Integration of tracking and adaptive Gaussian mixture models for posture recognition
2006 (English)In: Proc. IEEE Int. Workshop Robot Human Interact. Commun., 2006, 623-628 p.Conference paper (Refereed)
In this paper, we present a system for continuous posture recognition. The main contributions of the proposed approach are the integration of an adaptive color model with a tracking system that allows for robust continuous posture recognition based on Principal Component Analysis. The adaptive color model uses Gaussian Mixture Models for skin and background color representation, Bayesian framework for classification and Kalman filter for tracking hands and head of a person that interacts with the robot. Experimental evaluation shows that the integration of tracking and an adaptive color model supports the robustness and flexibility of the system when illumination changes occur.
Place, publisher, year, edition, pages
2006. 623-628 p.
, Proceedings - IEEE International Workshop on Robot and Human Interactive Communication
Color, Communication channels (information theory), Control theory, Integration, Object recognition, Optical properties, Reverse osmosis, Robotics, Robots, Trellis codes, Background colors, Bayesian frameworks, Color models, Experimental evaluations, Gaussian Mixture models, Illumination changes, Posture recognitions, Tracking systems, Principal component analysis
IdentifiersURN: urn:nbn:se:kth:diva-155364DOI: 10.1109/ROMAN.2006.314469ScopusID: 2-s2.0-48349137726ISBN: 1424405653ISBN: 9781424405657OAI: oai:DiVA.org:kth-155364DiVA: diva2:762588
RO-MAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication, 6-8 September 2006, Hatfield, United Kingdom
QC 201411122014-11-122014-11-052014-11-12Bibliographically approved