Dirk Burghardt

An Approach for the Classification of Urban Building Structures Based on Discriminant Analysis Techniques

Recognition of urban structures is of interest in cartography and urban modelling. While a broad range of typologies of urban patterns have been published in the last century, relatively little research on the automated recognition of such structures exists. This work presents a sample-based approach for the recognition of five types of urban structures: (1) inner city areas, (2) industrial and commercial areas, (3) urban areas, (4) suburban areas and (5) rural areas. The classification approach is based only on the characterisation of building geometries with morphological measures derived from perceptual principles of Gestalt psychology. Thereby, size, shape and density of buildings are evaluated. After defining the research questions we develop the classification methodology and evaluate the approach with respect to several aspects. The experiments focus on the impact of different classification algorithms, correlations and contributions of measures, parameterisation of buffer-based indices, and mode filtering. In addition to that, we investigate the influence of scale and regional factors. The results show that the chosen approach is generally successful. It turns out that scale, algorithm parameterisation, and regional heterogeneity of building structures substantially influence the classification performance.

Generalization Services on the Web-Classification and an Initial Prototype Implementation

Much progress has been made in the field of web-based cartography through standards developed by the Open Geospatial Consortium (OGC). While automated access and presentation of cartographic data have been defined, the services for automated generalization are yet to be standardized. This paper aims to show advantages of applying the service concept to generalization and suggests several classification schemas of generalization services at different levels of granularity. A detailed explanation of a real implemented Generalization Service is provided. We show how software developers can make their generalization functionality available as a service and how these services can be accessed dynamically. For the implementation, the open source Java Unified Mapping Platform (JUMP) was extended to work as a framework for generalization. Generalization services could be used in different application scenarios, for instance as a middleware component extending a web map service with adaptive zooming or as stand-alone services supporting the production of topographic maps by national mapping agencies. They may also allow the development of a common research platform, where researchers would have access to a common generalization framework.

Methodology for evaluating automated map generalization in commercial software

This paper presents a methodology developed for a study to evaluate the state of the art of automated map generalization in commercial software without applying any customization. The objectives of this study are to learn more about generic and specific requirements for automated map generalization, to show possibilities and limitations of commercial generalization software, and to identify areas for further research. The methodology had to consider all types of heterogeneity to guarantee independent testing and evaluation of available generalization solutions. The paper presents the two main steps of the methodology. The first step is the analysis of map requirements for automated generalization, which consisted of sourcing representative test cases, defining map specifications in generalization constraints, harmonizing constraints across the test cases, and analyzing the types of constraints that were defined. The second step of the methodology is the evaluation of generalized outputs. In this step, three evaluation methods were integrated to balance between human and machine evaluation and to expose possible inconsistencies. In the discussion the applied methodology is evaluated and areas for further research are identified.

Integrating ontological modelling and Bayesian inference for pattern classification in topographic vector data

This paper presents an ontology-driven approach for spatial database enrichment in support of map generalisation. Ontology-driven spatial database enrichment is a promising means to provide better transparency, flexibility and reusability in comparison to purely algorithmic approaches. Geographic concepts manifested in spatial patterns are formalised by means of ontologies that are used to trigger appropriate low level pattern recognition techniques. The paper focuses on inference in the presence of vagueness, which is common in definitions of spatial phenomena, and on the influence of the complexity of spatial measures on classification accuracy. The concept of the English terraced house serves as an example to demonstrate how geographic concepts can be modelled in an ontology for spatial database enrichment. Owing to their good integration into ontologies, and their ability to deal with vague definitions, supervised Bayesian inference is used for inferring complex concepts. The approach is validated in experiments using large vector datasets representing buildings of four different cities. We compare classification results obtained with the proposed approach to results produced by a more traditional ontology approach. The proposed approach performed considerably better in comparison to the traditional ontology approach. Besides clarifying the benefits of using ontologies in spatial database enrichment, our research demonstrates that Bayesian networks are a suitable method to integrate vague knowledge about conceptualisations in cartography and GIScience.

Mesh simplification for building typification

This paper describes an approach for the typification of buildings using a mesh‐simplification technique. The approach is adapted from the area of computer graphics and was originally developed for surface reconstruction and mesh simplification. The main goal was to develop an algorithm which creates fast and reproducible results. The typification procedure is modelled as a two‐stage process, with the steps ‘positioning’ and ‘representation’. While the positioning step determines the number and the position of the building objects based on Delaunay triangulation, the representation step is used to calculate the size and orientation for the replacement buildings. The results presented show the important influence of weights during positioning steps to control the object distribution. The proposed parameters are the number of objects as well as several object characteristics such as size, shape, orientation, and semantic. The approach has to be extended, if building alignments are also to be preserved. Further applications are imaginable, for instance the icon placement on dynamic maps.

