PERCEPTION Research team

Interpretation and Modelling of Images and Videos

Team presentation

The overall objective of the PERCEPTION researchers is to map images and videos onto 3-D visual representations and onto symbolic meaning. We address this objective both with an information processing approach and a computational cognitive approach. On one side, we investigate the mathematical models that are needed to extract 3-D geometric and physical information from the light stimuli (images) and which are the methods, algorithms, and software that best implement these models. On the other side, we investigate the biological/cognitive processes that govern the interactions between prior knowledge and the sensorial input, we attempt to describe these processes as mathematical and computational models, and we implement them as working computer programs.

Research themes

  • Image-based modelling of objects and scenes
  • Representation of visual dynamic scenes
  • Computational modelling of biological vision
  • Camera networks, augmented reality, interactive systems

International and industrial relations

European collaborations within IST and Marie Curie projects:
  • Research Training Network Visiontrain
  • IST projects Holonics and POP
Industrial partners:
  • Renault SA
  • Holografika (Hungary)
  • Total-Immersion SA
  • Eptron (Spain)
  • Digital Air (USA)

Keywords: Image analysis Computer vision Surface reconstruction Surface rendering Video analysis