特征分类与邻近图相结合的建筑物群空间分布特征提取方法

建筑物群综合过程中需要对建筑物群空间分布特征进行认知和识别。本文在分析国内外相关研究的基础上,从描述建筑物空间特征的大量指标中,利用主成份分析方法,总结并提出了有代表性的建筑物空间特征指标集:凸包面积、紧密度IPQ指标、边数和最小面积外接矩形方向,并基于这些指标研究了建筑物群的分类。在利用最小生成树邻近图(MST)划分建筑物空间子群时,考虑了建筑物成群与所处地理环境(河流和道路等因素)的关系。另外,基于最邻近图(NNG)、MST、相对邻近图(RNG)和Gabriel图(GG)4种建筑物群邻近图,提出了自动识别具有特定空间排列建筑物子群的方法,并比较分析了识别结果的影响因素和可用性。最后,选择北京某地区建筑物群为试验对象,实现了对建筑物群的分类和空间聚类,并提取了其中直线型空间排列的建筑物子群。     

直线排列建筑物群渐进式典型化方法

地图综合中,建筑物群的排列结构是需要重点考虑的因素。当不同排列的子建筑物群之间存在空间图形冲突时,这些建筑物群的综合就显得更为复杂。直线排列建筑物群的综合在大比例尺地形图上以典型化操作为主。本文提出一种相互之间存在潜在空间图形冲突的多个直线排列建筑物子群的渐进式典型化方法,渐进式地处理多个直线排列建筑物子群之间的空间图形冲突,保留建筑物群重要的直线排列结构;以建筑物表达的视觉图形约束为限制条件,自动确定典型化后的建筑物位置、形状、大小和方位。本文还研究了基于建筑物群空间邻近图的直线排列建筑物子群的自动识别方法,分析了这些直线排列之间的邻近关系和相交关系。最后,以1：5000地图上的建筑物群综合为1：25 000为试验对象,验证了所提出算法的可用性和有效性。     

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。     

Proximity-based grouping of buildings in urban blocks: a comparison of four algorithms

Grouping of buildings based on proximity is a pre-processing step of urban pattern (structure) recognition for contextual cartographic generalization. This paper presents a comparison of grouping algorithms for polygonal buildings in urban blocks. Four clustering algorithms, Minimum Spanning Tree (MST), Density-Based Spatial Clustering Application with Noise (DBSCAN), CHAMELEON and Adaptive Spatial Clustering based on Delaunay Triangulation (ASCDT) are reviewed and analysed to detect building groups. The success of the algorithms is evaluated based on group distribution characteristics (i.e. distribution of the buildings in groups) with two methods: S_Dbw and newly proposed Cluster Assessment Circles. A proximity matrix of the nearest distances between the building polygons, and Delaunay triangulation of building vertices are created as an input for the algorithms. A topographic data-set at 1:25,000 scale is used for the experiments. Urban block polygons are created to constrain the clustering processes from topological aspect. Findings of the experiment demonstrate that DBSCAN and ASCDT are superior to CHAMELEON and MST. Among them, MST has exhibited the worst performance for finding meaningful building groups in urban blocks.     

支持地图综合的面状目标约束Delaunay三角网剖分

针对多边形面状目标的综合问题,建立了二维空间中约束Ｄｅｌａｕｎａｙ三角网剖分结构,融入多边形的环、岛屿、边界、顶点的描述,通过形式化条件检索,在该结构上提取二维空间中各种感兴趣的由剖分三角形组成的区域,用于支持地图综合中邻近多边形的搜索、多边形弯曲部位的识别、冲突关系探测、多边形合并等操作。并对基于骨架线的图结构建立、分枝宽度计算等几何问题进行了详细讨论,指出了其在诸如双线河中轴化、街道中轴线网络模型建立、多边形合并中的邻近关系分析、面状目标注记自动定位领域的支持作用。     

A spatial contextual immune genetic algorithm to building cartographic displacement

