CSC I6716
Computer Vision- Fall 2009
http://www-cs.engr.ccny.cuny.edu/~zhu
Teaching Assistant: Mr. Wai L. Khoo
WKhoo@gc.cuny.edu
Credits: 3.0
Class Meet Time:
Monday and Wednesday 12:30-01:45PM, Room: NAC-7225
Office Hours:
Monday and Wednesday 02:00-03:00
PM,
Room: NAC 8/210
City
College
of
New York
Course Update Information
August 31, 2009. First
class meet of our course.
September 02, 2009.
Assignment 1 online, due on Sep
16
before
class. You may submit your homework to Mr. Wai L.
Khoo at WKhoo@gc.cuny.edu
September 13, 2009.
Assignment 2 online, due on Sep
30
before
class. You may submit your homework to Mr. Wai L.
Khoo.
September 22, 2009.
Grading for Assignment 1.
September 25, 2009.
Assignment 3 online, due on Oct 26 before class.
October 06, 2009.
Grading for Assignments 1
&2.
October 20, 2009, Project
Topics
.
October 31, 2009.
Grading for Homework 1 and
Assignments 1 - 3 .
October 31, 2009, Project
Topics
Updated
(I did not include the self-selected topics yet).
November 25, 2009.
Grading
for
Assignments 1
-3 and Midterm Exam. Have a
great Thanksgiving holiday!
December 07, 2009.
Grading
for
Assignments 1
-4, a Quiz and Midterm Exam.
December 10, 2009.
Final Grading
Course Objectives
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.
Note: In
addition to attending regular course lectures, students may also be
arranged to attend seminars of the CCNY
Lecture Series on Computer Vision, Robotics and Human-Computer
Interaction, hosted by
Prof. Zhigang Zhu of CS and Prof. Jizhong Xiao of EE. Students will
have opportunities
to talk with leading
researchers in the fields of computer vision, robotics and
Human-Computer Interaction (HCI).
Course Syllabus and Tentative Schedule (mm/dd)
(Academic
calendar,
Fall
2009)
Part I. Computer Vision Basics
I-1. Introduction: What, Why and How (slides)
-
08/31
I-2. Image Formation: Digital Image Basics (slides) - 09/02 (Assignment 1)
I-3. Image Enhancement (1): Histogram and How to Make a Picture
Prettier (slides for I-3 and I-4)
-
09/09
(No class meet on
09/07)
I-4. Image Enhancement (2): Noise Removal and How to Make a Picture
even Prettier (Assignment 2) - 09/14
I-5. Edge Detection (1): Edge Detectors and Sketch Generation (slides for I-5 & I-6)
- 09/16
I-6. Edge Detection (2): Hough Transform for Obtaining Shapes
- 09/21
Part II. 3D
Computer Vision
II-1. Camera Models (slides)-
09/23 (Geometric Projections: the Rules
Governing 2D Imaging),
09/29 (Camera Parameters: the Secrets Inside Your
Camera ) (Assignment 3),
09/30 (Linear Algebra Models: Make the Math Simpler)
II-2. Camera
Calibration (slides)
-
10/05 (Problem Definition: the Tools You Must
Know),
10/07,10/14 (Direct Approach: Divide and Conquer), (No class meet on 10/12)
10/19 (Projective Matrix Approach: All in One
)
II-2a Project
Topics
Discussion - 10/21
II-3. Stereo
Vision (slides)
10/26 (Problem Definition: Two is Better Than One) (
Assignment 4),
10/28 (Epipolar Geometry: the Trick for Simplifying
Your Task),
11/02 (Correspondence Problem: The Key to Success) ,
11/04 (Reconstruction Problem: Getting 3D from 2D
Data)
II-3a. Exam Review -11/18
II-4. Visual
Motion (slides)-
11/09 (The Motion Field of Rigid Motion: See the
Motion in Images) ,
11/11 (Optical Flow Approach: Spatio-Temporal
Gradients in Work) ,
11/16 (Feature-based Approach: Tracking Individual
Points) ,
11/18 (Advanced Topics: Video Mosaicing, Target
Tracking and Video Coding)
Part
III.
Exam,
Project
and Project Presentations
III-1.
Midterm
Exam - 11/23 (before Thanksgiving)
III-2.
Project
Designs
- 11/25
(no class meet)
III-3.
Exam
&
Project
Discussions - 11/30
III-4.
Student
Project Presentations - 12/2, 12/7, 12/9
Textbook and References
Textbook:
“Introductory Techniques for 3-D Computer
Vision”, Emanuele Trucco and Alessandro Verri, Prentice Hall,
Inc., 1998
(ISBN:
0132611082, 343 pages ).
References:
- “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.
This course is under I6700: Topics in Scientific and Statistical
Computing, in the area of "Computing Methodologies and
Mathematical Computing" of our Computer Science Master
Program. Students are required to have a good
preparation in both mathematics (linear algebra/numerical analysis) and
advanced
programming.
Copyright @ Zhigang Zhu ,
Fall 2009