CS543/ECE549: Computer Vision

Spring 2013, T TH 11:00-12:15 Siebel 1404 (moved as of 2/04!)

Instructor: Svetlana Lazebnik  (slazebni -at- illinois.edu)
Office hours (3308 Siebel): Tuesdays 1-2PM, Thursdays 4-5PM, and by appointment

TA: Tom Paine (paine1 -at- illinois.edu)
Office hours (207 Siebel): Mondays 5-6PM, Wednesdays 10-11AM, and by appointment

Lecture videos: https://wiki.engr.illinois.edu/display/ENGRonline/CS543

Discussion boards, assignment submission, and grades: https://compass2g.illinois.edu

Quick links: syllabus, announcements (updated 4/22), schedule, useful resources


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. 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 II. Grouping and fitting III. Geometric vision IV. Recognition V. "Miscellaneous"


Schedule (tentative)

Date Topic Readings (F&P 2nd ed.), assignments
January 15 What is computer vision? PPT, PDF Resource: MATLAB tutorial
January 17 Perspective projection: PPT, PDF Reading: F&P ch. 1
January 22 Cameras: PPT, PDF Homework: Assignment 1
January 24 Light and shading: PPT, PDF Reading: F&P ch. 2
January 29 Shading cont.  
January 31 Color: PPT, PDF Reading: F&P ch. 3
February 5 Linear filtering: PPT, PDF
Edge detection: PPT, PDF
Reading: F&P ch. 4, sec. 5.1, 5.2
February 7 Edge detection cont.
Assignment 1 due February 7, 11:59:59PM
February 12 Corner detection: PPT, PDF Reading: F&P sec. 5.3
Resource: Harris corner detector code
February 14 Blob detection: PPT, PDF Reading: F&P ch. 5
Homework: Assignment 2, project proposal
February 19 Least squares fitting, RANSAC: PPT, PDF Reading: F&P ch. 10, 22.1
February 21 Hough transform: PPT, PDF Reading: F&P sec. 10.1
February 26 Alignment: PPT, PDF Reading: F&P sec. 12.1
Distinctive image features from scale-invariant keypoints
February 28 Camera calibration: PPT, PDF Reading: F&P ch. 1
Assignment 2 due March 4, 11:59:59PM
March 5 Single-view metrology: PPT, PDF Reading: Ch. 2 from Hoiem and Savarese book
Homework: Assignment 3
March 7 Epipolar geometry: PPT, PDF Reading: F&P sec. 7.1
Project proposals due March 7, 11:59:59PM
March 12 Binocular stereo: PPT, PDF Reading: F&P ch. 7
Homework: Project progress report
March 14 Multi-view stereo: PPT, PDF  
March 26 Structure from motion: PPT, PDF Reading: F&P ch. 8
March 28 Intro to recognition: PPT, PDF Assignment 3 due April 1, 11:59:59PM
April 2 Recognition and machine learning: PPT, PDF Reading: Grauman and Leibe synthesis lecture
Homework: Assignment 4
April 4 Bags of features: PPT, PDF Reading: F&P ch. 16
April 9 Bags of features, SVMs: PPT, PDF Reading: F&P ch. 15
April 11 Face detection: PPT, PDF Reading: Robust Real-Time Face Detection
Reading: F&P ch. 17
Project progress reports are due April 11, 11:59:59PM
April 16 Deformable part-based models: PPT, PDF Reading (optional): Object detection with discriminatively trained part based models
April 18 Deformable part-based models cont. Reading (optional): Real-Time Human Pose Recognition in Parts from Single Depth Images (link includes slides)
Assignment 4 due April 18, 11:59:59PM
April 23 Segmentation: PPT, PDF Reading: F&P ch. 9
April 25 Optical flow: PPT, PDF Reading: F&P sec. 11.1.2
April 30 Project presentations  
May 7 Project presentations, 7-10PM, 2405 SC Final project reports due May 6, 11:59:59PM

Useful Resources

Tutorials, review materials

MATLAB reference

The real world