Representation and discovery of building patterns: a three-level relational approach

Du, Shihong; Shu, Mi; Feng, Chen‐Chieh

doi:10.1080/13658816.2015.1108421

Cited by 31 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Local typification is often combined with building grouping and pattern detection. Many ideas were proposed to detect building groups and recognize building patterns [15][16][17][18][19][20][21][22][23][24]. Local typification normally concentrates on the buildings with regular patterns, such as linear patterns and grid patterns.…”

Section: Related Workmentioning

confidence: 99%

A Mesh-Based Typification Method for Building Groups with Grid Patterns

Wang

Burghardt

2019

IJGI

View full text Add to dashboard Cite

Building groups with special patterns are common layouts in urban settlement areas, which should be carefully generalized. Typification is considered as an appropriate operator to generalize building groups with grid patterns. As an important operator in building generalization, the purpose of typification is to reduce the number of objects while preserving the original distribution characteristics as much as possible. This study proposes a mesh-based method to typify buildings with grid patterns. Firstly, the pattern is subdivided into perfect grid or grid-like patterns by considering the completeness of the grids. The proposed typification method consists of three steps: (1) generating mesh from the proximity graph of buildings; (2) eliminating triangular meshes; (3) determining the number, positions, and representations of the newly created buildings with the help of the related meshes. The proposed method is modeled as an iterative process to achieve hierarchical typification results, which provides support to the map multiple representation. The experimental results demonstrate that the mesh-based typification method can achieve satisfying results in the perfect grid pattern, as well as the grid-like pattern. The new distribution of the typified buildings preserves the original pattern characteristics.

show abstract

Section: Related Workmentioning

confidence: 99%

A Mesh-Based Typification Method for Building Groups with Grid Patterns

Wang

Burghardt

2019

IJGI

View full text Add to dashboard Cite

show abstract

“…Building patterns refer to visually salient structures exhibited collectively by a group of buildings [4]. Traditional patterns detection methods are to predefine some specific perceptual rules according to the characteristics of azimuth angle, direction difference and proximity, and then to inquire whether there is a local group that satisfy such rules [3][8] [10].…”

Section: Definition Of Building Pattern Classificationmentioning

confidence: 99%

Analysis of Irregular Spatial Data with Machine Learning: Classification of Building Patterns with a Graph Convolutional Neural Network

Yan,

2018

Preprint

View full text Add to dashboard Cite

Machine learning methods such as convolutional neural networks (CNNs) are becoming an integral part of scientific research in many disciplines, spatial vector data often fail to be analyzed using these powerful learning methods because of its irregularities. With the aid of graph Fourier transform and convolution theorem, it is possible to convert the convolution as a point-wise product in Fourier domain and construct a learning architecture of CNN on graph for the analysis task of irregular spatial data. In this study, we used the classification task of building patterns as a case study to test this method, and experiments showed that this method has achieved outstanding results in identifying regular and irregular patterns, and has significantly improved in comparing with other methods.

show abstract

“…As the most common geographical entities in urban areas, buildings are important directional objects for users when using maps for navigation. The linear pattern formed by buildings refers to the arrangement and the form exhibited by a collection of buildings at a certain scale in the mapping space [1,2]. The pattern looks like a line, and its elements, i.e., buildings, are homogeneous in terms of spatial properties (e.g., spacing, orientation, shape, and density) [3].…”

Section: Introductionmentioning

confidence: 99%

Recognizing Linear Building Patterns in Topographic Data by Using Two New Indices based on Delaunay Triangulation

Deng

Luo

2020

IJGI

View full text Add to dashboard Cite

Building pattern recognition is fundamental to a wide range of downstream applications, such as urban landscape evaluation, social analyses, and map generalization. Although many studies have been conducted, there is still a lack of satisfactory results, due to the imprecision of the relative direction model of any two adjacent buildings and the ineffective extraction methods. This study aims to provide an alternative for quantifying the direction and the spatial continuity of any two buildings on the basis of the Delaunay triangulation for the recognition of linear building patterns. First, constrained Delaunay triangulations (CDTs) are created for all buildings within each block and every two adjacent buildings. Then, the spatial continuity index (SCI), the direction index (DI), and other spatial relations (e.g., distance) of every two adjacent buildings are derived using the CDT. Finally, the building block is modelled as a graph based on derived matrices, and a graph segmentation approach is proposed to extract linear building patterns. In the segmentation process, the edges of the graph are removed first, according to the global thresholds of the SCI and distance, and are subsequently subdivided into subgraphs on direction rules. The proposed method is tested using three datasets. The experimental results suggest that the proposed method can recognize both collinear and curvilinear building patterns, given that the correctness values are all above 92% for the three study areas. The results also demonstrate that the novel SCI can effectively filter many insignificant neighbor relationships in the graph segmentation process. It is noteworthy that the proposed DI is capable of measuring building relative directions accurately and works efficiently in linear building pattern extraction.

show abstract

Representation and discovery of building patterns: a three-level relational approach

Cited by 31 publications

References 25 publications

A Mesh-Based Typification Method for Building Groups with Grid Patterns

A Mesh-Based Typification Method for Building Groups with Grid Patterns

Analysis of Irregular Spatial Data with Machine Learning: Classification of Building Patterns with a Graph Convolutional Neural Network

Recognizing Linear Building Patterns in Topographic Data by Using Two New Indices based on Delaunay Triangulation

Contact Info

Product

Resources

About