Visualization

Visualization shows data and is a fundamental tool for analysis and understanding of complex issues in many fields.

Interactive visualization allows an explorativ experiencing of data an builds the basis for a visually conrolled analysis process. The use of spatial data is the basis for comprehensive spatial visualizations. Thes produces understandable map-based representations which are of increasing relevance in desicion-making processes.

The institute is engaged in interacive geospatial visualization in different application fields. These includ controlling, security, social media and healthcare. The research and development work is focused in particular on Geovisual Analytic applications, including consideration of mobile devices.

Contact Person

Prof. Dr.-Ing. Klaus Böhm

Tel.: +49 6131-628-1431
Fax.: +49 6131-628-91431

Projects

Publications

–

Künstliche Intelligenz als Strategie in der Ingenieurgeodäsie – erste Schritte im Bahnumfeld

2020

PDF / RTF

zfv – Zeitschrift für Geodäsie, Geoinformation und Landmanagement

Für die Arbeiten im Gleisbereich ist ein System zur Erfassung von Zugfahrten unverzichtbar. Künstliche Intelligenz kann einen Teil dazu beitragen. Im Folgenden wird ein erster Ansatz, basierend auf Deep Learning Technologie, vorgestellt, welcher auf Grundlage von Bilddaten automatisch Züge detektiert und so zu mehr Sicherheit im Gleisbereich beitragen kann. Darüber hinaus ist eine Softwarelösung entwickelt worden, welche den umfangreichen und bisher arbeitsintensiven Datenvorbereitungsaufwand signifikant reduziert. Im vorliegenden Beitrag werden das Potenzial und die flexible Einsetzbarkeit von Künstlicher Intelligenz im ingenieurgeodätischen Kontext aufgezeigt.

A system for recording train rides for work in the track area is crucial. The usage of Artificial Intelligence contributes to this. In the following article a first approach based on Deep Learning is presented, that automatically detects trains on the base of image data and can lead to more safety in the track area. In addition, a software has been developed that reduces the extensive and work-intensive data preparation effort significantly. This article presents the potential and the flexible deployment of Artificial Intelligence in the engineering geodetic domain.

–

An Overview of Approaches for automated intelligent Building Information Modeling

2020

PDF / RTF

FIG Working Week 2020

The digitalisation of architecture, engineering and construction (AEC) industry is gaining much attention especially through Building Information Modeling (BIM). While the use of IT-supported planning and construction processes is required for new building projects, the creation of BIM-valid data for existing buildings is currently inefficient. Academic and industry are spending a lot of effort into research for flexible methods to measure as-built conditions. The automated processing of the resulting 3D point cloud into BIM-valid 3D CAD models using intelligent software approaches is another major research.

This paper presents an overview of data acquisition techniques and 3D point cloud processing approaches regarding BIM for existing buildings, while identifying challenges and looking ahead for future research. To optimise decision making with respect to socially relevant issues, BIM as an instrument can revolutionise the AEC industry and provide the database for smart city applications.

–

Künstliche Intelligenz als Strategie in der Ingenieurgeodäsie – erste Schritte im Bahnumfeld

2020

PDF / RTF

zfv - Zeitschrift für Geodäsie, Geoinformation und Landmanagement

–

Qualitative GIS to Support Sustainable Regional Branding and Transition in Northern Germany

2020

RTF

Methods and Concepts of Land Management: Diversity, Changes and New Approaches

A mixed methods approach using GIS was applied to identify places relevant for regional branding and to support co-creation in a transdisciplinary process in Northern Germany. For this purpose, local stakeholders mapped characteristic landscape features, places of leisure activities and places where they feel happy. In addition, public authorities’ geodata were processed to identify landscape classes and elements, which are characteristic from a quantitative point of view. The results indicate a cross-thematic, cross-methodological and cross-regional significance of water landscapes. However, their relationship to other landscape elements and further topics differs significantly in the two study regions presented here, leading to different starting points for place branding. The use of maps as a basis for discussion helps bringing together stakeholders with different experiences and involving them in brand building. In this way, the chosen approach supports inter- and transdisciplinary changes towards a sustainable regional development and acts as a bridge between brand building and its implementation on site.

–

User-Generated Spatial Content for Sustainable Land Management – Experiences from Transdisciplinary Landscape Branding in Germany

2020

RTF

Conference Proceedings - FIG

Transdisciplinarity is a principle of integrative research, in which scientific and practical partners jointly generate new knowledge. This approach is supported by the German Federal Ministry of Education and Research (BMBF) within the funding priority "Innovation groups for a sustainable land use" (Förderschwerpunkt "Innovationsgruppen für eine nachhaltige Landnutzung"). One project that has been implemented within this regard is Regiobranding. The project aims at investigating the characteristics of landscapes in different Northern German regions in order to use their uniqueness for sustainable regional branding and development. The combination and integration of heterogeneous knowledge of the different project partners from eight institutions in three federal states was a central challenge for the transdisciplinary work. In the absence of a common technical language, "space" served as a common ground for bridging differences and actively involving local partners. Against this backdrop, the local public participated in the branding process via various mapping workshops. The results of the mapping exercises were later combined with GIS-based quantitative landscape analyses derived form scientific investigation by partners from the fields of surveying, archeology and environmental planning. The paper presents results of our approach and highlights the benefits of combining qualitative analyses based on user-generated spatial content with quantitative landscape analyses based on various sources of official agencies' geodata.

–

Ein Smart City Dashboard für die räumliche Analyse Machine Learning basierter Parkplatz-Vorhersagen

2020

PDF / RTF

8. Deutsches GeoForum 2020 - Bedeutung der Geoinformation für Gesellschaft und Wirtschaft

–

Räumliche Verortung von textbasierten Social-Media-Einträgen am Beispiel von Polizei-Tweets

2020

PDF / RTF

FOSSGIS Konferenz 2020

Ziel der Forschungsinitiative ist die Untersuchung der räumlichen Verortung deutscher Tweets auf Basis von verfügbaren Standardwerkzeugen. Zunächst werden die spezifischen Herausforderungen im Kontext der Sprache und der Eigenschaften von Tweets betrachtet. Die darauffolgende Entwicklung eines grundlegenden, algorithmischen Ablaufs schließt mit der Implementierung eines Prototyps ab. Dieser bildet die Basis für die Evaluation der Genauigkeit und führt zur Betrachtung des Verbesserungspotentials.

–

i3mainz - Jahresbericht 2018

2019

PDF / RTF

Jahrebericht 2018

Im Jahresbericht werden die Projekte und Aktivitäten des i3mainz in komprimierter Form vorgestellt.

more publications »