顾及功能语义特征的建筑物空间分布模式识别方法

本文从空间-语义双重约束角度,提出一种顾及空间邻近和功能语义相似的建筑物空间分布模式识别方法。首先,基于建筑物的空间位置邻近性(即建筑物间的最小距离)约束进行聚类,获得建筑物的空间分布模式和建筑物间的空间邻近关系;然后,根据建筑物的功能语义相似性约束进行分割,获得建筑物的初步聚类结果;最后,考虑簇内相似性与簇间差异性进行整体优化,获得最终聚类结果。试验验证表明,本文方法比现有方法能够更有效地识别空间邻近与功能语义一致的建筑物群,服务于智慧城市建设中对建筑物进行语义层次综合和对城市结构进行深入研究的需求。     

On the spatial distribution of buildings for map generalization

Information on spatial distribution of buildings must be explored as part of the process of map generalization. A new approach is proposed in this article, which combines building classification and clustering to enable the detection of class differences within a pattern, as well as patterns within a class. To do this, an analysis of existing parameters describing building characteristics is performed via principal component analysis (PCA), and four major parameters (i.e. convex hull area, IPQ compactness, number of edges, and smallest minimum bounding rectangle orientation) are selected for further classification based on similarities between building characteristics. A building clustering method based on minimum spanning tree (MST) considering rivers and roads is then applied. Theory and experiments show that use of a relative neighbor graph (RNG) is more effective in detecting linear building patterns than either a nearest neighbor graph (NNG), an MST, or a Gabriel graph (GssG). Building classification and clustering are therefore conducted separately using experimental data extracted from OpenStreetMap (OSM), and linear patterns are then recognized within resultant clusters. Experimental results show that the approach proposed in this article is both reasonable and efficient for mining information on the spatial distribution of buildings for map generalization.     

Object based building footprint detection from high resolution multispectral satellite image using K-means clustering algorithm and shape parameters

Object-based image analysis (OBIA) has been a new area of research in satellite image processing applications, since it improves the quality of information acquisition about geospatial objects and also enables to add spatial and contextual information to the objects of interest. The extraction of buildings from High Resolution Satellite (HRS) image in an urban scenario has been an intricate problem due to their different size, shape, varying rooftop textures and low contrast between building and surrounding region. In this study, a new object-based automatic building extraction technique has been proposed to extract building footprints from HRS pan sharpened IKONOS multispectral image. The study is mainly emphasizing on obtaining optimal values for segmentation parameters, shape parameters, and defining rule set to extract buildings and eliminate misclassified other urban features. The suitability of the technique has been judged using different indicators, such as, completeness, correctness and quality.     

一种利用点云邻域信息的建筑物屋顶面高精度自动提取方法

从LiDAR数据中高精度地提取建筑物屋顶面是构建屋顶面拓扑关系、实现建筑物三维模型重建的关键。本文针对现有算法提取复杂建筑物屋顶面适应性较差、精度较低等问题,提出了一种利用点云邻域信息的建筑物屋顶面高精度自动提取方法。通过主成分分析计算点云特征,构建特征直方图,选取可靠种子点;利用提出的局部点云法向量分布密度聚类算法聚类种子点,快速准确地提取初始屋顶面片;构建基于邻域信息的投票模型,有效地解决屋顶面竞争现象。试验结果表明,本文方法可自动、高精度地提取屋顶面,对不同复杂程度的建筑物具有较好的适应性,能为建筑物三维模型重建提供可靠的屋顶面信息。     

矢量居民地多边形多级图划分聚类方法

针对复杂居民地多边形的信息挖掘问题,提出了一种多级图划分聚类分析方法,构造居民地多边形的图模型,并通过对图模型进行粗化匹配与重构、初始化分和细化得到聚类结果.首先构建研究区域内居民地建筑物的Delaunay三角网,生成包含研究对象之间的邻接信息图;然后结合空间认知准则和人类认知的特点,采用形状狭长度、面积比、凹凸性、距...     

