Virtual Friend: Tracking and Generating Natural Interactive Behaviours in Real Video

Zheng, Yue, Hicks, Yulia A. ORCID: https://orcid.org/0000-0002-7179-4587, Cosker, Darren P., Marshall, Andrew David ORCID: https://orcid.org/0000-0003-2789-1395, Mostaza, Juan and Chambers, Jonathon 2006. Virtual Friend: Tracking and Generating Natural Interactive Behaviours in Real Video. Presented at: ICSP '06: 2006 8th International Conference on Signal Processing, Guilin, China, 16-20 November 2006. Published in: Baozong, Yuan, Qiuqi, Ruan and Xiaofang, Tang eds. Proceedings: ICSP '06: 2006 8th International Conference on Signal Processing. , vol.2 Piscataway, NJ: IEEE Press, 10.1109/ICOSP.2006.345649

Full text not available from this repository.

Abstract

The aim of our research is to create a "virtual friend" i.e., a virtual character capable of responding to actions obtained from observing a real person in video in a realistic and sensible manner. In this paper, we present a novel approach for generating a variety of complex behavioural responses for a fully articulated "virtual friend" in three dimensional (3D) space. Our approach is model-based. First of all, we train a collection of dual hidden Markov models (HMMs) on 3D motion capture (MoCap) data representing a number of interactions between two people. Secondly, we track 3D articulated motion of a single person in ordinary 2D video. Finally, using the dual HMM, we generate a moving "virtual friend" reacting to the motion of the tracked person and place it in the original video footage. In this paper, we describe our approach in depth as well as present the results of experiments, which show that the produced behaviours are very close to those of real people.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics Engineering
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Uncontrolled Keywords:	3D articulated motion, 3D motion capture, HMM, dual hidden Markov models, natural interactive behaviours, real video, virtual friend
Publisher:	IEEE Press
ISBN:	9780780397361
Related URLs:	Organisation
Last Modified:	24 Oct 2022 10:45
URI:	https://orca.cardiff.ac.uk/id/eprint/45781

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item