Leonid Sigal

Professor, University of British Columbia



Course Information


Computer vision, broadly speaking, is a research field aimed to enable computers to process and interpret visual data (namely in the form of images and video), as sighted humans can. It is one of the most exciting areas of research in computing science and among the fastest growing technologies in today's industry. This course provides an introduction to the fundamental principles and applications of computer vision, including image formation, sampling and filteering, colour analysis, single and multi-image geometry, feature detection and matching, stereo imaging, motion estimation, segmentation, image classification and object detection. We'll study basic methods and application of these concepts to a variety of visual task.


Instructor:
Leonid Sigal (lsigal@cs.ubc.ca)
      Office hours: Friday 1-2pm (ICCS 119)

TAs:
Bicheng Xu (bichengx@cs.ubc.ca)
      Office hours: Monday 7-8pm (virtual, Zoom link on Piazza)

Rayat Hossain (rayat137@cs.ubc.ca)
      Office hours: Tuesday noon-1pm (ICCS X239)

Shih-Han Chou (shchou75@cs.ubc.ca)
      Office hours: Wednsday 7-8pm (virtual, Zoom link on Piazza)

Jiayun Luo (letitial@student.ubc.ca)
      Office hours: Thursday 1-2pm (ICCS X141)

Wan-Cyuan (Chris) Fan (wancyuan@cs.ubc.ca)
      Office hours: Friday 4-5pm (ICCS X239)


Class meets:
Monday and Wednsday 3:30 - 5:00 pm, MacMillan Building (MCML), Room 166

                  

Piazza
piazza.com/ubc.ca/winterterm12024/cpsc_v4251011022024w1
piazza.com/ubc.ca/winterterm12024/cpsc_v4251011022024w1/home (class link)

Prerequisites: MATH 200, MATH 221 and either (a) CPSC 221 or (b) CPSC 260, EECE 320.


Textbook

Recemended (but not required):

Computer Vision: A Modern Approach (2nd edition) Computer Vision: Algorithms and Applications
Computer Vision: A Modern Approach (2nd edition), by D.A. Forsyth and J. Ponce, Pearson, 2012. (buy) Computer Vision: Algorithms and Applications (2nd Edition), by R. Szeliski, Springer, 2022. (download)

Note that while reading is not required, it will generally lead to broader understanding of the topics covered in class. I would suggest reading relevant chapters once they are covered in the lecture.


Grading


Quizzes10%
Assignments45%
Midterm exam15%
Final exam30%

Grade Disputes, Re-grading and Grade-related Policies: Despite best efforts, sometimes miss-grading does happen. All grade disputes and re-grading must be brought to instructor's or TA's attention within 1 week of the grade being released. All such requests must be done through a Piazza as a direct post to the instructors. You must clearly identify the issues and describe why you believe re-grading is warranted. Similarly, if you have a ligitimate excuse for missing a quiz, please let instructor know and provide appropitate evidance within 1 week of the original quiz date. Note that quiz missed for ligitimate and documented reason (e.g., attandance of conferences, sickness, travel for job interview) will be dropped. You will be asked to provide supporting documentation (note from a doctor, travel and conference registration, etc.). There will be no make-ups for missed Midterms.


Assignments (45% of the grade)

All assignments are to be done individually. There are 6 graded (and 1 ungraded) asssignment each worth the same amount. The ungraded assignment is Assignment 0. Assignment 1 to 6 are graded.

Late Policy: Every student is allotted three ``late days'', which allow assignments to be handed in late without penalty on three days or parts of days during the term. The purpose of late days is to allow students the flexibility to manage unexpected obstacles to coursework that arise during the course of the term, such as travel, moderate illness, conflicts with other courses, extracurricular obligations, job interviews, etc. Thus, additional late days will NOT be granted except under truly exceptional circumstances. If an assignment is submitted late and a student has used up all of her/his late days, 25% will be deducted for every day the assignment is late. (e.g., an assignment 2 days late and graded out of 100 points will be awarded a maximum of 50 points.) How late does something have to be to use up a late day? A day is defined as a 24-hour block of time beginning at 10 minutes past 11:59pm on the day an assignment is due. To use a late day, write the number of late days claimed on the first page of your assignment. Examples: Handing in an assignment at 1am the night assignment is due will use up 1 late day. Handing in an assignment at 10:15am the morning after it is due similarly consumes one late day. Handing in an assignment at 10:15am on the following day consumes two late days.

Expectations: To get top marks, programs must not only work correctly, but also must be clearly documented and easily understood. Marks may be deducted for lack of comments. Note that default comments provided in starter files are not considered sufficient for full credit. You will be deducted points if either the PDF writeup or your code are missing. The material you hand in, including figures, must be legible.

