Robotics Institute
Seminar, February 6
Time
and Place | Seminar Abstract | Speaker
Biography | Speaker Appointments
Visual 3D Modeling using Cameras and Camera
Networks
Marc Pollefeys
University of North Carolina
at Chapel Hill
Mauldin Auditorium (NSH 1305)
Refreshments 3:15 pm
Talk 3:30 pm
This talk consists of
two main parts. First, a fully automatic
approach to reconstruct detailed 3D models from camera images is presented. The
approach can deal with uncalibrated image sequences acquired with a hand-held
camera. Based on tracked or matched features the relation between multiple
views are computed. From this both the structure of the scene and the motion of
the camera are retrieved. The ambiguity on the reconstruction is restricted
from projective to metric through self-calibration. A flexible multi-view
stereo matching scheme is used to obtain a dense estimation of the surface
geometry. From the computed data detailed 3D surface models or alternative
visual representations are constructed.
Issues such as key-frame selection, dominant planes and camera
auto-exposure are addressed. Next, the calibration and synchronization of
camera networks is addressed. An
efficient and robust algorithm that computes the epipolar geometry from
silhouttes of dynamic objects is presented.
This makes this approach particularly suitable for visual hull
systems. Using the pairwise epipolar
geometries, the complete calibration of the network is computed, and refined
through bundle adjustment. A specific
difficulty is that in general only two view matches are available (frontier
points). This approach is also extended to deal with unsynchronized video
streams. Ongoing efforts to extend this
research to active pan-tilt-zoom camera networks is also briefly discussed.
Marc Pollefeys is an Assistant
Professor of Computer Science at the University
of North Carolina at Chapel Hill. He received his M.S. and Ph.D. degrees from
the K.U.Leuven in 1994 and 1999, respectively. His main area of research is computer
vision, more specifically multi-view geometry, structure from motion,
(self-)calibration, stereo, image-based rendering and applications. One of his
main research goals is to develop flexible approaches to capture visual
representations of real world objects, scenes and events. Dr. Pollefeys has
received several prizes for his research, including the prestigious Marr prize
at ICCV '98. Recently he also obtained an NSF career award. He is the author or
co-author of more than 70 technical papers. He has organized workshops and
courses at major vision and graphics conferences. He has been serving on the
program committees of major conferences such as ICCV, CVPR and ECCV and is a
regular reviewer for most of the major vision, graphics and photogrammetry
journals.
For appointments, please contact Bob Collins
The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.
