CS 554: Computer Vision

Spring 2022

Instructor: Hamdi Dibeklioglu

Office hours: by appointment / online

Class hours:

Wednesday 8:50-10:20 (block); Friday 13:30-15:20.
While every other week we will have 2+2 hours of lectures, other weeks there will be one 2-hours lecture. Please see the schedule below for the dates of the lectures.

Class room:

Online (EA-502)

UPDATES / NEWS:

All important dates (including homework, project/project progress, and survey submission/presentation deadlines, and midterm date) have been announced.
Homework details have been announced (04.03.2022), please see the homework section below.
Lectures start as of 04 February 2022.

Catalog Description: Basic concepts in computational vision. Relation to human visual perception. The analysis and understanding of image and video data. Mathematical foundations, image representation, feature extraction, camera geometry and image alignment, stereo and 3-D reconstruction, convolutional neural networks, face processing, object and scene recognition, conditional and Markov random fields, tracking, action recognition.

Recommended Books:

R. Szeliski. Computer Vision: Algorithms and Applications, Springer Science & Business Media, 2010. [Available Online]
D.A. Forsyth and Jean Ponce. Computer Vision: A Modern Approach, Prentice Hall Professional Technical Reference, 2002.
I. Goodfellow, Y. Bengio, A. Courville. Deep Learning, MIT Press, 2016. [Available Online]

Assessment Methods:

Homework	20%
Literature Survey and Presentation	10% + 5%
Midterm:Essay/written	30%
Project	35%

Any of the following will directly result in an F grade:

not submitting a project or homework (including report),
not presenting a survey on the pre-scheduled date,
being absent in the midterm,
being absent in a project presentation.

Prerequisites:

Basic calculus and linear algebra.
Basic probability theory and statistics.
Good programming skills.

Passing Grade: No predetermined grade to pass the course.

Makeup Policy: Medical report holders will be entitled for the midterm make up. Makeup exam will be comprehensive.

Homework:
Please follow this link to access the homework details. Homework details/materials are accessible only within Bilkent network. Use VPN to access from home.

Literature Survey and Presentation:

Groups of two students will choose a topic related to computer vision, and prepare a short survey on it.
Surveys should be based on about 10 papers (report: 5 pages max.).
You will make a presentation on your survey in class. The presentation should be in parallel with your report.
Survey topics should be confirmed first. Very similar topics to others’ will not be allowed (priority: first come, first served).
Your chosen survey topic and a few lines explanation (indicating group members) should be sent to dibeklioglu@cs.bilkent.edu.tr by 15 February 2022, 23.59 (Turkey time).

Project:

By groups of two students.
Projects related to your research topics are encouraged.
Build a “real” computer vision application and test it on some data.
You may re-use existing code, but indicate what you code you have re-used and what code you have developed yourself.
Three stages:

Proposal: one-page description of the project topic and the planning (indicating group members) for the project should be sent to dibeklioglu@cs.bilkent.edu.tr by 18 February 2022 (23:59 Turkey time)
Progress report & presentation (report: 2 pages max.)
Final report & presentation (report: 4 pages max.)

Examples of projects:

Performing face verification for automatic passport control
Recognizing the identity or expression of faces
Recognizing gestures for communication via sign language
Recognizing or detecting objects in images (Pascal VOC / ImageNet)
Segmenting parts in medical images
Performing restoration of old, deteriorated photographs
Performing automatic morphing of images
Performing video stabilization using object tracking
Identifying the writer of a piece of handwriting

Template for the Reports:
All reports (including homework report) must be prepared using the IEEE double-column transactions article template (i.e. "bare_jrnl.tex").

Important Dates:

Event	Date / Deadline
Midterm Exam	29 April 2022, 13:30
Literature Survey Proposal submission [subject line: cs554_2022s_survey]	15 February 2022, 23:59
Literature Survey Report submission (including the presentation) [via Moodle]	21 April 2022, 23:59
Literature Survey Presentation	20 April 2022
Homework submission (including the report) [via Moodle]	26 March 2022, 23:59
Project Proposal submission [subject line: cs554_2022s_proj]	18 February 2022, 23:59
Project Progress Presentation	15 April 2022
Project Progress Report submission (including the presentation) [via Moodle]	16 April 2022, 23:59
Project Final Presentation	11 May 2022
Project submission (including the report and presentation) [via Moodle]	12 May 2022, 23:59

Tentative Schedule & Lecture Notes:
Lecture notes below are downloadable only within Bilkent network. Use VPN to access from home.

Week	Topic	Dates	Lecture Notes
1	Introduction, human vision, overview of basics	04 February 2022 (13:30-15:20)
2	Feature point extraction, Feature point description and matching	09 February 2022 (08:30-10:20) 11 February 2022 (13:30-15:20)
3	Homography and image stitching	16 February 2022 (08:50-10:20)
4	Camera geometry, Stereo vision and depth estimation	23 February 2022 (08:50-10:20) 25 February 2022 (13:30-15:20)
5	Stereo vision and depth estimation, Motion	02 March 2022 (08:50-10:20) 04 March 2022 (13:30-15:20)	>>
6	Spring Break	No Lecture
7	Face Processing, Shape, scene, and object recognition,	16 March 2022 (08:50-10:20) 18 March 2022 (13:30-15:20)
8	Conditional and Markov random fields	25 March 2022 (13:30-15:20)
9	Visual Tracking, Action recognition and motion magnification	30 March 2022 (08:50-10:20) 01 April 2022 (13:30-15:20)
10	Action recognition and motion magnification	06 April 2022 (08:50-10:20)	>>
11	Motion magnification, Deep learning Project Progress Presentations	13 April 2022 (08:50-10:20) 15 April 2022 (13:30-15:20)	>> -
12	Survey Presentations	20 April 2022 (08:40-10:20)	-
13	Deep learning, Midterm	27 April 2022 (08:50-10:20) 29 April 2022 (13:30-15:20)	-
14	Deep learning & QA	6 May 2022 (13:30-15:20)	>>
15	Project presentations	11 May 2022 (08:40-10:20)	-