|
KTP592: Computer Vision and Machine Learning
Spring 2023
|
Instructor |
Min Hyuk Kim, [email]
Tae-kyun Kim, [email]
Seunghoon Hong, [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 |
1—5 weeks, Prof. Min H. Kim, Wednesday 14:00—17:00, Lecture rooms: KAIST Dogok campus or online
6—10 weeks, Prof. Tae-Kyun Kim, Wednesday 14:00—17:00, Lecture rooms: KAIST Dogok campus or online
11—15 weeks, Prof. Seunghoon Hong, Thursday 19:00—22:00, Lecture rooms: KAIST Dogok campus or online
|
Reference books |
Richard Szeliski (2010) Computer Vision: Algorithms and Applications, Springer [site]
Richard Hartley and Andrew Zisserman (2011) Multiple View Geometry in Computer Vision, Cambridge Press [site]
Christopher M. Bishop (2006) Pattern Recognition and Machine Learning, Springer [site]
Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016) Deep Learning, MIT Press [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.) |
| |
Index |
Date |
Lecture |
Professor |
Slides |
|
| |
1 |
3/1 |
No lecture (national holiday) |
Min H. Kim |
KLMS |
|
| |
2 |
3/8 |
Introduction, color camera and transform |
Min H. Kim |
KLMS |
|
| |
3 |
3/15 |
Image filter, frequency domain, point and corner |
Min H. Kim |
KLMS |
|
| |
4 |
3/22 |
Feature matching, feature descriptor, bag-of-words |
Min H. Kim |
KLMS |
|
| |
5 |
3/29 |
Image formation model and thin lens optics |
Min H. Kim |
KLMS |
|
| |
6 |
4/5 |
Machine learning for computer vision |
Tae-Kyun Kim |
KLMS |
|
| |
7 |
4/12 |
Deep learning introduction |
Tae-Kyun Kim |
KLMS |
|
| |
|
4/17--21 |
Mid-term exam period |
|
|
|
| |
8 |
4/19 |
Topics in deep learning and vision |
Tae-Kyun Kim |
KLMS |
|
| |
9 |
4/26 |
Generative networks |
Tae-Kyun Kim |
KLMS |
|
| |
10 |
5/4 |
Data augmentation |
Tae-Kyun Kim |
KLMS |
|
| |
11 |
5/13 |
Semantic segmentation |
Seunghoon Hong |
KLMS |
|
| |
12 |
5/25 |
Object detection |
Seunghoon Hong |
KLMS |
|
| |
13 |
6/1 |
Motion and tracking |
Seunghoon Hong |
KLMS |
|
| |
14 |
6/8 |
Video recognition |
Seunghoon Hong |
KLMS |
|
| |
15 |
6/15 |
Attention and Transformers for vision |
Seunghoon Hong |
KLMS |
|
| |
|
6/12--16 |
Final-term exam period |
|
|
|
Grading |
First quiz (30%), second quiz (30%), third quiz (30%), attendance (10%) |
|
|
|
|
Hosted by Visual Computing Laboratory, School of Computing, KAIST.
|
 |
|
