CMSC 491/691: Computer Vision

Instructor: Tejas Gokhale (OH: Wednesday 2 PM - 3:30 PM or by appointment; ITE 214);
Teaching Assistant: Sourajit Saha (OH: Monday 1:30 -- 3:30 PM & Tuesday 2:30 -- 4:30 PM; ITE 344);
Time: Monday and Wednesday 4:00pm - 5:15pm
Location: ENGR 231

Course description

This course will offer a comprehensive introduction to the field of computer vision which has the broad goal of understanding visual signals (images and videos) for low/mid/high-level perceptual tasks. This course will introduce fundamental principles and concepts for developing computer vision systems such as image formation, acquisition, and processing, stereo and 3D vision, machine learning algorithms and neural networks for image understanding.

Prerequisites: We will assume that you have a basic (but solid) expertise in linear algebra, geometry, probability, and Python programming. Recommended classes at UMBC are: MATH 221 (Linear Algebra), STAT 355 or CMPE 320 (Probability and Statistics), MATH 151 (Calculus and Analytical Geometry). If you are unfamiliar with linear algebra or calculus, you should consider taking both: without these tools, you are likely to struggle with the course. Although we will provide brief math refreshers of these necessary topics, CMSC 491/691 should not be your first introduction to these topics. Homework 0 (an ungraded homework available on demand, that will NOT contribute to your grade) is meant to be a reflection of these prerequisites. If you struggle with HW0, please get in touch with the instructor as soon as possible to discuss remedial options before the drop deadline.
We understand that some students may have had some prior exposure to signal/image/audio processing, computer graphics, machine learning, etc. However, none of these are pre-requisites -- the class is designed to be self-contained.

Reference Books There are no required textbooks. The following books may be useful to accompany the lectures:

Computer Vision: Algorithms and Applications by Szeliski. Available for free online.
Deep Learning by Goodfellow, Bengio, and Courville. Available for free online. See Part I for brushing up on pre-requisities mentioned above.

Schedule

Schedule is tentative and subject to change.

Class notes submitted by students are here .

	Topic	Resources	Announcements
1	Introduction	[slides]
2	Image Formation and Acquisition	[slides] Szeliski Ch 2
3	Image Filtering I	[slides] Szeliski Ch 3
4	Image Filtering II	[slides] Szeliski Ch 3	HW 1 released. Due 02/23
5	Image Features I	[slides] Szeliski Ch 3
6	Image Features II	[slides] Torralba Ch 3; SIFT paper
7	Machine Learning for Computer Vision I	[slides] Szeliski Ch 5, Goodfellow Ch 5	HW2 released. Due 03/15
8	ML-for-CV II (Neural Networks)	[slides] Goodfellow Ch 6.1-6.4, Shree Nayar FPCV Playlist
9	ML-for-CV III (Gradient Descent)	[slides] Goodfellow Ch 6.5, Roger Grosse: Optimization Notes
10	Visual Recognition	[slides] Szeliski Ch 6, Forsyth Ch 18
11	Image Transformations	[slides] Szeliski 3.6
12	Homographies	[slides] Hartley&Zisserman Part 0 (Ch 2, 3, 4), SVD Tutorial
13	Camera Models	[slides] Hartley&Zisserman Part 1 (Ch 6, 7, 8)	Midterm on 04/01 in Class
14	Triangulation & Epipolar Geometry	[slides]
15	Stereo Vision	[slides]
16	Vision-and-Language	[slides]
17	Image Synthesis	[slides]

Homework

All material for homework assignments (handouts, code, data, etc.) will be available to download from Blackboard.

Grading

Homework Assignments: 40%
Midterm Exam: 15%
Scribing: 5%
Project: 40%

Work hard, be attentive in class and participate in discussions, enjoy the homeworks, be creative in your projects, and seek help when needed!

Projects

The class has a mix of PhD, MS, and BS students. Projects will be judged on the basis of relative growth (from where you start to where you end).

BS or MS (coursework) students: Pick one of the seed ideas or propose your own idea. I recommend working in groups of 4 students.
PhD or MS (thesis) students: Consult with Tejas during Office Hours and discuss your existing research agenda. We will integrate the course project into that agenda if possible. Group sizes (or individual projects) will be decided on a case-by-case basis.

Proposal: Clearly state the following:
- Problem you wish to tackle (and why)
- Proposed approach and methods
- Timeline
- What each student in the group will do.
- Expected Outcome and Worst-Case Outcome

Scribing

Please use this template for scribing. For a quick tutorial on LaTeX, visit: this Overleaf Tutorial. Signup sheet for scribing: here.
To submit, email your notes as PDF, with subject: "[Scribing Submission] lecture-date" to gokhale@umbc.edu AND the TAssaha2@umbc.edu.

Late Submissions

Each student will get 7 late days. Each late day extends the deadline by 24 hours and does not influence the grade. The late days can be used for homeworks and scribing only. Late submissions turned in after all 7 late days have been exhausted will not be evaluated and will receive 0 points. Start working on your assignments early.

Academic Integrity

Please read UMBC's policy on Academic Integrity. I take academic integrity seriously. I hope that we will never have to deal with violations -- they are never pleasant for anyone involved. Please read the policies stated in the Syllabus .