COMP 776: Computer Vision

Spring 2011, T TH 3:30-4:45 SN 115

Instructor: Svetlana Lazebnik  (lazebnik -at- cs.unc.edu)

Quick links: syllabus, schedule, useful resources

Overview

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.

Textbook: Computer Vision: A Modern Approach by David Forsyth and Jean Ponce is the recommended textbook for the course, though the instruction will follow this book very loosely. Another recommended book is Richard Szeliski's Computer Vision: Algorithms and Applications (draft available online).

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 three or four minor programming assignments and a larger final assignment which will most likely consist of a recognition competition (details to follow). Class participation will be another important component of the grade. This involves coming to class regularly, asking questions, and answering review questions. Without satisfactory participation, it will be impossible to get an "H" in the class. The weights assigned to different course components will be as follows:

Syllabus

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

Schedule (tentative)

Date Topic Readings, assignments
January 11 What is computer vision? PPT, PDF Resource: MATLAB tutorial
January 13 Cameras: PPT, PDF Reading: F&P ch. 1
January 18 Cameras cont. Homework: Assignment 1 out
January 20 Light and shading: PPT, PDF Reading: F&P ch. 4, 5
January 25 Color: PPT, PDF Reading: F&P ch. 6
January 27 Linear filtering: PPT, PDF Reading: F&P ch. 7
February 1 Edge detection: PPT, PDF Reading: F&P ch. 8
Assignment 1 due at 11:59 PM
February 3 Corner detection: PPT, PDF Resource: Harris corner detector code
February 8 Blob detection: PPT, PDF Homework: Assignment 2 out
February 10 Fitting: PPT, PDF Reading: F&P sec. 3.1
February 15 RANSAC (see previous lecture);
Hough transform: PPT, PDF
Reading: F&P ch. 15
February 17 Alignment: PPT, PDF  
February 22 Robust and large-scale alignment: PPT, PDF
Reading: Distinctive image features from scale-invariant keypoints Assignment 2 due at 11:59 PM
February 24 Single-view geometry: PPT, PDF Reading: F&P ch. 2, 3
Homework: Assignment 3 out
March 1 Epipolar geometry: PPT, PDF Reading: F&P sec. 10.1
March 3 Binocular stereo: PPT, PDF Reading: F&P ch. 11
March 15 Stereo cont.  
March 17 Multi-view stereo: PPT, PDF Assignment 3 due at 11:59 PM
March 22 Structure from motion: PPT, PDF Reading: F&P sec. 12.3, 12.4, 13.3.1, 13.4, 13.5
Homework: Assignment 4 out
March 24 Intro to recognition: PPT, PDF Resource: ICCV 2009 Short Course on Object Recognition, AAAI 2008 Tutorial
March 29 Recognition and machine learning: PPT, PDF  
March 31 Bags of features: PPT, PDF  
April 5 Bags of features, classifiers: PPT, PDF Reading: F&P sec. 22.1, 22.2, 22.5
Assignment 4 due at 11:59 PM
April 7 Part-based models: PPT, PDF Homework: Assignment 5 out
April 12 Face detection: PPT, PDF Reading: Robust Real-Time Face Detection
Reading: F&P sec. 22.3
April 14 Discriminative part-based models: PPT, PDF Reading (optional): Object detection with discriminatively trained part based models
April 19 Segmentation: PPT, PDF Reading: F&P ch. 14
April 21 Optical flow: PPT, PDF Assignment 5 due on Saturday, April 23, 11:59 PM
Contest entry due on Monday, April 25, 11:59PM
April 26 Recognition contest discussion
Tracking: PPT, PDF
 

Useful Resources

Tutorials, review materials

General reference

MATLAB reference

The real world