PRIMA Research team
Perception, recognition and integration for observation of activity
- Leader : James Crowley
- Type : Project team
- Research center(s) : Grenoble
- Field : Perception, Cognition, Interaction
- Theme : Vision, Perception and Multimedia Understanding
- Université Joseph Fourier (Grenoble), Institut polytechnique de Grenoble, CNRS, Laboratoire d'Informatique de Grenoble (LIG) (UMR5217)
Team presentationThe overall goal of the PRIMA project-team is the elaboration of a scientific foundation for interactive environments. An interactive environment requires the capabilities of perception, action and communication. An environment is said to be perceptive if it is capable of maintaining a model of its occupants and their activities. Such may a model includes the identity of individuals, an estimation of their position, their recent trajectory, as well as recognition of the activities of individuals and groups. An environment becomes active when it is capable of action. Actions may include presentation of information. They may also include the capability to manage visual and acoustic communications, as well as the capability to transport documents and material. Controlling an environment that is perceptive and active requires a capability to interact. This capability may rely on speech recognition, gesture interpretation, interpretation of the manipulation of object and observation of the interaction of people.
The PRIMA project-team has as its mission to develop and integrate these three capabilities.
- The capacity to perceive and model the environment and its contents.
- The capacity to act by presenting information or service, or by transporting materials
- The capactive to communicate and interact with occupants.
Research themesThe PRIMA project-team concerns the development of techniques for machine perception of people and their activities. The research is organized along four axes:
- Multi-modal observation and tracking of people
- Integration and control of perceptual processes
- New forms of man-machine interaction
- Recognition and learning guided by the context of interaction
International and industrial relations
- Founder of the start up company "Blue-Eye Video" to commercialize results from our participation in project IST VISOR -BASE (IST-1999-10808).
- French National Project RNTL ContAct (jan 2003 - Décembre 2004) The ContAct project (with Xerox Research Centre Europe) seeks to develop a demonstration of context sensitive services to aid individuals and groups. The PRIMA project is reponsable for perception techniques and for interpreting human action and interaction.
- European Project IST CAVIAR (IST 2001- 37540) (nov 2002 - oct 2005) The CAVIAR project (with U. Edinburgh and Univ. of Lisbon) concerns the development of vision systems context driven perception of human activity. CAVIAR (for "Context Aware Vision and Recognition") will develop methods for learning and recognition guided by context models. CAVIAR is par of the EU IST Cognitive Vision program.
- European Project ? IST FAME (IST-2000-28323) ? ?Facilitating Agent for Multi-cultural Communication?, with Sony, Univ. Karlsruhe, IRST (Trento Italie), UPC (Barcelone, Esp.) and Laboratoire CLIPS-IMAG . Start date : october 2001, duration 40 months. FAME will develop methods for context driven multi-modal interaction.
- European Project IST DETECT, IST-2001-32157 « Real Time Detection of Motion Picture Content in Live Broadcasts » The goal of DETECT is to implement systems to recognize and count corporate logos in video productions of sports matchs. Start data was November 2001. Duration is 24 months. Partners are Joanneum Research (A), Taurus Media Technik (D), HS-ART Digital Services (A), Laboratoire GRAVIR, UMR CNRS 5527, Duvideo (P) and Videocation (D).
- Project FET GLOSS ? Global Smart Spaces, Framework V, FET Proactive Disappearing Computer), Start Date : January 2001, duration 36 months. Partners include University of Strathclyde (GB), Trinity College Dublin (IR), Université Joseph Fourier (F), University St Andrews (GB).
- ECVision : Network of excellence in cognitive vision. (sart date feb 2002, duration 36 months). Responsible for research planning activities and member of steering committee.
- Member of the national research network RTP 25: Image, Vision and Scene Analysis. Participant in the AS Perception, Modelisation and interpreation of human geture.
- FGNet - IST Thematic Network on Face and Gesture. Start date October 2001. Responsible for organizing workshops.
Research teams of the same theme :
- AYIN - Stochastic models for remote sensing and skincare image processing
- LEAR - Learning and recognition in vision
- MAGRIT - Visual Augmentation of Complex Environments
- MORPHEO - Capture and Analysis of Shapes in Motion
- PERCEPTION - Interpretation and Modelling of Images and Videos
- SIROCCO - Analysis representation, compression and communication of visual data
- STARS - Spatio-Temporal Activity Recognition Systems
- TEXMEX - Multimedia content-based indexing
- WILLOW - Models of visual object recognition and scene understanding