图残差神经网络支持下的建筑物群组模式分类

建筑物作为城市中的重要地物,分析其群组模式对地图综合、导航定位、市政规划等具有重要作用。建筑物群组模式分析目前主要有基于规则的方法和基于机器学习的方法两种。基于规则的方法和基于传统机器学习分类器的方法均需要大量的人工处理过程。近年来兴起的深度学习特别是图卷积神经网络前期无需人工处理,因此提高了建筑物群组模式分析的自动化程度。传统的图卷积神经网络模型在训练深层网络时易出现退化问题,提取深层特征困难。为解决此问题,本文引入了图残差神经网络模型用于建筑物群组的模式分类。首先使用道路和河流等作为约束条件,利用K-means方法对建筑物进行聚类;然后根据Bertin视觉变量计算对应的建筑物特征指标,在每个建筑物群组中以建筑物质心为节点,连接节点的最小生成树作为边,构建建筑物群组图结构;最后将得到的图结构数据输入图残差神经网络进行训练,得到规则和不规则两种建筑物群组模式。试验结果表明,该模型较好地解决了传统图卷积神经网络模型的退化问题,并取得了更高的精度。     

A Bayesian characterization of urban land use configurations from VHR remote sensing images

The composition and arrangement of spatial entities, i.e., land cover objects, play a key role in distinguishing land use types from very high resolution (VHR) remote sensing images, in particular in urban environments. This paper presents a new method to characterize the spatial arrangement for urban land use extraction using VHR images. We derive an adjacency unit matrix to represent the spatial arrangement of land cover objects obtained from a VHR image, and use a graph convolutional network to quantify the spatial arrangement by extracting hidden features from adjacency unit matrices. The distribution of the spatial arrangement variables, i.e., hidden features, and the spatial composition variables, i.e., widely used land use indicators, are then estimated. We use a Bayesian method to integrate the variables of spatial arrangement and composition for urban land use extraction. Experiments were conducted using three VHR images acquired in two urban areas: a Pleiades image in Wuhan in 2013, a Superview image in Wuhan in 2019, and a GeoEye image in Oklahoma City in 2012. Our results show that the proposed method provides an effective means to characterize the spatial arrangement of land cover objects, and produces urban land use extractions with overall accuracies (i.e., 86% and 93%) higher than existing methods (i.e., 83% and 88%) that use spatial arrangement information based on building types on the Pleiades and GeoEye datasets. Moreover, it is unnecessary to further categorize the dominant land cover type into finer types for the characterization of spatial arrangement. We conclude that the proposed method has a high potential for the characterization of urban structure using different VHR images, and for the extraction of urban land use in different urban areas.     

Polygonal Clustering Analysis Using Multilevel Graph‐Partition

Existing methods of spatial data clustering have focused on point data, whose similarity can be easily defined. Due to the complex shapes and alignments of polygons, the similarity between non‐overlapping polygons is important to cluster polygons. This study attempts to present an efficient method to discover clustering patterns of polygons by incorporating spatial cognition principles and multilevel graph partition. Based on spatial cognition on spatial similarity of polygons, four new similarity criteria (i.e. the distance, connectivity, size and shape) are developed to measure the similarity between polygons, and used to visually distinguish those polygons belonging to the same clusters from those to different clusters. The clustering method with multilevel graph‐partition first coarsens the graph of polygons at multiple levels, using the four defined similarities to find clusters with maximum similarity among polygons in the same clusters, then refines the obtained clusters by keeping minimum similarity between different clusters. The presented method is a general algorithm for discovering clustering patterns of polygons and can satisfy various demands by changing the weights of distance, connectivity, size and shape in spatial similarity. The presented method is tested by clustering residential areas and buildings, and the results demonstrate its usefulness and universality.     

基于邻近图的点群层次聚类方法的研究

空间聚类是点状空间目标群在地图综合中必须解决的问题。分析点群的几种常用邻近图的特征及其层次关系,并基于原始的点集合生成的DT构建相应的GG,UG,MST和NNG,然后在所选择的密度适应性约束、距离适应性约束和偏差适应性约束这三种条件下,利用所生成的邻近图进行了点群的层次聚类。研究并改进现有的点状空间目标群的无监督层次聚类方法,并通过实例验证该算法的可行性。     

鲁棒多特征谱聚类的高光谱影像波段选择

传统谱聚类的高光谱影像波段选择模型中,采用的波段相似矩阵受到噪声或异常值的影响且仅能表征波段的单一相似特征,导致波段子集的选取结果受到限制.本文从波段选择的目的 出发,提出鲁棒多特征谱聚类方法,整合多个特征的波段相似矩阵来形成综合相似矩阵以解决上述问题.该方法假设4种相似性度量包括光谱信息散度、光谱角度距离、波段相关性...     

