Computer Vision Fall 2006

CSC I6716 Computer Vision- Fall 2006

Click on the image above to see a full-size, stereo, panoramic image of the CCNY campus.

Time: Tuesday 04:30-07:00 PM, Room: SH-77, Credits: 3.0
Office Hours: Tuesday 2:00 - 4:00 pm

Course Update Information

July 14, 2006. Course website online.

September 29, 2006. About homework submission: 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.
October 12, 2006. Grading for Assignment 1 (Check out: Orignal image; Bayer image; Reconstructed image).
Oct 17, 2006, You are welcome to attend the talk on Oct 18, 2006 at 2:00 pm, at NAC 7/311, given by Dr. Ying-Li Tian on IBM Surveillance System
October 24, 2006, Homework 3 online.
October 31, 2006. Grading for Assignments 1 & 2.
November 22, 2006. Grading for Assignments 1, 2, writing part of 3 and Mid-term Exam.
***************************************
December 05, 2006. The MS student project presentations are scheduled on Tuesday Dec 12, 2006. Here are a few notices:

Each student (or team) please bring a hard copy of your final project report to the class.
Please come to class on time - we are going to start the presentation right at 4:30 pm.
Everyone will only have 8 minutes including transition times, so please prepare to show the important things (motivations, ideas, implementations, results) in 5 minutes.
Please send me emails on your team members and project topics by the end of this week, if you have not done so.
Please send the source code of your project to me before the class on Dec 12.
Nothing will be accepted after Dec 12, 2006.

Dec 13, 2006. Final Grading, and Grading for Assignments 1-3, Mid-term Exam and Project.

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 synthesis, video segmentation, video compression, video registration, 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:

Computer Vision Basics - Introduction, Sensors, Image Formations, Feature Extraction
3D Computer Vision - Camera Models, Camera Calibration, Stereo Vision, Visual Motion
Video Computing - Video Mosaicing, Stereo Mosaicing, Image-Based Rendering, Content-Based Video Understanding, Motion Segmentation and Human Tracking

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. Students will have opportunities to talk with leading researchers in the fields of computer vision, robotics and HCI.

Course Syllabus

Part I. Computer Vision Basics

Topic I-1. Introduction: Image, Vision and 3D Vision (slides) - Sep 5
Topic I-2. Visual Sensors (slides) - Sep 12
Topic I-3. Image Formation and Processing (slides) (Homework 1) - Sep 12, Sep 19
Topic I-4. Features and Feature Extraction (part 1, part 2), (Homework 2)- Sep 19, Sep 26

Part II. 3D Computer Vision

Topic II-1. Camera Models (slides) - Oct 10
Topic II-2. Omnidirectional Cameras (slides) - Oct 17
Topic II-3. Camera Calibration (slides)- Oct 17, Oct 24
Topic II-4. Stereo Vision (slides) ( Homework 3) - Oct 24, Oct 31
Topic II-5. Visual Motion (slides) - Oct 31, Nov 07

Reviews and Project Topics - Nov 07
Midterm Exam - Nov 14
Project Designs & Implementations - Nov 21 (No class meet)

Part III. Video Computing

Exam & Project Discussions - Nov 28

Topic III-1. Video Mosaicing and Image-Based Rendering - Dec 05
Topic III-2. Multimodal Sensing and Integration - Dec 05

Student Project Presentations - Dec 12

Textbook and References

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

References:

“Computer Vision – A Modern Approach” Forsyth and Ponce, 2003.
“Three Dimensional Computer Vision: A Geometric Viewpoint” O. Faugeras
“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 3 assignments of paperwork only (30%), one midterm exam (40%), and one programming project with exit interview (30%, 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.