Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Real-time generation of interactive virtual human behaviours

Zheng, Yue, Hicks, Yulia Alexandrovna ORCID: https://orcid.org/0000-0002-7179-4587, Marshall, David and Cosker, Darren P. 2009. Real-time generation of interactive virtual human behaviours. Presented at: Computer vision and computer graphics : theory and applications, Funchal-Madeira, Portugal, 22-25 January 2008. Published in: Ranchordas, A., Araujo, H., Madeiras Pereira, J. and Braz, J. eds. Computer vision and Computer Graphics : Theory and Applications International Conference (VISIGRAPP 2008), Funchal-Madeira, Portugal, 22-25 January 2008. Communications in computer and information science , vol.24 Springer, pp. 70-82. 10.1007/978-3-642-10226-4_6

Full text not available from this repository.

Abstract

In this paper, we propose a new approach for generating interactive behaviours for virtual characters, namely the windowed Viterbi algorithm, capable of doing so in real-time. Consequently, we compare the performance of the standard Viterbi algorithm and the windowed Viterbi algorithm within our system. Our system tracks and analyses the behaviour of a real person in video input and produces a fully articulated three dimensional (3D) character interacting with the person in the video input. Our system is model-based. Prior to tracking, we train a collection of dual-input Hidden Markov Model (HMM) on 3D motion capture (MoCap) data representing a number of interactions between two people. Then using the dual-input HMM, we generate a moving virtual character reacting to (the motion of) a real person. In this article, we present the detailed evaluation of using the windowed Viterbi algorithms within our system, and show that our approach is suitable for generating interactive behaviours in real-time. Furthermore, in order to enhance the tracking capabilities of the algorithm, we develop a novel technique that splits the complex motion data in an automated way. This results in improved tracking of the human motion from our model.

Item Type: Conference or Workshop Item (Paper)
Status: Published
Schools: Computer Science & Informatics
Engineering
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Uncontrolled Keywords: Real-time; Windowed Viterbi algorithm; Generating interactive behaviours; Dual-input HMM; Splitting motion automatically
Publisher: Springer
ISBN: 9783642102257
ISSN: 1865-0929
Last Modified: 19 Oct 2022 08:57
URI: https://orca.cardiff.ac.uk/id/eprint/19601

Citation Data

Actions (repository staff only)

Edit Item Edit Item