This course gives an overview of fundamental methods in computer vision from a computational perspective. Topics include the geometry of one and two views, camera calibration, stereo reconstruction, edge and feature detectors, motion, tracking, image segmentation and classification. The methods will be illustrated by applications in computational photography, object detection and medical image analysis.
This course is intended for first year graduate students and advanced undergraduates. The only listed prerequisite is Data Structures. However, familiarity with calculus and basic linear algebra is also necessary to fully understand the material in the course. Elementary probability and statistics is also useful.
| Dates | Content | Resources | |
|---|---|---|---|
| 1 | Aug. 30 | Introduction | slides |
| Sep. 01 | Image Processing | slides matlab demo lena | |
| 2 | Sep. 06 | slides | |
| Sep. 08 | 3D Vision I | slides | |
| 3 | Sep. 13 | slides | |
| Sep. 15 | slides projgeom_appendix | ||
| 4 | Sep. 20 | TA lecture | slides SIFT paper |
| Sep. 22 | slides Tsai_paper Zhang_paper | ||
| 5 | Sep. 27 | 3D Vision II | slides |
| Sep. 29 | TA lecture | mathprimer | |
| 6 | Oct. 04 | slides | |
| Oct. 06 | slides | ||
| 7 | | [NO CLASS] | |
| Oct. 13 | Motion analysis | slides | |
| 8 | Oct. 18 | Face recognition | slides eigenfaces paper |
| Oct. 20 | Segmentation | slides | |
| 9 | Oct. 25 | slides | |
| Oct. 27 | Recognition | slides | |
| 10 | Nov. 01 | slides | |
| Nov. 03 | slides | ||
| 11 | Nov. 08 | Object detection | slides detection paper |
| Nov. 10 | Tracking | slides tracking survey | |
| 12 | Nov. 15 | 3D Vision III | slides |
| Nov. 17 | slides | ||
| 13 | Nov. 22 | Texture synthesis | slides synthesis paper |
| | [NO CLASS] | ||
| 14 | Nov. 29 | Project Presentations | |
| Dec. 01 |
There is no required textbook. Suggested textbooks are:
|
|
