H2020 MSCA Innovative Training Network for the research on Advanced Hardware/Software Components for Integrated/Embedded Vision Systems


Cooperative camera scene modelling using metadata

@ Dep. Telecommunications and Information Processing (Ghent University), Belgium

Smart cameras target low power consumption and low bandwidth communication. To achieve that, the cameras perform embedded processing of video streams and typically output metadata that is exchanged between cameras and with the computer vision core. The first goal of this research project is to identify the different required metadata for cooperative vision and to propose the models for data exchange. The second goal is to develop methods for creating geometric models of the scene. A third goal is to develop algorithms that can detect and classify objects from thermal cameras. Objects of interest, such as people and vehicles, are often well differentiated from background objects in thermal imaging. Therefore, thermal cameras are promising in applications such as bicycle and pedestrian detection and perimeter surveillance. The main innovation will be to increase the robustness of connectivity and occlusion mapping through the exchange of metadata.

Patrick Heyer



Patrick Heyer was born in Puebla Mexico. He obtained Bachelor in Computer Sciences at Instituto de Estudios Universitarios (IEU) Mexico in 2014. He joined the Markovito robotic research group at National Institute of Astrophysics, Optics and Electronics (INAOE) as research assistant in 2010, promoted to team captain by 2012. His main contribution was in the creation of a plug-in based robot software architecture. He obtained Master degree from INAOE in 2017. In 2018 he joined Gent University for his Phd. His main research interests focus on efficient data representation.









"Scene analysis for traffic monitoring"

My project focuses on creating a human readable representation of a scenario (i.e. description of the environment in the context of urban road intersections) from the information obtained by different types of sensors (e.g. thermal and video cameras). The objective of the representation is to model the information processed by the sensors in a way that a cooperative system can use it to infer information about the traffic situation and pedestrians to take the corresponding actions. The main challenges are related to the size of the representation that will be sent over different networks with limitations on bandwidth and the development of the algorithms that map this information to a human readable format.


  • Create high level representation of an environment.
  • Map the sensed data (e.g. video) into the proposed representation and implement using Quasar.
  • Evaluate the proposed methods for cooperative monitoring system.


Reliable human readable representation for embedded systems on the camera implemented using the Quasar programming language.