imagery. The consistency of the urban mask and sealed surface proportion time-series was imposed through an urban change trajectory analysis. The physically based rainfall-runoff model WetSpa was successfully adapted for integration of remote sensing derived information of detailed urban land use and sealed surface characteristics.A first scenario compares the original land-use class based approach for hydrological parameterisation with a remote sensing sub-pixel based approach. A second scenario assesses the impact of urban growth on hydrology. Study area is the Tolka River basin in Dublin, Ireland.The grid-based approach of WetSpa enables an optimal use of the spatially distributed properties of remote sensing derived input.Though change trajectory analysis remains little used in urban studies it is shown to be of utmost importance in case of time series analysis. The analysis enabled to assign a rational trajectory to 99% of all pixels. The study showed that consistent remote sensing derived land-use maps are preferred over alternative sources (such as CORINE) to avoid over-estimation errors, interpretation inconsistencies and assure enough spatial detail for urban studies. Scenario 1 reveals that both the class and remote sensing sub-pixel based approaches are able to simulate discharges at the catchment outlet in an equally satisfactory way, but the sub-pixel approach yields considerably higher peak discharges. The result confirms the importance of detailed information on the sealed surface proportion for hydrological simulations in urbanised catchments. In addition a major advantage with respect to hydrological parameterisation using remote sensing is the fact that it is site- and period-specific. Regarding the assessment of the impact of urbanisation (scenario 2) the hydrological simulations revealed that the steady urban growth in the Tolka basin between 1988 and 2006 had a considerable impact on peak discharges. Additionally, the hydrological response is quicker as a result of urbanisation. Spatially distributed surface runoff maps identify the zones with high runoff production.It is evident that this type of information is important for urban water management and decision makers. The results of the remote sensing supported modelling approach do not only indicate increased volumes due to urbanisation, but also identifies the locations where the most relevant impacts took place.     

区域规划空间信息系统建设与应用研究——以江苏省城乡规划信息系统为例

区域性城乡规划信息系统建设开展较晚,与城市级规划信息系统不同,其应用需求、数据构成、技术架构具有其独特性。结合新一轮江苏省城镇体系规划修编工作,开展全省城乡规划信息数据建库和应用平台的开发工作,系统根据区域规划的编制和研究应用需求,制定了面向未来区域规划工作需求的数据标准,集成了全省多源、多尺度、多时态的空间数据,实现了跨专业、跨平台空间信息的整合与共享。为江苏省城镇体系规划以及其他相关编制提供数据分析、规划决策支撑等服务,并预留未来与其他各类地理信息系统的应用接口。     

顾及属性特征的城市设施热点识别方法

研究城市设施的热点分布对把握当前城市形态具有重要意义。传统的设施热点识别方法容易忽略设施的特征尺度且多以区域识别为主,缺少精准化提取设施热点的方法体系。针对上述问题,本文提出了一种顾及属性特征的设施热点识别方法,并以北京市住宅设施为例进行了试验分析。首先将设施的属性值作为权重,进行加权核密度估计生成密度值表面,利用极值点探测模型提取极值点;然后采用Getis-Ord G_i^*统计进行空间自相关分析,生成具有显著统计学意义的热点区域,筛选极值点得到热点。结果表明,该方法能够准确有效地识别设施热点并进行合理的等级划分,为城市设施空间布局研究提供多样化视角。     

城市简单目标方向亮温研究

本研究以哈尔滨野外试验数据为基础，分析了城市表面亮温分布地表测量中，典型目标选择、目标亮温变化以及分类等方面的问题。结果表明，城市典型目标的选择，不仅需用材料特性划分，而且还需考虑阳光与周围环境的变化。此外，城市典型目标的亮温在数值上均随测量时间改变，并且变化比较复杂，需深入研究。在以上实验分析的基础上，建立了一种简单情况下的城市方向亮温模拟模型。模型中，抓住部分建筑区楼房以行结构为主要空间分布特征的特点，将建筑物进行简化，得到了不同观测角度下城市方向亮温的数值。模拟结果显示，方向亮温极化图中出现了条带结构，这与实验结果很吻合，但未能发现热点效应，需要进一步深入研究。     

结合尺度空间的面向对象高分辨率影像城市道路提取

基于遥感影像的城市道路提取对于城市建设、规划和地图更新等有重要意义。针对高分辨率遥感影像城市道路网的复杂性,结合尺度空间思想提出一种面向对象的城市道路自动提取算法。在此基础上,使用Canny算子获取像元簇梯度图,并进行标记分水岭分割得到区域对象;建立城市道路与几何、光谱特征相关的道路规则,从分割结果中筛选出道路区域对象;使用形态学方法提取道路区域的骨架,并对骨架进行连接、光滑等后处理,最后输出道路网提取结果。实验结果表明,该方法用于复杂城市道路的高精度自动提取,对城市道路网更新有一定参考意义。     

