Sophia Karagiorgou

A comparison and evaluation of map construction algorithms using vehicle tracking data

Map construction methods automatically produce and/or update street map datasets using vehicle tracking data. Enabled by the ubiquitous generation of geo-referenced tracking data, there has been a recent surge in map construction algorithms coming from different computer science domains. A cross-comparison of the various algorithms is still very rare, since (i) algorithms and constructed maps are generally not publicly available and (ii) there is no standard approach to assess the result quality, given the lack of benchmark data and quantitative evaluation methods. This work represents a first comprehensive attempt to benchmark such map construction algorithms. We provide an evaluation and comparison of seven algorithms using four datasets and four different evaluation measures. In addition to this comprehensive comparison, we make our datasets, source code of map construction algorithms and evaluation measures publicly available on http://mapconstruction.org.. This site has been established as a repository for map construction data and algorithms and we invite other researchers to contribute by uploading code and benchmark data supporting their contributions to map construction algorithms.

On vehicle tracking data-based road network generation

Road networks are important datasets for an increasing number of applications. However, the creation and maintenance of such datasets pose interesting research challenges. This work proposes an automatic road network generation algorithm that takes vehicle tracking data in the form of trajectories as input and produces a road network graph. This effort addresses the challenges of evolving map data sets, specifically by focusing on (i) automatic map-attribute generation (weights), (ii) automatic road network generation, and (iii) by providing a quality assessment. An experimental study assesses the quality of the algorithms by generating a part of the road network of Athens, Greece, using trajectories derived from GPS tracking a school bus fleet.

Crowdsourcing urban form and function

Urban form and function have been studied extensively in urban planning and geographical information science. However, gaining a greater understanding of how they merge to define the urban morphology remains a substantial scientific challenge. Toward this goal, this paper addresses the opportunities presented by the emergence of crowdsourced data to gain novel insights into form and function in urban spaces. We are focusing in particular on information harvested from social media and other open-source and volunteered datasets (e.g. trajectory and OpenStreetMap data). These data provide a first-hand account of form and function from the people who define urban space through their activities. This novel bottom-up approach to study these concepts complements traditional urban studies to provide a new lens for studying urban activity. By synthesizing recent advancements in the analysis of open-source data, we provide a new typology for characterizing the role of crowdsourcing in the study of urban morphology. We illustrate this new perspective by showing how social media, trajectory, and traffic data can be analyzed to capture the evolving nature of a city’s form and function. While these crowd contributions may be explicit or implicit in nature, they are giving rise to an emerging research agenda for monitoring, analyzing, and modeling form and function for urban design and analysis.

Providing Universal Access to History Textbooks: A Modified GIS Case

Integrating and accessing structured textual content from various sources is a challenging task and becomes even more so when dealing with multiple languages. The objective of this work is to showcase the technological efforts towards the creation of a digital European history textbook repository that integrates respective textbooks from various countries and publishers. The content integration is achieved by introducing language independent metadata based on space (locations), time (dates), and thematic categories (history gazetteer). Providing adequate interfaces such metadata can be used to provide language-independent access to Multilanguage history textbook content. The specific focus in this work will be on (i) presenting the metadata, (ii) the data management approach including indexing the history textbook content and (iii) the resulting textbook repository including its GIS-based interface allowing for a combination of map, timeline and keyword based search of the history content.

Map Construction Algorithms

The book provides an overview of the state-of-the-art of map construction algorithms, which use tracking data in the form of trajectories to generate vector maps. The most common trajectory type is GPS-based trajectories. It introduces three emerging algorithmic categories, outlines their general algorithmic ideas, and discusses three representative algorithms in greater detail. To quantify map construction algorithms, the authors include specific datasets and evaluation measures. The datasets, source code of map construction algorithms and evaluation measures are publicly available on http://www.mapconstruction.org. The web site serves as a repository for map construction data and algorithms and researchers can contribute by uploading their own code and benchmark data. Map Construction Algorithms is an excellent resource for professionals working in computational geometry, spatial databases, and GIS. Advanced-level students studying computer science, geography and mathematics will also find this book a useful tool.

