Developing context sensitive HMM gesture recognition

Sage, Kingsley, Howell, A.J. and Buxton, Hilary (2004) Developing context sensitive HMM gesture recognition. In: Camurri, Antonio and Volpe, Gualtiero (eds.) Gesture-Based Communication in Human-Computer Interaction. Lecture Notes in Computer Science, 2915 . Springer Link, New York, USA, pp. 277-287. ISBN 9783540210726

[img] PDF
Restricted to SRO admin only

Download (941kB)


We are interested in methods for building cognitive vision systems to understand activities of expert operators for our ActIPret System. Our approach to the gesture recognition required here is to learn the generic models and develop methods for contextual bias of the visual interpretation in the online system. The paper first introduces issues in the development of such flexible and robust gesture learning and recognition, with a brief discussion of related research. Second, the computational model for the Hidden Markov Model (HMM) is described and results with varying amounts of noise in the training and testing phases are given. Third, extensions of this work to allow both top-down bias in the contextual processing and bottom-up augmentation by moment to moment observation of the hand trajectory are described.

Item Type: Book Section
Schools and Departments: School of Engineering and Informatics > Informatics
Subjects: Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Depositing User: Chris Keene
Date Deposited: 12 Feb 2008
Last Modified: 17 Sep 2019 09:29
Google Scholar:7 Citations

View download statistics for this item

📧 Request an update