KIRAS Security Research

Call results by calendar year

Call results by funding instruments

Projects of the joint German-Austrian call

Cooperative Research and Innovation Projects >Call 2020 >

MUSIG - Multi-sensor Information Generation to Support Crisis Management and Prevention

The FFG KIRAS project MUSIG focuses on the automated, AI-based derivation and fusion of movement information from geo-social media, mobile phone data and in-situ cameras. This fused movement information is then enriched with context information (semantic topics and sentiments from geo-social media, movement speeds and crowd densities from in-situ cameras) and tested in real scenarios for their added value in crisis management and its prevention.

Collective mass movements and activities in public space are increasingly present-ing authorities and action forces with major challenges in terms of situation assessment, crisis management and prevention. Events in the recent past such as the storming of the US Capitol, people gatherings despite unauthorised demonstrations, non-compliance with curfews during pandemics, etc. show the relevance and urgency of this topic.
Therefore, the MUSIG project focuses on the automated extraction of collective movement information from geo-social media, mobile phone data and in-situ im-agery with AI methods, and the scenario-oriented fusion of movement information in a new mixed-methods approach, as well as its provision for crisis management and prevention in near real time including nowcasting information.
Fusing movement information from heterogeneous sources creates a high-quality and reliable information base that can be used reliably in crisis management and prevention. The MUSIG project extracts semantic information (what do people talk about in a group?) and mood information (sentiment analysis - how relaxed, tense, escalating, etc. is a situation?) beyond pure movement analysis (determination of the number, density and speed of movement). Methodological approaches:

  • Research into robust and transparent AI algorithms for multi-sensory analysis of movement information (number of persons, crowd distribution, density and behav-iour) from geo-social media, cell phone data and in-situ image data.
  • Research into a mixed-method approach to fusing movement information: combina-tion of heterogeneous information layers – crowd densities and movement speeds ob-tained from mobile phone and image data, geographically and temporally localized emo-tions extracted from geo-social media (moods - Sentiment Analysis) and dynamically changing topics of conversation (nowcasting).
  • Legal, sociological and ethical issues are a central part of the MUSIG project (Ethical Board) and are reflected in the technical research developments.
  • The needs of end users are scientifically assessed in a structured manner and tested in a practical setting in 2 „cold cases“, 1 „warm case“ in a TRL 4 test environment (the BMI is centrally integrated into the project by means of a LoI) and interoperability with existing systems is guaranteed.
  • Consortium partners and associated partners (BMI, Hutchison Drei Austria, DCNA) have agreed on a comprehensive exploitation strategy with a clear commitment to de-veloping a joint service beyond the end of the project.

ProjektleiterIn
Assoz.-Prof. Dr. Bernd Resch, Universität Salzburg, Fachbereich Geoinformatik – Z_GIS
Auflistung der weiteren Projekt- bzw. KooperationspartnerInnen

Projektpartner

  • Universität Salzburg, Fachbereich Geoinformatik – Z_GIS
  • Österreichisches Rotes Kreuz (ÖRK)
  • Johanniter Österreich Ausbildung und Forschung gemeinnützige GmbH (JOAFG)
  • Spatial Services GmbH (SPASE)
  • JOANNEUM RESEARCH (JR)
  • eurofunk KAPPACHER GmbH (EFK)

Assoziierte Partner

  • Bundesministerium für Inneres (BMI)
  • Hutchison Drei Austria GmbH
  • Disaster Competence Network Austria (DCNA)

Kontakt
Assoz.-Prof. Dr. Bernd Resch
Universität Salzburg, Fachbereich Geoinformatik – Z_GIS
Schillerstraße 30
A-5020 Salzburg
Tel: +43-662-8044-7551
Fax: +43-662-8044-7560
E-mail: bernd.resch@plus.ac.at 
Website: http://zgis.at 
Projekt-Website: https://geosocial.zgis.at/musig