Probabilistic LMA-based Human behaviour Understanding by Conjugation of Frequency and Spatial Domains
Project Type: PhD Project
Research Field: Body Motion-based Human Behaviour Understanding
Sponsors: Fundação para a Ciência e a Tecnologia: Ph.D. Scholarship - SFRH/BD/70640/2010
Time span: 04/2011-09/2013
Poster

Description:
Behaviour refers to activities of an object depend on its environment. And human behaviour derives from the set of behaviours imposed by culture, attitudes, emotions, etc. In fact, human behaviour (and even of other organisms or mechanisms) can range from being considered regular or acceptable to irregular or unacceptable with in a particular context.

Human behaviour modeling is one of the big challenges in artificial intelligence science. There are many applications related to the subject for example; surveillance systems (e.g. airport, bank, train station, etc.), virtual reality (e.g. interactive virtual worlds, virtual studios teleconferencing, etc.), motion analysis (e.g. choreography of dance, clinical studies of orthopedic patients, etc.) and Human-Robot Interaction.

Human behaviour comes from different human actions and reactions which usually appear by the person’s body motion, voice and facial expressions. Researchers are investigating all the possibilities to recognize human behaviours depending on their applications.

Nowadays, most of the related applications such as the surveillance systems, are relied on the human movements. The movements are the lowest level of human motions which do not need any previous knowledge to be identified, but to understand human action or behaviour we need to recognize a sequence of human movements or states, related to the environment or scenario.

This project has three branches which we are interested to investigate such a bottom-up approach:
  1. Individual body-centered human motion analysis: By using Laban Movement Analysis (LMA) to extract needed features in both spatial and frequency space.
  2. Context-based human behaviour analysis: By using LMA.Relationship component to interpret human behaviour based on human motions and environmental conditions.
  3. Interpersonal behaviour analysis: By exploring in the existent connection between human interaction behaviour in social aspect and human movements.

Related Projects

PROMETHEUS - Prediction and interpretation of human behaviour based on probabilistic structures and heterogeneous sensors

Related People

Jorge Dias
Kamrad Khoshhal