Sites Inria

Version française

PERCEPTION Research team

Interpretation and Modelling of Images and Videos

Team presentation

The research topic of the PERCEPTION group is to investigate computational models for the problem of mapping images and sounds onto meaning. We address this objective with an interdisciplinary approach: computer vision, auditory scene analysis, machine learning and robotics. In particular, we develop methods for the representation and recognition of visual and auditory events, audio-visual fusion, recognition of human actions, gestures, and speech, and human-robot interaction.

Research themes

  • Computer vision: spatio-temporal representation of 2D and 3D visual information, action and gesture recognition, 3D sensors, binocular vision, multiple-camera systems,
  • Auditory scene analysis: binocular hearing, sound source localization and separation, speech communication, sound-event classification
  • Machine learning: mixture models, supervised and unsupervised mapping methods, graphical models
  • Robotics: robot vision, robot hearing, human robot interaction

International and industrial relations

European collaborations within IST and Marie Curie projects:

  • Marie-Curie Research Training Network Visiontrain (2005-2009)
  • ICT-FP6 project POP (2006-2009)
  • ICT-FP7 project HUMAVIPS (2010-2013)
  • ICT-FP7 project EARS (2014-2016)
  • ERC Advanced Grant VHIA (2014-2019)

Industrial partners:

  • Samsung Advanced Institute of Technology, Seoul, Korea
  • 4D View Solutions, Grenoble, France
  • Aldebaran Robotics, Paris, France
  • Samsung DMC R&D Laboratory

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