In map generalization, displacement is the most frequently used operator to reduce the proximity conflicts caused by reducing scales or other generalization operations. Building displacement can be formalized as a combinatorial optimization problem, and a heuristic or intelligent search algorithm can be borrowed to obtain the solution. In this way, we can explicitly resolve minimum distance conflicts and control positional accuracy during the displacement. However, maintaining spatial relations and patterns of buildings can be challenging. To address spatial conflicts as well as preserve the significant spatial relations and patterns of buildings, we propose a new spatial contextual displacement algorithm based on an immune genetic algorithm. To preserve important spatial relations and global patterns of map objects and avoid topology errors, displacement safety zones are constructed by overlapping the Voronoi tessellation and buffer areas of the buildings. Additionally, a strategy to shift the buildings in a building group synchronously is used to maintain local building patterns. To demonstrate the effectiveness of our algorithm, two data sets with different building densities were tested. The results indicate that the new algorithm has obvious advantages in preventing topology errors and preserving spatial relations and patterns.     

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。     

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...     

A typification method for linear pattern in urban building generalisation

This paper presents a typification method for linear pattern in urban building generalization. The proposed method includes two processes. Firstly, structural knowledge in terms of linear pattern is detected using a two-step algorithm taking the advantages of Gestalt visual perception, computational geometry and graph theory. Spatial neighbourhood is captured using interpolated constrained Delaunay triangulation and the resulting proximity graph is pruned to be heterogeneous to get acceptable linear patterns with regard to Gestalt visual perception. Then, a typification strategy is proposed, in which typification is regarded as a progressive and iterative process consisting of elimination, exaggeration and displacement. The typification strategy iteratively executes eliminating the building with minimum overall effect, exaggerating remaining buildings considering key location and spatial characteristics and displacing them to preserve the linear pattern until elimination quantity is satisfied. Experiments show that this proposed strategy is effective and linear patterns are guaranteed with correctness and completeness.     

一种建筑物只能聚类方法

建筑物聚类是大比例尺地图自动制图综合中需要解决的关键问题。通过分析Gestalt原理的邻近性、相似性等,采用建筑物重心、建筑物间的距离、建筑物与邻近线状地物要素间位置关系等参数描述建筑物。本文提出的建筑物智能聚类方法包含两个连续的步骤:首先计算建筑物的描述参数,利用SOM网络的聚类能力,进行建筑物的初步聚类;然后,利用SOM竞争层行列扫描的方法,对初步聚类的建筑物类簇进行精确划分,获得满足建筑物聚类的全局和局部约束条件等制图要求的建筑物聚类群组。     

Graph distance and feature-guided multi-view clustering: A novel method for clustering urban buildings

Urban buildings are an integral component of urban space, and accurately identifying their spatial configurations and grouping them is vital for various urban applications. However, most existing building clustering methods only utilize the original spatial and nonspatial features of buildings, disregarding the potential value of complementary information from multiple perspectives. This limitation hinders their effectiveness in scenarios with intricate spatial configurations. To address this, this article proposes a novel multi-view building clustering method that captures cross-view information from spatial and nonspatial features. Drawing inspiration from both spatial proximity characteristics and nonspatial attributes, three views are established, including two spatial distance graphs (centroid distance graph and the nearest outlier distance graph) and a building attribute graph (multiple-attribute graph). The three graphs undergo iterative cross-diffusion processes to amplify similarities within each predefined graph view, culminating in their fusion into a unified graph. This fusion facilitates the comprehensive correlation and mutual enhancement of spatial and nonspatial information. Experiments were conducted using 10 real-world community-building datasets from Wuhan and Chengdu, China. The results demonstrate that our approach achieves 21.27% higher accuracy and 22.28% higher adjusted rand index in recognizing diverse complex arrangements compared to existing methods. These findings highlight the importance of leveraging complementary and consensus information across different feature dimensions for improving the performance of building clustering.     

