
|
CS484: Introduction to Computer Vision
Fall 2021
|
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 [refer to KLMS] |
TA office hours |
Wednesday and Friday 1:00PM—4:00PM, Zoom meeting [refer to KLMS]
(contact TAs for appoinments by email in advance) |
Teaching Assistants |
Dahyun Kang (ex. 7864, )
Inseung Hwang (ex. 7864, )
Donggun Kim (ex. 7864, )
Jungwoo Kim (ex. 7864, )
|
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 |
Slides |
HW |
Due |
|
1 |
08/31 |
Introduction to computer vision |
slide01 |
|
|
|
2 |
09/02 |
Light |
slide02 |
|
|
|
3 |
09/07 |
Light, color camera, photography |
slide03v2 |
hw1 |
9/15, 23:55 |
|
4 |
09/09 |
Color imaging |
slide04 |
|
|
|
5 |
09/14 |
Image filter |
slide05 |
|
|
|
6 |
09/16 |
Fourier Series & Transforms |
slide06 |
hw2v2 |
10/3, 23:55 |
|
|
09/21,23 |
No lecture (Chuseok Holidays) |
|
|
|
|
7 |
09/28 |
Image formation of camera |
slide07v5 |
|
|
|
8 |
09/30 |
Epipolar geometry |
slide08 |
|
|
|
9 |
10/05 |
Homography, camera calibration |
slide09v2 |
|
|
|
10 |
10/07 |
Stereo matching |
slide10v5 |
hw3 |
10/29, 23:55 |
|
11 |
10/12 |
Multiview geometry |
slide11 |
|
|
|
12 |
10/14 |
3D scanning workflow |
slide12v3 |
|
|
|
|
10/19 |
Mid-term exam (Tuesday, 13:00 ~ 15:45) |
|
|
|
|
13 |
10/26 |
Feature detection (Harris corner detector) |
slide13v2 |
|
|
|
14 |
11/02 |
Feature matching (blob dectection) |
slide14 |
|
|
|
15 |
11/04 |
Feature descriptor (SIFT) |
slide15 |
hw4 |
11/19, 23:55 |
|
16 |
11/09 |
Optical Flow & Tracking |
slide16 |
|
|
|
17 |
11/11 |
Machine learning for computer vision |
slide17 |
|
|
|
18 |
11/16 |
Linear regression and denosing |
slide18 |
|
|
|
19 |
11/18 |
GLM, RANSAC, generalization error |
slide19 |
|
|
|
20 |
11/23 |
Classification |
slide20 |
|
|
|
21 |
11/25 |
Clustering |
slide21 |
|
|
|
22 |
11/30 |
Recognition (Bag-of-words) |
slide22 |
hw5 |
12/16, 23:55 |
|
23 |
12/07 |
Dimension reduction & introduction to network |
slide23(1), slide23(2) |
|
|
|
24 |
12/09 |
Intro and learning convolutional neural network |
slide24(1)v2, slide24(2) |
|
|
|
|
12/14 |
Final exam (Tuesday, 13:00 ~ 15:45) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Grading |
Attendance (10%), mid-term exam (25%), final exam (25%), homework assignments (40%) |
|
|
|
Hosted by Visual Computing Laboratory, School of Computing, KAIST.
|
 |
|