Assignment Available Due
Assignment 0: Introduction to Python for Computer Vision (link) Sep 3 optionally Sep 11
Assignment 1: Image Filtering and Hybrid Images (link) Sep 11 Sep 26
Assignment 2: Scaled Representations, Face Detection and Image Blending (link) Sep 26 Oct 16
Assignment 3: Texture Synthesis (link) Oct 16 Oct 24
Assignment 4: RANSAC and Panorama Stiching (link) Oct 24 Nov 8
Assignment 5: Stereo and Optical Flow (link) Nov 8 Nov 25
Assignment 6: Deep Learning (link) Nov 25 Dec 5
(please note that these dates are given as guidelines and are subject to change)

Schedule


Date Topic Reading
W1: Sep 4 Introduction: Intro to computer vision, Course logistics (slides) None
W2: Sep 9 Image Formation: Pinhole, Perspective, Weak perspective and Orthographic projection, Lenses (slides) Forsyth & Ponce, 1.1.1 -- 1.1.3, 2.1
W2: Sep 11 Image Formation: Lenses, Human Eye (slides)
Image Filtering: Image as a function, Image transformations, Linear filters, Correlation and Convolution (slides)
(optional) Assignment 0: Introduction to Python for Computer Vision
Forsyth & Ponce, 1.1.4, 1.2.1, 4.1
Lecture Notes: Image Formation
W3: Sep 16 Image Filtering: Gaussian filter, Separability, Pillbox filter, Speeding up Convolution, Fourier representation (slides) Forsyth & Ponce, 4.2, 4.3
W3: Sep 18 Image Filtering: Speeding up Convolution, Low-/High-Pass, Non-linear Filters, Bilateral Filter (slides)
Lecture Notes: Image Filtering
W4: Sep 23 Sampling: Sampling Theory, Bandlimited Signal, Nyquist Rate, Aliasing, Color Filter Arrays, Demosicing (slides) Forsyth & Ponce, 4.4
Lecture Notes: FFT, Sampling, Cameras
W4: Sep 25 Scaled Representations: Template Matching, Image Pyramids, Gaussian Pyramid, Laplacian Pyramid (slides) Forsyth & Ponce, 4.5, 4.6, 4.7
W4: Sep 26 Assignment 1: Image Filtering and Hybrid Images
W5: Sep 30 Holiday (no class)
W5: Oct 2 Scaled Representations (cont): Laplacian Pyramids, Image Blending, Improving Template Matching (slides) Forsyth & Ponce, 5.1 - 5.2
W6: Oct 7 Local Image Features: Image Gradients, Sobel, Marr / Hildreth Edge Detection, Canny Edge Detection, Image Boundaries (slides) Forsyth & Ponce, 5.1 - 5.2
W6: Oct 9 Local Image Features: Autocorrelation, Harris, Blob Detection, Characteristic Scale (slides) Forsyth & Ponce, 5.3.0 -- 5.3.1
Lecture Notes: Derivatives, Edge Detection, Corner and Blob Detection
W7: Oct 14 Holiday (no class)
W7: Oct 16 Local Image Features: Blob Detection, Characteristic Scale (slides)
Texture: Introduction, Synthesis (slides)
Assignment 2: Scaled Representations, Face Detection and Image Blending
Forsyth & Ponce, 6.1, 6.3, 3.1--3.3
W8: Oct 21 Midterm
W8: Oct 23 Features Matching : SIFT, HoG, SURF (slides) Forsyth & Ponce, 3.1--3.3, 5.4 and SIFT
Lecture Notes: SIFT
W8: Oct 24 Assignment 3: Texture Synthesis
W9: Oct 28 Model Fitting: Image Alignment, RANSAC, Object Detection (slides) Forsyth & Ponce, 5.4, 10.4.2, 10.1, 10.2
W9: Oct 30 Model Fitting: Hough Transform (slides) Forsyth & Ponce, 5.4, 10.4.2, 10.1, 10.2
W10: Non 4 Stereo: Rectification, Block Matching, Ordering Constraints, More Cameras (slides) Forsyth & Ponce, 10.6, 6.2.2, 9.3.1, 9.3.3, 9.4.2
W10: Nov 6 Optical Flow: Introduction, Aperture Problem, Lucas-Kanade, Horn-Schunck (slides)
W10: Nov 7 Assignment 4: RANSAC and Panorama Stiching
W11: Nov 11 Midterm Break (no class)
W11: Nov 13 Midterm Break (no class)
W12: Nov 18 Classification: Bayes' Rule, Bayes' Risk, Loss Functions, kNN, Support Vector Machines, Bag of Words Representations (slides)
W12: Nov 20 Classification: Review, Case study on CIFAR 10, Decision Trees, Boosting (slides)
W13: Nov 25 TBD: TBD (slides)
Assignment 5: Scene Recognition with Bag of Words
W13: Nov 27 TBD: TBD (slides)
W14: Dec 2 TBD: TBD (slides)
W14: Dec 4 TBD: TBD (slides)
W14: Dec 5 Assignment 6: Deep Learning
TBD Final Exam

Academic Conduct and Integrity

The academic enterprise is founded on honesty, civility, and integrity. As members of this enterprise, all students are expected to know, understand, and follow the university policies and codes of conduct regarding academic integrity. At the most basic level, this means submitting only original work done by you and acknowledging all sources of information or ideas, and attributing them to others as required. This also means you should not cheat, copy, or mislead others about what is your work; nor should you help others to do the same. For example, it is prohibited to: share your past assignments and answers with other students; work with other students on an assignment when an instructor has not expressly given permission; or spread information through word of mouth, social media, or other channels that subverts the fair evaluation of a class exercise, or assessment. Violations of academic integrity (i.e., misconduct) lead to the breakdown of the academic enterprise, and therefore serious consequences arise and harsh sanctions are imposed. For example, incidences of plagiarism or cheating may result in a mark of zero on the assignment or exam and more serious consequences may apply if the matter is referred to the President's Advisory Committee on Student Discipline. Careful records are kept in order to monitor and prevent recurrences. For further information please consult:

- Computer Science Department Policies on Academic Integrity
- UBC policy on Academic Misconduct
- Computer Science Department Policies on Equality, Inclusion and Wellness
- Computer Science Department Policies and Responsibilities.