CSC I6716  Computer Vision- Spring 2017

Instructor: Professor Zhigang Zhu 

Section: 2RR Code: 46418 Credits: 3.0

Class Meet Time:    Tuesdays 4:50PM - 7:20PM ,  Room: NAC 4/210

Office Hours:   Tuesdays  10:30 am - 12:00 pm, Room: NAC  8/211

   
City College of New York

Course Update Information 

• Jan 31, 2017. First class meet of our course.  CUNY has recently made several software available for use ( including MathWorks MatLab that we will use for the class ), through the CUNY Virtual Desktop.  Please review the information provided on this CUNY website.
• March 4, 2017. Grading for Assignment 1.
  
• March 07, 2017. Assignment 2 deadline has been extended to Sunday March 11, 2017
  
• March 07, 2017. Assignment 3 online, due Sunday March 25, 2017
• March 08, 2017. Possible Vision Project Topics.
  
• March 14, 2017. You can start to work on Assignment 4, due Friday April 28, 2017.
• May 09, 2017. Exam Discussions and Project Discussions. Grading so far including Assignments #1 to #4 and the Exam.
  
• May 16, 2017. Presentations of all student teams (Tentative Schedule). Please send your title by the end of Wednesday. The final project report is due on Friday 05/19 midnight.  Project Presentation and Report Requirements: (1) Introduction (problem: Why this need to be done, with real-world applications); (2) Related Work (What has been done, with a few references); (3) Your Approach (How you are going to do it, with algorithms, equations, figures) (4) Your Implementation  and Analysis (What you do, with images, tables, and numbers) (5) Your Conclusions (Itemized conclusions, observations and discussions)
• May 25, 2017. Final Grading will be submitted by the end of Sunday May 28, 2017. Have a great summer!
  

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 2017 academic calendar)

Part 0. Introduction and Human Vision

Part I. 2D Computer Vision Basics 

I-1. Image Formation: Digital Image Basics (slides)   (Assignment 1)-02/07
I-2. Image Enhancement  (slides)   (Lecture notes on feature extraction:I-2 and I-3) - 02/14, 02/21
I-3. Edge Detection: (slides) (Assignment 2 on I-2 and I-3) - 02/21 

Part II.  3D Computer Vision

II-1.  Camera Models (slides) (lecture notes)  - 02/28

II-2.  Camera Calibration (slides) (lecture notes) (Assignment 3 on II-1 and II-2) - 03/07

    (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 on II-3 and II-4) -03/14, 03/21

    (Problem Definition & Epipolar Geometry), Project Discussions

    (Correspondence Problem & Reconstruction Problem)  

II-4.  Visual Motion - (slides) (lecture notes) - 03/28, 04/04

    (The Motion Field of Rigid Motion) 

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

Part III. Exam, Projects and  Project Presentations

III-0. Exam Review, Homework and Project Discussions - 04/25

III-1. Exam  -05/02

III-2. Exam and Project Discussions  - 05/09

III-3. All Student Project Presentations  - 05/16; Project Reports due 05/19 (Friday) midnight!

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, biomedical 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  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 2017