CSC I6716  Computer Vision- Spring 2014



Instructor: Professor Zhigang Zhu 



Section: 2TU Code: 3593 Credits: 3.0

Class Meet Time:    Tuesdays 7:30 - 10:00 PM Room: Harris Hall (Rm HR 12)

Office Hours:   Tuesdays 3:30 - 5:00 pm Room: NAC  8/211

   
City College of New York



Course Update Information 

Jan 28 (Tuesday), 2014. First class meet of our course. 


Feb 10, 2014. Each student please send me your up-to-date resume. We will use this for obtaining your contact information and recommending course projects, and connecting with possible research opportunities, some requiring US Citizens/Permanent Residents. Please add in your research interests and your citizenship.


March 08, 2014, Grading for Assignment 1.

March 10, 2014. Professor Jeff Bigham from CMU will give a talk on Crowd Agents: A Top-Down Approach to Truly Intelligent Systems. You are encouraged to attend this interesting talk, at 12:15 pm in Room NAC 6/113.


March 17, 2014. Course Project Requirements and Possible Project Topics

March 24, 2014, Grading for Assignments 1 and 2. Assignment 3 deadline is extended to April 1, before class.


April 07, 2014, Grading for Assignments 1to  3. We will discuss Assignment 3 and do a review of the exam in class on Tuesday April 8.


April 23, 2014Three important notices: (1) Assignment 4 will be due on April 29, 2014 before class. (2) We will have our exam on April 29, 2014, from 7:30 - 9:10 pm for 100 minutes. (3) ALL students will present for 10 minutes (7 minutes talk + 3 minutes QAs) on May 06, 2014 from 7:30 am - 9:50 pm. Reports will be due before the class on May 15, 2014, when we will discuss Assignment 4, the Exam, and have some make-up presentations.


May 06, 2014. The student presentations will be held in NAC 8/207, the Computer Science Conference Room at the same time, 7:30 - 9:50 pm


May 13, 2014, Grading for Assignment 4 and Exam.


May 15, 2014. The last class will be changed to May 15 (Thursday) in  NAC 8/207, the same time 7:30 pm. We will discuss the Exam, projects and homework #4. Reports will be due in class on May 15.

May 25, 2014. Final Grading.


Course Objectives

Computer vision has a rich history of fundamental work on color,  stereo and visual motion, which has dealt with the problems of color image understanding, 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 and rendering, video mosaicing, video segmentation, video compression and transmission, video manipulation,  mobile vision, and first person vision. The best successful vision systems that computer vision researchers can learn from are human vision systems. Therefore this course will also briefly discuss human vision science and explore how the brain sees the world, thus including introductory on computational neuroscience, motion, color and several other topics. 


Course Syllabus and Tentative Schedule (mm/dd)

(Spring 2014 academic calendar)


Part 0. Introduction and Human Vision

0-1. Introduction (slides) & Human Eyes (slides)  -01/28
0-2. Visual Brain (slides), Depth (slides), & Color (slides) -02/04

Part I. 2D Computer Vision Basics 

I-1. Image Formation: Digital Image Basics (slides)   (Assignment 1)-02/11
I-2. Image Enhancement  (slides)   (Lecture notes on feature extraction:I-2 and I-3) -02/18
I-3. Edge Detection: (slides) (Assignment 2) - 02/25

Part II.  3D Computer Vision

II-1.  Camera Models (slides) (lecture notes)  - 03/04

II-2.  Camera Calibration (slides) (lecture notes) (Assignment 3) - 03/11

    (Problem Definition:  the Tools You Must Know), 

    (Direct Approach: Divide and Conquer), 

    (Projective Matrix Approach: All in One )  

II-3.  Stereo Vision (slides) (lecture notes ) (Assignment 4) -03/18, 03/25

    (Problem Definition & Epipolar Geometry) , Project Discussions

    (Correspondence Problem & Reconstruction Problem)  

II-4.  Visual Motion - (slides) (lecture notes) - 04/01, 04/08

    (The Motion Field of Rigid Motion) 

    (Optical Flow Approach & Feature-based Approach)   & Exam Review


Part III. Exam, Projects and  Project Presentations

III-1. Exam  -04/29


III-2. Student Project Presentations  - 05/06


III-3. Project Reports due; Exam and Homework Discussions; Project Make-up Presentations and Discussions 05/13



Textbook and References

Main Textbook:    

  1. Computer Vision,  In the form of Lecture Notes and Slides;  will be provided by the instructor 
  2. Vision and Brain - How We Perceive the World, By James V. Stone, The MIT Press. Paperback | $30.00  | ISBN: 9780262517737 | 264 pp. | 6 x 9 in | 25 color illus., 132 b&w illus.| September 2012 (For students with little experience in vision and neuroscience to know human vision, brain and computational neuroscience)

Reference Textbook:

  1.   “Computer Vision – A Modern Approach” , David A. Forsyth, Jean Ponce, Prentice Hall, 2003 (ISBN: 0130851981 , 693 pages).
  2.   “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.


Copyright @ Zhigang Zhu , Spring 2014