Computer Vision (Fall 2019)

Instructor: Professor Zhigang Zhu

The City College of New York

Course No and Section (Code): CSC I6716 – 1EF (57964) Credits: 3.0
Class Meet Time: Monday 2:00 – 4:30 PM, Room: NAC 6/110
Office Hours: Every Thursday  2:30 pm – 4:30 pm, Room: NAC  8/211

Course Update Information

  • 09/05 (Thursday but on a Monday Schedule): First day of our class. CUNY has  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. If you are asked for a server, please enter https://vdi.cuny.edu
  • 09/11. Alternatively, CUNY faculty and students will be able to download a standalone Matlab version by creating an account using your CCNY email account at this website. On this website, go to “Matlab Portal” to create your account and download the software installer. You will need the account information to install and use the software too. It might be very slow when you downloading the real software & tools in installation. So please do not add new tools to the default but instead remove simulink etc. that you won’t use.
  • 10/14, 2019. Grading so far. We will discuss the assignment on Wednesday in class.
  • 10/25, 2019. Grading so far. We will discuss the assignment on Monday Oct 28 in class.

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) 

(Fall 2019 academic calendar)

Part 0. Introduction and Human Vision 

  • 0-1. Introduction (slides) & Human Eyes (slides)  -09/05 (TH) 
  • 0-2. Visual Brain (slides) -09/05 (TH), 09/09
  • 0-3. Depth (slides) -09/09
  • 0-4. Color (slides) -09/09

Part I. 2D Computer Vision Basics 

Part II.  3D Computer Vision

Part III. Exam, Projects and  Project Presentations

  • III-1. Exam  – 11/25
  • III-2. Exam and Project Discussions – 12/02
  • III-3. All Student Project Presentations  – 12/09; Project Reports due 12/15 (Sunday) 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.