Now showing 1 - 10 of 26
  • Publication
    Inferring Semantics from Geometry - the Case of Street Networks
    This paper proposes a method for automatically inferring semantic type information for a street network from its corresponding geometrical representation. Specifically, a street network is modelled as a probabilistic graphical model and semantic type information is inferred by performing learning and inference with respect to this model. Learning is performed using a maximum-margin approach while inference is performed using a fusion moves approach. The proposed model captures features relating to individual streets, such as linearity, as well as features relating to the relationships between streets such as the co occurrence of semantic types. On a large street network containing 32,412 street segments, the proposed model achieves precision and recall values of 68% and 65% respectively. One application of this work is the automation of street network mapping.
  • Publication
    Storage, manipulation, and visualization of LiDAR data
    (International Society of Photogrammetry and Remote Sensing, 2009-02) ; ; ;
    In recent years, three-dimensional (3D) data has become increasingly available, in part as a result of significant technological progresses in Light Detection and Ranging (LiDAR). LiDAR provides longitude and latitude information delivered in conjunction with a GPS device, and elevation information generated by a pulse or phase laser scanner, which together provide an effective way of acquiring accurate 3D information of a terrestrial or manmade feature. The main advantages of LiDAR over conventional surveying methods lie in the high accuracy of the data and the relatively little time needed to scan large geographical areas. LiDAR scans provide a vast amount of data points that result in especially rich, complex point clouds. Spatial Information Systems (SISs)are critical to the hosting, querying, and analyzing of such spatial data sets. Feature-rich SISs have been well-documented. However, the implementation of support for 3D capabilities in such systems is only now being addressed. This paper analyzes shortcomings of current technology and discusses research efforts to provide support for the querying of 3D data records in SISs.
  • Publication
    Evaluating the benefits of Octree-based indexing for LiDAR data
    (American Society for Photogrammetry & Remote Sensing, 2012) ; ; ;
    In recent years the geospatial domain has seen a significant increase in the availability of very large three dimensional (3D) point datasets. These datasets originate from a variety of sources, such as for example Light Detection and Ranging (LiDAR) or meteorological weather recordings. Increasingly, a desire within the geospatial community has been expressed to exploit these types of 3D point data in a meaningful engineering context that goes beyond mere visualization. However, current Spatial Information Systems (SISs) provide only limited support for vast 3D point datasets. Even those systems that advertise their support for in-built 3D data types provide very limited functionality to manipulate such data types. In particular, an effective means of indexing large 3D point datasets is yet missing, however it is crucial for effective analysis. Next to the large size of 3D point datasets they may also be information rich, for example they may contain color information or some other associated semantic. This paper presents an alternative spatial indexing technique, which is based on an octree data structure. We show that it outperforms R-tree index, while being able to group 3D points based on their attribute values at the same time. This paper presents an evaluation employing this octree spatial indexing technique and successfully highlights its advantages for sparse as well as uniformly distributed data on the basis of an extensive LiDAR dataset.
  • Publication
    Three-dimensional spatial information systems : state of the art review
    A spatial information system (SIS) is critical to the hosting, querying, and analyzing of spatial data sets. The increasing availability of three-dimensional (3D) data (e.g. from aerial and terrestrial laser scanning) and the desire to use such data in large geo-spatial platforms have been dual drivers in the evolution of integrated SISs. Within this context, recent patents demonstrate efforts to handle large data sets, especially complex point clouds. While the development of feature-rich geo-systems has been well documented, the implementation of support for 3D capabilities is only now being addressed. This paper documents the underlying technologies implemented for the support for 3D features in SISs. Examples include ESRI’s ArcGIS geo-database with its support for two-and-a-half dimensions (2.5D) in its Digital Elevation Model (DEM) and Triangular Irregular Network (TIN), the more recent development of the Terrain feature class, and support for 3D objects and buildings with its multi-patch feature class. Recent patents and research advances aim to extract DEMs and TINs automatically from point cloud data. In this context, various data structuring innovations are presented including both commercial and open source alternatives.