Controlled Line Smoothing by Snakes

A major focus of research in recent years has been the development of algorithms for automated line smoothing. However, combination of the algorithms with other generalization operators is a challenging problem. In this research a key aim was to extend a snakes optimization approach, allowing displacement of lines, to also be used for line smoothing. Furthermore, automated selection of control parameters is important for fully automated solutions. An existing approach based on line segmentation was used to control the selection of smoothing parameters dependent on object characteristics. Additionally a new typification routine is presented, which uses the same preprocessed analysis for the segmentation of lines to find suitable candidates from curve bends. The typification is realized by deleting undersized bends and emphasizing the remaining curve bends. The main results of this research are two new algorithms for line generalization, where the importance of the line smoothing algorithm lies in the usage of a optimization approach which can also be used for line displacement.

Multi-representation Databases with Explicitly Modeled Horizontal, Vertical, and Update Relations

This paper presents a new approach to combining multi-representation databases with the generalization and update processes. It leads to a tightly integrated model which is a part of the existing cartographic GIS axpand. The approach is based on the mathematical concept of relations and, in particular, on three different types of relations: horizontal (within one resolution), vertical (between different resolutions), and update. Horizontal relations allow the representation of relationships between features within one resolution. Examples are partitions, neighborhoods, and topology. The vertical relation represents the relationship between features of different resolutions. This originates from a generalization or matching process. The update relation describes temporal changes of features. After a detailed theory about the relation types introduced, the paper continues with a discussion of their similarities and differences, with a focus on implementation in a multi-representation database. A prototype demonstrates the generalization of buildings and roads from vector data at 1: 25,000 to 1: 50,000 scales. The paper ends with conclusions and an outlook on further research tasks.

Web service approaches for providing enriched data structures to generalisation operators

Web service technologies can be used to establish an interoperable framework between different generalisation systems. In a previous article three categories of generalisation web services were identified, including support services, operator services and processing services. This paper focuses on the category of support services. In a service‐based generalisation system, the purpose of support services is to assist the generalisation process by providing auxiliary measures, procedures and data structures that allow the representation of structural cartographic knowledge. The structural knowledge of the spatial and semantic context and the modelling of structural and spatial relationships is critical for the understanding of the role of cartographic features and thus for automated generalisation. Support services should extract and model this knowledge from the raw data and make it available to other generalisation operators. On the one hand the structural knowledge can be expressed by enriching map features with additional geometries or attributes. On the other hand, there exist various hierarchical and non‐hierarchical relationships between map features, many of which can be represented by graph data structures. After a brief introduction to the interoperable web service framework, this paper proposes a taxonomy of generalisation support services and discusses its elements. It is then shown how the complex output of such services can be represented for use with web services and stored in a reusable fashion. Finally, the utilisation of support services is illustrated on four implementation examples of support services that also highlight the interactions with the generalisation operators that use these auxiliary services.

Integrating and Generalising Volunteered Geographic Information

The availability of spatial data on the web has greatly increased through the availability of user-generated community data and geosensor networks. The integration of such multi-source data is providing promising opportunities, as integrated information is richer than can be found in only one data source, but also poses new challenges due to the heterogeneity of the data, the differences in quality and in respect of tag-based semantic modelling. The chapter describes approaches for the integration of official and informal sources, and discusses the impact of integrating user-generated data on automated generalisation and visualisation.

Automated processing for map generalization using web services

In map generalization various operators are applied to the features of a map in order to maintain and improve the legibility of the map after the scale has been changed. These operators must be applied in the proper sequence and the quality of the results must be continuously evaluated. Cartographic constraints can be used to define the conditions that have to be met in order to make a map legible and compliant to the user needs. The combinatorial optimization approaches shown in this paper use cartographic constraints to control and restrict the selection and application of a variety of different independent generalization operators into an optimal sequence. Different optimization techniques including hill climbing, simulated annealing and genetic deep search are presented and evaluated experimentally by the example of the generalization of buildings in blocks. All algorithms used in this paper have been implemented in a web services framework. This allows the use of distributed and parallel processing in order to speed up the search for optimized generalization operator sequences.