MARVEL: how to increase urban security while respecting the privacy of citizens

The goal of the Trento Smart City project, and of the Municipality of Trento in general, is to improve citizens’ well-being and quality of life.

This attempt to provide even better and customizable services according to the needs of individuals must be combined with the protection of the data and privacy of each individual, as established by the GDPR 2016/679. Security and privacy of personal data are the keystones of the MARVEL project, which is funded by the European Union under the HORIZON 2020 program and aims to increase urban security through the analysis of anomalous and potentially dangerous situations.

The importance of the protection of citizens’ privacy has also been pointed out in the discussions that took place with the wide audience during the project’s first Info Day, organized at the end of January.

Figure 1 “Feste Vigiliane” popolar event in Duomo Square – Trento

MARVEL, like every other European project, has been conceived and implemented in compliance with strict privacy regulations to create a value system based on high data security standards.

In that context, MARVEL makes use of a data analysis method that should not be confused with conventional surveillance technology. MARVEL’s data analysis method is based on the use of at times invasive cameras and audio-visual equipment. Experimentations carried out by the project aim to act supportively to established security systems used by local authorities

Figure 2: Christmas market in Fiera Square – Trento

The audio-visual data that will be analysed, will be anonymized at the source, near the devices used to collect such information. They will not be shared with third parties and will not be utilised for the profiling of citizens.

Situations, where intervention by authorities might be needed, are checked by analysing multimedia information in real-time, using machine learning algorithms. To describe it in a simple way: software and algorithms dedicated to identifying anomalies will be used to compare the audio and video received, with a set of previously simulated audio and video tests, to instruct the MARVEL system to recognize dangerous situations. 

Figure 3: Christmas market in Fiera Square – Trento

The simulations are recorded through ad-hoc sessions, in which researchers and staff dedicated to the realization of the project, play different roles and “stage” dangerous situations. The goal is to recreate emergency circumstances to be used as material for teaching the algorithm to recognize the anomaly.

Once the anomaly has been recognized, the system alerts local authorities, reporting the type of event, so that they can intervene more quickly and in a timelier manner in support of citizenship. The MARVEL system is not able to analyse or understand conversations, but only to associate audio and video to situations considered dangerous.

Blog signed by: the MT team

What do you think of the MARVEL approach to increase urban security while respecting the privacy of citizens?

Feel free to reach out using the MARVEL contact form or to find and talk to us on Twitter and LinkedIn and share your thoughts with us!

Key Facts

  • Project Coordinator: Dr. Sotiris Ioannidis
  • Institution: Foundation for Research and Technology Hellas (FORTH)
  • E-mail: 
  • Start: 01.01.2021
  • Duration: 36 months
  • Participating Organisations: 17
  • Number of countries: 12

Get Connected



This project has received funding from the European Union’s Horizon 2020 Research and Innovation program under grant agreement No 957337. The website reflects only the view of the author(s) and the Commission is not responsible for any use that may be made of the information it contains.