A Layered Approach for More Robust Generation of Road Network Maps from Vehicle Tracking Data

Nowadays, large amounts of tracking data are generated via GPS-enabled devices and other advanced tracking technologies. These constitute a rich source for inferring the structure of transportation networks. In this work, we present a novel methodology for revealing a road network map from vehicle trajectories. Specifically, we propose an enhanced and robust map construction algorithm that is based on segmenting the original tracking data according to different types of movement and then constructing the topology of the road network hierarchically. The segmentation produces separate road network layers, which are then fused into a single network. This provides a more efficient way to addresses the challenges imposed by noisy and low sampling rate trajectories. It also allows for a mechanism to accommodate automatic map maintenance on updates. Thus, the proposed approach overcomes the limitations of existing methods and introduces a map construction algorithm that is robust against heterogeneous and sparse data and capable to incorporate changes and improvements. An experimental evaluation extensively assesses the quality of the proposed methodology by constructing large parts of the road networks of four major cities, namely Athens, Berlin, Vienna, and Chicago, using as input GPS tracking data of utility vehicles and taxi fleets. Our results show significant improvements concerning the spatial accuracy and the quality of the constructed road network over the current state of the art.

Geosemantic Network-of-Interest Construction Using Social Media Data

An ever increasing amount of geospatial data generated by mobile devices and social media applications becomes available and presents us with applications and also research challenges. The scope of this work is to discover persistent and meaningful knowledge from user-generated location-based “stories” as reported by Twitter data. We propose a novel methodology that converts geocoded tweets into a mixed geosemantic network-of-interest (NOI). It does so by introducing a novel network construction algorithm on segmented input data based on discovered mobility types. The generated network layers are then combined into a single network. This segmentation addresses also the challenges imposed by noisy, low-sampling rate “social media” trajectories. An experimental evaluation assesses the quality of the algorithms by constructing networks for London and New York. The results show that this method is robust and provides accurate and interesting results that allow us to discover transportation hubs and critical transportation infrastructure.

TraceBundle Map Construction Algorithm

This chapter presents the TraceBundle algorithm, which is a representative of the intersection linking category of map construction algorithms . The main approach is to first detect intersection nodes, then “bundle” trajectories around them in order to construct edges. Changes in movement direction and speed are used as turn indicators, and similar turns are combined to form intersection nodes. In an improved version of the algorithm the hierarchical nature of the road network is considered and different road categories are taken into account. By segmenting the trajectories based on speed, hierarchical road network layers are derived which are then combined into a single network. Segmentation also addresses the challenges imposed by noisy, low-sampling rate trajectories and provides for a mechanism for accommodating incremental map updates.

Fréchet Distance-Based Map Construction Algorithm

This chapter presents an incremental track insertion algorithm for map construction that is based on partial map-matching of the trajectories to the graph. The Frechet distance is used as part of the map-matching algorithm and to provide quality guarantees for the constructed map. One of the contributions of this work is to separate edge regions from vertex regions when providing quality guarantees, and to specify the extent of these regions. The algorithm itself is easy to implement and it can compute non-planar road configurations, such as bridges, if altitude information is provided with the trajectory measurements. While the description complexity of the computed road geometries can be guaranteed to be small when using a simplification algorithm, in practice the algorithm provides good results even without simplifying or merging trajectory portions that correspond to the same road segment.

Density-Based Map Construction Pipeline

This chapter presents a density-based algorithm pipeline to construct a road map from a set of input trajectories. In the first step of the pipeline a data density function is computed and an undirected skeleton graph is constructed using grayscale skeletonization of the density. In several different steps the pipeline then uses the trajectory data to refine the topology and the geometry of the graph using the continuous information represented in the trajectories. Additional information including edge directions, lanes, and turn lanes are also added to the graph in these later steps.