基于高分一号卫星的城市扩张变化监测研究

廊坊是京津冀城市群的地理中心,位于京津两个国际都市之间。本文选取廊坊市中心为研究对象,利用高分一号卫星数据和航空影像,分析廊坊市2010~2016年的城市扩张变化情况,为京津冀协同发展制定政策并为城市制订规划提供依据。首先对遥感影像进行预处理,对高分一号卫星影像,按用地类型分别采用监督分类、面向对象和植被指数法提取城市2016年地表现状信息,并进行精度评价;对2010年的航空影像进行数字化,两类数据结合进行基于分类的变化检测和精度评价,分析城市空间变化特征。结果表明,厂房、建筑和未建成区分别采用监督分类、建筑阈值分类和面向对象法分类效果较好;廊坊市城市扩张的驱动力主要为经济发展、政策因素、历史条件、地形等。     

Spatio‐Temporal Building Population Estimation for Highly Urbanized Areas Using GIS

Detailed population information is crucial for the micro‐scale modeling and analysis of human behavior in urban areas. Since it is not available on the basis of individual persons, it has become necessary to derive data from aggregated census data. A variety of approaches have been published in the past, yet they are not entirely suitable for use in the micro‐scale context of highly urbanized areas, due mainly to their broad spatial scale and missing temporal scale. Here we introduce an enhanced approach for the spatio‐temporal estimation of building populations in highly urbanized areas. It builds upon other estimation methodologies, but extends them by introducing multiple usage categories and the temporal dimension. This allows for a more realistic representation of human activities in highly urbanized areas and the fact that populations change over time as a result of these activities. The model makes use of a variety of micro‐scale data sets to operationalize the activities and their spatio‐temporal representations. The outcome of the model provides estimated population figures for all buildings at each time step and thereby reveals spatio‐temporal behavior patterns. It can be used in a variety of applications concerning the implications of human behavior in urban areas.     

核密度估计法支持下的网络空间POI点可视化与分析

城市空间POI点的分布模式、分布密度在基础设施规划、城市空间分析中具有重要意义,表达该特征的核密度法(kernel density estimation)由于顾及了地理学第一定律的区位影响,比其他密度表达方法(如样方密度、基于Voronoi图密度)占优。然而,传统的核密度计算方法往往基于二维延展的欧氏空间,忽略了城市网络空间中设施点的服务功能及相互联系发生于网络路径距离而非欧氏距离的事实。本研究针对该缺陷,给出了网络空间核密度计算模型,分析了核密度方法在置入网络结构中受多种约束条件的扩展模式,讨论了衰减阈值及高度极值对核密度特征表达的影响。通过实际多种POI点分布模式(随机型、稀疏型、区域密集型、线状密集型)下的核密度分析试验,讨论了POI基础设施在城市区域中的分布特征、影响因素、服务功能。     

基于深度学习的城市地理国情地表覆盖分类研究

作为图像识别的研究热点,利用深度学习对遥感影像进行自动分类具有较强的应用实践价值。本文基于全卷积神经网络的深度学习框架,提出了一套城市地理国情地表覆盖分类技术方法:利用地理国情成果,构建城市遥感影像样例库,训练全卷积神经网络,实现地表覆盖自动分类,并通过相似性系数对专题地物进行变化检测。文章选取了上海局部区域作为实验对象,结果发现该方法可以有效减少时间成本,对人文和自然地理要素之间具有较好的区分度,可以为地理国情成果应用和实践提供新的思路和方法。     

城市局部气候分区对地表温度的影响 ——以大连市区为例

以大连市区建筑数据、SPOT 5和Landsat 8遥感数据为基础,运用局部气候带分类、地表温度反演方法,研究大连市局部气候带分区类型和特征,进而分析不同局部气候带对城市地表温度的影响。研究结果表明：①大连市建筑类型高度主要为低层建筑、多层建筑和中高层建筑,建筑密度为中密度和较高密度,甘井子区分布大量森林绿地,中山区具有丰富的公园绿地;②地表温度整体偏高,空间上呈现东高西低的趋势,其中半数以上地区地表温度达到28℃~31℃,并且有超过1%的地区地表温度大于38℃,该区域出现极端高温;③同一建筑高度上,密度越大的建筑区域,地表温度越高;同一建筑密度,多层建筑高度覆盖区地表温度较高。森林绿地地表温度最低,公园绿地和社区绿地地表温度几乎一致,附属绿地地表温度最高。     

基于Landsat7 ETM+全色数据纹理和结构信息复合的城市建筑信息提取

提出了利用主成分分析方法有效地复合纹理和结构信息，从Landsat7 ETM^*全色数据中直接提取区域尺度的城市建筑信息的新方法，并在此基础上评估了Landsat7 ETM^ 全色数据和SPOT全色数据在城市建筑信息提取上的相互替代性。     