密集城区高分辨率遥感影像建筑物提取

建筑物在地理国情监测中是一个重要目标,快速、准确地提取城市建筑物可以带来巨大的经济价值。本文在前人针对城市区域的建筑物提取研究基础上,对现有提取方法存在的问题,提出了一种针对密集城区的面向对象自动化建筑物提取流程。首先利用高分辨率遥感影像得到阴影和建筑物初提取结果;然后利用阴影和建筑物的空间位置关系,建立筛选条件,对疑似建筑物区域过滤;最后通过图割算法来精确建筑物轮廓。通过使用武汉地区的两幅QuickBird影像进行算法验证试验,可得到准确的检测结果。本算法可应用于密集城区的建筑物检测,能够有效减少人工判图的工作量。     

一种公寓式建筑物三维产权群集自动构建方法

建筑物在不同视角下分为物理群集和产权群集,后者依附于前者.现有的群集对象构建方法可以自动地构建同一栋建筑物的物理群集和产权群集,但生成的两个群集相互独立.这不仅增加建模成本,也不利于后期模型数据的更新和维护.针对该问题,研究公寓式建筑物物理群集与产权群集的关系,发现连通边界的层级性决定了胞腔聚合的产权体,提出了一种将物...     

空间聚类方法的分类

目前,空间聚类的研究成果主要集中在点目标方面,现有的分类方法也主要针对点目标的聚类。随着空间聚类研究和应用的不断深入,线目标、面目标的空间聚类方法也逐渐被提出,因此本文从空间目标的维度、是否顾及非空间属性、算法思想等3个方面,探讨了空间聚类的分类方法,进而简要阐述每种空间聚类方法的典型算法。     

一种可见光影像稠密匹配点云的单栋建筑物提取方法

建筑物点云提取是城市快速三维建模的基础。针对城区中建筑物和树木空间距离较近导致建筑物点云误提取的问题,提出一种颜色约束的欧式聚类算法。该方法利用低空拍摄可见光影像进行三维重建、获取点云数据,在建立点云K邻域索引和表面估计的基础上,以曲率最小的点作为欧式聚类的种子点,将点云的RGB值转换成Lab颜色模型,对建筑物点云的聚类提取进行约束。实验表明,该方法可以有效地解决可见光影像匹配点云中建筑物提取时将树木误提取的问题。     

空间知识挖掘的自然面群聚集度聚类方法

空间聚类是挖掘空间知识的重要手段之一。针对现有方法难以处理几何、分布特征差异大的面群聚类问题,本文提出了一种面要素分布密度的描述参数—聚集度,并设计了一种自然面群聚类方法。首先,分析了面要素分布密度的影响因子,定义了聚集度的概念,设计其计算方法并验证其有效性及优势;然后,基于聚集度和边界最短距离建立相邻面从属关系,识别聚类中心,完成初始群组的构建;最后,围绕群组特征设计了边缘检测和群组合并模型,实现了邻近相似群组的合并。试验表明,相较于最小生成树、强度函数聚类方法,本文方法兼顾几何特征、分布特征的复杂性,有效提升了自然面群的聚类效果。     

Optimisation of building detection in satellite images by combining multispectral classification and texture filtering

Conventional multispectral classification methods show poor performance with respect to detection of urban object classes, such as buildings, in high spatial resolution satellite images. This is because objects in urban areas are very complicated with respect to both their spectral and spatial characteristics. Multispectral classification detects object classes only according to the spectral information of the individual pixels, while a large amount of spatial information is neglected. In this study, a technique is described which attempts to detect urban buildings in two stages. The first stage is a conventional multispectral classification. In the second stage, the classification of buildings is improved by means of their spatial information through a modified co-occurrence matrix based filtering. The direction dependence of the co-occurrence matrix is utilised in the filtering process. The method has been tested by using TM and SPOT Pan merged data for the whole area of the city of Shanghai, China. After the co-occurrence matrix based filtering, the average user accuracy increased by about 46% and the average Kappa statistic by about 57%. This result is about 26% better than the accuracy improvement through normal texture filtering. The method presented in this study is very useful for a rapid estimation of urban building and city development, especially in metropolitan areas of developing countries.     

