CS 554: Computer Vision

Fall 2022

UPDATES / NEWS:


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:

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:


Prerequisites:

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:

Project:

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 November 2022
Literature Survey Proposal submission
[subject line: cs554_2022f_survey]
25 September 2022, 23:59
Literature Survey Report submission
(including the presentation)
[via Moodle]
06 December 2022, 23:59
Literature Survey Presentation 06 December 2022
Homework submission (including the report)
[via Moodle]
12 November 2022, 23:59
Project Proposal submission
[subject line: cs554_2022f_proj]
28 September 2022, 23:59
Project Progress Presentation 24 November 2022
Project Progress Report submission
(including the report and presentation)
[via Moodle]
24 November 2022, 23:59
Project Final Presentation 13 December 2022
Project submission
(including the report and presentation)
[via Moodle]
13 December 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 15 September 2022 (13:30-15:20)  
2 Feature point extraction,
Feature point description and matching
20 September 2022 (08:30-10:20)
22 September 2022 (13:30-15:20)
 
 
 3 Homography and image stitching,
Camera geometry
27 September 2022 (08:50-10:20)
29 September 2022 (13:30-15:20)
 
 
4 No Lecture -

5 Stereo vision and depth estimation
Motion
11 October 2022 (08:50-10:20)
13 October 2022 (13:30-15:20)
 
 
6 Motion cont'd &
Face Processing
20 October 2022 (13:30-15:20)   >>
 
7 Face Processing cont'd &
Shape, scene, and object recognition,
25 October 2022 (08:50-10:20)   >>
 
8 Shape, scene, and object recognition cont'd,
Conditional and Markov random fields
01 November 2022 (08:50-10:20)
03 November 2022 (13:30-15:20)
  >>
 
9 Visual Tracking 10 November 2022 (13:30-15:20)  
10 Action recognition and motion magnification 15 November 2022 (08:50-10:20)
17 November 2022 (13:30-15:20)
 
  >>
11 Project Progress Presentations 24 November 2022 (13:30-15:20)    -
12 Midterm
Deep learning
29 November 2022 (08:50-10:20)
01 December 2022 (13:30-15:20)
   -
 
13 Survey Presentations
Deep learning
06 December 2022 (08:30-10:20)
08 December 2022 (13:30-15:20)
   -
  >>
14 Project presentations
Overview