Computer Vision

Spring 2019 CS 543/ECE 549: Computer Vision

Quick links: schedule, lecture videos (choose Log In Via Institution), Piazza (announcements and discussion), Compass (assignment submission and grades)

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

TAs: Maghav Kumar (mkumar10), Medhini Narasimhan (medhini2), Xinke Deng (xdeng12), Shuai Tang (stang30), Zhe Xu (zhex2), Wilfredo Torres Calderon (trrscld2)
TA office hours: M W F 11AM-12PM, 2-3PM, by the whiteboard outside 3407 Siebel

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

Overview

In the simplest terms, computer vision is the discipline of "teaching machines how to see." This field dates back more than fifty years, but the recent explosive growth of digital imaging and machine learning technologies 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 provide a coherent perspective on the different aspects of computer vision, and give students the ability to understand state-of-the-art vision literature and implement components that are fundamental to many modern vision systems.

Prerequisites: Basic knowledge of probability, linear algebra, and calculus. Python (preferred) or MATLAB programming experience and previous exposure to image processing are highly desirable.

Recommended textbooks:

Computer Vision: A Modern Approach by David Forsyth and Jean Ponce (2nd ed.)
Computer Vision: Algorithms and Applications by Richard Szeliski (PDF available online)

Grading scheme:

Programming assignments: 50%
- Five MPs, done individually, in Python
Final project: 30%
- Groups of two to four; deliverables include proposal, intermediate progress report, final report. Selected groups may do a brief presentation for extra credit
Unit quizzes: 20%
- Four multiple-choice online quizzes on the four units from the syllabus below
Participation: up to 3% extra credit
- Students can get extra credit for actively participating in class (preferred), on Piazza, or during office hours

Be sure to read the course policies!

Syllabus

I. Image formation and low-level vision

Camera models
Light and color
Linear filters and edges
Feature extraction
Optical flow and feature tracking

II. Grouping and fitting

Least squares fitting, robust fitting
RANSAC
Alignment, image stitching

III. Geometric vision

Camera calibration
Epipolar geometry
Two-view and multi-view stereo
Structure from motion

IV. Recognition and beyond

Statistical learning framework
Image classification
Deep convolutional neural networks
Object detection
Segmentation

Schedule (tentative)

Date	Topic	Readings (F&P 2nd ed.), assignments
January 15	Introduction: PPTX, PDF	Homework: Assignment 0
January 17	Perspective projection: PPTX, PDF	Reading: F&P ch. 1
January 22	Cameras: PPTX, PDF
January 24	Light and shading: PPTX, PDF	Reading: F&P ch. 2 Assignment 0 due January 25, 11:59:59PM
January 29	Color: PPTX, PDF	Reading: F&P ch. 3 Homework: Assignment 1
January 31	Linear filtering: PPTX, PDF	Reading: F&P ch. 4
February 5	Edge detection: PPTX, PDF	Reading: F&P sec. 5.1-5.2
February 7	Corner detection: PPTX, PDF	Reading: F&P sec. 5.3
February 12	SIFT keypoints: PPTX, PDF	Reading: Distinctive image features from scale-invariant keypoints Assignment 1 due February 11, 11:59:59PM
February 14	Optical flow: PPTX, PDF	Reading: F&P sec. 11.1 Homework: Assignment 2, project proposal
February 19	Fitting: PPTX, PDF No class -- watch video on Echo360	Reading: F&P sec. 10.2-10.4, 22.1
February 21	Hough transform: PPTX, PDF No class -- watch video on Echo360
February 26	Alignment: PPTX, PDF	Reading: F&P sec. 12.1
February 28	Alignment cont.
March 5	Camera calibration: PPTX, PDF	Reading: F&P ch. 1 Assignment 2 due March 4, 11:59:59PM
March 7	Single-view modeling: PPTX, PDF	Reading: Ch. 2 from Hoiem and Savarese book Project proposals due March 11, 11:59:59PM
March 12	Epipolar geometry: PPTX, PDF	Reading: F&P sec. 7.1 Homework: Assignment 3
March 14	Structure from motion: PPTX, PDF	Reading: F&P ch. 8
March 26	Two-view stereo: PPTX, PDF	Reading: F&P ch. 7
March 28	Multi-view stereo: PPTX, PDF
April 2	Intro to recognition: PPTX, PDF
April 4	Neural networks: PPTX, PDF
April 9	Deep convolutional networks: PPTX, PDF	Assignment 3 due April 8, 11:59:59PM
April 11	Deep convolutional networks cont.	Homework: Assignment 4
April 16	Detection: PPTX, PDF	Project progress reports due April 15, 11:59:59PM
April 18	Detection cont.
April 23	Segmentation: PPTX, PDF
April 25	CNNs for segmentation and beyond: PPTX, PDF
April 30	Selected project presentations	Assignment 4 due May 1, 11:59:59PM Final project reports due May 6

Spring 2019 CS 543/ECE 549: Computer Vision

Overview

Syllabus

Schedule (tentative)

Resources