Robotics Institute
Seminar, April 23
Time
and Place | Seminar Abstract | Speaker
Biography | Speaker Appointments
Visual Recognition from Invariant Local
Features
David
Lowe
Computer Science
Department
University of British Columbia
Mauldin Auditorium (NSH 1305)
Refreshments 3:15 pm
Talk 3:30 pm
Within the past few
years, new methods for identifying invariant local features in images have
provided successful solutions to a range of recognition and image matching
problems. For recognition applications,
it has proved particularly important to develop features that are distinctive
as well as invariant, so that a single feature can be used to index into a
large database of features from previous images. Robust recognition can then be achieved by
identifying clusters of features using a Hough transform and detailed model
fitting. In addition to describing the
invariant feature approach, some recent applications will be presented,
including location recognition and the detection of image panoramas from
unordered sets of images. A demo will be
given of a system that can recognize objects at near real-time speeds.
David Lowe is a professor of
computer science at the University of British Columbia in Vancouver, Canada. He received his Ph.D. in computer science
from Stanford University in 1984. His research interests include object
recognition, local invariant features for image matching, machine learning for
recognition, robot localization, and models of human visual recognition. He is on the Editorial Board of the
International Journal of Computer Vision and was co-chair of ICCV 2001 in Vancouver, Canada.
For appointments, please contact Monica Hopes.
The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.
