CSC I6716  Computer Vision- Fall 2007

Instructor: Prof. Zhigang Zhu

Credits: 3.0
Time: Tuesday 04:30-07:00 PM,  Room: SH-77
Office Hours:
Wednesday 11:00 AM- 1:00 PMRoom: NAC  8/210

Course Update Information

August 28, 2007. first class meet.

Sept 06
, 2007,  There will be a talk at 11:00 am on Wednesday,  Sept 12 .  fir details, please click CCNY Lecture Series on Computer Vision, Robotics and Human-Computer Interaction.
September 11, 2007. Homework 1 online, due Sept. 25. If you could not hand in your submission in class, or during my office hours, please drop your submission in my mailbox in the Main Office of the CS Dept (the office will be closed at 5:00 pm). If you cannot make either of them before the deadline, please send your code and your softcopy via email before the deadline, indicating you are going to bring a hardcopy to me in the next class meet.
September 25, 2007. Homework 2 online, due Oct 09.
October 02, 2007 Homework 3 online, due Oct 23.
October 02, 2007 Project Topics online
October 09, 2007, Grading for Homework 1
October 16, 2007 Homework 4 online, due Nov 13, before the mid-term exam.
October 17, 2007, Grading for Homework #1 and #2
October 24, 2007. For those who didn't come to class or didn't bring your submissions for homework #3 on last Tuesday, please bring your hard copies to me on Tuesday, Oct 30.
November 06, 2007, Grading for Homework #1- #3
November 06, 2007, Midterm Exam - Nov 13, 2007, 4:30 - 6:30 pm in classroom SH-77, Close Book Exam.
November 06, 2007,  Please send the topic of your team before Nov 20. One email per team, please. In your email body, please list the topic title, full names and IDs of team members. Each team cannot have more than 2 students.  Student presentations will be held on Dec 04 and Dec 12 in class meet times. You will need to hand in your report before your presentations.  I will announce presentation schedules on Nov 27. If you don't send in your topics in time, I will put you on Dec 04 by default.
November 14, 2007, Grading for Homework #1- #4 and midterm exam. Those who did not turned in your Assignment #4 submissions before November 14 will only automatically lose 50% of the total (and the scores are not given yet).
Nov 24, 2006Project Presentation Schedule can be found here (updated). Note that those who did not send your choices were listed first on Dec 04. Please be prepared. Everyone: please check out the schedule and read the notices carefully. Correction: the second group will present on Dec 11, 2007 (Tuesday).
November 28, 2007, Final Grading for Homework #1- #4 and midterm exam. No submissions will be accepted to this point.
December 25, 2007. Final Grading. Note: The grading is FINAL. Please do not send me email for changing grades.

Course Objectives

Computer vision has a rich history of 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 present in multiple images or a video sequence is also being used to solve several other problems, for instance video modeling, video mosaicing, video segmentation, video compression, and video surveillance an monitoring. This is 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 considered 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. The topics will be divided into three parts: 
Note: In addition to attending regular course lectures, students may also be arranged (if appropriate) to attend seminars of the CCNY Lecture Series on Computer Vision, Robotics and Human-Computer Interaction  hosted  by Prof. Zhu of CS and Prof. Xiao of EE. Students will have opportunities to talk with leading researchers in the fields of computer vision, robotics and HCI.

Course Syllabus and Tentative Schedule

Part I. Computer Vision Basics 

Topic  I-1. Introduction: Image, Vision and 3D Vision (slides) - Aug 28
Topic  I-2. Visual Sensors (slides) - Sep 04
Topic  I-3. Image Formation and Processing  (slides) (Homework 1) - Sep 11 (No class meet on Sept 18)
Topic  I-4. Features and Feature Extraction  (part 1) (part 2) (Homework 2)- Sep 25
Project Topics - Oct 02

Part II.  3D Computer Vision

Topic  II-1.  Camera Models  (slides) (Homework 3)- Oct 02
Topic  II-2.  Camera Calibration  (slides); Discussion of Homework #1 & #2 - Oct 09
Topic  II-3.  Stereo Vision (slides)( Homework 4) -  Oct 16
Research Experience in Stereo Mosaicing- Oct 23
Topic  II-4.  Visual Motion (slides)-Oct 30

Part III. Video Computing and Projects

Motion Segmentation and Human Tracking; Reviews and Project Topics - Nov 06
Midterm Exam - Nov 13
Video Mosaicing and Image-Based Rendering, Exam & Project Discussions - Nov 27
Student Project Presentations - Dec 04, Dec 11

Textbook and References

    “Introductory Techniques for 3-D Computer Vision”,  Trucco and Verri, 1998.


  1.     “Computer Vision – A Modern Approach” Forsyth and Ponce, 2003.
  2.     “Three Dimensional Computer Vision: A Geometric Viewpoint” O. Faugeras
  3.     “Image Processing, Analysis and Machine Vision” Sonika, Hlavac and Boyle, 1999
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 of paperwork only (40%), one midterm exam (40%), and  one programming project with exit interview (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 will be counted for both "Intelligent Systems" and "Scientific and Statistical Computing Computer Science" Groups for graduate students, and for both "Computational Techniques for Science and Engineering" and "Net-Centric Computing"  Electives for undergraduate students. 

Copyright @ Zhigang Zhu , Fall  2007