Aim
The main aim of this project is to develop models, algorithms
and intelligent systems for automatic human activity recognition in
surveillance environments. More specifically:
- To carry out a survey of the State of the Art in the
considered problem.
- To make a revision of the available benchmark data.
- To develop a video database for algorithm testing.
- To adapt the developed tracking algoritmhs for the
considered problem.
- To develop new knowledge-based models and reasoning models
for human activity recognition.
- To develop pattern recognition-based methods for human
activity recognition in surveillance environments.
- To develop learning-based methods to allow the system to
learn from the process history.
- To develop an intelligent camera prototype (laptop +
webcam) capable to produce a simple scene description using a captured
video sequence.
- Test the prototype for video surveillance applications,
using standard benchmarks and real-time situations.