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。     

自发地理信息兴趣点数据在线综合与多尺度可视化方法

移动及Web环境下,集成各种自发地理信息POI数据与地理框架背景数据的混搭式地图应用,越来越多地出现在主流地理信息平台及LBS服务中。由于缺乏适宜的在线多尺度可视化机制,这种POI数据表达上通常出现拥挤、压盖等冲突现象。针对该问题,本研究将传统的尺度变换方法与在线环境相结合,提出一种面向城市设施POI数据的多尺度可视化策略。即由服务器端通过预处理方式对POI数据进行多层次结构化组织;在此基础上,客户端依据显示比例尺导出对应层次的POI目标,并通过移位操作解决局部存在的符号表达冲突现象。试验表明,该方法符合数字化网络应用的在线实时需求,同时也能获得较高质量的多尺度表达效果。     

A Robust Texture Analysis and Classification Approach for Urban Land‐Use and Land‐Cover Feature Discrimination

Abstract

Attempts to analyze urban features and to classify land use and land cover directly from high‐resolution satellite data with traditional computer classification techniques have proven to be inefficient for two primary reasons. First, urban landscapes are composed of complex features. Second, traditional classifiers employ spectral information based on single pixel value and ignore a great amount of spatial information. Texture plays an important role in image segmentation and object recognition, as well as in interpretation of images in a variety of applications. This study analyzes urban texture features in multi‐spectral image data. Recent developments in the very powerful mathematical theory of wavelet transforms have received overwhelming attention by image analysts. An evaluation of the ability of wavelet transform in urban feature extraction and classification was performed in this study, with six types of urban land cover features classified. The preliminary results of this research indicate that the accuracy of texture analysis in classifying urban features in fine resolution image data could be significantly improved with the use of wavelet transform approach.     

Comparative Study of Approaches to Delineating Built‐Up Areas Using Road Network Data

Delineated built‐up areas may be used for applications such as navigation, database enrichment and the identification of urban sprawl. As more road network data have become available, many studies have considered using road network data to delineate built‐up areas. This study investigated the three existing approaches to delineating built‐up areas on a map: the grid‐based approach, kernel density analysis and an approach based on street blocks. These approaches are evaluated and compared from three angles. First, two measures were proposed to quantitatively evaluate the land area of the delineated built‐up areas; second, a questionnaire was designed to visually compare the representations of the delineated built‐up areas; and, third, the time complexity of using each approach was tested. The three approaches were applied to different sets of road network data for New Zealand; data from buildings and residential areas were used as benchmarks. The results showed that: (1) in a quantitative assessment, both the grid‐based approach and kernel density analysis can usually detect more built‐up areas than the approach based on street blocks; (2) on visual inspection, most of the students who completed the questionnaire performed the representations using the approach based on street blocks; and (3) in time complexity, the approach based on street blocks always takes the least time.     

Analysis of urban built-up areas and surface urban heat island using downscaled MODIS derived land surface temperature data

Regional scale urban built-up areas and surface urban heat islands (SUHI) are important for urban planning and policy formation. Owing to coarse spatial resolution (1000 m), it is difficult to use Moderate Resolution Imaging Spectroradiometer (MODIS) Land surface temperature (LST) products for mapping urban areas and visualization, and SUHI-related studies. To overcome this problem, the present study downscaled MODIS (1000 m resolution)-derived LST to 250 m resolution to map and visualize the urban areas and identify the basic components of SUHI over 12 districts of Punjab, India. The results are compared through visual interpretation and statistical procedure based on similarity analysis. The increased entropy value in the downscaled LST signifies higher information content. The temperature variation within the built-up and its environs is due to difference in land use and is depicted better in the downscaled LST. The SUHI intensity analysis of four cities (Ludhiana, Patiala, Moga and Vatinda) indicates that mean temperature in urban built-up core is higher (38.87 °C) as compared to suburban (35.85 °C) and rural (32.41 °C) areas. The downscaling techniques demonstrated in this paper enhance the usage of open-source wide swath MODIS LST for continuous monitoring of SUHI and urban area mapping, visualisation and analysis at regional scale. Such initiatives are useful for the scientific community and the decision-makers.     

Evaluation of Land Suitability for Urban Land‐Use Planning: Case Study Dhaka City

The aim of this research is evaluation of land suitability for urban land‐use planning. Four factors and fourteen criteria were selected for suitability analysis and land‐use planning. Factors and criteria were defined based on literature survey, experts’ opinions, local contexts and availability of data. GIS‐based Analytical Hierarchy Process (AHP) was used as a Multi‐criteria Decision Making model. The study was conducted on a selected area of Dhaka city, which is one of the fastest growing mega‐cities of the world. The research result shows that highly suitable area (13%) should be used for urban residential zone; moderately suitable area (35%) should be designated as mixed use zone; low suitable area (42%) should be reserved for agricultural use and open spaces; and not suitable area (10%) should be protected from any types of activities except agriculture. The research approached an urban land‐use planning at a regional scale.