Characterising Space via Pattern Recognition Techniques

Heinzle, Frauke; Anders, Karl–Heinrich

doi:10.1016/b978-008045374-3/50014-4

Cited by 46 publications

(35 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such sequences, so-called strokes, correspond to major road axes that need to be preserved during generalization, for example, when selecting a subset of all roads for a map. Heinzle and Anders (2007) present algorithms to find star-like structures, rings, and regular grids in road networks in order to improve the generalization of networks. Christophe and Ruas (2002) as well as Ruas and Holzapfel (2003) present methods to find alignments of buildings.…”

Section: Related Workmentioning

confidence: 99%

A symmetry detector for map generalization and urban-space analysis

Haunert¹

2012

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

A symmetry detector for map generalization and urban-space analysis

Haunert¹

2012

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

“…These two methods for grid recognition are both polygon-based structural recognition approach. For star pattern, Heinzle et al (2005Heinzle et al ( , 2007 take any node in the graph as potential center point, use the Dijkstra algorithm to compute the single source shortest path from this node to all other nodes, and then use a circle with a certain radius to search the center. The fuzzy center is determined by a cluster algorithm.…”

Section: Methods Of Recognition Of Patternsmentioning

confidence: 99%

Graph Based Recognition of Grid Pattern in Street Networks

Tian

Jia

2012

Lecture Notes in Geoinformation and Cartography

View full text Add to dashboard Cite

ABSTRACT:Pattern recognition is an important step in map generalization. Pattern recognition in street network is significant for street network generalization. A grid is characterized by a set of mostly parallel lines, which are crossed by a second set of parallel lines with roughly right angle. Inspired by object recognition in image processing, this paper presents an approach to the grid recognition in street network based on graph theory. Firstly, the bridges and isolated points of the network are identified and deleted repeatedly. Secondly, the similar orientation graph is created, in which the vertices represent street segments and the edges represent the similar orientation relation between streets. Thirdly, the candidates are extracted through graph operators such as finding connected component, finding maximal complete sub-graph, join and intersection. Finally, the candidate are evaluated by deleting bridges and isolated lines repeatedly, reorganizing them into stroke models, changing these stroke models into street intersection graphs in which vertices represent strokes and edges represent strokes intersecting each other, and then calculating the clustering coefficient of these graphs. Experimental result shows the proposed approach is valid in detecting the grid pattern in lower degradation situation.

show abstract

“…[18] find repetitive structures based on local similarity sets gained with the approach of [15], and extend them to uniform grids. Recognition of repetitive structures in road networks has been investigated by [19]. Another possibility is to use formal grammars as a structural representation of facades, as has been used for the interpretation of building facades [20] and for building reconstruction [21].…”

Section: Existing Spatial Properties and Relations Relevant To The Mamentioning

confidence: 99%

Towards a typology of spatial relations and properties for urban applications

Bucher

Falquet

Clementini

et al. 2012

Usage, Usability, and Utility of 3D City Models – European COST Action TU0801

View full text Add to dashboard Cite

Abstract.Relations that occur between features located in space-like the fact that a street is surrounded by very high buildings, that an airport is close to a city-as well as spatial properties of features-like the height and width of a door-play an important role for many urban applications. Digital models of cities can assist in the evaluation of these relations and properties either through visualisation or through computation, mainly based on geometrical information. Hence, considering the objective of explaining to potential users of these city models what useful information they can derive from these data and how, a possible way to address this objective lies in the usage of a pivot model composed of relevant spatial properties and relations, connected to information meaningful to the user and connected to the possible computation of them on available data. This paper firstly sets the ground for a typology of such relevant relations and properties that are shared by different applications and that can be derived/approximated from existing data. It then proposes a model to describe these properties and relations and connect them to their possible computation based on data (2D or 3D). An important aspect of this model is to distinguish between a conceptual layer where relations occur between "real world" features and an implementation layer where they are calculated based on database features and geometries.

show abstract

Characterising Space via Pattern Recognition Techniques

Cited by 46 publications

References 0 publications

A symmetry detector for map generalization and urban-space analysis

A symmetry detector for map generalization and urban-space analysis

Graph Based Recognition of Grid Pattern in Street Networks

Towards a typology of spatial relations and properties for urban applications

Contact Info

Product

Resources

About