Title: Seminar on Laban Movement Analysis: A Bayesian Computation Approach to Hierarchical Motion Analysis and Learning
Date: 2013-11-27
Source: http://www.cs.ucy.ac.cy/colloquium/presentations.php#cs.ucy.pres.2013.santos
Description:

Luis Santos will present a seminar about his Ph.D. research at the Department of Computer Science - University of Cyprus entitled "Laban Movement Analysis: A Bayesian Computation Approach to Hierarchical Motion Analysis and Learning", due on Tuesday, December 3, 2013, 11:00-12:00 EET

Abstract: Laban Movement Analysis is a descriptive language for visualizing and understanding all forms of human movement. In this talk, a probabilistic framework is proposed for its computational implementation. Several topics from signal processing, machine learning and Bayesian theory will be discussed towards the application of the so called Computational Laban Movement Analysis in the Action and Person Recognition areas. We demonstrate that Laban elements are action invariant and can be composed from a bottom-up perspective to interpret motion information of higher complexities. Action comprehensive annotation from motion analysis and intelligent video surveillance case studies are presented to validate our models using both 3-D and 2-D data. This talk focuses on the core of Ph.D. studies of Luis Santos at the Institute of Systems and Robotics from the University of Coimbra and is integrated in the knowledge transfer paradigm of the Social Robot, a project funded by the European Commission within the Seventh Framework Programme FP7, by People Programme, Industry-Academia Partnerships and Pathways (IAPP), under grant agreement 285870.