ReActivS

An important and active interdisciplinary research area deals
with the development of computational systems capable of automatically
interpret a video sequence and extract an useful and close to natural
language information.
The main aim of this project is to develop models, algorithms and intelligent systems for automatic human activity recognition in surveillance environments.
The hypothesis can be formulated as follows: “The combination
of visual tracking methods, pattern recognition methods and learning
methods can produce effective and efficient automatic human activity
recognition systems”. Involved people are expertise in image
processing, computer vision, pattern recognition, heuristic
optimization and software development . More specifically,
they have a solid experience in the development of video based visual
tracking algorithms.