  • Publication
    An agent-based architecture for wireless bus travel assistants
    Multi-agent systems are open and extensible systems that allow for the deployment of autonomous and proactive software components. This paper describes how a multi-agent architecture has been developed to extend a previously implemented bus travel assistant prototype called Bus Catcher [2]. Such a system was developed to provide accurate information about bus locations and arrival times to Dublin Bus users. The new version of the system is more flexible and easily extensible as it relies on generic agents responsible for channeling context sensitive services. New features have also been added to the system, including user profiling and monitoring of available hardware/service characteristics
  • Publication
    The Similarity Jury: Combining expert judgements on geographic concepts
    A cognitively plausible measure of semantic similarity between geographic concepts is valuable across several areas, including geographic information retrieval, data mining, and ontology alignment. Semantic similarity measures are not intrinsically right or wrong, but obtain a certain degree of cognitive plausibility in the context of a given application. A similarity measure can therefore be seen as a domain expert summoned to judge the similarity of a pair of concepts according to her subjective set of beliefs, perceptions, hypotheses, and epistemic biases. Following this analogy, we first define the similarity jury as a panel of experts having to reach a decision on the semantic similarity of a set of geographic concepts. Second, we have conducted an evaluation of 8 WordNet-based semantic similarity measures on a subset of OpenStreetMap geographic concepts. This empirical evidence indicates that a jury tends to perform better than individual experts, but the best expert often outperforms the jury. In some cases, the jury obtains higher cognitive plausibility than its best expert.
      601Scopus© Citations 7
  • Publication
    Mining Spatio-temporal Data at Different Levels of Detail
    In this paper we propose a methodology for mining very large spatio-temporal datasets. We propose a two-pass strategy for mining and manipulating spatio-temporal datasets at different levels of detail (i.e., granularities). The approach takes advantage of the multi-granular capability of the underlying spatio-temporal model to reduce the amount of data that can be accessed initially. The approach is implemented and applied to real-world spatio-temporal datasets. We show that the technique can deal easily with very large datasets without losing the accuracy of the extracted patterns, as demonstrated in the experimental results.
      1105Scopus© Citations 6
  • Publication
    An open-source web architecture for adaptive location-based services
    (International Society for Photogrammetry and Remote Sensing, 2010) ; ; ;
    As the volume of information available online continues to grow, there is an increasing problem with information overload. This issue is also escalating in the spatial domain as the amount of geo-tagged information expands. With such an abundance of geo-information, it is difficult for map users to find content that is relevant to them. The problem is intensified when considering Location-Based Services. These services, which are dependent upon a user’s geographic location, generally operate on portable devices. These devices have a reduced screen size coupled with a limited processing power and so the need to provide personalised content is of paramount importance. Our previous work has focused on examining techniques to determine user interests in order to provide adapted and personalised map content which is suitable to display on portable devices. In this paper, in order to reduce the processing load on the user’s device, a novel client server architecture is employed. The framework is designed using open-source, web-based technologies which monitor user locations and interactions with map content overtime to produce a user profile. This profile is then used to render personalised maps. By utilising the power of web-based technologies in an innovative manner, any operational issues between different mobile devices is alleviated, as the device only requires a web-browser to receive map content. This article describes the techniques, architecture and technologies used to achieve this.
  • Publication
    Automated Highway Tag Assessment of OpenStreetMap Road Networks
    OpenStreetMap (OSM) has been demonstrated to be a valuable source of spatial data in the context of many applications. However concerns still exist regarding the quality of such data and this has limited the proliferation of its use. Consequently much research has been invested in the development of methods for assessing and/or improving the quality of OSM data. However most of these methods require ground-truth data, which, in many cases, may not be available. In this paper we present a novel solution for OSM data quality assessment that does not require ground-truth data. We consider the semantic accuracy of OSM street network data, and in particular, the associated semantic class (road class) information. A machine learning model is proposed that learns the geometrical and topological characteristics of di erent semantic classes of streets. This model is subsequently used to accurately determine if a street has been assigned a correct/incorrect semantic class.
      867Scopus© Citations 44
  • Publication
    Cognitively Adequate Topological Robot Localization and Mapping
    Simultaneous Localization and Mapping (SLAM) is a fundamental problem in the eld of robotics which concerns mapping an environment or space while simultaneously localizing within this map. Given that one of the major goals of robotics is to perform tasks commonly performed by humans, we argue that SLAM methods should be cognitively adequate; that is, they should model the same properties of a space as the human cognition models. Topological properties are considered the most fundamental of those modlelled by the human cognition. Therefore in order to achieve cognitive adequacy such properties must be modelled explicitly. Research in the domain of spatial cognition has demonstrated that the topological properties modelled by the human cognition can be quanti ed using the Egenhofer Nine-Intersection Model (9-IM). In this work we propose a conceptual SLAM method which models the same properties as the 9-IM. Relative to existing topological SLAM methods, which model a single topological property of connectivity between locations, this method achieves a stronger degree of cognitive adequacy.