Fall 2022 CS 543/ECE 549: Computer Vision
Quick links:
schedule,
Campuswire (announcements and discussion),
Canvas (assignment submission and grades),
Mediaspace (lecture recordings)
Instructor: Svetlana Lazebnik (slazebni -at- illinois.edu)
Lectures: M W 11:00-12:15 1404 Siebel
TAs: Daniel McKee (dbmckee2), Zitong Zhan (zitongz3), Nan Liu (nanliu4), Nikash Walia (nikashw2), Hang Zhang (hangz2)
Instructor and TA office hours: see Campuswire
Contacting the course staff: For emergencies and special circumstances, please email the instructor. For questions about lectures and assignments, use Campuswire. For questions about your scores (including regrade requests), email the responsible TAs.
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 programming
experience and previous exposure to image processing are highly desirable.
Recommended textbooks:
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
- 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, on Piazza, or during office hours
Be sure to read the course policies!
Syllabus
I. Image processing and low-level vision
- Image sampling, interpolation, transformations
- 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. Image formation and geometric vision
- Camera models
- Light, shading and color
- Camera calibration
- Epipolar geometry
- Two-view and multi-view stereo
- Structure from motion
IV. Recognition and beyond
- Statistical learning framework
- Image classification
- Deep learning
- Object detection
- Segmentation
- Advanced topics (depending on time, student interest, and instructor choice): image generation and manipulation, deep learning for 3D vision, vision and language, video
Schedule (tentative)
Date
| Topic
| Readings (F&P 2nd ed.), assignments
|
August 22
| Introduction: PPTX, PDF
| Self-study: See resources for Python and linear algebra tutorials, feel free to try U Mich EECS442 Mastery Assignment as a warmup
|
August 24
| Image processing: PPTX, PDF
|
|
August 29
| Image processing cont. (slides above)
| Homework: Assignment 1
|
August 31
| No lecture
|
|
September 7
| Image filtering: PPTX, PDF
| Reading: F&P ch. 4
|
September 12
| Fourier analysis: PPTX, PDF
| Reading: Szeliski 3.4
Assignment 1 due
|
September 14
| Edge detection: PPTX, PDF
| Reading: F&P sec. 5.1-5.2
|
September 19
| Corner detection: PPTX, PDF
| Reading: F&P sec. 5.3
|
September 21
| SIFT keypoint detection: PPTX, PDF
| Reading: Distinctive image features from scale-invariant keypoints
Homework: Assignment 2
|
September 26
| Optical flow: PPTX, PDF
| Reading: F&P sec. 11.1
|
September 28
| Fitting: PPTX, PDF
| Reading: F&P sec. 10.2-10.4, 22.1
|
October 3
| Alignment: PPTX, PDF
| Reading: F&P sec. 12.1
|
October 5
| Alignment cont.
| Assignment 2 due October 6
|
October 10
| Cameras: PPTX, PDF
| Reading: F&P ch. 1
Project proposals due
|
October 12
| Light and shading: PPTX, PDF
| Reading: F&P ch. 2
Homework: Assignment 3
|
October 17
| Color: PPTX, PDF
| Reading: F&P ch. 3
|
October 19
| Perspective projection: PPTX, PDF
| Reading: F&P ch. 1
|
October 24
| Camera calibration: PPTX, PDF
| Reading: F&P ch. 1
|
October 26
| Single-view modeling: PPTX, PDF
|
|
October 31
| Epipolar geometry: PPTX, PDF
| Reading: F&P sec. 7.1, H&Z ch. 9
Assignment 3 due
|
November 2
| Structure from motion: PPTX, PDF
| Reading: F&P ch. 8
Homework: Assignment 4
|
November 7
| Two-view stereo: PPTX, PDF
| Reading: F&P ch. 7
|
November 9
| Two-view stereo cont.
| Project progress reports due November 11
|
November 14
| Multi-view stereo: PPTX, PDF
| Assignment 4 due November 15
|
November 16
| Light field modeling: PPTX, PDF
| Homework: Assignment 5
|
November 28
| Recognition: PPTX, PDF
|
|
November 30
| Recognition cont.
|
|
December 5
| Project presentations
| Assignment 5 due December 6
|
December 7
| Project presentations
| Final project reports due December 12
|
Resources
|