April 28, 2012.Student Presentation
Schedule.
All
project
reports are due on May 10 (in class). For students who present on
May 03, you can still work on your projects based on my comments
on your presentations and put the new results in your reports.
May 01, 2012.Grading for Assignments 1-3 and Exam.
We are going to discuss exam questions in the first 30 minutes of
class on May 3. All are required to attend no matter on which day
you will present. Please bring the hard copy of your homework 4
submissions to class on May 3. This is a firm deadline.
Computer vision has a rich history of fundamental work on stereo
and visual motion, which has dealt with the problems of 3D
reconstruction from multiple images, and structure from motion
from video sequences. Recently, in addition to these traditional
problems, the stereo and motion information presented in multiple
images or a video sequence is also being used to solve several
other interesting problems, for example, large-scale scene
modeling, video mosaicing, video segmentation, video compression,
video manipulation and video surveillance. This is sometimes
summarized as video computing. Computer vision is playing an
important and somewhat different role in solving these problems in
video computing than the original image analysis approach in the
early days of vision research.The course "Computer Vision"
will include advanced topics in video computing as well as
fundamentals in stereo and motion.
II-1. Camera Models (slides)
(lecture
notes) (Assignment 3) - 03/01
II-2. Camera Calibration (slides) (lecture
notes) -
03/08 (Problem Definition: the Tools You
Must Know),
03/08,03/15 (Direct Approach: Divide and
Conquer),
03/15 (Projective Matrix Approach: All in One
)
II-3. Stereo Vision (slides)
(lecture
notes) (Assignment 4)
03/22 (Problem Definition & Epipolar
Geometry) ,
03/29 (Correspondence Problem &
Reconstruction Problem)
II-4. Visual Motion - (slides)
(lecture
notes)
04/05 (The Motion Field of Rigid Motion) , Project Discussions & Exam Review (Spring break 04/06 - 04/15)
04/19 (Optical Flow Approach & Feature-based
Approach)
Part III. Exam, Projects
and Project Presentations III-1. Exam - 04/26 III-2.
Exam
Discussions; Student Project Presentations (1) - 05/03 III-3. Student
Project Presentations (2) - 05/10
Textbook and References
Main Textbook:
In the form of
Lecture Notes and
Slides; will be provided by the instructor
Reference Textbook:
“Introductory Techniques for 3-D Computer Vision”,
Emanuele Trucco and Alessandro Verri, Prentice Hall, Inc., 1998
(ISBN: 0132611082, 343 pages ).
“Computer Vision – A Modern Approach” , David A.
Forsyth, Jean Ponce, Prentice Hall, 2003 (ISBN: 0130851981 , 693
pages).
“Three Dimensional Computer Vision: A Geometric
Viewpoint” , Olivier Faugeras, The MIT Press, November 19, 1993
(ISBN: 0262061589 , 695 pages)
Supplements:
Online References and additional readings when
necessary.
Grading and Prerequisites
The course will accommodate both graduate and senior
undergraduate students with background in computer science,
electrical and computer engineering, or applied mathematics.
Students who take the course for credits will be required to finish 4 assignments (40%), one
midterm exam (40%), and one programming project (20%,
including submit a report and give a small presentation to the
class at the end of the semester). The topics of the
projects will be given in the middle of the semester and will be
related to the material presented in the lectures.
Students are required to have a good preparation in both
mathematics (linear algebra/numerical analysis) and advanced
programming.