|
Introduction:
Our group's research is in the areas of Computer vision, Graphics, Image
processing and Multimedia systems. In particular, we are interested in
modeling nonrigid body motion with emphasis on its application towards
analysis of facial motion, tongue motion and cloud motion.
Facial research include, Analysis, Synthesis and Transmission of facial
animation parameters (MPEG-4 based FAPs) from real-time 2D/3D facial images.
Potential applications of this research include video-conferencing with very
low bandwidth requirements, gesture and intention recognition with
applications towards natural language understanding, entertainment industry
applications etc.
Research in cloud motion analysis consists of estimating the structure and
cloud-drift wind velocities from satellite imagery. This analysis is quite
challenging due to the complex dynamics of the imaging instruments and the
underlying non-linear phenomena of cloud formation and weather. Accurate cloud
heights and winds are important for a number of meteorological and climate
applications.
Studies on tongue motion analysis is being done from ultrasound digital
sequences using deformable contour modeling. Automatic extraction and
tracking of the tongue surface can provide valuable information for speech
and swallowing research, including application in the areas of disordered
speech, linguistics, speech processing, aging research, tongue modeling and
language training.
Facilities:
Location:
The VIMS Lab
is located at 212 Smith Hall.
Locate
us on wikimapia
or on Live
maps.
Consult
the UD campus
map.
|
