|
CS484: Introduction to Computer Vision
Fall 2020
|
Instructor |
Min H. Kim, [Room] 2403, [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 |
Tuesday and Thursday 1:00PM—2:30PM, Zoom meeting |
TA office hours |
Tuesday and Thursday 2:30PM—5:30PM, Zoom meeting
(contact TAs for appoinments by email in advance) |
Teaching Assistants |
Hyeonjoong Jang (ex. 7864, )
Inseung Hwang (ex. 7864, )
|
Reference books |
Richard Szeliski (2010) Computer Vision: Algorithms and Applications, Springer [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 |
Slides |
HW |
Due |
| |
1 |
09/01 |
Introduction to computer vision |
slide01 |
|
|
| |
2 |
09/03 |
Light |
slide02 |
|
|
| |
3 |
09/08 |
Color imaging (1) |
slide03 |
|
|
| |
4 |
09/10 |
Color imaging (2) |
slide03 |
|
|
| |
5 |
09/15 |
Image filter |
slide04 |
|
|
| |
6 |
09/17 |
Frequency domain |
slide05 |
HW1 |
9/20, 23:59 |
| |
7 |
09/22 |
Image formation of camera |
slide06 |
HW2 |
10/4 23:59 |
| |
8 |
09/24 |
Epipolar geometry |
slide07 |
|
|
| |
9 |
09/29 |
Camera calibration |
slide08 |
|
|
| |
|
10/01 |
No lecture (Chuseok Holidays) |
|
|
|
| |
10 |
10/06 |
Stereo matching |
slide09(v.2) |
|
|
| |
11 |
10/08 |
Multiview geometry |
slide10 |
|
|
| |
12 |
10/13 |
3D scanning workflow |
slide11 |
|
|
| |
13 |
10/15 |
Thin lens optics |
slide12 |
HW3 |
11/01 23:59 |
| |
14 |
10/19 |
Mid-term exam period |
|
|
|
| |
15 |
10/27 |
Feature detection (Harris corner detector) |
slide13 |
|
|
| |
16 |
10/29 |
Feature matching (blob dectection) |
slide14 |
|
|
| |
17 |
11/03 |
Feature descriptor (SIFT) |
slide15 |
HW4 |
11/15 23:59 |
| |
18 |
11/05 |
Machine learning for computer vision |
slide16 |
|
|
| |
19 |
11/10 |
Linear regression |
slide17v2 |
|
|
| |
20 |
11/12 |
GLM, RANSAC, generalization error |
slide18 |
|
|
| |
21 |
11/19 |
Classification |
slide19v2 |
|
|
| |
22 |
11/24 |
Clustering |
slide20 |
|
|
| |
23 |
11/26 |
Dimension reduction |
slide21 |
|
|
| |
24 |
12/01 |
Recognition |
slide22 |
HW5 |
12/20 23:59 |
| |
25 |
12/03 |
Introduction to CNN |
slide23v2 |
|
|
| |
26 |
12/08 |
Training CNN |
slide24 |
|
|
| |
27 |
12/10 |
No lecture (KAIST enterance exam) |
|
|
|
| |
28 |
12/15 |
Final exam (Tuesday, 13:00 ~ 15:45) |
|
|
|
| |
|
|
|
|
|
|
| |
|
|
|
|
|
|
Grading |
Attendance (10%), final exam (50%), assignments (40%) |
|
|
|
|
Hosted by Visual Computing Laboratory, School of Computing, KAIST.
|
 |
|
