Please use this identifier to cite or link to this item:
Title: Laban Movement Analysis: A Bayesian Computational Approach to Hierarchical Motion Analysis and Learning
Authors: Santos, Luís Carlos Gonçalves Ferreira dos 
Orientador: Dias, Jorge Manuel Miranda
Keywords: Laban Movement Analysis; Action Recognition; Person Recognition; Cognitive Skill Models
Issue Date: 4-Apr-2014
Keywords: Laban Movement Analysis; Action Recognition; Person Recognition; Cognitive Skill Models
Issue Date: 4-Apr-2014
Citation: SANTOS, Luís Carlos Gonçalves Ferreira dos - Laban movement analysis : a bayesian computational approach to hierarchical motion analysis and learning. Coimbra : [s.n.], 2014. Tese de doutoramento. Disponível na WWW:
Abstract: The development of intelligent and autonomous robots is envisioned as a breakthrough in science and is expected to have significant impact in the future of our society. Scientists estimate that in the future, robots will be able to coexist in society with humans. A wave of intelligent robots will be capable to autonomously perceive the environment, follow a set of contextual social rules, and make their own decisions into fulfilling several tasks, relieving them from humans. Moreover, a set of cognitive capabilities will allow them to reconfigure themselves to new tasks, learn new actions, reason about unknown reactions and learn new social rules. The challenge is that robots have to cope with a limited prior knowledge about themselves and the environment, while operating without supervision in an uncertain world. To address these challenges, currently robotic system as developed towards specific scenarios, within well defined environments and properties. This fact, makes it difficult for them to deal with unknown situations, where its perception is subject to uncertainty and noise. In our thesis, we present a set of novel methodologies and concepts that enable robots to comprehensively interpret human motion and extend such knowledge via hierarchical analysis of different types of information. The proposed methods in this thesis address the following main three topics: (1) Defining a model which can robustly infer different types of information from human motion, using a generalizable grounding language; (2) Encoding the unique expressive properties of each person’s motion, so as to develop action invariant motion signatures towards a person recognition framework; (3) Develop a system’s action memory, which can store and retrieve action generalized information towards incrementally learn new actions and executing them to solve a task in has respectively. This thesis starts by presenting an innovative approach to hierarchical analysis of human motion, based on a descriptive motion language, Laban Movement Analysis. This allows a system to infer multiple levels of information, from dynamic characteristics to intentions or behaviour patterns, by observing the 3D trajectories, generated from a given motion instance. Then, we exploit the outcome of Laban qualities classification into encoding this information to develop individual motion profiles. Such characteristics are then applied to develop a Bayesian-based action invariant person recognition framework. The two aforementioned techniques are then integrated and adapted to develop an intelligent video-surveillance framework, showing to be capable of robustly recognize actions and person identities. The last part of our work focuses on developing a set of cognitive skills, allowing the system to build its own memory, by either learning new actions or incrementally fuse newly performed actions to existing knowledge. All methods have been developed using probabilistic learning and inference, more specifically, Bayesian methodologies. They have been implemented and thoroughly evaluated using cross-validation procedures and different kinds of experimental scenarios so as to allow withdrawing conclusions based on produced evidences. Results demonstrate a highly robust and precise framework, whose main characteristics are flexibility, scalability and adaptability, showing to be useful to increase perception capabilities of artificial systems and have the potential to make significant impact in our future economy and society.
Description: Tese de doutoramento em Engenharia Electrotécnica e de Computadores, no ramo de especialização Automação e Robótica, apresentada ao Departamento de Engenharia Electrotécnica e de Computadores da Faculdade de Ciências e Tecnologia da Universidade de Coimbra
Rights: openAccess
Appears in Collections:FCTUC Eng.Electrotécnica - Teses de Doutoramento

Files in This Item:
File Description SizeFormat
Laban Movement Analysis.pdf18.46 MBAdobe PDFView/Open
Show full item record

Page view(s)

checked on Aug 20, 2019

Download(s) 10

checked on Aug 20, 2019

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.