Building Displacement Based on the Topological Structure

Map data at smaller scales than their source can result in spatial conflict, whereby map symbols become too close, or overlaid. Server map generalisation operators may be applied to solve this problem, including displacement. In this paper, we show how an optimisation algorithm, the snake algorithm, was used to displace multiple objects in order to resolve spatial conflicts and maintain important spatial relationships between objects during displacement. Two principles based on the snake algorithm are proposed in this paper. First, the truss structure mirroring spatial proximity relationships between buildings and between building and road is formed based on the weighted proximity graph derived from constrained Delaunay triangulations (CDT) in each map partition. In the weighted proximity graph, each connecting line is determined as a snake and as an element unit to assemble the global stiffness matrix in snake algorithm. Second, a buffer method that calculates force between a building and a road (or other linear features) or between pair of buildings is adopted in the snake algorithm. This avoids the imbalance phenomenon caused by different force calculation methods during the displacement. The feasibility of the approach is demonstrated in obtaining real geographic data. Finally, the results are cartographically usable and in particular, the spatial relationships between objects are preserved.     

The market value of cultural heritage in urban areas: an application of spatial hedonic pricing

The current literature often values intangible goods like cultural heritage by applying stated preference methods. In recent years, however, the increasing availability of large databases on real estate transactions and listed prices has opened up new research possibilities and has reduced various existing barriers to applications of conventional (spatial) hedonic analysis to the real estate market. The present paper provides one of the first applications using a spatial autoregressive model to investigate the impact of cultural heritage—in particular, listed buildings and historic–cultural sites (or historic landmarks)—on the value of real estate in cities. In addition, this paper suggests a novel way of specifying the spatial weight matrix—only prices of sold houses influence current price—in identifying the spatial dependency effects between sold properties. The empirical application in the present study concerns the Dutch urban area of Zaanstad, a historic area for which over a long period of more than 20 years detailed information on individual dwellings, and their market prices are available in a GIS context. In this paper, the effect of cultural heritage is analysed in three complementary ways. First, we measure the effect of a listed building on its market price in the relevant area concerned. Secondly, we investigate the value that listed heritage has on nearby property. And finally, we estimate the effect of historic–cultural sites on real estate prices. We find that, to purchase a listed building, buyers are willing to pay an additional 26.9 %, while surrounding houses are worth an extra 0.28 % for each additional listed building within a 50-m radius. Houses sold within a conservation area appear to gain a premium of 26.4 % which confirms the existence of a ‘historic ensemble’ effect.     

基于多距离空间聚类的城市建筑景观时空分异研究

以大连市中山区6个街道建筑信息为数据基础,选取建筑景观指标,基于ArcGIS空间统计与多距离空间聚类分析方法研究了各街道10年间建筑景观空间格局分异特征。结果表明：从2003-2013年,各街道建筑景观逐渐由水平向垂直空间扩展,其中青泥洼桥街道、人民路街道及海军广场街道城市建筑景观变化明显突出;2003年4种类型建筑物在尺度为928.68 m时,空间分布上均呈聚集状态,当大于928.68 m时,超高层建筑空间聚集程度降低。到2013年,高层建筑物随尺度的增加聚集程度逐渐减低,低层、多层和超高层建筑在空间分布上均呈一定的聚集状态。     

利用目标区域拓扑关系图提取建筑物点云

建筑物提取一直是机载激光点云数据处理研究的热点,其中建筑物和其他地物之间的区分是研究的核心和难点。为提高建筑物与其他地物在机载激光点云中的区分能力,提出了一种建筑物点云层次提取方法。首先,在点云滤波后,从非地面点云中提取建筑物候选区域;然后,通过形态学重建和点云平面分割方法对建筑物候选区域构建多尺度空间,并建立目标区域的拓扑关系图;最后,在拓扑关系图基础上,利用5种特征量对目标区域分类,并精确提取建筑物点云。为了测试算法的有效性和可靠性,利用国际摄影测量与遥感学会（International Society for Photogrammetry and Remote Sensing,ISPRS）提供的Vaihingen和Toronto两组测试数据集进行实验,并由ISPRS对结果进行评估,其中基于面积和目标的完整度、正确率和提取质量分别都大于87.8%、94.7%、87.3%。与其他建筑物提取方法相比,该方法在基于面积和目标的质量指标方面最为稳定。实验结果表明,在不同的城市场景下,该算法能够稳健地提取建筑物,并保持很高的正确率。