一种建筑群同质二元组直线模式的识别方法

建筑群空间分布模式识别对制图综合、多尺度表达及空间数据挖掘具有重要意义.针对建筑群中以建筑物组合结构为单元的直线模式识别问题,提出一种建筑群同质二元组直线模式的识别方法.首先分析研究同质二元组直线模式的认知特征和定义;然后利用Delaunay三角网构建建筑群邻近关系,以建筑物邻近性、尺寸和方向相似性约束进行聚类,考虑邻...     

基于格式塔识别原则挖掘空间分布模式

面向空间群目标的分布模式识别是空间数据挖掘比较关注的问题。本研究基于空间认知原理与视觉识别格式塔完形原则并结合空间聚类方法对该问题进行研究,提出用于描述实体间差异的"视觉距离"概念,其定义综合考虑视觉识别中的位置、方向、大小差异,通过Delaunay三角网计算几何构造建立该距离计算的模型。在实验基础上提出基于最小支撑树MST的聚类方法,获得与视觉认知相一致的结果。研究试图表明一个观念,即通用性的数据处理模型在GIS实际应用时,需要根据GIS作为"空间认知"科学的原理,作技术方法上的改进,需要考虑认知主体在感知、辨析、识别、推理不同思维过程中的认知心理原则。     

基于图分割的可变比例尺地图分幅回溯算法

总结了地图分幅需遵循的原则,并针对地图集中可变比例尺的分幅,将其定义为基于约束条件的图分割问题,用最小生成树(minimum spanning tree,MST)将制图区域关联起来,基于回溯算法对MST裁剪实现地图集的分幅。实验结果表明,所提出的方法能较好顾及地图集分幅的相关原则,满足地图集制作的要求。同时,利用该方法设计的地图集分幅工具已成功应用于《武汉市汉阳地区地名图集》等的制作,有效提高了地图设计人员的工作效率。     

制图综合中建筑物多边形的合并与化简

讨论了数字环境下顾及建筑物矩形几何特征的多边形自动综合算法,针对多边形之间的拓扑邻近与视觉邻近两种空间关系,提出了基于矢量和基于栅格的两种建筑物多边形合并方法。关于建筑物形状的化简,本文提出了矩形差分方法,并在此基础上建立了建筑物多边形化简的层次化途径。     

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.     

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.     

一种基于降维技术的街区综合方法

大比例尺城市建筑物综合一直是自动综合研究的重点。利用大比例尺城市建筑物和街道之间存在几何空间互补的特点,提出依据建筑物骨架线和街道骨架线对街区进行综合的新方法。定义骨架线提取方法,分析建筑物骨架线和街道骨架线之间的特性,在此基础上,提出基于降维技术的建筑物合并、化简、位移等综合方法。进一步,充分概括了本方法在自动综合技术实现上的优越性,并通过实验证明其有效性。     

全局局部细节感知条件随机场的高分辨率遥感影像建筑物提取

条件随机场模型由于其较强的上下文信息建模能力,被广泛应用于建筑物提取任务中。然而,面对高分辨率遥感影像丰富的地物信息,基于条件随机场的提取方法存在建筑物边界模糊的问题。本文提出了一种全局局部细节感知条件随机场框架,该框架提出全局局部一体化D-LinkNet,在有效利用多尺度建筑物信息的同时保留局部结构信息,解决了传统条件随机场一元势能丢失边界信息的问题。同时,该框架融合分割先验以缓解建筑物类内光谱差异较大的影响,利用更大尺度的上下文信息来精确提取建筑物,并引入局部类别标记代价从而保持细节信息以获取清晰的建筑物边界。实验结果表明,该框架在WHU卫星和航空数据集上的精度评价指标均优于其他对比方法,其IoU分别达89.82%和91.72%,对于复杂场景下的建筑物信息能够获得较好的提取效果。     

多因子影响的地图居民地自动聚群与综合研究

提出了地图综合目的的居民地聚群需要遵循Gestalt的邻近性、相似性和方向性原则,描述居民地结构、形态及其关系需要6个因子,即居民地间的距离、可视区域面积、大小相似度、形状相似度、方向关系、居民地内部方向;进而运用这些原则和因子,给出了居民地的自动聚群和综合方法.