CS543/ECE549: Computer Vision

Quick links: announcements (last updated 4/27), schedule, lecture videos, Piazza (discussion board), Compass (assignment submission and grades)

Instructor: Svetlana Lazebnik  (slazebni -at- illinois.edu)
Lectures: T TH 11:00-12:15, 1310 DCL
Instructor office hours (starting 1/26): T TH 2-3PM, 3308 Siebel

TAs: Liwei Wang (lwang97 -at- illinois.edu), Zhicheng Yan (zyan3 -at- illinois.edu)
TA office hours (starting 1/27): W 4-5PM (207 Siebel), F 4-5PM (3238A Siebel)

Always check announcements for short-notice changes to instructor and TA office hours!


In the simplest terms, computer vision is the discipline of "teaching machines how to see." This field dates back more than forty years, but the recent explosive growth of digital imaging technology makes the problems of automated image interpretation more exciting and relevant than ever. There are two major themes in the computer vision literature: 3D geometry and recognition. The first theme is about using vision as a source of metric 3D information: given one or more images of a scene taken by a camera with known or unknown parameters, how can we go from 2D to 3D, and how much can we tell about the 3D structure of the environment pictured in those images? The second theme, by contrast, is all about vision as a source of semantic information: can we recognize the objects, people, or activities pictured in the images, and understand the structure and relationships of different scene components just as a human would? This course will strive to provide a unified perspective on the different aspects of computer vision, and give students the ability to understand vision literature and implement components that are fundamental to many modern vision systems.

Prerequisites: Basic knowledge of probability, linear algebra, and calculus. MATLAB programming experience and previous exposure to image processing are desirable, but not required.

Recommended textbooks: Grading: Computer vision is a very hands-on subject. For this reason, the coursework will primarily consist of implementation (please make sure you have access to MATLAB with the Image Processing Toolbox installed). There will be four or five programming assignments and a final project (details TBA). For on-campus students, class participation will be another important component of the grade. This involves coming to class regularly, asking and answering questions, and participating on the class discussion board. The weights assigned to different course components will be as follows: Academic integrity policy: You are encouraged to discuss assignments with each other, but coding and writing of reports must be done individually unless specifically instructed otherwise. You are also encouraged to search the Web for tips or code snippets, provided this does not make the assignment trivial and all external sources are explicitly acknowledged in the report. At the first instance of cheating (copying from other students or unacknowledged sources on the Web), a grade of zero will be given for the respective assignment or test. At the second instance, you will automatically receive an F for the entire course.


I. Image formation and low-level vision II. Grouping and fitting III. Geometric vision IV. Recognition and beyond


Schedule (tentative)

Date Topic Readings (F&P 2nd ed.), assignments
January 19 Introduction: PPT, PDF Resource: MATLAB tutorial
January 21 Perspective projection: PPT, PDF
(Guest lecture given by David Forsyth)
Reading: F&P ch. 1
January 26 Cameras: PPT, PDF  
January 28 Light and shading: PPT, PDF Homework: Assignment 1 is out
Reading: F&P ch. 2
February 2 Color: PPT, PDF Reading: F&P ch. 3
February 4 Linear filtering: PPT, PDF Reading: F&P ch. 4
February 9 Edge detection: PPT, PDF Reading: F&P sec. 5.1-5.2
February 11 Corner detection: PPT, PDF Reading: F&P sec. 5.3, Distinctive image features from scale-invariant keypoints
Resource: Harris corner detector code
February 16 SIFT keypoints: PPT, PDF Assignment 1 due February 15, 11:59:59PM
February 18 Optical flow: PPT, PDF Reading: F&P sec. 11.1
Homework: Assignment 2, project proposal
February 23 Fitting: PPT, PDF Reading: F&P sec. 10.2-10.4, 22.1
February 25 Hough transform: PPT, PDF Reading: F&P sec. 10.1
March 1 Alignment: PPT, PDF Reading: F&P sec. 12.1
March 3 Alignment cont. Assignment 2 due March 7, 11:59:59PM
March 8 Camera calibration: PPT, PDF Reading: F&P ch. 1
March 10 Single-view modeling: PPT, PDF Reading: Ch. 2 from Hoiem and Savarese book
March 15 Epipolar geometry: PPT, PDF Reading: F&P sec. 7.1
Project proposals due March 14, 11:59:59PM
Homework: Assignment 3 is out
March 17 Binocular stereo: PPT, PDF Reading: F&P ch. 7
March 29 Multi-view stereo: PPT, PDF  
March 31 Structure from motion: PPT, PDF Reading: F&P ch. 8
April 5 Intro to recognition: PPT, PDF Assignment 3 due April 4, 11:59:59PM
April 7 Classifiers (see slides above) Project progress reports due April 11, 11:59:59PM
April 12 Deep learning: PPT, PDF Homework: Optional extra credit assignment
April 14 Deep learning cont. Homework: Assignment 4 is out (PPT walkthrough)
April 19 Detection: Viola-Jones: PPT, PDF Reading: Robust Real-Time Face Detection, F&P ch. 17
April 21 Detection: Deformable part models: PPT, PDF  
April 26 Detection: Deep models: PPT, PDF Extra credit assignment due April 27, 11:59:59PM
April 28 Segmentation: PPT, PDF  
May 3 Project presentations Assignment 4 due May 4, 11:59:59PM
May 9 Project presentations, 8-11AM, 1310 DCL Final project reports due May 11, 11:59:59PM

Useful Resources

Tutorials, review materials

MATLAB reference