Acronym CAVIAR
Funding Reference EU-FP5-IST-2001-37540
Dates 2002-10|2005-09

The main objective is to develop the theory of context-aware visual recognition systems. We will implement the theory in a complete closed-loop vision system, and apply it to two applications (city street surveillance and customer behaviour analysis). To achieve these objectives, we will develop new feature grouping, attention and appearance-based recognition processes. This will also require development of new techniques for acquiring, representing and using visual context and situation knowledge.

The work developed consisted mainly in two main areas:
– The use of Gabor filters for the detection of interest points and for the the representation of local image regions for posterior recognition.
– Feature selection and classifier design for the recognition of human activities from video.

Research Groups Computer and Robot Vision Lab (VisLab)
Project Partners University of Edimburgh (UK), INRIA/INPG (F)
ISR/IST Responsible
José Santos-Victor
Alexandre Bernardino
Pedro Ribeiro
Plinio Moreno
Jonas Hörnstein
[1] V. J. Traver, Alexandre Bernardino, Plinio Moreno, José Santos-Victor, Appearance-based object detection in space-variant images: a multi-model approach, Proc. ICIAR - International Conference on Image Analysis and Recognition, Porto, Portugal, 2004 - PDF