CPS 843/CP 8307 Introduction to Computer Vision
Winter 2014, Friday 3:00  6:00pm, SHE 651.
Instructor: Kosta Derpanis
Course Description
This course introduces the fundamental concepts of vision
with emphasis on computer science and engineering. In
particular, the course covers the image formation process, image
representation, feature extraction, stereopsis, motion analysis,
3D parameter estimation and applications. Prerequisites
This course requires programming experience as well as linear algebra, basic calculus, and basic probability. The following courses are prerequisites (or equivalent courses at other institutions): Linear Algebra (MTH 108)
 Calculus (MTH 310)
Textbook
 Richard Szeliski, Computer Vision: Algorithms and Applications (available for free or purchase)
Reference Textbooks
 Gilbert Strang, Linear Algebra and Its Applications (video lectures available)
 Berthold Horn, Robot Vision
 Emanuele Trucco and Alessandro Verri,
Introductory Techniques for 3D Computer Vision
Grading
The final grade for is based on the following components: Assignment 0 (MATLAB warmup): 5%
 Assignment 13: 30%
 Midterm: 30%
 (For CPS 843) Final: 30%
 (For CP 8307) Project: 30%
 Participation: 5%
Late Policy
You have three "late days" for this course. Specifically, the first 24 hours after the due date and time counts as 1 day, up to 48 hours is two and 72 for the third late day. After the three "late days" have been exhausted, an automatic zero will be assigned.Useful Links
 Matlab
install for Ryerson students
 Matlab tutorial
 Matlab primer
 Basic linear algebra review with MATLAB
 Linear algebra review
 Linear
algebra review and reference
Syllabus (tentative)
Class Date  Topic  Slides  Reading  Assignment 
Jan. 10th 
Introduction to computer vision  pdf mov 
Szeliski  Chapter 1 Eero Simoncelli, A Geometric Review of Linear Algebra 



Jan. 10th  Cameras and optics (part
1) 
pdf mov 
Szeliski  Chapter 2.1  
Jan. 17th 
Cameras and optics (part
2) 
pdf mov 
Szeliski  Chapter 2.1 
A0 released 
Jan. 24th  Image filtering
(smoothing) 
pdf mov 
Szeliski  Chapter 3.2
(up to and including 3.2.2) 
A0 due 
Jan. 31st  Image filtering (edge
detection) 
pdf mov 
Szeliski  Chapter 4.2 Pedro Felzenszwalb, Edge Detection 

Features and Fitting 

Feb. 7th 
Image features (corner
detection and SIFT) 
pdf mov 
Szeliski  Chapter 4.1  
Feb. 14th 
Midterm  A1 released  
Feb. 21st  NO CLASS (READING WEEK) 

Feb. 28th  Model fitting  pdf mov 
Szeliski  Chapters 4.3.2, 6.1.1, 6.1.2, 6.1.4  A1 due A2 released 
Frequency Analysis 

Mar. 7th  Frequency analysis (Part I)  pdf mov 
Szeliski  Chapter 3.4 Horn  Chapters 6, 7 (Blackboard: Course readings) 

Mar. 14th  Frequency analysis (Part II)  pdf mov 

A2 due 
Multiple Views 

Mar. 21st  Stereopsis  pdf mov 


Mar. 28th  Motion analysis  pdf mov 
Fleet and Weiss, Optical flow Estimation  
Apr. 4th  3D structure and motion 
pdf mov 