CSc 471  Computer Vision- Fall 2017

Instructor: Professor Zhigang Zhu

Section: E  Code: 56404 Credits: 3.0

Class Meet Time:    M/W 2:00 - 3:15 PM Room: SH-275

Office Hours:   Monday 3:30 - 5:30 pmRoom: NAC  8/211

    City College of New York

Course Update Information 

August 28 (Monday), 2017. First class meet of this course.
September 21, 2017. Grading for Assignment 1.

October 20, 2017. If you still cannot find the links of some of the slides, please reload your page.
22, 2017. Grading for Assignments 1-2.
October 30, 2017. Project Requirements and Possible Topics. Please see the following for schedules of class presentations. The final reports will be due on Dec 15, 2017.

November 11, 2017. Grading for Assignments 1-3.
November 23, 2017. Here is the schedule for the final presentations. Happy Thanksgiving to All!
November 24, 2017. Grading for Assignments 1-3 and Exam. We will discuss the exam questions in class on Monday November 27, 2017.
November 24, 2017. Grading for Assignments 1-4.
December 23, 2017. Final Grading. Merry Christmas and Happy New Year!

Course Objectives

Computer vision has a rich history of fundamental 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 presented in multiple images or a video sequence is also being used to solve several other interesting problems, for example, large-scale scene modeling, video mosaicing, video segmentation, video compression, video manipulation and video surveillance. This is sometimes 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 approach 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. 

Course Syllabus and Tentative Schedule (mm/dd)

(Fall 2017 academic calendar)

Part I. Computer Vision Basics 

I-1. Introduction: What, Why and How (pptx slides) -08/28
I-2. Image Formation: Digital Image Basics (pptx slides)  (Assignment 1)-08/30, 09/06
I-3. Image Enhancement: point operations, histograms and neighborhood operations   (slides)  (Assignment 2) ( Lecture notes in PDF:I-3 and I-4) -09/11, 09/13, 09/18
I-4. Edge Detection: basics, advanced, and Hough Transform (slides)  - 09/25, 09/27, 10/02

Part II.  3D Computer Vision

II-1.  Camera Models (slides) (lecture notes in PDF) (Assignment 3)
    (Geometric Projection of a Camera) - 01/04
    (Camera Parameters) - 10/11
    (Camera Models Revisited) - 10/16

II-2.  Camera Calibration (slides) (lecture notes in PDF

    (Problem Definition:  the Tools You Must Know), 10/18

    (Direct Approach: Divide and Conquer), 10/23

    (Projective Matrix Approach: All in One ), 10/25

II-3.  Stereo Vision (slides) (lecture notes in PDF) (Assignment 4)

    (Problem Definition) &  Project Discussions, 10/30
Epipolar Geometry), 11/01

    (Correspondence Problem & Reconstruction Problem) , 11/06

II-4.  Visual Motion - (slides) (lecture notes)

    (The Motion Field of Rigid Motion), 11/08

    (Optical Flow Approach & Feature-based Approach),11/13  
    Exam Review
, 11/15

Part III. Exam, Projects and  Project Presentations

III-1. Exam  -11/20 (before Thanksgiving Break 11/23-11/26)

III-2.  Project Discussions and Exam Discussions -  11/22, 11/27

III-3. Student Group Project Presentations (1) (2) (3), (4) - 11/29, 12/04, 12/06, 12/11

Textbook and References

Main Textbook:
   In the form of Lecture Notes and Slides, provided by the instructor (above).

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)


    Online References and additional readings when necessary. 


Grading and Prerequisites

The course will accommodate senior undergraduate students with background in computer science and computer engineering. 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 , Fall 2017