VCLab

 

RESEARCH AREAS   PEOPLE   PUBLICATIONS   COURSES   ABOUT US
Home / Courses / CS681

indicator

 

CS484: Introduction to Computer Vision

Fall 2018

 

Instructor

Min H. Kim, [Room] 3429, [email]

Course description

 

This course provides a comprehensive introduction to low-level computer vision, including the foundations of camera image formation, geometric optics, feature detection, stereo matching, motion estimation, image recognition, scene understanding, etc. This course will help students develop intuitions and mathematics of various computer vision applications.

Lecture time and place

Monday and Wednesday 1:00PM—2:30PM, Rm. 1501, Bldg. E3-1

TA office hours

Monday and Wednesday 6:00PM—8:00PM, Rm. 402, Bldg. N-1
Thursday 2:30PM—5:30PM, Rm. 404, Bldg. N-1

Teaching assistants

Suk Jun Jeon, [e-mail]
Hyunho Ha, [e-mail]
Hyeonjoong Jang, [e-mail]
Shinyoung Yi, [e-mail]
Inseung Hwang, [e-mail]

Reference books

Reinhard Klette (2014) Concise Computer Vision, Springer [site]
Richard Szeliski (2010) Computer Vision: Algorithms and Applications, Springer [site]

Prerequisites

There are no official course prerequisites.

Course goal

Student will establish theoretical and practical foundations of computer vision and be familiar with various computer vision applications.

Tentative schedule

(Note that this curriculum will be revised adaptively.)

  Week Date Lecture Readings Slides HW Due
  1 08/27 Introduction to computer vision Klette: 1, Szeliski: 2.2, 2.3 slide01    
    08/29 Light and color Klette: 1, Szeliski: 2.2, 2.3 slide02    
  2 09/03 Color vector and transformation Klette: 1, Szeliski: 2.2, 2.3 slide03    
    09/05 Color space and gamma correction Klette: 1, Szeliski: 2.2, 2.3 slide04    
  3 09/12 Convolution and cross-correlation Klette: 1, 2, Szeliski: 3.2 slide05 HW1 9/16,23:55
  4 09/17 Spatial vs. frequency domain Klette: 1, 2, Szeliski: 3.4 slide06 HW2 10/7, 23:55
    09/19 Fourier series and Fourier transforms Klette: 1, 2, Szeliski: 3.5.2, 8.1.1 slide07    
  5 09/24 Mid-Authumn Festival Days      
  6 10/01 Fourier transforms and convolution Theorem Klette: 1, 2, Szeliski: 3.5.2, 8.1.1 slide08    
    10/03 No lecture (National Foundation Day)      
  7 10/8 Edge detection Klette: 2, Szeliski: 4.2 slide09    
    10/10 Corner detection Klette: 2, Szeliski: 4.1 slide10    
  8 10/15 Mid-term exam (Monday, 13:00 ~ 15:45)        
  9 10/22 Invariant feature detection Klette: 2, Szeliski: 4.1 slide11    
    10/24 Local image descriptors and matching Klette: 2, Szeliski: 4.1 slide12 HW3 11/11, 23:55
  10 10/29 Segmentation and grouping Klette: 5, Szeliski: 5 slide13    
    10/31 Fitting, RANSAC, and Hough transform Klette: 9, Szeliski: 6 slide14    
  11 11/05 Machine learning for computer vision Klette:  10, Szeliski: 14 slide15    
  12 11/12 Classification (kNN, Bayes, logistic regression, SVM) Klette: 10, Szeliski: 14 slide16    
    11/14 Recognition Klette:  9, Szeliski: 14 slide17 HW4 11/25, 23:55
  13 11/19 Visual tracking and optical flow      
    11/21 Image formation model for camera      
  14 11/26 Epipolar geometry for 3D imaging     HW5 TBA
    11/28 No lecture (KAIST enterance exam)      
  15 12/03 Convolutional neural networks (CNN)      
    12/05 No lecture (SIGGRAPH Asia 2018)      
  16 12/10 Final exam (Monday, 13:00 ~ 15:45)        
               

Grading

Attendance (10%), midterm/final exams (50%), assignments (30%), quizzes (10%)

Resources

Computer Graphics papers
Computer Vision papers

http://kesen.realtimerendering.com/
http://www.cvpapers.com/

Hosted by Visual Computing Laboratory, School of Computing, KAIST.

KAIST