Thursday, September 19, 2002
Noon - 1:30 pm
Intel Seminar (417 S. Craig Street - 3rd Floor)
EVENTS PAGE: http://www.intel-research.net/pittsburgh/events.htm
HP Labs - Cambridge Research Laboratory
Computer Vision for Projected Displays
We present methods for enhancing projected displays using computer vision.
Visual feedback in camera-projector systems enables us to solve problems
that are traditionally difficult in passive camera settings. This talk
focuses on three issues: geometric alignment, photometric correction and
user interfaces for projected displays. We illustrate our ideas with three
practical systems: (1) a self-calibrating presentation system that allows
users to place the projector anywhere in the room and control the presentation
using a laser pointer or handheld computer; (2) a display that uses redundant
lighting from several micro-portable projectors to dynamically eliminate
shadows cast by the user; (3) an algorithm for automatically aligning
tiled multi-projector displays walls of arbitrary size.
Rahul Sukthankar is a senior researcher at HP Labs Cambridge Research
Lab (formerly Compaq/DEC CRL) and also holds a courtesy appointment as
adjunct faculty (Robotics) in the School of Computer Science at Carnegie
Mellon. He was previously a research scientist at Just Research for three
years. Rahul received his Ph.D. at CMU in 1997, and his B.S.E. summa cum
laude in computer science at Princeton in 1991. His current research focuses
on computer vision and machine learning, particularly in the areas of
face recognition and innovative user interfaces.
Contact Kim Kaan, 412-605-1203,
or visit http://www.intel-research.net.
SDI Home: http://www.pdl.cmu.edu/SDI/