Abstracts - Short CVs
Prof.
Pere Brunet (Topic:
Virtual Reality , Confirmed)
Title:
Discrete Techniques for Real-Time Inspection and Interaction in Virtual Reality
Abstract
|
Virtual
Reality (VR) Systems allow immersive inspection of very complex environments,
with direct interaction with the objects in the virtual scene. Low cost
and affordable VR systems are becoming essential in application areas
like Industrial Design, Medical Applications and Cultural Heritage.
The specific requirements in these areas will be discussed, together with the advantages of using VR devices and immersive inspection techniques. Discrete geometric models can very useful for some involved geometry processing algorithms like model repair, occlusion culling and mutiresolution and level of detail. The interest of these techniques and their potential in present and future VR applications will be discussed. The talk will also address the present limitations and future perspectives of VR techniques in medicine, industrial design and cultural applications. |
Short CV
|
Pere Brunet is professor of Computer Science at the Polytechnical University of Catalonia in Barcelona. He received an engineering degree and a PhD. in the same University in 1976. He is responsible for the Computer Graphics Group in the department of software, and he has been vice-president for research of the Polytechnical University of Catalonia from 1988 to 1992. His research interests include Computer-Aided Geometric Design, Solid Modeling, Octree Representations and Virtual Reality. His group is working in different research activities and projects including CAD and piping for ship design, free form surface design, rendering algorithms and volume modelling and visualization for medical applications. He promoted the Virtual Reality Center of Barcelona and is presently the UPC responsible of the Center. He is a member of the
editorial board of the international journals Computer-Aided Design,
Computer-Aided Geometric Design, IEEE Transactions on Visualization
and Computer Graphics and Computers & Graphics. He has published
refereed papers in well-known international research journals and has
participated actively in many International Conferences. He was the
chairman of the Spanish Chapter of Eurographics since its creation in
1986 until 1990, and a member of the Eurographics Executive Committee
since 1989. He was the Chairman of the Eurographics '93 Conference,
Chairman of the Eurographics Association during 2001 and 2002, co-chair
of tutorials at Eurographics '97, co-chair of the International Programme
Committee for Eurographics'99 and Eurographics'03 and member of the
Siggraph'2000 courses committee. He has been awarded with a number of
honours, and he is a member of the Spanish Academy of Engineering. |
Dr
Richard Bowden (Topic: Human
Sign Recognition, Confirmed)
Title:
Progress in Sign and Gesture Recognition
Abstract
Sign
Language is a visual language (without a conventional written form)
and consists of 3 major components, 1) Fingerspelling - used to spell
words on a letter by letter basis, 2) Word level sign vocabulary - used
for the majority of communication, 3) Non manual features - Facial expressions,
tongue/mouth position and body posture used to modify sign meaning.
Todate no system exists which has sufficient reliability and vocabulary
to convert sign to speech at the level required for translation. This
talk will present our work towards this goal. The talk will cover static
pose recognition and tracking of the human hand, followed by the use
of boosting for head and hand detection. It will be shown how prior
statistical models of body configuration can be used to locate body
parts, disambiguate the hands of the subject and predict the likely
position of elbows and other body parts. Finally, it will be shown how
these components are combined in a novel two-stage classifier architecture
that provides a flexible monocular vision system capable of recognising
sign lexicons far in excess of previous approaches. The approach boasts
classification rates as high as 92 % for a lexicon of 164 words with
as little as s single training instance per word, outperforming previous
approaches where thousands of training examples are required. |
Short CV
| Dr Richard Bowden (BSc (Hons), MSc, PhD, MIEEE, ILTM) Received his BSc in Computer Science from the University of London, an MSc with distinction in Vision, Visualisation and Virtual Working Environments from the University of Leeds and his PhD in Computer Vision at Brunel University for which he was awarded the Sullivan doctoral thesis prize. He joined CVSSP as Lecturer in Multimedia Signal Processing after running his own research group at Brunel University where he was Lecturer in Image Processing and is currently a visiting Research Fellow at the University of Oxford working on Sign Language Interpretation. Dr Bowden is an active researcher in Computer and Cognitive Vision, a member of the British Machine Vision Association (BMVA), the Institute of Electrical and Electronics Engineers and the Institute of Learning and Teaching. He has been a member of the BMVA executive committee and director of the company for 7 years and has organised 16 conferences and workshops in related areas. His award winning research centres on the use of computers to locate, track and understand humans with a specific interest in human computer interaction and contributions which include Markerless Human Motion Capture, Human Simulation, Artificial Life, Intelligent Visual Surveillance, Sign Language Recognition and Augmented Reality. His recent research into tracking and artificial life has received world wide media coverage and appeared at the British Science Museum and is currently on permanent exhibition at the Minnesota Science Museum, USA.
|