News

Course Info

Syllabus

Lectures

• Wednesday and Friday, 5:10 pm - 6:30 pm in SHA 133

Office hours

• Friday, 12:00 pm - 1:00 pm or by appointment
• in-person in in UA4032
• online at https://meet.google.com/qta-qyuk-aja
• Or by appointment

Lab times and locations are available here.

Canvas (requires login)

Labs and inclass exercises will be submitted through course canvas site.

Course notes

Check out these course notes here.

Description

This course introduces students to computer vision – the science and technology to make computers “see.” The goal of computer vision is to develop computational machinery to extract useful information from images and videos. The course will study various steps of the overall image analysis pipeline. Topics covered will include: image formation, image representation, segmentation, feature extraction, motion analysis, object detection, camera calibration, and 3D visual reconstruction. A secondary focus of this course will be computer vision applications, which rely heavily upon the fundamental theory and techniques covered in this course.

Grading

• Class participation and exercises 10%
• Lab participation and completion 15%
• Midterms 60%
• Project 15%

A student must get 50% in the midterm examinations to pass this course.

Important dates

• Midterm 1, Friday, February 7, in class.
• Study break during the week of February 17.
• Midterm 2, Friday, March 21, in class.
• Project selection by March 3
  You may loose up to 10% of the course project grade if project selection isn’t finalized by Mar 4. You may loose up to an additional 20% of the course project grade if the project selection isn’t finalized by Mar 11. If the project isn’t selected by Mar 11, you’ll be asked to provide a written explanation for the delay.
• Project topics presentations, March 7
• Project report due by April 6, 11:59 pm

Ontario Tech University’s academic calendar that lists important dates (and deadlines) is available at here.

Course calendar

Reading assignments are from the course textbook

Computer Vision: Algorithms and Applications, 2nd Edition by Richard Szelski.

The book is available to download in PDF format at https://szeliski.org/Book/download.php. Or you can purchase a hard copy from your favorite bookstore.

Week 1 and 2

Topics

• Introduction
• Image representation and image processing

Notes

• Image representations
• Image formation
• Jan 15 in-class notes
• Linear filtering
• Linear filtering Slides

Lab

• Setup
• Workbook (iPython notebook)

Assigned readings

• Chapter 1
• Sections 3.2–3.5,

Week 3 and 4

Topics

• Modeling fitting
• Optimization

Notes

• Least squares
• Robust least squares
• RANSAC

Lab

• Detecting traffic stop signs

Assigned readings

• Sections 4.1, 4.2, 8.1.4

Week 5 and 6

Miderm 1 on Feb 7

Topics

• Deep learning for computer vision

Notes

• Neural Networks History
• Linear Regression
• Logistic Regression
• Logistic Regression Python
• In class discussions
• Convolutional networks for object detection

Lab

• Image classification using MLPs

Assigned readings

• Sections 5.1.1, 5.2.3, 5.3, 5.4
• CNNs for object detection

Week 7

Topics

• Frequency analysis
• Edge detection

Notes

• Fourier analysis
• Discrete Fourier Transform Notes
• Canny edge detection

Lab

• ResNet

Assigned readings

• Sections 3.4, 7.2

Week 8 and 9

Topics

• Texture analysis
• Feature detection and matching
• Interest points (Keypoints)

Notes

• Texture analysis notebook
• Local features
• Interest points

Lab

• Object detection using YOLO

Assigned readings

• Sections 7.1, 7.4, 10.5, 6.2.1

Week 10

Midterm 2 (cumulative) on Mar 21

Topics

• Corner detection (continued from last week)

Week 11

Topics

• Image formation
• Camera calibration

Notes

• Image formation
• Camera calibration

Assigned readings

• Sections 11.1

Week 12

Topics

• Depth estimation

Notes

• Epipolar geometry

Assigned readings

• Sections 11.1, 11.3

Course project (Slides)

The course project is an independent exploration of a specific problem within the context of this course. The topic of the project will be decided in consultation with the instructor.

Project grade will depend on the ideas, how well you present them in the report, how well you position your work in the related literature, how thorough are your experiments and how thoughtful are your conclusions.

Teams of up to two students are allowed.

Final report and a three-minutes video

For your final project write-up you must use the VCLab course project template available at Overleaf. Project report is expected to be between 4 to 8 pages.

Additionally, you may submit a 3 minutes video for your project.

Resources

Textbook

We will use the following textbook for this course.

• Foundations of Computer Vision by Antonio Torralba, Phillip Isola, and William T. Freeman

Previously, we have used the following textbook for this course, and assigning reading assignments refer t this textbook. I plan to update the assigned readings as we move along.

• Computer Vision: Algorithms and Applications by Richard Szelski.

Students are encouraged to take their own notes during lectures.

Other readings and notes

You may find the following notes and books useful.

• Computer vision notes.
• Fundamentals of Computer Vison by Mubarak Shah
• Multi View Geometry in Computer Vision by Richard Hartley and Andrew Zisserman
• Computer Vision: Models, Learning, and Inference by Simon J.D. Prince.

Programming resources

We will primarily use Python + OpenCV in this course. I recommend that you install Anaconda Python Distribution, which comes prepackaged with all the necessary packages. The following Python packages/environment are highly relevant for this course:

• OpenCV;
• numpy;
• scipy;
• matplotlib; and
• jupyter notebook.

Check out the development with python for some ideas about how best to use Python for software development.