|
Computer Vision (MA-INF 2201) Summer Semester 2010
Times:
Monday & Wednesday: 9 - 11am (lectures); Thursday: 8:15 - 10 am (exercises) Place:
rooms A207 (lectures), and A7a (exercises), both in Romerstr. 164
Professors
Lectures:
Cristian
Sminchisescu (cristian.sminchisescu at ins uni-bonn de) Exercises and projects:
Fuxin Li (fuxin.li
at ins uni-bonn de)
Adrian Ion (ion at
ins uni-bonn de) Course email:
tutors.inf2201.10 at gmail.com (please, use this email for all general
course inquiries) Goals of the course
The main goal of computer vision is to make computers
see, hence to infer properties of the three-dimensional world from digital
images or video. Problems in this field include identifying the
three-dimensional structure of a visual scene, determining where objects in the
scene are moving, and recognizing people and objects, all through analyzing
information acquired with digital or video cameras. This course provides
an introduction to computer vision including topics like image representation
and processing, feature detection and matching, image segmentation, motion
estimation, object tracking, 3D reconstruction of rigid and articulated objects,
and object recognition. Modern machine learning techniques intrinsic to reliable
visual recognition, including the modeling of structured spatial and temporal
dependencies, inference and prediction are also covered in the course. Along the
way, different models and algorithms will be illustrated by means of practical demonstrations based on
state of the art research prototypes
or commercially available systems. Prerequisites Foundations of Graphics, Vision and Audio (MA-INF
2101) Basic linear algebra (but we will review during the
first exercise sessions) Basic vector calculus (reviewed also during the first
exercise sessions) Fundamentals of algorithms and data structures Working knowledge of Matlab or C/C++ No prior knowledge of computer vision assumed! Textbooks
David Forsyth & Jean Ponce: Computer Vision: A Modern Approach, Pearson,
2002, ISBN 0130851981
Richard Szeliski: Computer Vision: Algorithms and
Applications (pdf draft, 25MB), local mirror pdf also available
here.
Christopher Bishop: Pattern Recognition and Machine Learning,
Springer,2007, ISBN: 978-0387310732 Optional:
Andrew Blake and Michael Isard: Active Contours, Springer, 1998, ISBN
978-3540762171 Optional:
Richard Hartley and Andrew Zisserman: Multiple View Geometry, Cambridge,
2004, ISBN: 052154051 Administrative To
access course materials, get username and password in class! Matlab licences can be
obtained at discounted UniBonn student rates. For license information, see: For queries, and for turning in
projects or assignments, please send email to: tutors.inf2201.10 at gmail.com.
All assignments (exercises and programming results) must be turned-in as
hardcopies to the tutors during the exercise sessions indicated in the
Syllabus. For programming assignments please send also your source code (no
binaries!) by email, with subject line: "Assignment
assignment_number_you_turn_in". Late policy: Assignments cannot be turned in later
than indicated in the Syllabus. Grading
50% oral exam, 50% successful exercise/assignment completion |
