CSCI 574 Computer Vision

Fall 2007


=================================================

Important Announcements

To registered students: As the class is full and there are many students on the waiting list, we are attempting to determine which students are actually interested in continuing in the class. If a registered student has not attended the August 26 class and does not attend the August 28, he/she will be automatically dropped from the class. Absences for good reason should be communicated to the instructor prior to August 28. Attendance will be determined by marking the sign up sheet circulated in the class. No action is required from those attending the class.

To students on wait list: It is not possible to expand the size of the class due to physical space limitations. It is not allowed for students to take the class on web without becoming a DEN student. As you can see, we are making effort to find registered students who do not intend to actually take the class. Meanwhile, you are advised to continue to come to the class, provided that there are enough seats for you.

Please Refer Main Class WEB page at http://den.usc.edu/ for lectures, assignments and handouts.

 =================================================

Instructor

Prof. Ram Nevatia
Phone : (213) 740-6427
Email :
Office Hours : MW 3:00 - 4:30 PM
Office Location : PHE 204

Teaching Assistant

Email:
Li Zhang
Phone : (213) 740-6437
Office Hours : TTh 10:00 - 11:30 AM
Office Location : PHE 224
Quan Wang
Phone : (213) 740-4250
Office Hours : WF 10:00 - 11:30 AM
Office Location : SAL 103

Textbooks

Required:
  1. Computer Vision : A Mordern Approach, D. Forsyth and J. Ponce, Prentice-Hall, 2001
  2. We will also use some additional papers that will be made available on-line to the class.

References

  1. A Guided Tour of Computer Vision, V. S. Nalwa, Addison Wesley, 1993
  2. Robot Vision, B.K.P. Horn, MIT Press, 1986
  3. Three-Dimensional Computer Vision, O. Faugeras, MIT Press, 1993
  4. Multiple View Geometry in Computer Vision, Richard Hartley and Andrew Zisserman, Cambridge University Press, 2000
  5. Digital Image Processing (2nd Edition), Rafael C. Gonzalez, Richard E. Woods, Prentice Hall, 2002
  6. Image Processing, Analysis, and Machine Vision (3rd Edition), Milan Sonka, Vaclav Hlavac, and Roger Boyle, Thomson Engineering, 2007

Prerequisite

1. CSCI 455 or equivalent - Data Structures, good programming skills. Ability to convert informal descriptions into computer algorithms. Students must be able to program in C or C++.
2. Basic Mathematics - Knowledge of and ability to use calculus, analytical solid geometry and linear algebra (matrix theory) is essential. Knowledge of elementary probability theory will also be needed. If you have not used them for several years, you must be prepared to spend some time to review them.
3. CSCI 561 and 573 (Artifical Intelligence) are helpful but NOT required.

Course Objective

The objective of this course is to understand the basic issues in computer vision and major approaches that address them. Computer vision is not a "solved" problem, hence, definitive solutions are available only rarely; most of the time, we will discuss alternatives and their limitations. After completing the course, the students may expect to have the knowledge needed to read and understand the more advanced topics and current research literature, and the ability to start working in industry or in academic research. However, this course is NOT designed to be a "cookbook" course that gives just a survey of the methods needed in "practice", nor will it cover "commercial" systems in any detail.

Course Requirement

There will be two exams:

  1. Exam1: Scheduled on Monday, October 15th.
  2. Exam2: on the last day of the class. (subject to student approval)
Both exams will be conducted during class hours. Exam1 will count for 25%, and Exam2 will count for 35% of the course grade. Homework assignments, written and programming together, will also count for 30% of the grade. 10% of the weight will be given to class attendance and participation (except for remote students). Note that all assignments are considered an intergral part of the course and MUST be completed. Not completing assignments may result in "F" grade.

Academic Integrity

The USC Student Conduct Code prohibits plagiarism. All USC students are responsible for reading and following the Student Conduct Code, which appears on pp. 83-97 of the 1997-1998 SCampus.

In this course we encourage students to study together. This includes discussing general strategies to be used for individual assignments. However, all work submitted for the class is to be done individually, unless an assignment specifies otherwise.

Some examples of what is not allowed by the conduct code: copying all or part of someone else's work, and submitting it as your own; giving another student in the class a copy of your assignment solution; consulting with another student during an exam. If you have questions about what is allowed, please discuss it with the instructor.

Violations of the Student Conduct Code will be filed with the Office of Student Conduct, and appropriate sanctions will be given.

Programming Facility

A software library of basic image processing algorithms, called OpenCV, will be used in programming assignments; this library is available for free download for educational purpose. This library is available for MS Windows and Linux; however, we will only provide TA support for the windows version. Students may choose to complete assignments using USC computer facilities or their own PCs. OpenCV can be downloaded here.

Other useful links for OpenCV:

Course Outline

Following is a list of topics expected to be covered, in anticipated order, and with expected time to be spent on them. This list is intended to be only indicative, the actual topics, the order and the time may vary somewhat depending on various factors including student interests and preparation.

  1. Introduction (1 week)
    Background, requirements and issues, human vision.

  2. Image formation: geometry and photometry (2 weeks)
    Geometry, brightness, color, Camera calibration

  3. Image segmentation (2 weeks)
    Region segmentation, Edge and line finding

  4. Multi-view Geometry (3 weeks)
    Shape from stereo and motion, feature matching, surface fitting, Active ranging

  5. Image classification(2 weeks)
    Pixel classification, region classification, face detection and identification

  6. Object Recognition(2 weeks)
    Alignment methods, Shape descriptions

  7. Motion analysis (1 week)
    Motion detection and tracking, Inference of human activity from image sequences

  8. Applications survey, Review (1 week)
    Industrial, navigation, mapping, multimedia

Course Lectures

Date Topic Notes
08/27/07 Introduction to Vision Lecture 1
08/29/07 Course Overview, Image Formation Lecture 2
09/05/07 Image Formation (contd), Transformations Lecture 3

Assignments

Due on Topic Homework
09/05/07 Homework 0: Basic Geometry and Linear Algebra hw0.pdf
09/12/07 Homework 1: Camera Parameters hw1.pdf

Please submit hard copies in class on the due day.



The University of Southern California does not screen or control the content on this website and thus does not guarantee the accuracy, integrity, or quality of such content. All content on this website is provided by and is the sole responsibility of the person from which such content originated, and such content does not necessarily reflect the opinions of the University administration or the Board of Trustees